diff --git a/.rat-excludes b/.rat-excludes index dccf2db8055ce..dc08c4a3673d2 100644 --- a/.rat-excludes +++ b/.rat-excludes @@ -74,5 +74,12 @@ logs .*scalastyle-output.xml .*dependency-reduced-pom.xml known_translations +json_expectation +local-1422981759269/* +local-1422981780767/* +local-1425081759269/* +local-1426533911241/* +local-1426633911242/* +local-1430917381534/* DESCRIPTION NAMESPACE diff --git a/R/pkg/DESCRIPTION b/R/pkg/DESCRIPTION index 1c1779a763c7e..efc85bbc4b316 100644 --- a/R/pkg/DESCRIPTION +++ b/R/pkg/DESCRIPTION @@ -15,11 +15,11 @@ Suggests: Description: R frontend for Spark License: Apache License (== 2.0) Collate: + 'schema.R' 'generics.R' 'jobj.R' 'RDD.R' 'pairRDD.R' - 'schema.R' 'column.R' 'group.R' 'DataFrame.R' diff --git a/R/pkg/NAMESPACE b/R/pkg/NAMESPACE index 3fb92be0940b7..7611f479a628b 100644 --- a/R/pkg/NAMESPACE +++ b/R/pkg/NAMESPACE @@ -26,7 +26,6 @@ exportMethods("cache", "intersect", "isLocal", "join", - "length", "limit", "orderBy", "names", @@ -101,9 +100,6 @@ export("cacheTable", "tables", "uncacheTable") -export("sparkRSQL.init", - "sparkRHive.init") - export("structField", "structField.jobj", "structField.character", diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R index 47d92f141cc7d..354642e7bc307 100644 --- a/R/pkg/R/DataFrame.R +++ b/R/pkg/R/DataFrame.R @@ -45,6 +45,9 @@ setMethod("initialize", "DataFrame", function(.Object, sdf, isCached) { #' @rdname DataFrame #' @export +#' +#' @param sdf A Java object reference to the backing Scala DataFrame +#' @param isCached TRUE if the dataFrame is cached dataFrame <- function(sdf, isCached = FALSE) { new("DataFrame", sdf, isCached) } @@ -244,7 +247,7 @@ setMethod("columns", }) #' @rdname columns -#' @export +#' @aliases names,DataFrame,function-method setMethod("names", signature(x = "DataFrame"), function(x) { @@ -399,23 +402,23 @@ setMethod("repartition", dataFrame(sdf) }) -#' toJSON -#' -#' Convert the rows of a DataFrame into JSON objects and return an RDD where -#' each element contains a JSON string. -#' -#' @param x A SparkSQL DataFrame -#' @return A StringRRDD of JSON objects -#' @rdname tojson -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' sqlCtx <- sparkRSQL.init(sc) -#' path <- "path/to/file.json" -#' df <- jsonFile(sqlCtx, path) -#' newRDD <- toJSON(df) -#'} +# toJSON +# +# Convert the rows of a DataFrame into JSON objects and return an RDD where +# each element contains a JSON string. +# +#@param x A SparkSQL DataFrame +# @return A StringRRDD of JSON objects +# @rdname tojson +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# sqlCtx <- sparkRSQL.init(sc) +# path <- "path/to/file.json" +# df <- jsonFile(sqlCtx, path) +# newRDD <- toJSON(df) +#} setMethod("toJSON", signature(x = "DataFrame"), function(x) { @@ -578,8 +581,8 @@ setMethod("limit", dataFrame(res) }) -# Take the first NUM rows of a DataFrame and return a the results as a data.frame - +#' Take the first NUM rows of a DataFrame and return a the results as a data.frame +#' #' @rdname take #' @export #' @examples @@ -644,22 +647,22 @@ setMethod("first", take(x, 1) }) -#' toRDD() -#' -#' Converts a Spark DataFrame to an RDD while preserving column names. -#' -#' @param x A Spark DataFrame -#' -#' @rdname DataFrame -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' sqlCtx <- sparkRSQL.init(sc) -#' path <- "path/to/file.json" -#' df <- jsonFile(sqlCtx, path) -#' rdd <- toRDD(df) -#' } +# toRDD() +# +# Converts a Spark DataFrame to an RDD while preserving column names. +# +# @param x A Spark DataFrame +# +# @rdname DataFrame +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# sqlCtx <- sparkRSQL.init(sc) +# path <- "path/to/file.json" +# df <- jsonFile(sqlCtx, path) +# rdd <- toRDD(df) +# } setMethod("toRDD", signature(x = "DataFrame"), function(x) { @@ -706,6 +709,7 @@ setMethod("groupBy", #' #' Compute aggregates by specifying a list of columns #' +#' @param x a DataFrame #' @rdname DataFrame #' @export setMethod("agg", @@ -721,7 +725,7 @@ setMethod("agg", # the requested map function. # ################################################################################### -#' @rdname lapply +# @rdname lapply setMethod("lapply", signature(X = "DataFrame", FUN = "function"), function(X, FUN) { @@ -729,14 +733,14 @@ setMethod("lapply", lapply(rdd, FUN) }) -#' @rdname lapply +# @rdname lapply setMethod("map", signature(X = "DataFrame", FUN = "function"), function(X, FUN) { lapply(X, FUN) }) -#' @rdname flatMap +# @rdname flatMap setMethod("flatMap", signature(X = "DataFrame", FUN = "function"), function(X, FUN) { @@ -744,7 +748,7 @@ setMethod("flatMap", flatMap(rdd, FUN) }) -#' @rdname lapplyPartition +# @rdname lapplyPartition setMethod("lapplyPartition", signature(X = "DataFrame", FUN = "function"), function(X, FUN) { @@ -752,14 +756,14 @@ setMethod("lapplyPartition", lapplyPartition(rdd, FUN) }) -#' @rdname lapplyPartition +# @rdname lapplyPartition setMethod("mapPartitions", signature(X = "DataFrame", FUN = "function"), function(X, FUN) { lapplyPartition(X, FUN) }) -#' @rdname foreach +# @rdname foreach setMethod("foreach", signature(x = "DataFrame", func = "function"), function(x, func) { @@ -767,7 +771,7 @@ setMethod("foreach", foreach(rdd, func) }) -#' @rdname foreach +# @rdname foreach setMethod("foreachPartition", signature(x = "DataFrame", func = "function"), function(x, func) { @@ -788,6 +792,7 @@ setMethod("$", signature(x = "DataFrame"), getColumn(x, name) }) +#' @rdname select setMethod("$<-", signature(x = "DataFrame"), function(x, name, value) { stopifnot(class(value) == "Column" || is.null(value)) @@ -1009,7 +1014,7 @@ setMethod("sortDF", }) #' @rdname sortDF -#' @export +#' @aliases orderBy,DataFrame,function-method setMethod("orderBy", signature(x = "DataFrame", col = "characterOrColumn"), function(x, col) { @@ -1046,7 +1051,7 @@ setMethod("filter", }) #' @rdname filter -#' @export +#' @aliases where,DataFrame,function-method setMethod("where", signature(x = "DataFrame", condition = "characterOrColumn"), function(x, condition) { diff --git a/R/pkg/R/RDD.R b/R/pkg/R/RDD.R index d1018c2361670..73999a6737032 100644 --- a/R/pkg/R/RDD.R +++ b/R/pkg/R/RDD.R @@ -19,16 +19,16 @@ setOldClass("jobj") -#' @title S4 class that represents an RDD -#' @description RDD can be created using functions like -#' \code{parallelize}, \code{textFile} etc. -#' @rdname RDD -#' @seealso parallelize, textFile -#' -#' @slot env An R environment that stores bookkeeping states of the RDD -#' @slot jrdd Java object reference to the backing JavaRDD -#' to an RDD -#' @export +# @title S4 class that represents an RDD +# @description RDD can be created using functions like +# \code{parallelize}, \code{textFile} etc. +# @rdname RDD +# @seealso parallelize, textFile +# +# @slot env An R environment that stores bookkeeping states of the RDD +# @slot jrdd Java object reference to the backing JavaRDD +# to an RDD +# @export setClass("RDD", slots = list(env = "environment", jrdd = "jobj")) @@ -108,14 +108,14 @@ setMethod("initialize", "PipelinedRDD", function(.Object, prev, func, jrdd_val) .Object }) -#' @rdname RDD -#' @export -#' -#' @param jrdd Java object reference to the backing JavaRDD -#' @param serializedMode Use "byte" if the RDD stores data serialized in R, "string" if the RDD -#' stores strings, and "row" if the RDD stores the rows of a DataFrame -#' @param isCached TRUE if the RDD is cached -#' @param isCheckpointed TRUE if the RDD has been checkpointed +# @rdname RDD +# @export +# +# @param jrdd Java object reference to the backing JavaRDD +# @param serializedMode Use "byte" if the RDD stores data serialized in R, "string" if the RDD +# stores strings, and "row" if the RDD stores the rows of a DataFrame +# @param isCached TRUE if the RDD is cached +# @param isCheckpointed TRUE if the RDD has been checkpointed RDD <- function(jrdd, serializedMode = "byte", isCached = FALSE, isCheckpointed = FALSE) { new("RDD", jrdd, serializedMode, isCached, isCheckpointed) @@ -200,19 +200,19 @@ setValidity("RDD", ############ Actions and Transformations ############ -#' Persist an RDD -#' -#' Persist this RDD with the default storage level (MEMORY_ONLY). -#' -#' @param x The RDD to cache -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10, 2L) -#' cache(rdd) -#'} -#' @rdname cache-methods -#' @aliases cache,RDD-method +# Persist an RDD +# +# Persist this RDD with the default storage level (MEMORY_ONLY). +# +# @param x The RDD to cache +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10, 2L) +# cache(rdd) +#} +# @rdname cache-methods +# @aliases cache,RDD-method setMethod("cache", signature(x = "RDD"), function(x) { @@ -221,22 +221,22 @@ setMethod("cache", x }) -#' Persist an RDD -#' -#' Persist this RDD with the specified storage level. For details of the -#' supported storage levels, refer to -#' http://spark.apache.org/docs/latest/programming-guide.html#rdd-persistence. -#' -#' @param x The RDD to persist -#' @param newLevel The new storage level to be assigned -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10, 2L) -#' persist(rdd, "MEMORY_AND_DISK") -#'} -#' @rdname persist -#' @aliases persist,RDD-method +# Persist an RDD +# +# Persist this RDD with the specified storage level. For details of the +# supported storage levels, refer to +# http://spark.apache.org/docs/latest/programming-guide.html#rdd-persistence. +# +# @param x The RDD to persist +# @param newLevel The new storage level to be assigned +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10, 2L) +# persist(rdd, "MEMORY_AND_DISK") +#} +# @rdname persist +# @aliases persist,RDD-method setMethod("persist", signature(x = "RDD", newLevel = "character"), function(x, newLevel) { @@ -245,21 +245,21 @@ setMethod("persist", x }) -#' Unpersist an RDD -#' -#' Mark the RDD as non-persistent, and remove all blocks for it from memory and -#' disk. -#' -#' @param x The RDD to unpersist -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10, 2L) -#' cache(rdd) # rdd@@env$isCached == TRUE -#' unpersist(rdd) # rdd@@env$isCached == FALSE -#'} -#' @rdname unpersist-methods -#' @aliases unpersist,RDD-method +# Unpersist an RDD +# +# Mark the RDD as non-persistent, and remove all blocks for it from memory and +# disk. +# +# @param x The RDD to unpersist +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10, 2L) +# cache(rdd) # rdd@@env$isCached == TRUE +# unpersist(rdd) # rdd@@env$isCached == FALSE +#} +# @rdname unpersist-methods +# @aliases unpersist,RDD-method setMethod("unpersist", signature(x = "RDD"), function(x) { @@ -268,24 +268,24 @@ setMethod("unpersist", x }) -#' Checkpoint an RDD -#' -#' Mark this RDD for checkpointing. It will be saved to a file inside the -#' checkpoint directory set with setCheckpointDir() and all references to its -#' parent RDDs will be removed. This function must be called before any job has -#' been executed on this RDD. It is strongly recommended that this RDD is -#' persisted in memory, otherwise saving it on a file will require recomputation. -#' -#' @param x The RDD to checkpoint -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' setCheckpointDir(sc, "checkpoint") -#' rdd <- parallelize(sc, 1:10, 2L) -#' checkpoint(rdd) -#'} -#' @rdname checkpoint-methods -#' @aliases checkpoint,RDD-method +# Checkpoint an RDD +# +# Mark this RDD for checkpointing. It will be saved to a file inside the +# checkpoint directory set with setCheckpointDir() and all references to its +# parent RDDs will be removed. This function must be called before any job has +# been executed on this RDD. It is strongly recommended that this RDD is +# persisted in memory, otherwise saving it on a file will require recomputation. +# +# @param x The RDD to checkpoint +# @examples +#\dontrun{ +# sc <- sparkR.init() +# setCheckpointDir(sc, "checkpoint") +# rdd <- parallelize(sc, 1:10, 2L) +# checkpoint(rdd) +#} +# @rdname checkpoint-methods +# @aliases checkpoint,RDD-method setMethod("checkpoint", signature(x = "RDD"), function(x) { @@ -295,18 +295,18 @@ setMethod("checkpoint", x }) -#' Gets the number of partitions of an RDD -#' -#' @param x A RDD. -#' @return the number of partitions of rdd as an integer. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10, 2L) -#' numPartitions(rdd) # 2L -#'} -#' @rdname numPartitions -#' @aliases numPartitions,RDD-method +# Gets the number of partitions of an RDD +# +# @param x A RDD. +# @return the number of partitions of rdd as an integer. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10, 2L) +# numPartitions(rdd) # 2L +#} +# @rdname numPartitions +# @aliases numPartitions,RDD-method setMethod("numPartitions", signature(x = "RDD"), function(x) { @@ -315,24 +315,24 @@ setMethod("numPartitions", callJMethod(partitions, "size") }) -#' Collect elements of an RDD -#' -#' @description -#' \code{collect} returns a list that contains all of the elements in this RDD. -#' -#' @param x The RDD to collect -#' @param ... Other optional arguments to collect -#' @param flatten FALSE if the list should not flattened -#' @return a list containing elements in the RDD -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10, 2L) -#' collect(rdd) # list from 1 to 10 -#' collectPartition(rdd, 0L) # list from 1 to 5 -#'} -#' @rdname collect-methods -#' @aliases collect,RDD-method +# Collect elements of an RDD +# +# @description +# \code{collect} returns a list that contains all of the elements in this RDD. +# +# @param x The RDD to collect +# @param ... Other optional arguments to collect +# @param flatten FALSE if the list should not flattened +# @return a list containing elements in the RDD +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10, 2L) +# collect(rdd) # list from 1 to 10 +# collectPartition(rdd, 0L) # list from 1 to 5 +#} +# @rdname collect-methods +# @aliases collect,RDD-method setMethod("collect", signature(x = "RDD"), function(x, flatten = TRUE) { @@ -343,12 +343,12 @@ setMethod("collect", }) -#' @description -#' \code{collectPartition} returns a list that contains all of the elements -#' in the specified partition of the RDD. -#' @param partitionId the partition to collect (starts from 0) -#' @rdname collect-methods -#' @aliases collectPartition,integer,RDD-method +# @description +# \code{collectPartition} returns a list that contains all of the elements +# in the specified partition of the RDD. +# @param partitionId the partition to collect (starts from 0) +# @rdname collect-methods +# @aliases collectPartition,integer,RDD-method setMethod("collectPartition", signature(x = "RDD", partitionId = "integer"), function(x, partitionId) { @@ -361,17 +361,17 @@ setMethod("collectPartition", serializedMode = getSerializedMode(x)) }) -#' @description -#' \code{collectAsMap} returns a named list as a map that contains all of the elements -#' in a key-value pair RDD. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(list(1, 2), list(3, 4)), 2L) -#' collectAsMap(rdd) # list(`1` = 2, `3` = 4) -#'} -#' @rdname collect-methods -#' @aliases collectAsMap,RDD-method +# @description +# \code{collectAsMap} returns a named list as a map that contains all of the elements +# in a key-value pair RDD. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(list(1, 2), list(3, 4)), 2L) +# collectAsMap(rdd) # list(`1` = 2, `3` = 4) +#} +# @rdname collect-methods +# @aliases collectAsMap,RDD-method setMethod("collectAsMap", signature(x = "RDD"), function(x) { @@ -381,19 +381,19 @@ setMethod("collectAsMap", as.list(map) }) -#' Return the number of elements in the RDD. -#' -#' @param x The RDD to count -#' @return number of elements in the RDD. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' count(rdd) # 10 -#' length(rdd) # Same as count -#'} -#' @rdname count -#' @aliases count,RDD-method +# Return the number of elements in the RDD. +# +# @param x The RDD to count +# @return number of elements in the RDD. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# count(rdd) # 10 +# length(rdd) # Same as count +#} +# @rdname count +# @aliases count,RDD-method setMethod("count", signature(x = "RDD"), function(x) { @@ -405,31 +405,31 @@ setMethod("count", sum(as.integer(vals)) }) -#' Return the number of elements in the RDD -#' @export -#' @rdname count +# Return the number of elements in the RDD +# @export +# @rdname count setMethod("length", signature(x = "RDD"), function(x) { count(x) }) -#' Return the count of each unique value in this RDD as a list of -#' (value, count) pairs. -#' -#' Same as countByValue in Spark. -#' -#' @param x The RDD to count -#' @return list of (value, count) pairs, where count is number of each unique -#' value in rdd. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, c(1,2,3,2,1)) -#' countByValue(rdd) # (1,2L), (2,2L), (3,1L) -#'} -#' @rdname countByValue -#' @aliases countByValue,RDD-method +# Return the count of each unique value in this RDD as a list of +# (value, count) pairs. +# +# Same as countByValue in Spark. +# +# @param x The RDD to count +# @return list of (value, count) pairs, where count is number of each unique +# value in rdd. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, c(1,2,3,2,1)) +# countByValue(rdd) # (1,2L), (2,2L), (3,1L) +#} +# @rdname countByValue +# @aliases countByValue,RDD-method setMethod("countByValue", signature(x = "RDD"), function(x) { @@ -437,23 +437,23 @@ setMethod("countByValue", collect(reduceByKey(ones, `+`, numPartitions(x))) }) -#' Apply a function to all elements -#' -#' This function creates a new RDD by applying the given transformation to all -#' elements of the given RDD -#' -#' @param X The RDD to apply the transformation. -#' @param FUN the transformation to apply on each element -#' @return a new RDD created by the transformation. -#' @rdname lapply -#' @aliases lapply -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' multiplyByTwo <- lapply(rdd, function(x) { x * 2 }) -#' collect(multiplyByTwo) # 2,4,6... -#'} +# Apply a function to all elements +# +# This function creates a new RDD by applying the given transformation to all +# elements of the given RDD +# +# @param X The RDD to apply the transformation. +# @param FUN the transformation to apply on each element +# @return a new RDD created by the transformation. +# @rdname lapply +# @aliases lapply +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# multiplyByTwo <- lapply(rdd, function(x) { x * 2 }) +# collect(multiplyByTwo) # 2,4,6... +#} setMethod("lapply", signature(X = "RDD", FUN = "function"), function(X, FUN) { @@ -463,31 +463,31 @@ setMethod("lapply", lapplyPartitionsWithIndex(X, func) }) -#' @rdname lapply -#' @aliases map,RDD,function-method +# @rdname lapply +# @aliases map,RDD,function-method setMethod("map", signature(X = "RDD", FUN = "function"), function(X, FUN) { lapply(X, FUN) }) -#' Flatten results after apply a function to all elements -#' -#' This function return a new RDD by first applying a function to all -#' elements of this RDD, and then flattening the results. -#' -#' @param X The RDD to apply the transformation. -#' @param FUN the transformation to apply on each element -#' @return a new RDD created by the transformation. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' multiplyByTwo <- flatMap(rdd, function(x) { list(x*2, x*10) }) -#' collect(multiplyByTwo) # 2,20,4,40,6,60... -#'} -#' @rdname flatMap -#' @aliases flatMap,RDD,function-method +# Flatten results after apply a function to all elements +# +# This function return a new RDD by first applying a function to all +# elements of this RDD, and then flattening the results. +# +# @param X The RDD to apply the transformation. +# @param FUN the transformation to apply on each element +# @return a new RDD created by the transformation. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# multiplyByTwo <- flatMap(rdd, function(x) { list(x*2, x*10) }) +# collect(multiplyByTwo) # 2,20,4,40,6,60... +#} +# @rdname flatMap +# @aliases flatMap,RDD,function-method setMethod("flatMap", signature(X = "RDD", FUN = "function"), function(X, FUN) { @@ -500,83 +500,83 @@ setMethod("flatMap", lapplyPartition(X, partitionFunc) }) -#' Apply a function to each partition of an RDD -#' -#' Return a new RDD by applying a function to each partition of this RDD. -#' -#' @param X The RDD to apply the transformation. -#' @param FUN the transformation to apply on each partition. -#' @return a new RDD created by the transformation. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' partitionSum <- lapplyPartition(rdd, function(part) { Reduce("+", part) }) -#' collect(partitionSum) # 15, 40 -#'} -#' @rdname lapplyPartition -#' @aliases lapplyPartition,RDD,function-method +# Apply a function to each partition of an RDD +# +# Return a new RDD by applying a function to each partition of this RDD. +# +# @param X The RDD to apply the transformation. +# @param FUN the transformation to apply on each partition. +# @return a new RDD created by the transformation. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# partitionSum <- lapplyPartition(rdd, function(part) { Reduce("+", part) }) +# collect(partitionSum) # 15, 40 +#} +# @rdname lapplyPartition +# @aliases lapplyPartition,RDD,function-method setMethod("lapplyPartition", signature(X = "RDD", FUN = "function"), function(X, FUN) { lapplyPartitionsWithIndex(X, function(s, part) { FUN(part) }) }) -#' mapPartitions is the same as lapplyPartition. -#' -#' @rdname lapplyPartition -#' @aliases mapPartitions,RDD,function-method +# mapPartitions is the same as lapplyPartition. +# +# @rdname lapplyPartition +# @aliases mapPartitions,RDD,function-method setMethod("mapPartitions", signature(X = "RDD", FUN = "function"), function(X, FUN) { lapplyPartition(X, FUN) }) -#' Return a new RDD by applying a function to each partition of this RDD, while -#' tracking the index of the original partition. -#' -#' @param X The RDD to apply the transformation. -#' @param FUN the transformation to apply on each partition; takes the partition -#' index and a list of elements in the particular partition. -#' @return a new RDD created by the transformation. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10, 5L) -#' prod <- lapplyPartitionsWithIndex(rdd, function(partIndex, part) { -#' partIndex * Reduce("+", part) }) -#' collect(prod, flatten = FALSE) # 0, 7, 22, 45, 76 -#'} -#' @rdname lapplyPartitionsWithIndex -#' @aliases lapplyPartitionsWithIndex,RDD,function-method +# Return a new RDD by applying a function to each partition of this RDD, while +# tracking the index of the original partition. +# +# @param X The RDD to apply the transformation. +# @param FUN the transformation to apply on each partition; takes the partition +# index and a list of elements in the particular partition. +# @return a new RDD created by the transformation. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10, 5L) +# prod <- lapplyPartitionsWithIndex(rdd, function(partIndex, part) { +# partIndex * Reduce("+", part) }) +# collect(prod, flatten = FALSE) # 0, 7, 22, 45, 76 +#} +# @rdname lapplyPartitionsWithIndex +# @aliases lapplyPartitionsWithIndex,RDD,function-method setMethod("lapplyPartitionsWithIndex", signature(X = "RDD", FUN = "function"), function(X, FUN) { PipelinedRDD(X, FUN) }) -#' @rdname lapplyPartitionsWithIndex -#' @aliases mapPartitionsWithIndex,RDD,function-method +# @rdname lapplyPartitionsWithIndex +# @aliases mapPartitionsWithIndex,RDD,function-method setMethod("mapPartitionsWithIndex", signature(X = "RDD", FUN = "function"), function(X, FUN) { lapplyPartitionsWithIndex(X, FUN) }) -#' This function returns a new RDD containing only the elements that satisfy -#' a predicate (i.e. returning TRUE in a given logical function). -#' The same as `filter()' in Spark. -#' -#' @param x The RDD to be filtered. -#' @param f A unary predicate function. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' unlist(collect(filterRDD(rdd, function (x) { x < 3 }))) # c(1, 2) -#'} -#' @rdname filterRDD -#' @aliases filterRDD,RDD,function-method +# This function returns a new RDD containing only the elements that satisfy +# a predicate (i.e. returning TRUE in a given logical function). +# The same as `filter()' in Spark. +# +# @param x The RDD to be filtered. +# @param f A unary predicate function. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# unlist(collect(filterRDD(rdd, function (x) { x < 3 }))) # c(1, 2) +#} +# @rdname filterRDD +# @aliases filterRDD,RDD,function-method setMethod("filterRDD", signature(x = "RDD", f = "function"), function(x, f) { @@ -586,30 +586,30 @@ setMethod("filterRDD", lapplyPartition(x, filter.func) }) -#' @rdname filterRDD -#' @aliases Filter +# @rdname filterRDD +# @aliases Filter setMethod("Filter", signature(f = "function", x = "RDD"), function(f, x) { filterRDD(x, f) }) -#' Reduce across elements of an RDD. -#' -#' This function reduces the elements of this RDD using the -#' specified commutative and associative binary operator. -#' -#' @param x The RDD to reduce -#' @param func Commutative and associative function to apply on elements -#' of the RDD. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' reduce(rdd, "+") # 55 -#'} -#' @rdname reduce -#' @aliases reduce,RDD,ANY-method +# Reduce across elements of an RDD. +# +# This function reduces the elements of this RDD using the +# specified commutative and associative binary operator. +# +# @param x The RDD to reduce +# @param func Commutative and associative function to apply on elements +# of the RDD. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# reduce(rdd, "+") # 55 +#} +# @rdname reduce +# @aliases reduce,RDD,ANY-method setMethod("reduce", signature(x = "RDD", func = "ANY"), function(x, func) { @@ -623,70 +623,70 @@ setMethod("reduce", Reduce(func, partitionList) }) -#' Get the maximum element of an RDD. -#' -#' @param x The RDD to get the maximum element from -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' maximum(rdd) # 10 -#'} -#' @rdname maximum -#' @aliases maximum,RDD +# Get the maximum element of an RDD. +# +# @param x The RDD to get the maximum element from +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# maximum(rdd) # 10 +#} +# @rdname maximum +# @aliases maximum,RDD setMethod("maximum", signature(x = "RDD"), function(x) { reduce(x, max) }) -#' Get the minimum element of an RDD. -#' -#' @param x The RDD to get the minimum element from -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' minimum(rdd) # 1 -#'} -#' @rdname minimum -#' @aliases minimum,RDD +# Get the minimum element of an RDD. +# +# @param x The RDD to get the minimum element from +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# minimum(rdd) # 1 +#} +# @rdname minimum +# @aliases minimum,RDD setMethod("minimum", signature(x = "RDD"), function(x) { reduce(x, min) }) -#' Add up the elements in an RDD. -#' -#' @param x The RDD to add up the elements in -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' sumRDD(rdd) # 55 -#'} -#' @rdname sumRDD -#' @aliases sumRDD,RDD +# Add up the elements in an RDD. +# +# @param x The RDD to add up the elements in +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# sumRDD(rdd) # 55 +#} +# @rdname sumRDD +# @aliases sumRDD,RDD setMethod("sumRDD", signature(x = "RDD"), function(x) { reduce(x, "+") }) -#' Applies a function to all elements in an RDD, and force evaluation. -#' -#' @param x The RDD to apply the function -#' @param func The function to be applied. -#' @return invisible NULL. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' foreach(rdd, function(x) { save(x, file=...) }) -#'} -#' @rdname foreach -#' @aliases foreach,RDD,function-method +# Applies a function to all elements in an RDD, and force evaluation. +# +# @param x The RDD to apply the function +# @param func The function to be applied. +# @return invisible NULL. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# foreach(rdd, function(x) { save(x, file=...) }) +#} +# @rdname foreach +# @aliases foreach,RDD,function-method setMethod("foreach", signature(x = "RDD", func = "function"), function(x, func) { @@ -697,37 +697,37 @@ setMethod("foreach", invisible(collect(mapPartitions(x, partition.func))) }) -#' Applies a function to each partition in an RDD, and force evaluation. -#' -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' foreachPartition(rdd, function(part) { save(part, file=...); NULL }) -#'} -#' @rdname foreach -#' @aliases foreachPartition,RDD,function-method +# Applies a function to each partition in an RDD, and force evaluation. +# +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# foreachPartition(rdd, function(part) { save(part, file=...); NULL }) +#} +# @rdname foreach +# @aliases foreachPartition,RDD,function-method setMethod("foreachPartition", signature(x = "RDD", func = "function"), function(x, func) { invisible(collect(mapPartitions(x, func))) }) -#' Take elements from an RDD. -#' -#' This function takes the first NUM elements in the RDD and -#' returns them in a list. -#' -#' @param x The RDD to take elements from -#' @param num Number of elements to take -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' take(rdd, 2L) # list(1, 2) -#'} -#' @rdname take -#' @aliases take,RDD,numeric-method +# Take elements from an RDD. +# +# This function takes the first NUM elements in the RDD and +# returns them in a list. +# +# @param x The RDD to take elements from +# @param num Number of elements to take +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# take(rdd, 2L) # list(1, 2) +#} +# @rdname take +# @aliases take,RDD,numeric-method setMethod("take", signature(x = "RDD", num = "numeric"), function(x, num) { @@ -762,39 +762,39 @@ setMethod("take", }) -#' First -#' -#' Return the first element of an RDD -#' -#' @rdname first -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' first(rdd) -#' } +# First +# +# Return the first element of an RDD +# +# @rdname first +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# first(rdd) +# } setMethod("first", signature(x = "RDD"), function(x) { take(x, 1)[[1]] }) -#' Removes the duplicates from RDD. -#' -#' This function returns a new RDD containing the distinct elements in the -#' given RDD. The same as `distinct()' in Spark. -#' -#' @param x The RDD to remove duplicates from. -#' @param numPartitions Number of partitions to create. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, c(1,2,2,3,3,3)) -#' sort(unlist(collect(distinct(rdd)))) # c(1, 2, 3) -#'} -#' @rdname distinct -#' @aliases distinct,RDD-method +# Removes the duplicates from RDD. +# +# This function returns a new RDD containing the distinct elements in the +# given RDD. The same as `distinct()' in Spark. +# +# @param x The RDD to remove duplicates from. +# @param numPartitions Number of partitions to create. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, c(1,2,2,3,3,3)) +# sort(unlist(collect(distinct(rdd)))) # c(1, 2, 3) +#} +# @rdname distinct +# @aliases distinct,RDD-method setMethod("distinct", signature(x = "RDD"), function(x, numPartitions = SparkR:::numPartitions(x)) { @@ -806,24 +806,24 @@ setMethod("distinct", resRDD }) -#' Return an RDD that is a sampled subset of the given RDD. -#' -#' The same as `sample()' in Spark. (We rename it due to signature -#' inconsistencies with the `sample()' function in R's base package.) -#' -#' @param x The RDD to sample elements from -#' @param withReplacement Sampling with replacement or not -#' @param fraction The (rough) sample target fraction -#' @param seed Randomness seed value -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' collect(sampleRDD(rdd, FALSE, 0.5, 1618L)) # ~5 distinct elements -#' collect(sampleRDD(rdd, TRUE, 0.5, 9L)) # ~5 elements possibly with duplicates -#'} -#' @rdname sampleRDD -#' @aliases sampleRDD,RDD +# Return an RDD that is a sampled subset of the given RDD. +# +# The same as `sample()' in Spark. (We rename it due to signature +# inconsistencies with the `sample()' function in R's base package.) +# +# @param x The RDD to sample elements from +# @param withReplacement Sampling with replacement or not +# @param fraction The (rough) sample target fraction +# @param seed Randomness seed value +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# collect(sampleRDD(rdd, FALSE, 0.5, 1618L)) # ~5 distinct elements +# collect(sampleRDD(rdd, TRUE, 0.5, 9L)) # ~5 elements possibly with duplicates +#} +# @rdname sampleRDD +# @aliases sampleRDD,RDD setMethod("sampleRDD", signature(x = "RDD", withReplacement = "logical", fraction = "numeric", seed = "integer"), @@ -867,23 +867,23 @@ setMethod("sampleRDD", lapplyPartitionsWithIndex(x, samplingFunc) }) -#' Return a list of the elements that are a sampled subset of the given RDD. -#' -#' @param x The RDD to sample elements from -#' @param withReplacement Sampling with replacement or not -#' @param num Number of elements to return -#' @param seed Randomness seed value -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:100) -#' # exactly 5 elements sampled, which may not be distinct -#' takeSample(rdd, TRUE, 5L, 1618L) -#' # exactly 5 distinct elements sampled -#' takeSample(rdd, FALSE, 5L, 16181618L) -#'} -#' @rdname takeSample -#' @aliases takeSample,RDD +# Return a list of the elements that are a sampled subset of the given RDD. +# +# @param x The RDD to sample elements from +# @param withReplacement Sampling with replacement or not +# @param num Number of elements to return +# @param seed Randomness seed value +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:100) +# # exactly 5 elements sampled, which may not be distinct +# takeSample(rdd, TRUE, 5L, 1618L) +# # exactly 5 distinct elements sampled +# takeSample(rdd, FALSE, 5L, 16181618L) +#} +# @rdname takeSample +# @aliases takeSample,RDD setMethod("takeSample", signature(x = "RDD", withReplacement = "logical", num = "integer", seed = "integer"), function(x, withReplacement, num, seed) { @@ -930,18 +930,18 @@ setMethod("takeSample", signature(x = "RDD", withReplacement = "logical", sample(samples)[1:total] }) -#' Creates tuples of the elements in this RDD by applying a function. -#' -#' @param x The RDD. -#' @param func The function to be applied. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(1, 2, 3)) -#' collect(keyBy(rdd, function(x) { x*x })) # list(list(1, 1), list(4, 2), list(9, 3)) -#'} -#' @rdname keyBy -#' @aliases keyBy,RDD +# Creates tuples of the elements in this RDD by applying a function. +# +# @param x The RDD. +# @param func The function to be applied. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(1, 2, 3)) +# collect(keyBy(rdd, function(x) { x*x })) # list(list(1, 1), list(4, 2), list(9, 3)) +#} +# @rdname keyBy +# @aliases keyBy,RDD setMethod("keyBy", signature(x = "RDD", func = "function"), function(x, func) { @@ -951,44 +951,44 @@ setMethod("keyBy", lapply(x, apply.func) }) -#' Return a new RDD that has exactly numPartitions partitions. -#' Can increase or decrease the level of parallelism in this RDD. Internally, -#' this uses a shuffle to redistribute data. -#' If you are decreasing the number of partitions in this RDD, consider using -#' coalesce, which can avoid performing a shuffle. -#' -#' @param x The RDD. -#' @param numPartitions Number of partitions to create. -#' @seealso coalesce -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(1, 2, 3, 4, 5, 6, 7), 4L) -#' numPartitions(rdd) # 4 -#' numPartitions(repartition(rdd, 2L)) # 2 -#'} -#' @rdname repartition -#' @aliases repartition,RDD +# Return a new RDD that has exactly numPartitions partitions. +# Can increase or decrease the level of parallelism in this RDD. Internally, +# this uses a shuffle to redistribute data. +# If you are decreasing the number of partitions in this RDD, consider using +# coalesce, which can avoid performing a shuffle. +# +# @param x The RDD. +# @param numPartitions Number of partitions to create. +# @seealso coalesce +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(1, 2, 3, 4, 5, 6, 7), 4L) +# numPartitions(rdd) # 4 +# numPartitions(repartition(rdd, 2L)) # 2 +#} +# @rdname repartition +# @aliases repartition,RDD setMethod("repartition", signature(x = "RDD", numPartitions = "numeric"), function(x, numPartitions) { coalesce(x, numPartitions, TRUE) }) -#' Return a new RDD that is reduced into numPartitions partitions. -#' -#' @param x The RDD. -#' @param numPartitions Number of partitions to create. -#' @seealso repartition -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(1, 2, 3, 4, 5), 3L) -#' numPartitions(rdd) # 3 -#' numPartitions(coalesce(rdd, 1L)) # 1 -#'} -#' @rdname coalesce -#' @aliases coalesce,RDD +# Return a new RDD that is reduced into numPartitions partitions. +# +# @param x The RDD. +# @param numPartitions Number of partitions to create. +# @seealso repartition +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(1, 2, 3, 4, 5), 3L) +# numPartitions(rdd) # 3 +# numPartitions(coalesce(rdd, 1L)) # 1 +#} +# @rdname coalesce +# @aliases coalesce,RDD setMethod("coalesce", signature(x = "RDD", numPartitions = "numeric"), function(x, numPartitions, shuffle = FALSE) { @@ -1012,19 +1012,19 @@ setMethod("coalesce", } }) -#' Save this RDD as a SequenceFile of serialized objects. -#' -#' @param x The RDD to save -#' @param path The directory where the file is saved -#' @seealso objectFile -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:3) -#' saveAsObjectFile(rdd, "/tmp/sparkR-tmp") -#'} -#' @rdname saveAsObjectFile -#' @aliases saveAsObjectFile,RDD +# Save this RDD as a SequenceFile of serialized objects. +# +# @param x The RDD to save +# @param path The directory where the file is saved +# @seealso objectFile +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:3) +# saveAsObjectFile(rdd, "/tmp/sparkR-tmp") +#} +# @rdname saveAsObjectFile +# @aliases saveAsObjectFile,RDD setMethod("saveAsObjectFile", signature(x = "RDD", path = "character"), function(x, path) { @@ -1037,18 +1037,18 @@ setMethod("saveAsObjectFile", invisible(callJMethod(getJRDD(x), "saveAsObjectFile", path)) }) -#' Save this RDD as a text file, using string representations of elements. -#' -#' @param x The RDD to save -#' @param path The directory where the partitions of the text file are saved -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:3) -#' saveAsTextFile(rdd, "/tmp/sparkR-tmp") -#'} -#' @rdname saveAsTextFile -#' @aliases saveAsTextFile,RDD +# Save this RDD as a text file, using string representations of elements. +# +# @param x The RDD to save +# @param path The directory where the partitions of the text file are saved +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:3) +# saveAsTextFile(rdd, "/tmp/sparkR-tmp") +#} +# @rdname saveAsTextFile +# @aliases saveAsTextFile,RDD setMethod("saveAsTextFile", signature(x = "RDD", path = "character"), function(x, path) { @@ -1061,21 +1061,21 @@ setMethod("saveAsTextFile", callJMethod(getJRDD(stringRdd, serializedMode = "string"), "saveAsTextFile", path)) }) -#' Sort an RDD by the given key function. -#' -#' @param x An RDD to be sorted. -#' @param func A function used to compute the sort key for each element. -#' @param ascending A flag to indicate whether the sorting is ascending or descending. -#' @param numPartitions Number of partitions to create. -#' @return An RDD where all elements are sorted. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(3, 2, 1)) -#' collect(sortBy(rdd, function(x) { x })) # list (1, 2, 3) -#'} -#' @rdname sortBy -#' @aliases sortBy,RDD,RDD-method +# Sort an RDD by the given key function. +# +# @param x An RDD to be sorted. +# @param func A function used to compute the sort key for each element. +# @param ascending A flag to indicate whether the sorting is ascending or descending. +# @param numPartitions Number of partitions to create. +# @return An RDD where all elements are sorted. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(3, 2, 1)) +# collect(sortBy(rdd, function(x) { x })) # list (1, 2, 3) +#} +# @rdname sortBy +# @aliases sortBy,RDD,RDD-method setMethod("sortBy", signature(x = "RDD", func = "function"), function(x, func, ascending = TRUE, numPartitions = SparkR:::numPartitions(x)) { @@ -1137,97 +1137,97 @@ takeOrderedElem <- function(x, num, ascending = TRUE) { resList } -#' Returns the first N elements from an RDD in ascending order. -#' -#' @param x An RDD. -#' @param num Number of elements to return. -#' @return The first N elements from the RDD in ascending order. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(10, 1, 2, 9, 3, 4, 5, 6, 7)) -#' takeOrdered(rdd, 6L) # list(1, 2, 3, 4, 5, 6) -#'} -#' @rdname takeOrdered -#' @aliases takeOrdered,RDD,RDD-method +# Returns the first N elements from an RDD in ascending order. +# +# @param x An RDD. +# @param num Number of elements to return. +# @return The first N elements from the RDD in ascending order. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(10, 1, 2, 9, 3, 4, 5, 6, 7)) +# takeOrdered(rdd, 6L) # list(1, 2, 3, 4, 5, 6) +#} +# @rdname takeOrdered +# @aliases takeOrdered,RDD,RDD-method setMethod("takeOrdered", signature(x = "RDD", num = "integer"), function(x, num) { takeOrderedElem(x, num) }) -#' Returns the top N elements from an RDD. -#' -#' @param x An RDD. -#' @param num Number of elements to return. -#' @return The top N elements from the RDD. -#' @rdname top -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(10, 1, 2, 9, 3, 4, 5, 6, 7)) -#' top(rdd, 6L) # list(10, 9, 7, 6, 5, 4) -#'} -#' @rdname top -#' @aliases top,RDD,RDD-method +# Returns the top N elements from an RDD. +# +# @param x An RDD. +# @param num Number of elements to return. +# @return The top N elements from the RDD. +# @rdname top +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(10, 1, 2, 9, 3, 4, 5, 6, 7)) +# top(rdd, 6L) # list(10, 9, 7, 6, 5, 4) +#} +# @rdname top +# @aliases top,RDD,RDD-method setMethod("top", signature(x = "RDD", num = "integer"), function(x, num) { takeOrderedElem(x, num, FALSE) }) -#' Fold an RDD using a given associative function and a neutral "zero value". -#' -#' Aggregate the elements of each partition, and then the results for all the -#' partitions, using a given associative function and a neutral "zero value". -#' -#' @param x An RDD. -#' @param zeroValue A neutral "zero value". -#' @param op An associative function for the folding operation. -#' @return The folding result. -#' @rdname fold -#' @seealso reduce -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(1, 2, 3, 4, 5)) -#' fold(rdd, 0, "+") # 15 -#'} -#' @rdname fold -#' @aliases fold,RDD,RDD-method +# Fold an RDD using a given associative function and a neutral "zero value". +# +# Aggregate the elements of each partition, and then the results for all the +# partitions, using a given associative function and a neutral "zero value". +# +# @param x An RDD. +# @param zeroValue A neutral "zero value". +# @param op An associative function for the folding operation. +# @return The folding result. +# @rdname fold +# @seealso reduce +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(1, 2, 3, 4, 5)) +# fold(rdd, 0, "+") # 15 +#} +# @rdname fold +# @aliases fold,RDD,RDD-method setMethod("fold", signature(x = "RDD", zeroValue = "ANY", op = "ANY"), function(x, zeroValue, op) { aggregateRDD(x, zeroValue, op, op) }) -#' Aggregate an RDD using the given combine functions and a neutral "zero value". -#' -#' Aggregate the elements of each partition, and then the results for all the -#' partitions, using given combine functions and a neutral "zero value". -#' -#' @param x An RDD. -#' @param zeroValue A neutral "zero value". -#' @param seqOp A function to aggregate the RDD elements. It may return a different -#' result type from the type of the RDD elements. -#' @param combOp A function to aggregate results of seqOp. -#' @return The aggregation result. -#' @rdname aggregateRDD -#' @seealso reduce -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(1, 2, 3, 4)) -#' zeroValue <- list(0, 0) -#' seqOp <- function(x, y) { list(x[[1]] + y, x[[2]] + 1) } -#' combOp <- function(x, y) { list(x[[1]] + y[[1]], x[[2]] + y[[2]]) } -#' aggregateRDD(rdd, zeroValue, seqOp, combOp) # list(10, 4) -#'} -#' @rdname aggregateRDD -#' @aliases aggregateRDD,RDD,RDD-method +# Aggregate an RDD using the given combine functions and a neutral "zero value". +# +# Aggregate the elements of each partition, and then the results for all the +# partitions, using given combine functions and a neutral "zero value". +# +# @param x An RDD. +# @param zeroValue A neutral "zero value". +# @param seqOp A function to aggregate the RDD elements. It may return a different +# result type from the type of the RDD elements. +# @param combOp A function to aggregate results of seqOp. +# @return The aggregation result. +# @rdname aggregateRDD +# @seealso reduce +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(1, 2, 3, 4)) +# zeroValue <- list(0, 0) +# seqOp <- function(x, y) { list(x[[1]] + y, x[[2]] + 1) } +# combOp <- function(x, y) { list(x[[1]] + y[[1]], x[[2]] + y[[2]]) } +# aggregateRDD(rdd, zeroValue, seqOp, combOp) # list(10, 4) +#} +# @rdname aggregateRDD +# @aliases aggregateRDD,RDD,RDD-method setMethod("aggregateRDD", signature(x = "RDD", zeroValue = "ANY", seqOp = "ANY", combOp = "ANY"), function(x, zeroValue, seqOp, combOp) { @@ -1240,25 +1240,25 @@ setMethod("aggregateRDD", Reduce(combOp, partitionList, zeroValue) }) -#' Pipes elements to a forked external process. -#' -#' The same as 'pipe()' in Spark. -#' -#' @param x The RDD whose elements are piped to the forked external process. -#' @param command The command to fork an external process. -#' @param env A named list to set environment variables of the external process. -#' @return A new RDD created by piping all elements to a forked external process. -#' @rdname pipeRDD -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' collect(pipeRDD(rdd, "more") -#' Output: c("1", "2", ..., "10") -#'} -#' @rdname pipeRDD -#' @aliases pipeRDD,RDD,character-method +# Pipes elements to a forked external process. +# +# The same as 'pipe()' in Spark. +# +# @param x The RDD whose elements are piped to the forked external process. +# @param command The command to fork an external process. +# @param env A named list to set environment variables of the external process. +# @return A new RDD created by piping all elements to a forked external process. +# @rdname pipeRDD +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# collect(pipeRDD(rdd, "more") +# Output: c("1", "2", ..., "10") +#} +# @rdname pipeRDD +# @aliases pipeRDD,RDD,character-method setMethod("pipeRDD", signature(x = "RDD", command = "character"), function(x, command, env = list()) { @@ -1274,41 +1274,41 @@ setMethod("pipeRDD", }) # TODO: Consider caching the name in the RDD's environment -#' Return an RDD's name. -#' -#' @param x The RDD whose name is returned. -#' @rdname name -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(1,2,3)) -#' name(rdd) # NULL (if not set before) -#'} -#' @rdname name -#' @aliases name,RDD +# Return an RDD's name. +# +# @param x The RDD whose name is returned. +# @rdname name +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(1,2,3)) +# name(rdd) # NULL (if not set before) +#} +# @rdname name +# @aliases name,RDD setMethod("name", signature(x = "RDD"), function(x) { callJMethod(getJRDD(x), "name") }) -#' Set an RDD's name. -#' -#' @param x The RDD whose name is to be set. -#' @param name The RDD name to be set. -#' @return a new RDD renamed. -#' @rdname setName -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(1,2,3)) -#' setName(rdd, "myRDD") -#' name(rdd) # "myRDD" -#'} -#' @rdname setName -#' @aliases setName,RDD +# Set an RDD's name. +# +# @param x The RDD whose name is to be set. +# @param name The RDD name to be set. +# @return a new RDD renamed. +# @rdname setName +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(1,2,3)) +# setName(rdd, "myRDD") +# name(rdd) # "myRDD" +#} +# @rdname setName +# @aliases setName,RDD setMethod("setName", signature(x = "RDD", name = "character"), function(x, name) { @@ -1316,25 +1316,25 @@ setMethod("setName", x }) -#' Zip an RDD with generated unique Long IDs. -#' -#' Items in the kth partition will get ids k, n+k, 2*n+k, ..., where -#' n is the number of partitions. So there may exist gaps, but this -#' method won't trigger a spark job, which is different from -#' zipWithIndex. -#' -#' @param x An RDD to be zipped. -#' @return An RDD with zipped items. -#' @seealso zipWithIndex -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list("a", "b", "c", "d", "e"), 3L) -#' collect(zipWithUniqueId(rdd)) -#' # list(list("a", 0), list("b", 3), list("c", 1), list("d", 4), list("e", 2)) -#'} -#' @rdname zipWithUniqueId -#' @aliases zipWithUniqueId,RDD +# Zip an RDD with generated unique Long IDs. +# +# Items in the kth partition will get ids k, n+k, 2*n+k, ..., where +# n is the number of partitions. So there may exist gaps, but this +# method won't trigger a spark job, which is different from +# zipWithIndex. +# +# @param x An RDD to be zipped. +# @return An RDD with zipped items. +# @seealso zipWithIndex +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list("a", "b", "c", "d", "e"), 3L) +# collect(zipWithUniqueId(rdd)) +# # list(list("a", 0), list("b", 3), list("c", 1), list("d", 4), list("e", 2)) +#} +# @rdname zipWithUniqueId +# @aliases zipWithUniqueId,RDD setMethod("zipWithUniqueId", signature(x = "RDD"), function(x) { @@ -1353,28 +1353,28 @@ setMethod("zipWithUniqueId", lapplyPartitionsWithIndex(x, partitionFunc) }) -#' Zip an RDD with its element indices. -#' -#' The ordering is first based on the partition index and then the -#' ordering of items within each partition. So the first item in -#' the first partition gets index 0, and the last item in the last -#' partition receives the largest index. -#' -#' This method needs to trigger a Spark job when this RDD contains -#' more than one partition. -#' -#' @param x An RDD to be zipped. -#' @return An RDD with zipped items. -#' @seealso zipWithUniqueId -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list("a", "b", "c", "d", "e"), 3L) -#' collect(zipWithIndex(rdd)) -#' # list(list("a", 0), list("b", 1), list("c", 2), list("d", 3), list("e", 4)) -#'} -#' @rdname zipWithIndex -#' @aliases zipWithIndex,RDD +# Zip an RDD with its element indices. +# +# The ordering is first based on the partition index and then the +# ordering of items within each partition. So the first item in +# the first partition gets index 0, and the last item in the last +# partition receives the largest index. +# +# This method needs to trigger a Spark job when this RDD contains +# more than one partition. +# +# @param x An RDD to be zipped. +# @return An RDD with zipped items. +# @seealso zipWithUniqueId +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list("a", "b", "c", "d", "e"), 3L) +# collect(zipWithIndex(rdd)) +# # list(list("a", 0), list("b", 1), list("c", 2), list("d", 3), list("e", 4)) +#} +# @rdname zipWithIndex +# @aliases zipWithIndex,RDD setMethod("zipWithIndex", signature(x = "RDD"), function(x) { @@ -1406,20 +1406,20 @@ setMethod("zipWithIndex", lapplyPartitionsWithIndex(x, partitionFunc) }) -#' Coalesce all elements within each partition of an RDD into a list. -#' -#' @param x An RDD. -#' @return An RDD created by coalescing all elements within -#' each partition into a list. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, as.list(1:4), 2L) -#' collect(glom(rdd)) -#' # list(list(1, 2), list(3, 4)) -#'} -#' @rdname glom -#' @aliases glom,RDD +# Coalesce all elements within each partition of an RDD into a list. +# +# @param x An RDD. +# @return An RDD created by coalescing all elements within +# each partition into a list. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, as.list(1:4), 2L) +# collect(glom(rdd)) +# # list(list(1, 2), list(3, 4)) +#} +# @rdname glom +# @aliases glom,RDD setMethod("glom", signature(x = "RDD"), function(x) { @@ -1432,21 +1432,21 @@ setMethod("glom", ############ Binary Functions ############# -#' Return the union RDD of two RDDs. -#' The same as union() in Spark. -#' -#' @param x An RDD. -#' @param y An RDD. -#' @return a new RDD created by performing the simple union (witout removing -#' duplicates) of two input RDDs. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:3) -#' unionRDD(rdd, rdd) # 1, 2, 3, 1, 2, 3 -#'} -#' @rdname unionRDD -#' @aliases unionRDD,RDD,RDD-method +# Return the union RDD of two RDDs. +# The same as union() in Spark. +# +# @param x An RDD. +# @param y An RDD. +# @return a new RDD created by performing the simple union (witout removing +# duplicates) of two input RDDs. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:3) +# unionRDD(rdd, rdd) # 1, 2, 3, 1, 2, 3 +#} +# @rdname unionRDD +# @aliases unionRDD,RDD,RDD-method setMethod("unionRDD", signature(x = "RDD", y = "RDD"), function(x, y) { @@ -1463,27 +1463,27 @@ setMethod("unionRDD", union.rdd }) -#' Zip an RDD with another RDD. -#' -#' Zips this RDD with another one, returning key-value pairs with the -#' first element in each RDD second element in each RDD, etc. Assumes -#' that the two RDDs have the same number of partitions and the same -#' number of elements in each partition (e.g. one was made through -#' a map on the other). -#' -#' @param x An RDD to be zipped. -#' @param other Another RDD to be zipped. -#' @return An RDD zipped from the two RDDs. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd1 <- parallelize(sc, 0:4) -#' rdd2 <- parallelize(sc, 1000:1004) -#' collect(zipRDD(rdd1, rdd2)) -#' # list(list(0, 1000), list(1, 1001), list(2, 1002), list(3, 1003), list(4, 1004)) -#'} -#' @rdname zipRDD -#' @aliases zipRDD,RDD +# Zip an RDD with another RDD. +# +# Zips this RDD with another one, returning key-value pairs with the +# first element in each RDD second element in each RDD, etc. Assumes +# that the two RDDs have the same number of partitions and the same +# number of elements in each partition (e.g. one was made through +# a map on the other). +# +# @param x An RDD to be zipped. +# @param other Another RDD to be zipped. +# @return An RDD zipped from the two RDDs. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd1 <- parallelize(sc, 0:4) +# rdd2 <- parallelize(sc, 1000:1004) +# collect(zipRDD(rdd1, rdd2)) +# # list(list(0, 1000), list(1, 1001), list(2, 1002), list(3, 1003), list(4, 1004)) +#} +# @rdname zipRDD +# @aliases zipRDD,RDD setMethod("zipRDD", signature(x = "RDD", other = "RDD"), function(x, other) { @@ -1502,24 +1502,24 @@ setMethod("zipRDD", mergePartitions(rdd, TRUE) }) -#' Cartesian product of this RDD and another one. -#' -#' Return the Cartesian product of this RDD and another one, -#' that is, the RDD of all pairs of elements (a, b) where a -#' is in this and b is in other. -#' -#' @param x An RDD. -#' @param other An RDD. -#' @return A new RDD which is the Cartesian product of these two RDDs. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:2) -#' sortByKey(cartesian(rdd, rdd)) -#' # list(list(1, 1), list(1, 2), list(2, 1), list(2, 2)) -#'} -#' @rdname cartesian -#' @aliases cartesian,RDD,RDD-method +# Cartesian product of this RDD and another one. +# +# Return the Cartesian product of this RDD and another one, +# that is, the RDD of all pairs of elements (a, b) where a +# is in this and b is in other. +# +# @param x An RDD. +# @param other An RDD. +# @return A new RDD which is the Cartesian product of these two RDDs. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:2) +# sortByKey(cartesian(rdd, rdd)) +# # list(list(1, 1), list(1, 2), list(2, 1), list(2, 2)) +#} +# @rdname cartesian +# @aliases cartesian,RDD,RDD-method setMethod("cartesian", signature(x = "RDD", other = "RDD"), function(x, other) { @@ -1532,24 +1532,24 @@ setMethod("cartesian", mergePartitions(rdd, FALSE) }) -#' Subtract an RDD with another RDD. -#' -#' Return an RDD with the elements from this that are not in other. -#' -#' @param x An RDD. -#' @param other An RDD. -#' @param numPartitions Number of the partitions in the result RDD. -#' @return An RDD with the elements from this that are not in other. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd1 <- parallelize(sc, list(1, 1, 2, 2, 3, 4)) -#' rdd2 <- parallelize(sc, list(2, 4)) -#' collect(subtract(rdd1, rdd2)) -#' # list(1, 1, 3) -#'} -#' @rdname subtract -#' @aliases subtract,RDD +# Subtract an RDD with another RDD. +# +# Return an RDD with the elements from this that are not in other. +# +# @param x An RDD. +# @param other An RDD. +# @param numPartitions Number of the partitions in the result RDD. +# @return An RDD with the elements from this that are not in other. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd1 <- parallelize(sc, list(1, 1, 2, 2, 3, 4)) +# rdd2 <- parallelize(sc, list(2, 4)) +# collect(subtract(rdd1, rdd2)) +# # list(1, 1, 3) +#} +# @rdname subtract +# @aliases subtract,RDD setMethod("subtract", signature(x = "RDD", other = "RDD"), function(x, other, numPartitions = SparkR:::numPartitions(x)) { @@ -1559,28 +1559,28 @@ setMethod("subtract", keys(subtractByKey(rdd1, rdd2, numPartitions)) }) -#' Intersection of this RDD and another one. -#' -#' Return the intersection of this RDD and another one. -#' The output will not contain any duplicate elements, -#' even if the input RDDs did. Performs a hash partition -#' across the cluster. -#' Note that this method performs a shuffle internally. -#' -#' @param x An RDD. -#' @param other An RDD. -#' @param numPartitions The number of partitions in the result RDD. -#' @return An RDD which is the intersection of these two RDDs. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd1 <- parallelize(sc, list(1, 10, 2, 3, 4, 5)) -#' rdd2 <- parallelize(sc, list(1, 6, 2, 3, 7, 8)) -#' collect(sortBy(intersection(rdd1, rdd2), function(x) { x })) -#' # list(1, 2, 3) -#'} -#' @rdname intersection -#' @aliases intersection,RDD +# Intersection of this RDD and another one. +# +# Return the intersection of this RDD and another one. +# The output will not contain any duplicate elements, +# even if the input RDDs did. Performs a hash partition +# across the cluster. +# Note that this method performs a shuffle internally. +# +# @param x An RDD. +# @param other An RDD. +# @param numPartitions The number of partitions in the result RDD. +# @return An RDD which is the intersection of these two RDDs. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd1 <- parallelize(sc, list(1, 10, 2, 3, 4, 5)) +# rdd2 <- parallelize(sc, list(1, 6, 2, 3, 7, 8)) +# collect(sortBy(intersection(rdd1, rdd2), function(x) { x })) +# # list(1, 2, 3) +#} +# @rdname intersection +# @aliases intersection,RDD setMethod("intersection", signature(x = "RDD", other = "RDD"), function(x, other, numPartitions = SparkR:::numPartitions(x)) { @@ -1596,26 +1596,26 @@ setMethod("intersection", keys(filterRDD(cogroup(rdd1, rdd2, numPartitions = numPartitions), filterFunction)) }) -#' Zips an RDD's partitions with one (or more) RDD(s). -#' Same as zipPartitions in Spark. -#' -#' @param ... RDDs to be zipped. -#' @param func A function to transform zipped partitions. -#' @return A new RDD by applying a function to the zipped partitions. -#' Assumes that all the RDDs have the *same number of partitions*, but -#' does *not* require them to have the same number of elements in each partition. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd1 <- parallelize(sc, 1:2, 2L) # 1, 2 -#' rdd2 <- parallelize(sc, 1:4, 2L) # 1:2, 3:4 -#' rdd3 <- parallelize(sc, 1:6, 2L) # 1:3, 4:6 -#' collect(zipPartitions(rdd1, rdd2, rdd3, -#' func = function(x, y, z) { list(list(x, y, z))} )) -#' # list(list(1, c(1,2), c(1,2,3)), list(2, c(3,4), c(4,5,6))) -#'} -#' @rdname zipRDD -#' @aliases zipPartitions,RDD +# Zips an RDD's partitions with one (or more) RDD(s). +# Same as zipPartitions in Spark. +# +# @param ... RDDs to be zipped. +# @param func A function to transform zipped partitions. +# @return A new RDD by applying a function to the zipped partitions. +# Assumes that all the RDDs have the *same number of partitions*, but +# does *not* require them to have the same number of elements in each partition. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd1 <- parallelize(sc, 1:2, 2L) # 1, 2 +# rdd2 <- parallelize(sc, 1:4, 2L) # 1:2, 3:4 +# rdd3 <- parallelize(sc, 1:6, 2L) # 1:3, 4:6 +# collect(zipPartitions(rdd1, rdd2, rdd3, +# func = function(x, y, z) { list(list(x, y, z))} )) +# # list(list(1, c(1,2), c(1,2,3)), list(2, c(3,4), c(4,5,6))) +#} +# @rdname zipRDD +# @aliases zipPartitions,RDD setMethod("zipPartitions", "RDD", function(..., func) { diff --git a/R/pkg/R/SQLContext.R b/R/pkg/R/SQLContext.R index 4f05ba524a01a..cae06e6af2bff 100644 --- a/R/pkg/R/SQLContext.R +++ b/R/pkg/R/SQLContext.R @@ -150,21 +150,21 @@ createDataFrame <- function(sqlCtx, data, schema = NULL, samplingRatio = 1.0) { dataFrame(sdf) } -#' toDF -#' -#' Converts an RDD to a DataFrame by infer the types. -#' -#' @param x An RDD -#' -#' @rdname DataFrame -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' sqlCtx <- sparkRSQL.init(sc) -#' rdd <- lapply(parallelize(sc, 1:10), function(x) list(a=x, b=as.character(x))) -#' df <- toDF(rdd) -#' } +# toDF +# +# Converts an RDD to a DataFrame by infer the types. +# +# @param x An RDD +# +# @rdname DataFrame +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# sqlCtx <- sparkRSQL.init(sc) +# rdd <- lapply(parallelize(sc, 1:10), function(x) list(a=x, b=as.character(x))) +# df <- toDF(rdd) +# } setGeneric("toDF", function(x, ...) { standardGeneric("toDF") }) @@ -207,23 +207,23 @@ jsonFile <- function(sqlCtx, path) { } -#' JSON RDD -#' -#' Loads an RDD storing one JSON object per string as a DataFrame. -#' -#' @param sqlCtx SQLContext to use -#' @param rdd An RDD of JSON string -#' @param schema A StructType object to use as schema -#' @param samplingRatio The ratio of simpling used to infer the schema -#' @return A DataFrame -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' sqlCtx <- sparkRSQL.init(sc) -#' rdd <- texFile(sc, "path/to/json") -#' df <- jsonRDD(sqlCtx, rdd) -#' } +# JSON RDD +# +# Loads an RDD storing one JSON object per string as a DataFrame. +# +# @param sqlCtx SQLContext to use +# @param rdd An RDD of JSON string +# @param schema A StructType object to use as schema +# @param samplingRatio The ratio of simpling used to infer the schema +# @return A DataFrame +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# sqlCtx <- sparkRSQL.init(sc) +# rdd <- texFile(sc, "path/to/json") +# df <- jsonRDD(sqlCtx, rdd) +# } # TODO: support schema jsonRDD <- function(sqlCtx, rdd, schema = NULL, samplingRatio = 1.0) { diff --git a/R/pkg/R/broadcast.R b/R/pkg/R/broadcast.R index 583fa2e7fdcfd..23dc38780716e 100644 --- a/R/pkg/R/broadcast.R +++ b/R/pkg/R/broadcast.R @@ -23,21 +23,21 @@ .broadcastValues <- new.env() .broadcastIdToName <- new.env() -#' @title S4 class that represents a Broadcast variable -#' @description Broadcast variables can be created using the broadcast -#' function from a \code{SparkContext}. -#' @rdname broadcast-class -#' @seealso broadcast -#' -#' @param id Id of the backing Spark broadcast variable -#' @export +# @title S4 class that represents a Broadcast variable +# @description Broadcast variables can be created using the broadcast +# function from a \code{SparkContext}. +# @rdname broadcast-class +# @seealso broadcast +# +# @param id Id of the backing Spark broadcast variable +# @export setClass("Broadcast", slots = list(id = "character")) -#' @rdname broadcast-class -#' @param value Value of the broadcast variable -#' @param jBroadcastRef reference to the backing Java broadcast object -#' @param objName name of broadcasted object -#' @export +# @rdname broadcast-class +# @param value Value of the broadcast variable +# @param jBroadcastRef reference to the backing Java broadcast object +# @param objName name of broadcasted object +# @export Broadcast <- function(id, value, jBroadcastRef, objName) { .broadcastValues[[id]] <- value .broadcastNames[[as.character(objName)]] <- jBroadcastRef @@ -45,13 +45,13 @@ Broadcast <- function(id, value, jBroadcastRef, objName) { new("Broadcast", id = id) } -#' @description -#' \code{value} can be used to get the value of a broadcast variable inside -#' a distributed function. -#' -#' @param bcast The broadcast variable to get -#' @rdname broadcast -#' @aliases value,Broadcast-method +# @description +# \code{value} can be used to get the value of a broadcast variable inside +# a distributed function. +# +# @param bcast The broadcast variable to get +# @rdname broadcast +# @aliases value,Broadcast-method setMethod("value", signature(bcast = "Broadcast"), function(bcast) { @@ -62,24 +62,24 @@ setMethod("value", } }) -#' Internal function to set values of a broadcast variable. -#' -#' This function is used internally by Spark to set the value of a broadcast -#' variable on workers. Not intended for use outside the package. -#' -#' @rdname broadcast-internal -#' @seealso broadcast, value +# Internal function to set values of a broadcast variable. +# +# This function is used internally by Spark to set the value of a broadcast +# variable on workers. Not intended for use outside the package. +# +# @rdname broadcast-internal +# @seealso broadcast, value -#' @param bcastId The id of broadcast variable to set -#' @param value The value to be set -#' @export +# @param bcastId The id of broadcast variable to set +# @param value The value to be set +# @export setBroadcastValue <- function(bcastId, value) { bcastIdStr <- as.character(bcastId) .broadcastValues[[bcastIdStr]] <- value } -#' Helper function to clear the list of broadcast variables we know about -#' Should be called when the SparkR JVM backend is shutdown +# Helper function to clear the list of broadcast variables we know about +# Should be called when the SparkR JVM backend is shutdown clearBroadcastVariables <- function() { bcasts <- ls(.broadcastNames) rm(list = bcasts, envir = .broadcastNames) diff --git a/R/pkg/R/context.R b/R/pkg/R/context.R index b4845b6948997..43be9c904fdf6 100644 --- a/R/pkg/R/context.R +++ b/R/pkg/R/context.R @@ -25,27 +25,27 @@ getMinPartitions <- function(sc, minPartitions) { as.integer(minPartitions) } -#' Create an RDD from a text file. -#' -#' This function reads a text file from HDFS, a local file system (available on all -#' nodes), or any Hadoop-supported file system URI, and creates an -#' RDD of strings from it. -#' -#' @param sc SparkContext to use -#' @param path Path of file to read. A vector of multiple paths is allowed. -#' @param minPartitions Minimum number of partitions to be created. If NULL, the default -#' value is chosen based on available parallelism. -#' @return RDD where each item is of type \code{character} -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' lines <- textFile(sc, "myfile.txt") -#'} +# Create an RDD from a text file. +# +# This function reads a text file from HDFS, a local file system (available on all +# nodes), or any Hadoop-supported file system URI, and creates an +# RDD of strings from it. +# +# @param sc SparkContext to use +# @param path Path of file to read. A vector of multiple paths is allowed. +# @param minPartitions Minimum number of partitions to be created. If NULL, the default +# value is chosen based on available parallelism. +# @return RDD where each item is of type \code{character} +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# lines <- textFile(sc, "myfile.txt") +#} textFile <- function(sc, path, minPartitions = NULL) { # Allow the user to have a more flexible definiton of the text file path path <- suppressWarnings(normalizePath(path)) - #' Convert a string vector of paths to a string containing comma separated paths + # Convert a string vector of paths to a string containing comma separated paths path <- paste(path, collapse = ",") jrdd <- callJMethod(sc, "textFile", path, getMinPartitions(sc, minPartitions)) @@ -53,27 +53,27 @@ textFile <- function(sc, path, minPartitions = NULL) { RDD(jrdd, "string") } -#' Load an RDD saved as a SequenceFile containing serialized objects. -#' -#' The file to be loaded should be one that was previously generated by calling -#' saveAsObjectFile() of the RDD class. -#' -#' @param sc SparkContext to use -#' @param path Path of file to read. A vector of multiple paths is allowed. -#' @param minPartitions Minimum number of partitions to be created. If NULL, the default -#' value is chosen based on available parallelism. -#' @return RDD containing serialized R objects. -#' @seealso saveAsObjectFile -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- objectFile(sc, "myfile") -#'} +# Load an RDD saved as a SequenceFile containing serialized objects. +# +# The file to be loaded should be one that was previously generated by calling +# saveAsObjectFile() of the RDD class. +# +# @param sc SparkContext to use +# @param path Path of file to read. A vector of multiple paths is allowed. +# @param minPartitions Minimum number of partitions to be created. If NULL, the default +# value is chosen based on available parallelism. +# @return RDD containing serialized R objects. +# @seealso saveAsObjectFile +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- objectFile(sc, "myfile") +#} objectFile <- function(sc, path, minPartitions = NULL) { # Allow the user to have a more flexible definiton of the text file path path <- suppressWarnings(normalizePath(path)) - #' Convert a string vector of paths to a string containing comma separated paths + # Convert a string vector of paths to a string containing comma separated paths path <- paste(path, collapse = ",") jrdd <- callJMethod(sc, "objectFile", path, getMinPartitions(sc, minPartitions)) @@ -81,24 +81,24 @@ objectFile <- function(sc, path, minPartitions = NULL) { RDD(jrdd, "byte") } -#' Create an RDD from a homogeneous list or vector. -#' -#' This function creates an RDD from a local homogeneous list in R. The elements -#' in the list are split into \code{numSlices} slices and distributed to nodes -#' in the cluster. -#' -#' @param sc SparkContext to use -#' @param coll collection to parallelize -#' @param numSlices number of partitions to create in the RDD -#' @return an RDD created from this collection -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10, 2) -#' # The RDD should contain 10 elements -#' length(rdd) -#'} +# Create an RDD from a homogeneous list or vector. +# +# This function creates an RDD from a local homogeneous list in R. The elements +# in the list are split into \code{numSlices} slices and distributed to nodes +# in the cluster. +# +# @param sc SparkContext to use +# @param coll collection to parallelize +# @param numSlices number of partitions to create in the RDD +# @return an RDD created from this collection +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10, 2) +# # The RDD should contain 10 elements +# length(rdd) +#} parallelize <- function(sc, coll, numSlices = 1) { # TODO: bound/safeguard numSlices # TODO: unit tests for if the split works for all primitives @@ -133,33 +133,33 @@ parallelize <- function(sc, coll, numSlices = 1) { RDD(jrdd, "byte") } -#' Include this specified package on all workers -#' -#' This function can be used to include a package on all workers before the -#' user's code is executed. This is useful in scenarios where other R package -#' functions are used in a function passed to functions like \code{lapply}. -#' NOTE: The package is assumed to be installed on every node in the Spark -#' cluster. -#' -#' @param sc SparkContext to use -#' @param pkg Package name -#' -#' @export -#' @examples -#'\dontrun{ -#' library(Matrix) -#' -#' sc <- sparkR.init() -#' # Include the matrix library we will be using -#' includePackage(sc, Matrix) -#' -#' generateSparse <- function(x) { -#' sparseMatrix(i=c(1, 2, 3), j=c(1, 2, 3), x=c(1, 2, 3)) -#' } -#' -#' rdd <- lapplyPartition(parallelize(sc, 1:2, 2L), generateSparse) -#' collect(rdd) -#'} +# Include this specified package on all workers +# +# This function can be used to include a package on all workers before the +# user's code is executed. This is useful in scenarios where other R package +# functions are used in a function passed to functions like \code{lapply}. +# NOTE: The package is assumed to be installed on every node in the Spark +# cluster. +# +# @param sc SparkContext to use +# @param pkg Package name +# +# @export +# @examples +#\dontrun{ +# library(Matrix) +# +# sc <- sparkR.init() +# # Include the matrix library we will be using +# includePackage(sc, Matrix) +# +# generateSparse <- function(x) { +# sparseMatrix(i=c(1, 2, 3), j=c(1, 2, 3), x=c(1, 2, 3)) +# } +# +# rdd <- lapplyPartition(parallelize(sc, 1:2, 2L), generateSparse) +# collect(rdd) +#} includePackage <- function(sc, pkg) { pkg <- as.character(substitute(pkg)) if (exists(".packages", .sparkREnv)) { @@ -171,30 +171,30 @@ includePackage <- function(sc, pkg) { .sparkREnv$.packages <- packages } -#' @title Broadcast a variable to all workers -#' -#' @description -#' Broadcast a read-only variable to the cluster, returning a \code{Broadcast} -#' object for reading it in distributed functions. -#' -#' @param sc Spark Context to use -#' @param object Object to be broadcast -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:2, 2L) -#' -#' # Large Matrix object that we want to broadcast -#' randomMat <- matrix(nrow=100, ncol=10, data=rnorm(1000)) -#' randomMatBr <- broadcast(sc, randomMat) -#' -#' # Use the broadcast variable inside the function -#' useBroadcast <- function(x) { -#' sum(value(randomMatBr) * x) -#' } -#' sumRDD <- lapply(rdd, useBroadcast) -#'} +# @title Broadcast a variable to all workers +# +# @description +# Broadcast a read-only variable to the cluster, returning a \code{Broadcast} +# object for reading it in distributed functions. +# +# @param sc Spark Context to use +# @param object Object to be broadcast +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:2, 2L) +# +# # Large Matrix object that we want to broadcast +# randomMat <- matrix(nrow=100, ncol=10, data=rnorm(1000)) +# randomMatBr <- broadcast(sc, randomMat) +# +# # Use the broadcast variable inside the function +# useBroadcast <- function(x) { +# sum(value(randomMatBr) * x) +# } +# sumRDD <- lapply(rdd, useBroadcast) +#} broadcast <- function(sc, object) { objName <- as.character(substitute(object)) serializedObj <- serialize(object, connection = NULL) @@ -205,21 +205,21 @@ broadcast <- function(sc, object) { Broadcast(id, object, jBroadcast, objName) } -#' @title Set the checkpoint directory -#' -#' Set the directory under which RDDs are going to be checkpointed. The -#' directory must be a HDFS path if running on a cluster. -#' -#' @param sc Spark Context to use -#' @param dirName Directory path -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' setCheckpointDir(sc, "~/checkpoint") -#' rdd <- parallelize(sc, 1:2, 2L) -#' checkpoint(rdd) -#'} +# @title Set the checkpoint directory +# +# Set the directory under which RDDs are going to be checkpointed. The +# directory must be a HDFS path if running on a cluster. +# +# @param sc Spark Context to use +# @param dirName Directory path +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# setCheckpointDir(sc, "~/checkpoint") +# rdd <- parallelize(sc, 1:2, 2L) +# checkpoint(rdd) +#} setCheckpointDir <- function(sc, dirName) { invisible(callJMethod(sc, "setCheckpointDir", suppressWarnings(normalizePath(dirName)))) } diff --git a/R/pkg/R/generics.R b/R/pkg/R/generics.R index 5838955f74dad..380e8ebe8c8f4 100644 --- a/R/pkg/R/generics.R +++ b/R/pkg/R/generics.R @@ -17,353 +17,353 @@ ############ RDD Actions and Transformations ############ -#' @rdname aggregateRDD -#' @seealso reduce -#' @export +# @rdname aggregateRDD +# @seealso reduce +# @export setGeneric("aggregateRDD", function(x, zeroValue, seqOp, combOp) { standardGeneric("aggregateRDD") }) -#' @rdname cache-methods -#' @export +# @rdname cache-methods +# @export setGeneric("cache", function(x) { standardGeneric("cache") }) -#' @rdname coalesce -#' @seealso repartition -#' @export +# @rdname coalesce +# @seealso repartition +# @export setGeneric("coalesce", function(x, numPartitions, ...) { standardGeneric("coalesce") }) -#' @rdname checkpoint-methods -#' @export +# @rdname checkpoint-methods +# @export setGeneric("checkpoint", function(x) { standardGeneric("checkpoint") }) -#' @rdname collect-methods -#' @export +# @rdname collect-methods +# @export setGeneric("collect", function(x, ...) { standardGeneric("collect") }) -#' @rdname collect-methods -#' @export +# @rdname collect-methods +# @export setGeneric("collectAsMap", function(x) { standardGeneric("collectAsMap") }) -#' @rdname collect-methods -#' @export +# @rdname collect-methods +# @export setGeneric("collectPartition", function(x, partitionId) { standardGeneric("collectPartition") }) -#' @rdname count -#' @export +# @rdname count +# @export setGeneric("count", function(x) { standardGeneric("count") }) -#' @rdname countByValue -#' @export +# @rdname countByValue +# @export setGeneric("countByValue", function(x) { standardGeneric("countByValue") }) -#' @rdname distinct -#' @export +# @rdname distinct +# @export setGeneric("distinct", function(x, numPartitions = 1) { standardGeneric("distinct") }) -#' @rdname filterRDD -#' @export +# @rdname filterRDD +# @export setGeneric("filterRDD", function(x, f) { standardGeneric("filterRDD") }) -#' @rdname first -#' @export +# @rdname first +# @export setGeneric("first", function(x) { standardGeneric("first") }) -#' @rdname flatMap -#' @export +# @rdname flatMap +# @export setGeneric("flatMap", function(X, FUN) { standardGeneric("flatMap") }) -#' @rdname fold -#' @seealso reduce -#' @export +# @rdname fold +# @seealso reduce +# @export setGeneric("fold", function(x, zeroValue, op) { standardGeneric("fold") }) -#' @rdname foreach -#' @export +# @rdname foreach +# @export setGeneric("foreach", function(x, func) { standardGeneric("foreach") }) -#' @rdname foreach -#' @export +# @rdname foreach +# @export setGeneric("foreachPartition", function(x, func) { standardGeneric("foreachPartition") }) # The jrdd accessor function. setGeneric("getJRDD", function(rdd, ...) { standardGeneric("getJRDD") }) -#' @rdname glom -#' @export +# @rdname glom +# @export setGeneric("glom", function(x) { standardGeneric("glom") }) -#' @rdname keyBy -#' @export +# @rdname keyBy +# @export setGeneric("keyBy", function(x, func) { standardGeneric("keyBy") }) -#' @rdname lapplyPartition -#' @export +# @rdname lapplyPartition +# @export setGeneric("lapplyPartition", function(X, FUN) { standardGeneric("lapplyPartition") }) -#' @rdname lapplyPartitionsWithIndex -#' @export +# @rdname lapplyPartitionsWithIndex +# @export setGeneric("lapplyPartitionsWithIndex", function(X, FUN) { standardGeneric("lapplyPartitionsWithIndex") }) -#' @rdname lapply -#' @export +# @rdname lapply +# @export setGeneric("map", function(X, FUN) { standardGeneric("map") }) -#' @rdname lapplyPartition -#' @export +# @rdname lapplyPartition +# @export setGeneric("mapPartitions", function(X, FUN) { standardGeneric("mapPartitions") }) -#' @rdname lapplyPartitionsWithIndex -#' @export +# @rdname lapplyPartitionsWithIndex +# @export setGeneric("mapPartitionsWithIndex", function(X, FUN) { standardGeneric("mapPartitionsWithIndex") }) -#' @rdname maximum -#' @export +# @rdname maximum +# @export setGeneric("maximum", function(x) { standardGeneric("maximum") }) -#' @rdname minimum -#' @export +# @rdname minimum +# @export setGeneric("minimum", function(x) { standardGeneric("minimum") }) -#' @rdname sumRDD -#' @export +# @rdname sumRDD +# @export setGeneric("sumRDD", function(x) { standardGeneric("sumRDD") }) -#' @rdname name -#' @export +# @rdname name +# @export setGeneric("name", function(x) { standardGeneric("name") }) -#' @rdname numPartitions -#' @export +# @rdname numPartitions +# @export setGeneric("numPartitions", function(x) { standardGeneric("numPartitions") }) -#' @rdname persist -#' @export +# @rdname persist +# @export setGeneric("persist", function(x, newLevel) { standardGeneric("persist") }) -#' @rdname pipeRDD -#' @export +# @rdname pipeRDD +# @export setGeneric("pipeRDD", function(x, command, env = list()) { standardGeneric("pipeRDD")}) -#' @rdname reduce -#' @export +# @rdname reduce +# @export setGeneric("reduce", function(x, func) { standardGeneric("reduce") }) -#' @rdname repartition -#' @seealso coalesce -#' @export +# @rdname repartition +# @seealso coalesce +# @export setGeneric("repartition", function(x, numPartitions) { standardGeneric("repartition") }) -#' @rdname sampleRDD -#' @export +# @rdname sampleRDD +# @export setGeneric("sampleRDD", function(x, withReplacement, fraction, seed) { standardGeneric("sampleRDD") }) -#' @rdname saveAsObjectFile -#' @seealso objectFile -#' @export +# @rdname saveAsObjectFile +# @seealso objectFile +# @export setGeneric("saveAsObjectFile", function(x, path) { standardGeneric("saveAsObjectFile") }) -#' @rdname saveAsTextFile -#' @export +# @rdname saveAsTextFile +# @export setGeneric("saveAsTextFile", function(x, path) { standardGeneric("saveAsTextFile") }) -#' @rdname setName -#' @export +# @rdname setName +# @export setGeneric("setName", function(x, name) { standardGeneric("setName") }) -#' @rdname sortBy -#' @export +# @rdname sortBy +# @export setGeneric("sortBy", function(x, func, ascending = TRUE, numPartitions = 1) { standardGeneric("sortBy") }) -#' @rdname take -#' @export +# @rdname take +# @export setGeneric("take", function(x, num) { standardGeneric("take") }) -#' @rdname takeOrdered -#' @export +# @rdname takeOrdered +# @export setGeneric("takeOrdered", function(x, num) { standardGeneric("takeOrdered") }) -#' @rdname takeSample -#' @export +# @rdname takeSample +# @export setGeneric("takeSample", function(x, withReplacement, num, seed) { standardGeneric("takeSample") }) -#' @rdname top -#' @export +# @rdname top +# @export setGeneric("top", function(x, num) { standardGeneric("top") }) -#' @rdname unionRDD -#' @export +# @rdname unionRDD +# @export setGeneric("unionRDD", function(x, y) { standardGeneric("unionRDD") }) -#' @rdname unpersist-methods -#' @export +# @rdname unpersist-methods +# @export setGeneric("unpersist", function(x, ...) { standardGeneric("unpersist") }) -#' @rdname zipRDD -#' @export +# @rdname zipRDD +# @export setGeneric("zipRDD", function(x, other) { standardGeneric("zipRDD") }) -#' @rdname zipRDD -#' @export +# @rdname zipRDD +# @export setGeneric("zipPartitions", function(..., func) { standardGeneric("zipPartitions") }, signature = "...") -#' @rdname zipWithIndex -#' @seealso zipWithUniqueId -#' @export +# @rdname zipWithIndex +# @seealso zipWithUniqueId +# @export setGeneric("zipWithIndex", function(x) { standardGeneric("zipWithIndex") }) -#' @rdname zipWithUniqueId -#' @seealso zipWithIndex -#' @export +# @rdname zipWithUniqueId +# @seealso zipWithIndex +# @export setGeneric("zipWithUniqueId", function(x) { standardGeneric("zipWithUniqueId") }) ############ Binary Functions ############# -#' @rdname cartesian -#' @export +# @rdname cartesian +# @export setGeneric("cartesian", function(x, other) { standardGeneric("cartesian") }) -#' @rdname countByKey -#' @export +# @rdname countByKey +# @export setGeneric("countByKey", function(x) { standardGeneric("countByKey") }) -#' @rdname flatMapValues -#' @export +# @rdname flatMapValues +# @export setGeneric("flatMapValues", function(X, FUN) { standardGeneric("flatMapValues") }) -#' @rdname intersection -#' @export +# @rdname intersection +# @export setGeneric("intersection", function(x, other, numPartitions = 1) { standardGeneric("intersection") }) -#' @rdname keys -#' @export +# @rdname keys +# @export setGeneric("keys", function(x) { standardGeneric("keys") }) -#' @rdname lookup -#' @export +# @rdname lookup +# @export setGeneric("lookup", function(x, key) { standardGeneric("lookup") }) -#' @rdname mapValues -#' @export +# @rdname mapValues +# @export setGeneric("mapValues", function(X, FUN) { standardGeneric("mapValues") }) -#' @rdname sampleByKey -#' @export +# @rdname sampleByKey +# @export setGeneric("sampleByKey", function(x, withReplacement, fractions, seed) { standardGeneric("sampleByKey") }) -#' @rdname values -#' @export +# @rdname values +# @export setGeneric("values", function(x) { standardGeneric("values") }) ############ Shuffle Functions ############ -#' @rdname aggregateByKey -#' @seealso foldByKey, combineByKey -#' @export +# @rdname aggregateByKey +# @seealso foldByKey, combineByKey +# @export setGeneric("aggregateByKey", function(x, zeroValue, seqOp, combOp, numPartitions) { standardGeneric("aggregateByKey") }) -#' @rdname cogroup -#' @export +# @rdname cogroup +# @export setGeneric("cogroup", function(..., numPartitions) { standardGeneric("cogroup") }, signature = "...") -#' @rdname combineByKey -#' @seealso groupByKey, reduceByKey -#' @export +# @rdname combineByKey +# @seealso groupByKey, reduceByKey +# @export setGeneric("combineByKey", function(x, createCombiner, mergeValue, mergeCombiners, numPartitions) { standardGeneric("combineByKey") }) -#' @rdname foldByKey -#' @seealso aggregateByKey, combineByKey -#' @export +# @rdname foldByKey +# @seealso aggregateByKey, combineByKey +# @export setGeneric("foldByKey", function(x, zeroValue, func, numPartitions) { standardGeneric("foldByKey") }) -#' @rdname join-methods -#' @export +# @rdname join-methods +# @export setGeneric("fullOuterJoin", function(x, y, numPartitions) { standardGeneric("fullOuterJoin") }) -#' @rdname groupByKey -#' @seealso reduceByKey -#' @export +# @rdname groupByKey +# @seealso reduceByKey +# @export setGeneric("groupByKey", function(x, numPartitions) { standardGeneric("groupByKey") }) -#' @rdname join-methods -#' @export +# @rdname join-methods +# @export setGeneric("join", function(x, y, ...) { standardGeneric("join") }) -#' @rdname join-methods -#' @export +# @rdname join-methods +# @export setGeneric("leftOuterJoin", function(x, y, numPartitions) { standardGeneric("leftOuterJoin") }) -#' @rdname partitionBy -#' @export +# @rdname partitionBy +# @export setGeneric("partitionBy", function(x, numPartitions, ...) { standardGeneric("partitionBy") }) -#' @rdname reduceByKey -#' @seealso groupByKey -#' @export +# @rdname reduceByKey +# @seealso groupByKey +# @export setGeneric("reduceByKey", function(x, combineFunc, numPartitions) { standardGeneric("reduceByKey")}) -#' @rdname reduceByKeyLocally -#' @seealso reduceByKey -#' @export +# @rdname reduceByKeyLocally +# @seealso reduceByKey +# @export setGeneric("reduceByKeyLocally", function(x, combineFunc) { standardGeneric("reduceByKeyLocally") }) -#' @rdname join-methods -#' @export +# @rdname join-methods +# @export setGeneric("rightOuterJoin", function(x, y, numPartitions) { standardGeneric("rightOuterJoin") }) -#' @rdname sortByKey -#' @export +# @rdname sortByKey +# @export setGeneric("sortByKey", function(x, ascending = TRUE, numPartitions = 1) { standardGeneric("sortByKey") }) -#' @rdname subtract -#' @export +# @rdname subtract +# @export setGeneric("subtract", function(x, other, numPartitions = 1) { standardGeneric("subtract") }) -#' @rdname subtractByKey -#' @export +# @rdname subtractByKey +# @export setGeneric("subtractByKey", function(x, other, numPartitions = 1) { standardGeneric("subtractByKey") @@ -372,8 +372,8 @@ setGeneric("subtractByKey", ################### Broadcast Variable Methods ################# -#' @rdname broadcast -#' @export +# @rdname broadcast +# @export setGeneric("value", function(bcast) { standardGeneric("value") }) @@ -477,8 +477,8 @@ setGeneric("showDF", function(x,...) { standardGeneric("showDF") }) #' @export setGeneric("sortDF", function(x, col, ...) { standardGeneric("sortDF") }) -#' @rdname tojson -#' @export +# @rdname tojson +# @export setGeneric("toJSON", function(x) { standardGeneric("toJSON") }) #' @rdname DataFrame diff --git a/R/pkg/R/pairRDD.R b/R/pkg/R/pairRDD.R index edeb8d9f75f7b..7694652856da5 100644 --- a/R/pkg/R/pairRDD.R +++ b/R/pkg/R/pairRDD.R @@ -21,23 +21,23 @@ NULL ############ Actions and Transformations ############ -#' Look up elements of a key in an RDD -#' -#' @description -#' \code{lookup} returns a list of values in this RDD for key key. -#' -#' @param x The RDD to collect -#' @param key The key to look up for -#' @return a list of values in this RDD for key key -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' pairs <- list(c(1, 1), c(2, 2), c(1, 3)) -#' rdd <- parallelize(sc, pairs) -#' lookup(rdd, 1) # list(1, 3) -#'} -#' @rdname lookup -#' @aliases lookup,RDD-method +# Look up elements of a key in an RDD +# +# @description +# \code{lookup} returns a list of values in this RDD for key key. +# +# @param x The RDD to collect +# @param key The key to look up for +# @return a list of values in this RDD for key key +# @examples +#\dontrun{ +# sc <- sparkR.init() +# pairs <- list(c(1, 1), c(2, 2), c(1, 3)) +# rdd <- parallelize(sc, pairs) +# lookup(rdd, 1) # list(1, 3) +#} +# @rdname lookup +# @aliases lookup,RDD-method setMethod("lookup", signature(x = "RDD", key = "ANY"), function(x, key) { @@ -49,21 +49,21 @@ setMethod("lookup", collect(valsRDD) }) -#' Count the number of elements for each key, and return the result to the -#' master as lists of (key, count) pairs. -#' -#' Same as countByKey in Spark. -#' -#' @param x The RDD to count keys. -#' @return list of (key, count) pairs, where count is number of each key in rdd. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(c("a", 1), c("b", 1), c("a", 1))) -#' countByKey(rdd) # ("a", 2L), ("b", 1L) -#'} -#' @rdname countByKey -#' @aliases countByKey,RDD-method +# Count the number of elements for each key, and return the result to the +# master as lists of (key, count) pairs. +# +# Same as countByKey in Spark. +# +# @param x The RDD to count keys. +# @return list of (key, count) pairs, where count is number of each key in rdd. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(c("a", 1), c("b", 1), c("a", 1))) +# countByKey(rdd) # ("a", 2L), ("b", 1L) +#} +# @rdname countByKey +# @aliases countByKey,RDD-method setMethod("countByKey", signature(x = "RDD"), function(x) { @@ -71,17 +71,17 @@ setMethod("countByKey", countByValue(keys) }) -#' Return an RDD with the keys of each tuple. -#' -#' @param x The RDD from which the keys of each tuple is returned. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(list(1, 2), list(3, 4))) -#' collect(keys(rdd)) # list(1, 3) -#'} -#' @rdname keys -#' @aliases keys,RDD +# Return an RDD with the keys of each tuple. +# +# @param x The RDD from which the keys of each tuple is returned. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(list(1, 2), list(3, 4))) +# collect(keys(rdd)) # list(1, 3) +#} +# @rdname keys +# @aliases keys,RDD setMethod("keys", signature(x = "RDD"), function(x) { @@ -91,17 +91,17 @@ setMethod("keys", lapply(x, func) }) -#' Return an RDD with the values of each tuple. -#' -#' @param x The RDD from which the values of each tuple is returned. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(list(1, 2), list(3, 4))) -#' collect(values(rdd)) # list(2, 4) -#'} -#' @rdname values -#' @aliases values,RDD +# Return an RDD with the values of each tuple. +# +# @param x The RDD from which the values of each tuple is returned. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(list(1, 2), list(3, 4))) +# collect(values(rdd)) # list(2, 4) +#} +# @rdname values +# @aliases values,RDD setMethod("values", signature(x = "RDD"), function(x) { @@ -111,23 +111,23 @@ setMethod("values", lapply(x, func) }) -#' Applies a function to all values of the elements, without modifying the keys. -#' -#' The same as `mapValues()' in Spark. -#' -#' @param X The RDD to apply the transformation. -#' @param FUN the transformation to apply on the value of each element. -#' @return a new RDD created by the transformation. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10) -#' makePairs <- lapply(rdd, function(x) { list(x, x) }) -#' collect(mapValues(makePairs, function(x) { x * 2) }) -#' Output: list(list(1,2), list(2,4), list(3,6), ...) -#'} -#' @rdname mapValues -#' @aliases mapValues,RDD,function-method +# Applies a function to all values of the elements, without modifying the keys. +# +# The same as `mapValues()' in Spark. +# +# @param X The RDD to apply the transformation. +# @param FUN the transformation to apply on the value of each element. +# @return a new RDD created by the transformation. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10) +# makePairs <- lapply(rdd, function(x) { list(x, x) }) +# collect(mapValues(makePairs, function(x) { x * 2) }) +# Output: list(list(1,2), list(2,4), list(3,6), ...) +#} +# @rdname mapValues +# @aliases mapValues,RDD,function-method setMethod("mapValues", signature(X = "RDD", FUN = "function"), function(X, FUN) { @@ -137,23 +137,23 @@ setMethod("mapValues", lapply(X, func) }) -#' Pass each value in the key-value pair RDD through a flatMap function without -#' changing the keys; this also retains the original RDD's partitioning. -#' -#' The same as 'flatMapValues()' in Spark. -#' -#' @param X The RDD to apply the transformation. -#' @param FUN the transformation to apply on the value of each element. -#' @return a new RDD created by the transformation. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(list(1, c(1,2)), list(2, c(3,4)))) -#' collect(flatMapValues(rdd, function(x) { x })) -#' Output: list(list(1,1), list(1,2), list(2,3), list(2,4)) -#'} -#' @rdname flatMapValues -#' @aliases flatMapValues,RDD,function-method +# Pass each value in the key-value pair RDD through a flatMap function without +# changing the keys; this also retains the original RDD's partitioning. +# +# The same as 'flatMapValues()' in Spark. +# +# @param X The RDD to apply the transformation. +# @param FUN the transformation to apply on the value of each element. +# @return a new RDD created by the transformation. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(list(1, c(1,2)), list(2, c(3,4)))) +# collect(flatMapValues(rdd, function(x) { x })) +# Output: list(list(1,1), list(1,2), list(2,3), list(2,4)) +#} +# @rdname flatMapValues +# @aliases flatMapValues,RDD,function-method setMethod("flatMapValues", signature(X = "RDD", FUN = "function"), function(X, FUN) { @@ -165,30 +165,30 @@ setMethod("flatMapValues", ############ Shuffle Functions ############ -#' Partition an RDD by key -#' -#' This function operates on RDDs where every element is of the form list(K, V) or c(K, V). -#' For each element of this RDD, the partitioner is used to compute a hash -#' function and the RDD is partitioned using this hash value. -#' -#' @param x The RDD to partition. Should be an RDD where each element is -#' list(K, V) or c(K, V). -#' @param numPartitions Number of partitions to create. -#' @param ... Other optional arguments to partitionBy. -#' -#' @param partitionFunc The partition function to use. Uses a default hashCode -#' function if not provided -#' @return An RDD partitioned using the specified partitioner. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' pairs <- list(list(1, 2), list(1.1, 3), list(1, 4)) -#' rdd <- parallelize(sc, pairs) -#' parts <- partitionBy(rdd, 2L) -#' collectPartition(parts, 0L) # First partition should contain list(1, 2) and list(1, 4) -#'} -#' @rdname partitionBy -#' @aliases partitionBy,RDD,integer-method +# Partition an RDD by key +# +# This function operates on RDDs where every element is of the form list(K, V) or c(K, V). +# For each element of this RDD, the partitioner is used to compute a hash +# function and the RDD is partitioned using this hash value. +# +# @param x The RDD to partition. Should be an RDD where each element is +# list(K, V) or c(K, V). +# @param numPartitions Number of partitions to create. +# @param ... Other optional arguments to partitionBy. +# +# @param partitionFunc The partition function to use. Uses a default hashCode +# function if not provided +# @return An RDD partitioned using the specified partitioner. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# pairs <- list(list(1, 2), list(1.1, 3), list(1, 4)) +# rdd <- parallelize(sc, pairs) +# parts <- partitionBy(rdd, 2L) +# collectPartition(parts, 0L) # First partition should contain list(1, 2) and list(1, 4) +#} +# @rdname partitionBy +# @aliases partitionBy,RDD,integer-method setMethod("partitionBy", signature(x = "RDD", numPartitions = "numeric"), function(x, numPartitions, partitionFunc = hashCode) { @@ -234,27 +234,27 @@ setMethod("partitionBy", RDD(r, serializedMode = "byte") }) -#' Group values by key -#' -#' This function operates on RDDs where every element is of the form list(K, V) or c(K, V). -#' and group values for each key in the RDD into a single sequence. -#' -#' @param x The RDD to group. Should be an RDD where each element is -#' list(K, V) or c(K, V). -#' @param numPartitions Number of partitions to create. -#' @return An RDD where each element is list(K, list(V)) -#' @seealso reduceByKey -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' pairs <- list(list(1, 2), list(1.1, 3), list(1, 4)) -#' rdd <- parallelize(sc, pairs) -#' parts <- groupByKey(rdd, 2L) -#' grouped <- collect(parts) -#' grouped[[1]] # Should be a list(1, list(2, 4)) -#'} -#' @rdname groupByKey -#' @aliases groupByKey,RDD,integer-method +# Group values by key +# +# This function operates on RDDs where every element is of the form list(K, V) or c(K, V). +# and group values for each key in the RDD into a single sequence. +# +# @param x The RDD to group. Should be an RDD where each element is +# list(K, V) or c(K, V). +# @param numPartitions Number of partitions to create. +# @return An RDD where each element is list(K, list(V)) +# @seealso reduceByKey +# @examples +#\dontrun{ +# sc <- sparkR.init() +# pairs <- list(list(1, 2), list(1.1, 3), list(1, 4)) +# rdd <- parallelize(sc, pairs) +# parts <- groupByKey(rdd, 2L) +# grouped <- collect(parts) +# grouped[[1]] # Should be a list(1, list(2, 4)) +#} +# @rdname groupByKey +# @aliases groupByKey,RDD,integer-method setMethod("groupByKey", signature(x = "RDD", numPartitions = "numeric"), function(x, numPartitions) { @@ -292,28 +292,28 @@ setMethod("groupByKey", lapplyPartition(shuffled, groupVals) }) -#' Merge values by key -#' -#' This function operates on RDDs where every element is of the form list(K, V) or c(K, V). -#' and merges the values for each key using an associative reduce function. -#' -#' @param x The RDD to reduce by key. Should be an RDD where each element is -#' list(K, V) or c(K, V). -#' @param combineFunc The associative reduce function to use. -#' @param numPartitions Number of partitions to create. -#' @return An RDD where each element is list(K, V') where V' is the merged -#' value -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' pairs <- list(list(1, 2), list(1.1, 3), list(1, 4)) -#' rdd <- parallelize(sc, pairs) -#' parts <- reduceByKey(rdd, "+", 2L) -#' reduced <- collect(parts) -#' reduced[[1]] # Should be a list(1, 6) -#'} -#' @rdname reduceByKey -#' @aliases reduceByKey,RDD,integer-method +# Merge values by key +# +# This function operates on RDDs where every element is of the form list(K, V) or c(K, V). +# and merges the values for each key using an associative reduce function. +# +# @param x The RDD to reduce by key. Should be an RDD where each element is +# list(K, V) or c(K, V). +# @param combineFunc The associative reduce function to use. +# @param numPartitions Number of partitions to create. +# @return An RDD where each element is list(K, V') where V' is the merged +# value +# @examples +#\dontrun{ +# sc <- sparkR.init() +# pairs <- list(list(1, 2), list(1.1, 3), list(1, 4)) +# rdd <- parallelize(sc, pairs) +# parts <- reduceByKey(rdd, "+", 2L) +# reduced <- collect(parts) +# reduced[[1]] # Should be a list(1, 6) +#} +# @rdname reduceByKey +# @aliases reduceByKey,RDD,integer-method setMethod("reduceByKey", signature(x = "RDD", combineFunc = "ANY", numPartitions = "numeric"), function(x, combineFunc, numPartitions) { @@ -333,27 +333,27 @@ setMethod("reduceByKey", lapplyPartition(shuffled, reduceVals) }) -#' Merge values by key locally -#' -#' This function operates on RDDs where every element is of the form list(K, V) or c(K, V). -#' and merges the values for each key using an associative reduce function, but return the -#' results immediately to the driver as an R list. -#' -#' @param x The RDD to reduce by key. Should be an RDD where each element is -#' list(K, V) or c(K, V). -#' @param combineFunc The associative reduce function to use. -#' @return A list of elements of type list(K, V') where V' is the merged value for each key -#' @seealso reduceByKey -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' pairs <- list(list(1, 2), list(1.1, 3), list(1, 4)) -#' rdd <- parallelize(sc, pairs) -#' reduced <- reduceByKeyLocally(rdd, "+") -#' reduced # list(list(1, 6), list(1.1, 3)) -#'} -#' @rdname reduceByKeyLocally -#' @aliases reduceByKeyLocally,RDD,integer-method +# Merge values by key locally +# +# This function operates on RDDs where every element is of the form list(K, V) or c(K, V). +# and merges the values for each key using an associative reduce function, but return the +# results immediately to the driver as an R list. +# +# @param x The RDD to reduce by key. Should be an RDD where each element is +# list(K, V) or c(K, V). +# @param combineFunc The associative reduce function to use. +# @return A list of elements of type list(K, V') where V' is the merged value for each key +# @seealso reduceByKey +# @examples +#\dontrun{ +# sc <- sparkR.init() +# pairs <- list(list(1, 2), list(1.1, 3), list(1, 4)) +# rdd <- parallelize(sc, pairs) +# reduced <- reduceByKeyLocally(rdd, "+") +# reduced # list(list(1, 6), list(1.1, 3)) +#} +# @rdname reduceByKeyLocally +# @aliases reduceByKeyLocally,RDD,integer-method setMethod("reduceByKeyLocally", signature(x = "RDD", combineFunc = "ANY"), function(x, combineFunc) { @@ -385,41 +385,41 @@ setMethod("reduceByKeyLocally", convertEnvsToList(merged[[1]], merged[[2]]) }) -#' Combine values by key -#' -#' Generic function to combine the elements for each key using a custom set of -#' aggregation functions. Turns an RDD[(K, V)] into a result of type RDD[(K, C)], -#' for a "combined type" C. Note that V and C can be different -- for example, one -#' might group an RDD of type (Int, Int) into an RDD of type (Int, Seq[Int]). - -#' Users provide three functions: -#' \itemize{ -#' \item createCombiner, which turns a V into a C (e.g., creates a one-element list) -#' \item mergeValue, to merge a V into a C (e.g., adds it to the end of a list) - -#' \item mergeCombiners, to combine two C's into a single one (e.g., concatentates -#' two lists). -#' } -#' -#' @param x The RDD to combine. Should be an RDD where each element is -#' list(K, V) or c(K, V). -#' @param createCombiner Create a combiner (C) given a value (V) -#' @param mergeValue Merge the given value (V) with an existing combiner (C) -#' @param mergeCombiners Merge two combiners and return a new combiner -#' @param numPartitions Number of partitions to create. -#' @return An RDD where each element is list(K, C) where C is the combined type -#' -#' @seealso groupByKey, reduceByKey -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' pairs <- list(list(1, 2), list(1.1, 3), list(1, 4)) -#' rdd <- parallelize(sc, pairs) -#' parts <- combineByKey(rdd, function(x) { x }, "+", "+", 2L) -#' combined <- collect(parts) -#' combined[[1]] # Should be a list(1, 6) -#'} -#' @rdname combineByKey -#' @aliases combineByKey,RDD,ANY,ANY,ANY,integer-method +# Combine values by key +# +# Generic function to combine the elements for each key using a custom set of +# aggregation functions. Turns an RDD[(K, V)] into a result of type RDD[(K, C)], +# for a "combined type" C. Note that V and C can be different -- for example, one +# might group an RDD of type (Int, Int) into an RDD of type (Int, Seq[Int]). + +# Users provide three functions: +# \itemize{ +# \item createCombiner, which turns a V into a C (e.g., creates a one-element list) +# \item mergeValue, to merge a V into a C (e.g., adds it to the end of a list) - +# \item mergeCombiners, to combine two C's into a single one (e.g., concatentates +# two lists). +# } +# +# @param x The RDD to combine. Should be an RDD where each element is +# list(K, V) or c(K, V). +# @param createCombiner Create a combiner (C) given a value (V) +# @param mergeValue Merge the given value (V) with an existing combiner (C) +# @param mergeCombiners Merge two combiners and return a new combiner +# @param numPartitions Number of partitions to create. +# @return An RDD where each element is list(K, C) where C is the combined type +# +# @seealso groupByKey, reduceByKey +# @examples +#\dontrun{ +# sc <- sparkR.init() +# pairs <- list(list(1, 2), list(1.1, 3), list(1, 4)) +# rdd <- parallelize(sc, pairs) +# parts <- combineByKey(rdd, function(x) { x }, "+", "+", 2L) +# combined <- collect(parts) +# combined[[1]] # Should be a list(1, 6) +#} +# @rdname combineByKey +# @aliases combineByKey,RDD,ANY,ANY,ANY,integer-method setMethod("combineByKey", signature(x = "RDD", createCombiner = "ANY", mergeValue = "ANY", mergeCombiners = "ANY", numPartitions = "numeric"), @@ -451,36 +451,36 @@ setMethod("combineByKey", lapplyPartition(shuffled, mergeAfterShuffle) }) -#' Aggregate a pair RDD by each key. -#' -#' Aggregate the values of each key in an RDD, using given combine functions -#' and a neutral "zero value". This function can return a different result type, -#' U, than the type of the values in this RDD, V. Thus, we need one operation -#' for merging a V into a U and one operation for merging two U's, The former -#' operation is used for merging values within a partition, and the latter is -#' used for merging values between partitions. To avoid memory allocation, both -#' of these functions are allowed to modify and return their first argument -#' instead of creating a new U. -#' -#' @param x An RDD. -#' @param zeroValue A neutral "zero value". -#' @param seqOp A function to aggregate the values of each key. It may return -#' a different result type from the type of the values. -#' @param combOp A function to aggregate results of seqOp. -#' @return An RDD containing the aggregation result. -#' @seealso foldByKey, combineByKey -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(list(1, 1), list(1, 2), list(2, 3), list(2, 4))) -#' zeroValue <- list(0, 0) -#' seqOp <- function(x, y) { list(x[[1]] + y, x[[2]] + 1) } -#' combOp <- function(x, y) { list(x[[1]] + y[[1]], x[[2]] + y[[2]]) } -#' aggregateByKey(rdd, zeroValue, seqOp, combOp, 2L) -#' # list(list(1, list(3, 2)), list(2, list(7, 2))) -#'} -#' @rdname aggregateByKey -#' @aliases aggregateByKey,RDD,ANY,ANY,ANY,integer-method +# Aggregate a pair RDD by each key. +# +# Aggregate the values of each key in an RDD, using given combine functions +# and a neutral "zero value". This function can return a different result type, +# U, than the type of the values in this RDD, V. Thus, we need one operation +# for merging a V into a U and one operation for merging two U's, The former +# operation is used for merging values within a partition, and the latter is +# used for merging values between partitions. To avoid memory allocation, both +# of these functions are allowed to modify and return their first argument +# instead of creating a new U. +# +# @param x An RDD. +# @param zeroValue A neutral "zero value". +# @param seqOp A function to aggregate the values of each key. It may return +# a different result type from the type of the values. +# @param combOp A function to aggregate results of seqOp. +# @return An RDD containing the aggregation result. +# @seealso foldByKey, combineByKey +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(list(1, 1), list(1, 2), list(2, 3), list(2, 4))) +# zeroValue <- list(0, 0) +# seqOp <- function(x, y) { list(x[[1]] + y, x[[2]] + 1) } +# combOp <- function(x, y) { list(x[[1]] + y[[1]], x[[2]] + y[[2]]) } +# aggregateByKey(rdd, zeroValue, seqOp, combOp, 2L) +# # list(list(1, list(3, 2)), list(2, list(7, 2))) +#} +# @rdname aggregateByKey +# @aliases aggregateByKey,RDD,ANY,ANY,ANY,integer-method setMethod("aggregateByKey", signature(x = "RDD", zeroValue = "ANY", seqOp = "ANY", combOp = "ANY", numPartitions = "numeric"), @@ -492,26 +492,26 @@ setMethod("aggregateByKey", combineByKey(x, createCombiner, seqOp, combOp, numPartitions) }) -#' Fold a pair RDD by each key. -#' -#' Aggregate the values of each key in an RDD, using an associative function "func" -#' and a neutral "zero value" which may be added to the result an arbitrary -#' number of times, and must not change the result (e.g., 0 for addition, or -#' 1 for multiplication.). -#' -#' @param x An RDD. -#' @param zeroValue A neutral "zero value". -#' @param func An associative function for folding values of each key. -#' @return An RDD containing the aggregation result. -#' @seealso aggregateByKey, combineByKey -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(list(1, 1), list(1, 2), list(2, 3), list(2, 4))) -#' foldByKey(rdd, 0, "+", 2L) # list(list(1, 3), list(2, 7)) -#'} -#' @rdname foldByKey -#' @aliases foldByKey,RDD,ANY,ANY,integer-method +# Fold a pair RDD by each key. +# +# Aggregate the values of each key in an RDD, using an associative function "func" +# and a neutral "zero value" which may be added to the result an arbitrary +# number of times, and must not change the result (e.g., 0 for addition, or +# 1 for multiplication.). +# +# @param x An RDD. +# @param zeroValue A neutral "zero value". +# @param func An associative function for folding values of each key. +# @return An RDD containing the aggregation result. +# @seealso aggregateByKey, combineByKey +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(list(1, 1), list(1, 2), list(2, 3), list(2, 4))) +# foldByKey(rdd, 0, "+", 2L) # list(list(1, 3), list(2, 7)) +#} +# @rdname foldByKey +# @aliases foldByKey,RDD,ANY,ANY,integer-method setMethod("foldByKey", signature(x = "RDD", zeroValue = "ANY", func = "ANY", numPartitions = "numeric"), @@ -521,28 +521,28 @@ setMethod("foldByKey", ############ Binary Functions ############# -#' Join two RDDs -#' -#' @description -#' \code{join} This function joins two RDDs where every element is of the form list(K, V). -#' The key types of the two RDDs should be the same. -#' -#' @param x An RDD to be joined. Should be an RDD where each element is -#' list(K, V). -#' @param y An RDD to be joined. Should be an RDD where each element is -#' list(K, V). -#' @param numPartitions Number of partitions to create. -#' @return a new RDD containing all pairs of elements with matching keys in -#' two input RDDs. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd1 <- parallelize(sc, list(list(1, 1), list(2, 4))) -#' rdd2 <- parallelize(sc, list(list(1, 2), list(1, 3))) -#' join(rdd1, rdd2, 2L) # list(list(1, list(1, 2)), list(1, list(1, 3)) -#'} -#' @rdname join-methods -#' @aliases join,RDD,RDD-method +# Join two RDDs +# +# @description +# \code{join} This function joins two RDDs where every element is of the form list(K, V). +# The key types of the two RDDs should be the same. +# +# @param x An RDD to be joined. Should be an RDD where each element is +# list(K, V). +# @param y An RDD to be joined. Should be an RDD where each element is +# list(K, V). +# @param numPartitions Number of partitions to create. +# @return a new RDD containing all pairs of elements with matching keys in +# two input RDDs. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd1 <- parallelize(sc, list(list(1, 1), list(2, 4))) +# rdd2 <- parallelize(sc, list(list(1, 2), list(1, 3))) +# join(rdd1, rdd2, 2L) # list(list(1, list(1, 2)), list(1, list(1, 3)) +#} +# @rdname join-methods +# @aliases join,RDD,RDD-method setMethod("join", signature(x = "RDD", y = "RDD"), function(x, y, numPartitions) { @@ -557,30 +557,30 @@ setMethod("join", doJoin) }) -#' Left outer join two RDDs -#' -#' @description -#' \code{leftouterjoin} This function left-outer-joins two RDDs where every element is of the form list(K, V). -#' The key types of the two RDDs should be the same. -#' -#' @param x An RDD to be joined. Should be an RDD where each element is -#' list(K, V). -#' @param y An RDD to be joined. Should be an RDD where each element is -#' list(K, V). -#' @param numPartitions Number of partitions to create. -#' @return For each element (k, v) in x, the resulting RDD will either contain -#' all pairs (k, (v, w)) for (k, w) in rdd2, or the pair (k, (v, NULL)) -#' if no elements in rdd2 have key k. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd1 <- parallelize(sc, list(list(1, 1), list(2, 4))) -#' rdd2 <- parallelize(sc, list(list(1, 2), list(1, 3))) -#' leftOuterJoin(rdd1, rdd2, 2L) -#' # list(list(1, list(1, 2)), list(1, list(1, 3)), list(2, list(4, NULL))) -#'} -#' @rdname join-methods -#' @aliases leftOuterJoin,RDD,RDD-method +# Left outer join two RDDs +# +# @description +# \code{leftouterjoin} This function left-outer-joins two RDDs where every element is of the form list(K, V). +# The key types of the two RDDs should be the same. +# +# @param x An RDD to be joined. Should be an RDD where each element is +# list(K, V). +# @param y An RDD to be joined. Should be an RDD where each element is +# list(K, V). +# @param numPartitions Number of partitions to create. +# @return For each element (k, v) in x, the resulting RDD will either contain +# all pairs (k, (v, w)) for (k, w) in rdd2, or the pair (k, (v, NULL)) +# if no elements in rdd2 have key k. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd1 <- parallelize(sc, list(list(1, 1), list(2, 4))) +# rdd2 <- parallelize(sc, list(list(1, 2), list(1, 3))) +# leftOuterJoin(rdd1, rdd2, 2L) +# # list(list(1, list(1, 2)), list(1, list(1, 3)), list(2, list(4, NULL))) +#} +# @rdname join-methods +# @aliases leftOuterJoin,RDD,RDD-method setMethod("leftOuterJoin", signature(x = "RDD", y = "RDD", numPartitions = "numeric"), function(x, y, numPartitions) { @@ -594,30 +594,30 @@ setMethod("leftOuterJoin", joined <- flatMapValues(groupByKey(unionRDD(xTagged, yTagged), numPartitions), doJoin) }) -#' Right outer join two RDDs -#' -#' @description -#' \code{rightouterjoin} This function right-outer-joins two RDDs where every element is of the form list(K, V). -#' The key types of the two RDDs should be the same. -#' -#' @param x An RDD to be joined. Should be an RDD where each element is -#' list(K, V). -#' @param y An RDD to be joined. Should be an RDD where each element is -#' list(K, V). -#' @param numPartitions Number of partitions to create. -#' @return For each element (k, w) in y, the resulting RDD will either contain -#' all pairs (k, (v, w)) for (k, v) in x, or the pair (k, (NULL, w)) -#' if no elements in x have key k. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd1 <- parallelize(sc, list(list(1, 2), list(1, 3))) -#' rdd2 <- parallelize(sc, list(list(1, 1), list(2, 4))) -#' rightOuterJoin(rdd1, rdd2, 2L) -#' # list(list(1, list(2, 1)), list(1, list(3, 1)), list(2, list(NULL, 4))) -#'} -#' @rdname join-methods -#' @aliases rightOuterJoin,RDD,RDD-method +# Right outer join two RDDs +# +# @description +# \code{rightouterjoin} This function right-outer-joins two RDDs where every element is of the form list(K, V). +# The key types of the two RDDs should be the same. +# +# @param x An RDD to be joined. Should be an RDD where each element is +# list(K, V). +# @param y An RDD to be joined. Should be an RDD where each element is +# list(K, V). +# @param numPartitions Number of partitions to create. +# @return For each element (k, w) in y, the resulting RDD will either contain +# all pairs (k, (v, w)) for (k, v) in x, or the pair (k, (NULL, w)) +# if no elements in x have key k. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd1 <- parallelize(sc, list(list(1, 2), list(1, 3))) +# rdd2 <- parallelize(sc, list(list(1, 1), list(2, 4))) +# rightOuterJoin(rdd1, rdd2, 2L) +# # list(list(1, list(2, 1)), list(1, list(3, 1)), list(2, list(NULL, 4))) +#} +# @rdname join-methods +# @aliases rightOuterJoin,RDD,RDD-method setMethod("rightOuterJoin", signature(x = "RDD", y = "RDD", numPartitions = "numeric"), function(x, y, numPartitions) { @@ -631,33 +631,33 @@ setMethod("rightOuterJoin", joined <- flatMapValues(groupByKey(unionRDD(xTagged, yTagged), numPartitions), doJoin) }) -#' Full outer join two RDDs -#' -#' @description -#' \code{fullouterjoin} This function full-outer-joins two RDDs where every element is of the form list(K, V). -#' The key types of the two RDDs should be the same. -#' -#' @param x An RDD to be joined. Should be an RDD where each element is -#' list(K, V). -#' @param y An RDD to be joined. Should be an RDD where each element is -#' list(K, V). -#' @param numPartitions Number of partitions to create. -#' @return For each element (k, v) in x and (k, w) in y, the resulting RDD -#' will contain all pairs (k, (v, w)) for both (k, v) in x and -#' (k, w) in y, or the pair (k, (NULL, w))/(k, (v, NULL)) if no elements -#' in x/y have key k. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd1 <- parallelize(sc, list(list(1, 2), list(1, 3), list(3, 3))) -#' rdd2 <- parallelize(sc, list(list(1, 1), list(2, 4))) -#' fullOuterJoin(rdd1, rdd2, 2L) # list(list(1, list(2, 1)), -#' # list(1, list(3, 1)), -#' # list(2, list(NULL, 4))) -#' # list(3, list(3, NULL)), -#'} -#' @rdname join-methods -#' @aliases fullOuterJoin,RDD,RDD-method +# Full outer join two RDDs +# +# @description +# \code{fullouterjoin} This function full-outer-joins two RDDs where every element is of the form list(K, V). +# The key types of the two RDDs should be the same. +# +# @param x An RDD to be joined. Should be an RDD where each element is +# list(K, V). +# @param y An RDD to be joined. Should be an RDD where each element is +# list(K, V). +# @param numPartitions Number of partitions to create. +# @return For each element (k, v) in x and (k, w) in y, the resulting RDD +# will contain all pairs (k, (v, w)) for both (k, v) in x and +# (k, w) in y, or the pair (k, (NULL, w))/(k, (v, NULL)) if no elements +# in x/y have key k. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd1 <- parallelize(sc, list(list(1, 2), list(1, 3), list(3, 3))) +# rdd2 <- parallelize(sc, list(list(1, 1), list(2, 4))) +# fullOuterJoin(rdd1, rdd2, 2L) # list(list(1, list(2, 1)), +# # list(1, list(3, 1)), +# # list(2, list(NULL, 4))) +# # list(3, list(3, NULL)), +#} +# @rdname join-methods +# @aliases fullOuterJoin,RDD,RDD-method setMethod("fullOuterJoin", signature(x = "RDD", y = "RDD", numPartitions = "numeric"), function(x, y, numPartitions) { @@ -671,23 +671,23 @@ setMethod("fullOuterJoin", joined <- flatMapValues(groupByKey(unionRDD(xTagged, yTagged), numPartitions), doJoin) }) -#' For each key k in several RDDs, return a resulting RDD that -#' whose values are a list of values for the key in all RDDs. -#' -#' @param ... Several RDDs. -#' @param numPartitions Number of partitions to create. -#' @return a new RDD containing all pairs of elements with values in a list -#' in all RDDs. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd1 <- parallelize(sc, list(list(1, 1), list(2, 4))) -#' rdd2 <- parallelize(sc, list(list(1, 2), list(1, 3))) -#' cogroup(rdd1, rdd2, numPartitions = 2L) -#' # list(list(1, list(1, list(2, 3))), list(2, list(list(4), list())) -#'} -#' @rdname cogroup -#' @aliases cogroup,RDD-method +# For each key k in several RDDs, return a resulting RDD that +# whose values are a list of values for the key in all RDDs. +# +# @param ... Several RDDs. +# @param numPartitions Number of partitions to create. +# @return a new RDD containing all pairs of elements with values in a list +# in all RDDs. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd1 <- parallelize(sc, list(list(1, 1), list(2, 4))) +# rdd2 <- parallelize(sc, list(list(1, 2), list(1, 3))) +# cogroup(rdd1, rdd2, numPartitions = 2L) +# # list(list(1, list(1, list(2, 3))), list(2, list(list(4), list())) +#} +# @rdname cogroup +# @aliases cogroup,RDD-method setMethod("cogroup", "RDD", function(..., numPartitions) { @@ -723,20 +723,20 @@ setMethod("cogroup", group.func) }) -#' Sort a (k, v) pair RDD by k. -#' -#' @param x A (k, v) pair RDD to be sorted. -#' @param ascending A flag to indicate whether the sorting is ascending or descending. -#' @param numPartitions Number of partitions to create. -#' @return An RDD where all (k, v) pair elements are sorted. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, list(list(3, 1), list(2, 2), list(1, 3))) -#' collect(sortByKey(rdd)) # list (list(1, 3), list(2, 2), list(3, 1)) -#'} -#' @rdname sortByKey -#' @aliases sortByKey,RDD,RDD-method +# Sort a (k, v) pair RDD by k. +# +# @param x A (k, v) pair RDD to be sorted. +# @param ascending A flag to indicate whether the sorting is ascending or descending. +# @param numPartitions Number of partitions to create. +# @return An RDD where all (k, v) pair elements are sorted. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, list(list(3, 1), list(2, 2), list(1, 3))) +# collect(sortByKey(rdd)) # list (list(1, 3), list(2, 2), list(3, 1)) +#} +# @rdname sortByKey +# @aliases sortByKey,RDD,RDD-method setMethod("sortByKey", signature(x = "RDD"), function(x, ascending = TRUE, numPartitions = SparkR:::numPartitions(x)) { @@ -785,25 +785,25 @@ setMethod("sortByKey", lapplyPartition(newRDD, partitionFunc) }) -#' Subtract a pair RDD with another pair RDD. -#' -#' Return an RDD with the pairs from x whose keys are not in other. -#' -#' @param x An RDD. -#' @param other An RDD. -#' @param numPartitions Number of the partitions in the result RDD. -#' @return An RDD with the pairs from x whose keys are not in other. -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd1 <- parallelize(sc, list(list("a", 1), list("b", 4), -#' list("b", 5), list("a", 2))) -#' rdd2 <- parallelize(sc, list(list("a", 3), list("c", 1))) -#' collect(subtractByKey(rdd1, rdd2)) -#' # list(list("b", 4), list("b", 5)) -#'} -#' @rdname subtractByKey -#' @aliases subtractByKey,RDD +# Subtract a pair RDD with another pair RDD. +# +# Return an RDD with the pairs from x whose keys are not in other. +# +# @param x An RDD. +# @param other An RDD. +# @param numPartitions Number of the partitions in the result RDD. +# @return An RDD with the pairs from x whose keys are not in other. +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd1 <- parallelize(sc, list(list("a", 1), list("b", 4), +# list("b", 5), list("a", 2))) +# rdd2 <- parallelize(sc, list(list("a", 3), list("c", 1))) +# collect(subtractByKey(rdd1, rdd2)) +# # list(list("b", 4), list("b", 5)) +#} +# @rdname subtractByKey +# @aliases subtractByKey,RDD setMethod("subtractByKey", signature(x = "RDD", other = "RDD"), function(x, other, numPartitions = SparkR:::numPartitions(x)) { @@ -819,41 +819,41 @@ setMethod("subtractByKey", function (v) { v[[1]] }) }) -#' Return a subset of this RDD sampled by key. -#' -#' @description -#' \code{sampleByKey} Create a sample of this RDD using variable sampling rates -#' for different keys as specified by fractions, a key to sampling rate map. -#' -#' @param x The RDD to sample elements by key, where each element is -#' list(K, V) or c(K, V). -#' @param withReplacement Sampling with replacement or not -#' @param fraction The (rough) sample target fraction -#' @param seed Randomness seed value -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:3000) -#' pairs <- lapply(rdd, function(x) { if (x %% 3 == 0) list("a", x) -#' else { if (x %% 3 == 1) list("b", x) else list("c", x) }}) -#' fractions <- list(a = 0.2, b = 0.1, c = 0.3) -#' sample <- sampleByKey(pairs, FALSE, fractions, 1618L) -#' 100 < length(lookup(sample, "a")) && 300 > length(lookup(sample, "a")) # TRUE -#' 50 < length(lookup(sample, "b")) && 150 > length(lookup(sample, "b")) # TRUE -#' 200 < length(lookup(sample, "c")) && 400 > length(lookup(sample, "c")) # TRUE -#' lookup(sample, "a")[which.min(lookup(sample, "a"))] >= 0 # TRUE -#' lookup(sample, "a")[which.max(lookup(sample, "a"))] <= 2000 # TRUE -#' lookup(sample, "b")[which.min(lookup(sample, "b"))] >= 0 # TRUE -#' lookup(sample, "b")[which.max(lookup(sample, "b"))] <= 2000 # TRUE -#' lookup(sample, "c")[which.min(lookup(sample, "c"))] >= 0 # TRUE -#' lookup(sample, "c")[which.max(lookup(sample, "c"))] <= 2000 # TRUE -#' fractions <- list(a = 0.2, b = 0.1, c = 0.3, d = 0.4) -#' sample <- sampleByKey(pairs, FALSE, fractions, 1618L) # Key "d" will be ignored -#' fractions <- list(a = 0.2, b = 0.1) -#' sample <- sampleByKey(pairs, FALSE, fractions, 1618L) # KeyError: "c" -#'} -#' @rdname sampleByKey -#' @aliases sampleByKey,RDD-method +# Return a subset of this RDD sampled by key. +# +# @description +# \code{sampleByKey} Create a sample of this RDD using variable sampling rates +# for different keys as specified by fractions, a key to sampling rate map. +# +# @param x The RDD to sample elements by key, where each element is +# list(K, V) or c(K, V). +# @param withReplacement Sampling with replacement or not +# @param fraction The (rough) sample target fraction +# @param seed Randomness seed value +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:3000) +# pairs <- lapply(rdd, function(x) { if (x %% 3 == 0) list("a", x) +# else { if (x %% 3 == 1) list("b", x) else list("c", x) }}) +# fractions <- list(a = 0.2, b = 0.1, c = 0.3) +# sample <- sampleByKey(pairs, FALSE, fractions, 1618L) +# 100 < length(lookup(sample, "a")) && 300 > length(lookup(sample, "a")) # TRUE +# 50 < length(lookup(sample, "b")) && 150 > length(lookup(sample, "b")) # TRUE +# 200 < length(lookup(sample, "c")) && 400 > length(lookup(sample, "c")) # TRUE +# lookup(sample, "a")[which.min(lookup(sample, "a"))] >= 0 # TRUE +# lookup(sample, "a")[which.max(lookup(sample, "a"))] <= 2000 # TRUE +# lookup(sample, "b")[which.min(lookup(sample, "b"))] >= 0 # TRUE +# lookup(sample, "b")[which.max(lookup(sample, "b"))] <= 2000 # TRUE +# lookup(sample, "c")[which.min(lookup(sample, "c"))] >= 0 # TRUE +# lookup(sample, "c")[which.max(lookup(sample, "c"))] <= 2000 # TRUE +# fractions <- list(a = 0.2, b = 0.1, c = 0.3, d = 0.4) +# sample <- sampleByKey(pairs, FALSE, fractions, 1618L) # Key "d" will be ignored +# fractions <- list(a = 0.2, b = 0.1) +# sample <- sampleByKey(pairs, FALSE, fractions, 1618L) # KeyError: "c" +#} +# @rdname sampleByKey +# @aliases sampleByKey,RDD-method setMethod("sampleByKey", signature(x = "RDD", withReplacement = "logical", fractions = "vector", seed = "integer"), diff --git a/assembly/pom.xml b/assembly/pom.xml index 2b4d0a990bf22..626c8577e31fe 100644 --- a/assembly/pom.xml +++ b/assembly/pom.xml @@ -92,6 +92,27 @@ true + + + org.apache.maven.plugins + maven-antrun-plugin + + + package + + run + + + + + + + + + + + + org.apache.maven.plugins diff --git a/core/pom.xml b/core/pom.xml index 164a836cb8f0b..fc42f48973fe9 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -228,6 +228,14 @@ json4s-jackson_${scala.binary.version} 3.2.10 + + com.sun.jersey + jersey-server + + + com.sun.jersey + jersey-core + org.apache.mesos mesos diff --git a/core/src/main/java/org/apache/spark/JobExecutionStatus.java b/core/src/main/java/org/apache/spark/JobExecutionStatus.java index 6e161313702bb..0287fb79f8dd2 100644 --- a/core/src/main/java/org/apache/spark/JobExecutionStatus.java +++ b/core/src/main/java/org/apache/spark/JobExecutionStatus.java @@ -17,9 +17,15 @@ package org.apache.spark; +import org.apache.spark.util.EnumUtil; + public enum JobExecutionStatus { RUNNING, SUCCEEDED, FAILED, - UNKNOWN + UNKNOWN; + + public static JobExecutionStatus fromString(String str) { + return EnumUtil.parseIgnoreCase(JobExecutionStatus.class, str); + } } diff --git a/core/src/main/java/org/apache/spark/status/api/v1/ApplicationStatus.java b/core/src/main/java/org/apache/spark/status/api/v1/ApplicationStatus.java new file mode 100644 index 0000000000000..8c7dcf776fda8 --- /dev/null +++ b/core/src/main/java/org/apache/spark/status/api/v1/ApplicationStatus.java @@ -0,0 +1,30 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.status.api.v1; + +import org.apache.spark.util.EnumUtil; + +public enum ApplicationStatus { + COMPLETED, + RUNNING; + + public static ApplicationStatus fromString(String str) { + return EnumUtil.parseIgnoreCase(ApplicationStatus.class, str); + } + +} diff --git a/core/src/main/java/org/apache/spark/status/api/v1/StageStatus.java b/core/src/main/java/org/apache/spark/status/api/v1/StageStatus.java new file mode 100644 index 0000000000000..9dbb565aab707 --- /dev/null +++ b/core/src/main/java/org/apache/spark/status/api/v1/StageStatus.java @@ -0,0 +1,31 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.status.api.v1; + +import org.apache.spark.util.EnumUtil; + +public enum StageStatus { + ACTIVE, + COMPLETE, + FAILED, + PENDING; + + public static StageStatus fromString(String str) { + return EnumUtil.parseIgnoreCase(StageStatus.class, str); + } +} diff --git a/core/src/main/java/org/apache/spark/status/api/v1/TaskSorting.java b/core/src/main/java/org/apache/spark/status/api/v1/TaskSorting.java new file mode 100644 index 0000000000000..f19ed01d5aebf --- /dev/null +++ b/core/src/main/java/org/apache/spark/status/api/v1/TaskSorting.java @@ -0,0 +1,48 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.status.api.v1; + +import org.apache.spark.util.EnumUtil; + +import java.util.HashSet; +import java.util.Set; + +public enum TaskSorting { + ID, + INCREASING_RUNTIME("runtime"), + DECREASING_RUNTIME("-runtime"); + + private final Set alternateNames; + private TaskSorting(String... names) { + alternateNames = new HashSet(); + for (String n: names) { + alternateNames.add(n); + } + } + + public static TaskSorting fromString(String str) { + String lower = str.toLowerCase(); + for (TaskSorting t: values()) { + if (t.alternateNames.contains(lower)) { + return t; + } + } + return EnumUtil.parseIgnoreCase(TaskSorting.class, str); + } + +} diff --git a/core/src/main/java/org/apache/spark/util/EnumUtil.java b/core/src/main/java/org/apache/spark/util/EnumUtil.java new file mode 100644 index 0000000000000..c40c7e727613c --- /dev/null +++ b/core/src/main/java/org/apache/spark/util/EnumUtil.java @@ -0,0 +1,38 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.util; + +import com.google.common.base.Joiner; +import org.apache.spark.annotation.Private; + +@Private +public class EnumUtil { + public static > E parseIgnoreCase(Class clz, String str) { + E[] constants = clz.getEnumConstants(); + if (str == null) { + return null; + } + for (E e : constants) { + if (e.name().equalsIgnoreCase(str)) { + return e; + } + } + throw new IllegalArgumentException( + String.format("Illegal type='%s'. Supported type values: %s", + str, Joiner.on(", ").join(constants))); + } +} diff --git a/core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.css b/core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.css index 8481710828455..18c72694f3e2d 100644 --- a/core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.css +++ b/core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.css @@ -16,40 +16,51 @@ */ #dag-viz-graph svg path { - stroke: #444444; + stroke: #444; stroke-width: 1.5px; } #dag-viz-graph svg g.cluster rect { - stroke-width: 4px; - stroke-opacity: 0.5; + stroke-width: 1px; +} + +#dag-viz-graph svg g.node circle { + fill: #444; } -#dag-viz-graph svg g.node circle, #dag-viz-graph svg g.node rect { - fill: #444444; + fill: #C3EBFF; + stroke: #3EC0FF; + stroke-width: 1px; +} + +#dag-viz-graph svg g.node.cached circle { + fill: #444; } -#dag-viz-graph svg g.node.cached circle, #dag-viz-graph svg g.node.cached rect { - fill: #FF0000; + fill: #B3F5C5; + stroke: #56F578; + stroke-width: 1px; } /* Job page specific styles */ #dag-viz-graph svg.job marker#marker-arrow path { - fill: #444444; + fill: #333; stroke-width: 0px; } #dag-viz-graph svg.job g.cluster rect { - fill: #FFFFFF; - stroke: #AADFFF; + fill: #A0DFFF; + stroke: #3EC0FF; + stroke-width: 1px; } #dag-viz-graph svg.job g.cluster[id*="stage"] rect { - stroke: #FFDDEE; - stroke-width: 6px; + fill: #FFFFFF; + stroke: #FF99AC; + stroke-width: 1px; } #dag-viz-graph svg.job g#cross-stage-edges path { @@ -57,27 +68,36 @@ } #dag-viz-graph svg.job g.cluster text { - fill: #AAAAAA; + fill: #333; } /* Stage page specific styles */ #dag-viz-graph svg.stage g.cluster rect { - fill: #F0F8FF; - stroke: #AADFFF; + fill: #A0DFFF; + stroke: #3EC0FF; + stroke-width: 1px; } #dag-viz-graph svg.stage g.cluster[id*="stage"] rect { fill: #FFFFFF; - stroke: #FFDDEE; - stroke-width: 6px; + stroke: #FFA6B6; + stroke-width: 1px; } #dag-viz-graph svg.stage g.node g.label text tspan { - fill: #FFFFFF; + fill: #333; } #dag-viz-graph svg.stage g.cluster text { - fill: #444444; - font-weight: bold; + fill: #333; +} + +#dag-viz-graph a, #dag-viz-graph a:hover { + text-decoration: none; +} + +#dag-viz-graph .label { + font-weight: normal; + text-shadow: none; } diff --git a/core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js b/core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js index a0e3e914c2547..764dd2cfcd76f 100644 --- a/core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js +++ b/core/src/main/resources/org/apache/spark/ui/static/spark-dag-viz.js @@ -52,9 +52,9 @@ */ var VizConstants = { - svgMarginX: 20, - svgMarginY: 20, - stageSep: 50, + svgMarginX: 16, + svgMarginY: 16, + stageSep: 40, graphPrefix: "graph_", nodePrefix: "node_", stagePrefix: "stage_", @@ -63,14 +63,16 @@ var VizConstants = { }; var JobPageVizConstants = { - clusterLabelSize: 11, - stageClusterLabelSize: 14 -} + clusterLabelSize: 12, + stageClusterLabelSize: 14, + rankSep: 40 +}; var StagePageVizConstants = { clusterLabelSize: 14, - stageClusterLabelSize: 18 -} + stageClusterLabelSize: 14, + rankSep: 40 +}; /* * Show or hide the RDD DAG visualization. @@ -149,11 +151,11 @@ function renderDagVizForStage(svgContainer) { var dot = metadata.select(".dot-file").text(); var containerId = VizConstants.graphPrefix + metadata.attr("stage-id"); var container = svgContainer.append("g").attr("id", containerId); - renderDot(dot, container); + renderDot(dot, container, StagePageVizConstants.rankSep); - // Round corners on RDDs + // Round corners on rectangles svgContainer - .selectAll("g.node rect") + .selectAll("rect") .attr("rx", "5") .attr("ry", "5"); } @@ -207,7 +209,13 @@ function renderDagVizForJob(svgContainer) { } // Actually render the stage - renderDot(dot, container); + renderDot(dot, container, JobPageVizConstants.rankSep); + + // Round corners on rectangles + container + .selectAll("rect") + .attr("rx", "4") + .attr("ry", "4"); // If there are any incoming edges into this graph, keep track of them to render // them separately later. Note that we cannot draw them now because we need to @@ -223,12 +231,13 @@ function renderDagVizForJob(svgContainer) { } /* Render the dot file as an SVG in the given container. */ -function renderDot(dot, container) { +function renderDot(dot, container, rankSep) { var escaped_dot = dot .replace(/</g, "<") .replace(/>/g, ">") .replace(/"/g, "\""); var g = graphlibDot.read(escaped_dot); + g.graph().rankSep = rankSep; var renderer = new dagreD3.render(); renderer(container, g); } @@ -248,12 +257,13 @@ function metadataContainer() { return d3.select("#dag-viz-metadata"); } * In general, the clustering support for dagre-d3 is quite limited at this point. */ function drawClusterLabels(svgContainer, forJob) { + var clusterLabelSize, stageClusterLabelSize; if (forJob) { - var clusterLabelSize = JobPageVizConstants.clusterLabelSize; - var stageClusterLabelSize = JobPageVizConstants.stageClusterLabelSize; + clusterLabelSize = JobPageVizConstants.clusterLabelSize; + stageClusterLabelSize = JobPageVizConstants.stageClusterLabelSize; } else { - var clusterLabelSize = StagePageVizConstants.clusterLabelSize; - var stageClusterLabelSize = StagePageVizConstants.stageClusterLabelSize; + clusterLabelSize = StagePageVizConstants.clusterLabelSize; + stageClusterLabelSize = StagePageVizConstants.stageClusterLabelSize; } svgContainer.selectAll("g.cluster").each(function() { var cluster = d3.select(this); @@ -283,7 +293,7 @@ function drawClusterLabel(d3cluster, fontSize) { .attr("x", labelX) .attr("y", labelY) .attr("text-anchor", "end") - .style("font-size", fontSize) + .style("font-size", fontSize + "px") .text(labelText); } @@ -303,12 +313,12 @@ function resizeSvg(svg) { })); var endX = VizConstants.svgMarginX + toFloat(d3.max(allClusters, function(e) { - var t = d3.select(e) + var t = d3.select(e); return getAbsolutePosition(t).x + toFloat(t.attr("width")); })); var endY = VizConstants.svgMarginY + toFloat(d3.max(allClusters, function(e) { - var t = d3.select(e) + var t = d3.select(e); return getAbsolutePosition(t).y + toFloat(t.attr("height")); })); var width = endX - startX; @@ -338,7 +348,7 @@ function drawCrossStageEdges(edges, svgContainer) { if (!dagreD3Marker.empty()) { svgContainer .append(function() { return dagreD3Marker.node().cloneNode(true); }) - .attr("id", "marker-arrow") + .attr("id", "marker-arrow"); svgContainer.selectAll("g > path").attr("marker-end", "url(#marker-arrow)"); svgContainer.selectAll("g.edgePaths def").remove(); // We no longer need these } @@ -394,12 +404,13 @@ function connectRDDs(fromRDDId, toRDDId, edgesContainer, svgContainer) { toPos.x += delta; } + var points; if (fromPos.y == toPos.y) { // If they are on the same rank, curve the middle part of the edge // upward a little to avoid interference with things in between // e.g. _______ // _____/ \_____ - var points = [ + points = [ [fromPos.x, fromPos.y], [fromPos.x + (toPos.x - fromPos.x) * 0.2, fromPos.y], [fromPos.x + (toPos.x - fromPos.x) * 0.3, fromPos.y - 20], @@ -413,7 +424,7 @@ function connectRDDs(fromRDDId, toRDDId, edgesContainer, svgContainer) { // / // | // _____/ - var points = [ + points = [ [fromPos.x, fromPos.y], [fromPos.x + (toPos.x - fromPos.x) * 0.4, fromPos.y], [fromPos.x + (toPos.x - fromPos.x) * 0.6, toPos.y], diff --git a/core/src/main/resources/org/apache/spark/ui/static/timeline-view.css b/core/src/main/resources/org/apache/spark/ui/static/timeline-view.css index 35ef14e5aaf1a..d40de704229c3 100644 --- a/core/src/main/resources/org/apache/spark/ui/static/timeline-view.css +++ b/core/src/main/resources/org/apache/spark/ui/static/timeline-view.css @@ -23,6 +23,10 @@ div#application-timeline, div#job-timeline { margin-top: 5px; } +.vis.timeline { + line-height: 14px; +} + .vis.timeline div.content { width: 100%; } @@ -32,48 +36,55 @@ div#application-timeline, div#job-timeline { } .vis.timeline .item.stage.succeeded { - background-color: #D5DDF6; + background-color: #A0DFFF; + border-color: #3EC0FF; } .vis.timeline .item.stage.succeeded.selected { - background-color: #D5DDF6; - border-color: #97B0F8; - z-index: auto; + background-color: #A0DFFF; + border-color: #3EC0FF; + z-index: auto; } .legend-area rect.completed-stage-legend { - fill: #D5DDF6; - stroke: #97B0F8; + fill: #A0DFFF; + stroke: #3EC0FF; } .vis.timeline .item.stage.failed { - background-color: #FF5475; + background-color: #FFA1B0; + border-color: #FF4D6D; } .vis.timeline .item.stage.failed.selected { - background-color: #FF5475; - border-color: #97B0F8; - z-index: auto; + background-color: #FFA1B0; + border-color: #FF4D6D; + z-index: auto; } .legend-area rect.failed-stage-legend { - fill: #FF5475; - stroke: #97B0F8; + fill: #FFA1B0; + stroke: #FF4D6D; } .vis.timeline .item.stage.running { - background-color: #FDFFCA; + background-color: #A2FCC0; + border-color: #36F572; } .vis.timeline .item.stage.running.selected { - background-color: #FDFFCA; - border-color: #97B0F8; - z-index: auto; + background-color: #A2FCC0; + border-color: #36F572; + z-index: auto; } .legend-area rect.active-stage-legend { - fill: #FDFFCA; - stroke: #97B0F8; + fill: #A2FCC0; + stroke: #36F572; +} + +.vis.timeline .foreground { + cursor: move; } .vis.timeline .item.job { @@ -81,76 +92,81 @@ div#application-timeline, div#job-timeline { } .vis.timeline .item.job.succeeded { - background-color: #D5DDF6; + background-color: #A0DFFF; + border-color: #3EC0FF; } .vis.timeline .item.job.succeeded.selected { - background-color: #D5DDF6; - border-color: #97B0F8; - z-index: auto; + background-color: #A0DFFF; + border-color: #3EC0FF; + z-index: auto; } .legend-area rect.succeeded-job-legend { - fill: #D5DDF6; - stroke: #97B0F8; + fill: #A0DFFF; + stroke: #3EC0FF; } .vis.timeline .item.job.failed { - background-color: #FF5475; + background-color: #FFA1B0; + border-color: #FF4D6D; } .vis.timeline .item.job.failed.selected { - background-color: #FF5475; - border-color: #97B0F8; - z-index: auto; + background-color: #FFA1B0; + border-color: #FF4D6D; + z-index: auto; } .legend-area rect.failed-job-legend { - fill: #FF5475; - stroke: #97B0F8; + fill: #FFA1B0; + stroke: #FF4D6D; } .vis.timeline .item.job.running { - background-color: #FDFFCA; + background-color: #A2FCC0; + border-color: #36F572; } .vis.timeline .item.job.running.selected { - background-color: #FDFFCA; - border-color: #97B0F8; - z-index: auto; + background-color: #A2FCC0; + border-color: #36F572; + z-index: auto; } .legend-area rect.running-job-legend { - fill: #FDFFCA; - stroke: #97B0F8; + fill: #A2FCC0; + stroke: #36F572; } .vis.timeline .item.executor.added { - background-color: #D5DDF6; + background-color: #A0DFFF; + border-color: #3EC0FF; } .legend-area rect.executor-added-legend { - fill: #D5DDF6; - stroke: #97B0F8; + fill: #A0DFFF; + stroke: #3EC0FF; } .vis.timeline .item.executor.removed { - background-color: #EBCA59; + background-color: #FFA1B0; + border-color: #FF4D6D; } .legend-area rect.executor-removed-legend { - fill: #EBCA59; - stroke: #97B0F8; + fill: #FFA1B0; + stroke: #FF4D6D; } .vis.timeline .item.executor.selected { - border-color: #FFC200; - background-color: #FFF785; + background-color: #A2FCC0; + border-color: #36F572; z-index: 2; } -tr.corresponding-item-hover>td, tr.corresponding-item-hover>th { - background-color: #FFE1FA !important; +tr.corresponding-item-hover > td, tr.corresponding-item-hover > th { + background-color: #D6FFE4 !important; } #application-timeline.collapsed { @@ -165,11 +181,15 @@ tr.corresponding-item-hover>td, tr.corresponding-item-hover>th { margin-bottom: 5px; } +.control-panel input[type="checkbox"] { + margin: 0; +} + span.expand-application-timeline, span.expand-job-timeline { cursor: pointer; } -.control-panel input+span { +.control-panel input + span { cursor: pointer; } @@ -180,3 +200,17 @@ span.expand-application-timeline, span.expand-job-timeline { .vis.timeline .item .tooltip-inner { max-width: unset !important; } + +.vispanel.center { + font-size: 12px; + line-height: 12px; +} + +.legend-area text { + fill: #4D4D4D; +} + +.additional-metrics ul { + list-style: none; + margin-left: 15px; +} diff --git a/core/src/main/resources/org/apache/spark/ui/static/timeline-view.js b/core/src/main/resources/org/apache/spark/ui/static/timeline-view.js index e4a891d47f035..48fbb33b1155b 100644 --- a/core/src/main/resources/org/apache/spark/ui/static/timeline-view.js +++ b/core/src/main/resources/org/apache/spark/ui/static/timeline-view.js @@ -156,9 +156,9 @@ function setupExecutorEventAction() { function setupZoomable(id, timeline) { $(id + '>input[type="checkbox"]').click(function() { if (this.checked) { - timeline.setOptions({zoomable: false}); - } else { timeline.setOptions({zoomable: true}); + } else { + timeline.setOptions({zoomable: false}); } }); diff --git a/core/src/main/resources/org/apache/spark/ui/static/webui.css b/core/src/main/resources/org/apache/spark/ui/static/webui.css index 669ad48937c05..e7c1d475d4e52 100644 --- a/core/src/main/resources/org/apache/spark/ui/static/webui.css +++ b/core/src/main/resources/org/apache/spark/ui/static/webui.css @@ -106,14 +106,18 @@ span.rest-uri { } pre { - font-size: 0.8em; + font-size: 12px; + line-height: 18px; + padding: 6px; + margin: 0; + border-radius: 3px; } .stage-details { max-height: 100px; overflow-y: auto; margin: 0; - transition: max-height 0.5s ease-out, padding 0.5s ease-out; + transition: max-height 0.25s ease-out, padding 0.25s ease-out; } .stage-details.collapsed { @@ -135,7 +139,7 @@ pre { max-height: 300px; overflow-y: auto; margin: 0; - transition: max-height 0.5s ease-out, padding 0.5s ease-out; + transition: max-height 0.25s ease-out, padding 0.25s ease-out; } .stacktrace-details.collapsed { @@ -158,7 +162,7 @@ span.additional-metric-title { } .tooltip { - font-weight: normal; + font-weight: normal; } .arrow-open { @@ -166,9 +170,9 @@ span.additional-metric-title { height: 0; border-left: 5px solid transparent; border-right: 5px solid transparent; - border-top: 5px solid black; - float: left; - margin-top: 6px; + border-top: 5px solid #08c; + display: inline-block; + margin-bottom: 2px; } .arrow-closed { @@ -176,8 +180,10 @@ span.additional-metric-title { height: 0; border-top: 5px solid transparent; border-bottom: 5px solid transparent; - border-left: 5px solid black; + border-left: 5px solid #08c; display: inline-block; + margin-left: 2px; + margin-right: 3px; } .version { @@ -196,3 +202,17 @@ span.additional-metric-title { .serialization_time, .getting_result_time { display: none; } + +.accordion-inner { + background: #f5f5f5; +} + +.accordion-inner pre { + border: 0; + padding: 0; + background: none; +} + +a.expandbutton { + cursor: pointer; +} diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index b5f040ceb15ca..b59f562d05ead 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -430,7 +430,7 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli _ui = if (conf.getBoolean("spark.ui.enabled", true)) { Some(SparkUI.createLiveUI(this, _conf, listenerBus, _jobProgressListener, - _env.securityManager,appName)) + _env.securityManager,appName, startTime = startTime)) } else { // For tests, do not enable the UI None diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala index 8a0327984e195..329fa06ba8ba5 100644 --- a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala +++ b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala @@ -332,6 +332,47 @@ object SparkSubmit { } } + // In yarn mode for a python app, add pyspark archives to files + // that can be distributed with the job + if (args.isPython && clusterManager == YARN) { + var pyArchives: String = null + val pyArchivesEnvOpt = sys.env.get("PYSPARK_ARCHIVES_PATH") + if (pyArchivesEnvOpt.isDefined) { + pyArchives = pyArchivesEnvOpt.get + } else { + if (!sys.env.contains("SPARK_HOME")) { + printErrorAndExit("SPARK_HOME does not exist for python application in yarn mode.") + } + val pythonPath = new ArrayBuffer[String] + for (sparkHome <- sys.env.get("SPARK_HOME")) { + val pyLibPath = Seq(sparkHome, "python", "lib").mkString(File.separator) + val pyArchivesFile = new File(pyLibPath, "pyspark.zip") + if (!pyArchivesFile.exists()) { + printErrorAndExit("pyspark.zip does not exist for python application in yarn mode.") + } + val py4jFile = new File(pyLibPath, "py4j-0.8.2.1-src.zip") + if (!py4jFile.exists()) { + printErrorAndExit("py4j-0.8.2.1-src.zip does not exist for python application " + + "in yarn mode.") + } + pythonPath += pyArchivesFile.getAbsolutePath() + pythonPath += py4jFile.getAbsolutePath() + } + pyArchives = pythonPath.mkString(",") + } + + pyArchives = pyArchives.split(",").map { localPath=> + val localURI = Utils.resolveURI(localPath) + if (localURI.getScheme != "local") { + args.files = mergeFileLists(args.files, localURI.toString) + new Path(localPath).getName + } else { + localURI.getPath + } + }.mkString(File.pathSeparator) + sysProps("spark.submit.pyArchives") = pyArchives + } + // If we're running a R app, set the main class to our specific R runner if (args.isR && deployMode == CLIENT) { if (args.primaryResource == SPARKR_SHELL) { diff --git a/core/src/main/scala/org/apache/spark/deploy/history/ApplicationHistoryProvider.scala b/core/src/main/scala/org/apache/spark/deploy/history/ApplicationHistoryProvider.scala index 6a5011af17458..298a8201960d1 100644 --- a/core/src/main/scala/org/apache/spark/deploy/history/ApplicationHistoryProvider.scala +++ b/core/src/main/scala/org/apache/spark/deploy/history/ApplicationHistoryProvider.scala @@ -19,7 +19,7 @@ package org.apache.spark.deploy.history import org.apache.spark.ui.SparkUI -private[history] case class ApplicationAttemptInfo( +private[spark] case class ApplicationAttemptInfo( attemptId: Option[String], startTime: Long, endTime: Long, @@ -27,7 +27,7 @@ private[history] case class ApplicationAttemptInfo( sparkUser: String, completed: Boolean = false) -private[history] case class ApplicationHistoryInfo( +private[spark] case class ApplicationHistoryInfo( id: String, name: String, attempts: List[ApplicationAttemptInfo]) diff --git a/core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala b/core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala index 993763f3aa092..45c2be34c8680 100644 --- a/core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala +++ b/core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala @@ -17,23 +17,21 @@ package org.apache.spark.deploy.history -import java.io.{IOException, BufferedInputStream, FileNotFoundException, InputStream} +import java.io.{BufferedInputStream, FileNotFoundException, IOException, InputStream} import java.util.concurrent.{ExecutorService, Executors, TimeUnit} import scala.collection.mutable -import scala.concurrent.duration.Duration -import com.google.common.util.concurrent.ThreadFactoryBuilder - -import com.google.common.util.concurrent.MoreExecutors -import org.apache.hadoop.fs.permission.AccessControlException +import com.google.common.util.concurrent.{MoreExecutors, ThreadFactoryBuilder} import org.apache.hadoop.fs.{FileStatus, Path} +import org.apache.hadoop.fs.permission.AccessControlException + +import org.apache.spark.{Logging, SecurityManager, SparkConf} import org.apache.spark.deploy.SparkHadoopUtil import org.apache.spark.io.CompressionCodec import org.apache.spark.scheduler._ import org.apache.spark.ui.SparkUI import org.apache.spark.util.{Clock, SystemClock, ThreadUtils, Utils} -import org.apache.spark.{Logging, SecurityManager, SparkConf} /** * A class that provides application history from event logs stored in the file system. @@ -151,7 +149,7 @@ private[history] class FsHistoryProvider(conf: SparkConf, clock: Clock) val conf = this.conf.clone() val appSecManager = new SecurityManager(conf) SparkUI.createHistoryUI(conf, replayBus, appSecManager, appId, - HistoryServer.getAttemptURI(appId, attempt.attemptId)) + HistoryServer.getAttemptURI(appId, attempt.attemptId), attempt.startTime) // Do not call ui.bind() to avoid creating a new server for each application } diff --git a/core/src/main/scala/org/apache/spark/deploy/history/HistoryServer.scala b/core/src/main/scala/org/apache/spark/deploy/history/HistoryServer.scala index 754c8e9b6668b..50522e69dc519 100644 --- a/core/src/main/scala/org/apache/spark/deploy/history/HistoryServer.scala +++ b/core/src/main/scala/org/apache/spark/deploy/history/HistoryServer.scala @@ -25,6 +25,7 @@ import org.eclipse.jetty.servlet.{ServletContextHandler, ServletHolder} import org.apache.spark.{Logging, SecurityManager, SparkConf} import org.apache.spark.deploy.SparkHadoopUtil +import org.apache.spark.status.api.v1.{ApplicationInfo, ApplicationsListResource, JsonRootResource, UIRoot} import org.apache.spark.ui.{SparkUI, UIUtils, WebUI} import org.apache.spark.ui.JettyUtils._ import org.apache.spark.util.{SignalLogger, Utils} @@ -45,7 +46,7 @@ class HistoryServer( provider: ApplicationHistoryProvider, securityManager: SecurityManager, port: Int) - extends WebUI(securityManager, port, conf) with Logging { + extends WebUI(securityManager, port, conf) with Logging with UIRoot { // How many applications to retain private val retainedApplications = conf.getInt("spark.history.retainedApplications", 50) @@ -56,7 +57,7 @@ class HistoryServer( require(parts.length == 1 || parts.length == 2, s"Invalid app key $key") val ui = provider .getAppUI(parts(0), if (parts.length > 1) Some(parts(1)) else None) - .getOrElse(throw new NoSuchElementException()) + .getOrElse(throw new NoSuchElementException(s"no app with key $key")) attachSparkUI(ui) ui } @@ -113,6 +114,10 @@ class HistoryServer( } } + def getSparkUI(appKey: String): Option[SparkUI] = { + Option(appCache.get(appKey)) + } + initialize() /** @@ -123,6 +128,9 @@ class HistoryServer( */ def initialize() { attachPage(new HistoryPage(this)) + + attachHandler(JsonRootResource.getJsonServlet(this)) + attachHandler(createStaticHandler(SparkUI.STATIC_RESOURCE_DIR, "/static")) val contextHandler = new ServletContextHandler @@ -160,7 +168,13 @@ class HistoryServer( * * @return List of all known applications. */ - def getApplicationList(): Iterable[ApplicationHistoryInfo] = provider.getListing() + def getApplicationList(): Iterable[ApplicationHistoryInfo] = { + provider.getListing() + } + + def getApplicationInfoList: Iterator[ApplicationInfo] = { + getApplicationList().iterator.map(ApplicationsListResource.appHistoryInfoToPublicAppInfo) + } /** * Returns the provider configuration to show in the listing page. diff --git a/core/src/main/scala/org/apache/spark/deploy/master/ApplicationInfo.scala b/core/src/main/scala/org/apache/spark/deploy/master/ApplicationInfo.scala index f59d550d4f3b3..1620e95bea218 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/ApplicationInfo.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/ApplicationInfo.scala @@ -28,7 +28,7 @@ import org.apache.spark.annotation.DeveloperApi import org.apache.spark.deploy.ApplicationDescription import org.apache.spark.util.Utils -private[deploy] class ApplicationInfo( +private[spark] class ApplicationInfo( val startTime: Long, val id: String, val desc: ApplicationDescription, diff --git a/core/src/main/scala/org/apache/spark/deploy/master/Master.scala b/core/src/main/scala/org/apache/spark/deploy/master/Master.scala index 0fac3cdcf55e7..fccceb3ea528b 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/Master.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/Master.scala @@ -165,7 +165,7 @@ private[master] class Master( (fsFactory.createPersistenceEngine(), fsFactory.createLeaderElectionAgent(this)) case "CUSTOM" => val clazz = Class.forName(conf.get("spark.deploy.recoveryMode.factory")) - val factory = clazz.getConstructor(conf.getClass, Serialization.getClass) + val factory = clazz.getConstructor(classOf[SparkConf], classOf[Serialization]) .newInstance(conf, SerializationExtension(context.system)) .asInstanceOf[StandaloneRecoveryModeFactory] (factory.createPersistenceEngine(), factory.createLeaderElectionAgent(this)) @@ -754,9 +754,9 @@ private[master] class Master( /** * Rebuild a new SparkUI from the given application's event logs. - * Return whether this is successful. + * Return the UI if successful, else None */ - private def rebuildSparkUI(app: ApplicationInfo): Boolean = { + private[master] def rebuildSparkUI(app: ApplicationInfo): Option[SparkUI] = { val appName = app.desc.name val notFoundBasePath = HistoryServer.UI_PATH_PREFIX + "/not-found" try { @@ -764,7 +764,7 @@ private[master] class Master( .getOrElse { // Event logging is not enabled for this application app.desc.appUiUrl = notFoundBasePath - return false + return None } val eventLogFilePrefix = EventLoggingListener.getLogPath( @@ -787,7 +787,7 @@ private[master] class Master( val logInput = EventLoggingListener.openEventLog(new Path(eventLogFile), fs) val replayBus = new ReplayListenerBus() val ui = SparkUI.createHistoryUI(new SparkConf, replayBus, new SecurityManager(conf), - appName + status, HistoryServer.UI_PATH_PREFIX + s"/${app.id}") + appName + status, HistoryServer.UI_PATH_PREFIX + s"/${app.id}", app.startTime) val maybeTruncated = eventLogFile.endsWith(EventLoggingListener.IN_PROGRESS) try { replayBus.replay(logInput, eventLogFile, maybeTruncated) @@ -798,7 +798,7 @@ private[master] class Master( webUi.attachSparkUI(ui) // Application UI is successfully rebuilt, so link the Master UI to it app.desc.appUiUrl = ui.basePath - true + Some(ui) } catch { case fnf: FileNotFoundException => // Event logging is enabled for this application, but no event logs are found @@ -808,7 +808,7 @@ private[master] class Master( msg += " Did you specify the correct logging directory?" msg = URLEncoder.encode(msg, "UTF-8") app.desc.appUiUrl = notFoundBasePath + s"?msg=$msg&title=$title" - false + None case e: Exception => // Relay exception message to application UI page val title = s"Application history load error (${app.id})" @@ -817,7 +817,7 @@ private[master] class Master( logError(msg, e) msg = URLEncoder.encode(msg, "UTF-8") app.desc.appUiUrl = notFoundBasePath + s"?msg=$msg&exception=$exception&title=$title" - false + None } } diff --git a/core/src/main/scala/org/apache/spark/deploy/master/ui/ApplicationPage.scala b/core/src/main/scala/org/apache/spark/deploy/master/ui/ApplicationPage.scala index 273f077bd8f57..06e265f99e231 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/ui/ApplicationPage.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/ui/ApplicationPage.scala @@ -23,10 +23,8 @@ import scala.concurrent.Await import scala.xml.Node import akka.pattern.ask -import org.json4s.JValue -import org.json4s.JsonAST.JNothing -import org.apache.spark.deploy.{ExecutorState, JsonProtocol} +import org.apache.spark.deploy.ExecutorState import org.apache.spark.deploy.DeployMessages.{MasterStateResponse, RequestMasterState} import org.apache.spark.deploy.master.ExecutorDesc import org.apache.spark.ui.{UIUtils, WebUIPage} @@ -37,21 +35,6 @@ private[ui] class ApplicationPage(parent: MasterWebUI) extends WebUIPage("app") private val master = parent.masterActorRef private val timeout = parent.timeout - /** Executor details for a particular application */ - override def renderJson(request: HttpServletRequest): JValue = { - val appId = request.getParameter("appId") - val stateFuture = (master ? RequestMasterState)(timeout).mapTo[MasterStateResponse] - val state = Await.result(stateFuture, timeout) - val app = state.activeApps.find(_.id == appId).getOrElse({ - state.completedApps.find(_.id == appId).getOrElse(null) - }) - if (app == null) { - JNothing - } else { - JsonProtocol.writeApplicationInfo(app) - } - } - /** Executor details for a particular application */ def render(request: HttpServletRequest): Seq[Node] = { val appId = request.getParameter("appId") diff --git a/core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala b/core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala index 1f2c3fdbfb2bc..756927682cd24 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/ui/MasterPage.scala @@ -35,10 +35,13 @@ private[ui] class MasterPage(parent: MasterWebUI) extends WebUIPage("") { private val master = parent.masterActorRef private val timeout = parent.timeout - override def renderJson(request: HttpServletRequest): JValue = { + def getMasterState: MasterStateResponse = { val stateFuture = (master ? RequestMasterState)(timeout).mapTo[MasterStateResponse] - val state = Await.result(stateFuture, timeout) - JsonProtocol.writeMasterState(state) + Await.result(stateFuture, timeout) + } + + override def renderJson(request: HttpServletRequest): JValue = { + JsonProtocol.writeMasterState(getMasterState) } def handleAppKillRequest(request: HttpServletRequest): Unit = { @@ -68,8 +71,7 @@ private[ui] class MasterPage(parent: MasterWebUI) extends WebUIPage("") { /** Index view listing applications and executors */ def render(request: HttpServletRequest): Seq[Node] = { - val stateFuture = (master ? RequestMasterState)(timeout).mapTo[MasterStateResponse] - val state = Await.result(stateFuture, timeout) + val state = getMasterState val workerHeaders = Seq("Worker Id", "Address", "State", "Cores", "Memory") val workers = state.workers.sortBy(_.id) diff --git a/core/src/main/scala/org/apache/spark/deploy/master/ui/MasterWebUI.scala b/core/src/main/scala/org/apache/spark/deploy/master/ui/MasterWebUI.scala index dea0a65eeeaa6..eb26e9f99c70b 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/ui/MasterWebUI.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/ui/MasterWebUI.scala @@ -19,6 +19,7 @@ package org.apache.spark.deploy.master.ui import org.apache.spark.Logging import org.apache.spark.deploy.master.Master +import org.apache.spark.status.api.v1.{ApplicationsListResource, ApplicationInfo, JsonRootResource, UIRoot} import org.apache.spark.ui.{SparkUI, WebUI} import org.apache.spark.ui.JettyUtils._ import org.apache.spark.util.RpcUtils @@ -28,12 +29,15 @@ import org.apache.spark.util.RpcUtils */ private[master] class MasterWebUI(val master: Master, requestedPort: Int) - extends WebUI(master.securityMgr, requestedPort, master.conf, name = "MasterUI") with Logging { + extends WebUI(master.securityMgr, requestedPort, master.conf, name = "MasterUI") with Logging + with UIRoot { val masterActorRef = master.self val timeout = RpcUtils.askTimeout(master.conf) val killEnabled = master.conf.getBoolean("spark.ui.killEnabled", true) + val masterPage = new MasterPage(this) + initialize() /** Initialize all components of the server. */ @@ -43,6 +47,7 @@ class MasterWebUI(val master: Master, requestedPort: Int) attachPage(new HistoryNotFoundPage(this)) attachPage(masterPage) attachHandler(createStaticHandler(MasterWebUI.STATIC_RESOURCE_DIR, "/static")) + attachHandler(JsonRootResource.getJsonServlet(this)) attachHandler(createRedirectHandler( "/app/kill", "/", masterPage.handleAppKillRequest, httpMethods = Set("POST"))) attachHandler(createRedirectHandler( @@ -60,6 +65,23 @@ class MasterWebUI(val master: Master, requestedPort: Int) assert(serverInfo.isDefined, "Master UI must be bound to a server before detaching SparkUIs") ui.getHandlers.foreach(detachHandler) } + + def getApplicationInfoList: Iterator[ApplicationInfo] = { + val state = masterPage.getMasterState + val activeApps = state.activeApps.sortBy(_.startTime).reverse + val completedApps = state.completedApps.sortBy(_.endTime).reverse + activeApps.iterator.map { ApplicationsListResource.convertApplicationInfo(_, false) } ++ + completedApps.iterator.map { ApplicationsListResource.convertApplicationInfo(_, true) } + } + + def getSparkUI(appId: String): Option[SparkUI] = { + val state = masterPage.getMasterState + val activeApps = state.activeApps.sortBy(_.startTime).reverse + val completedApps = state.completedApps.sortBy(_.endTime).reverse + (activeApps ++ completedApps).find { _.id == appId }.flatMap { + master.rebuildSparkUI + } + } } private[master] object MasterWebUI { diff --git a/core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala b/core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala index f9f78852f032b..64ba27f34d2f1 100644 --- a/core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala +++ b/core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala @@ -32,6 +32,7 @@ import org.apache.spark._ import org.apache.spark.api.python.PythonBroadcast import org.apache.spark.broadcast.HttpBroadcast import org.apache.spark.network.nio.{GetBlock, GotBlock, PutBlock} +import org.apache.spark.network.util.ByteUnit import org.apache.spark.scheduler.{CompressedMapStatus, HighlyCompressedMapStatus} import org.apache.spark.storage._ import org.apache.spark.util.BoundedPriorityQueue @@ -51,18 +52,18 @@ class KryoSerializer(conf: SparkConf) private val bufferSizeKb = conf.getSizeAsKb("spark.kryoserializer.buffer", "64k") - if (bufferSizeKb >= 2048) { + if (bufferSizeKb >= ByteUnit.GiB.toKiB(2)) { throw new IllegalArgumentException("spark.kryoserializer.buffer must be less than " + - s"2048 mb, got: + $bufferSizeKb mb.") + s"2048 mb, got: + ${ByteUnit.KiB.toMiB(bufferSizeKb)} mb.") } - private val bufferSize = (bufferSizeKb * 1024).toInt + private val bufferSize = ByteUnit.KiB.toBytes(bufferSizeKb).toInt val maxBufferSizeMb = conf.getSizeAsMb("spark.kryoserializer.buffer.max", "64m").toInt - if (maxBufferSizeMb >= 2048) { + if (maxBufferSizeMb >= ByteUnit.GiB.toMiB(2)) { throw new IllegalArgumentException("spark.kryoserializer.buffer.max must be less than " + s"2048 mb, got: + $maxBufferSizeMb mb.") } - private val maxBufferSize = maxBufferSizeMb * 1024 * 1024 + private val maxBufferSize = ByteUnit.MiB.toBytes(maxBufferSizeMb).toInt private val referenceTracking = conf.getBoolean("spark.kryo.referenceTracking", true) private val registrationRequired = conf.getBoolean("spark.kryo.registrationRequired", false) diff --git a/core/src/main/scala/org/apache/spark/shuffle/FileShuffleBlockManager.scala b/core/src/main/scala/org/apache/spark/shuffle/FileShuffleBlockResolver.scala similarity index 97% rename from core/src/main/scala/org/apache/spark/shuffle/FileShuffleBlockManager.scala rename to core/src/main/scala/org/apache/spark/shuffle/FileShuffleBlockResolver.scala index e9b4e2b955dc8..6ad427bcac7f9 100644 --- a/core/src/main/scala/org/apache/spark/shuffle/FileShuffleBlockManager.scala +++ b/core/src/main/scala/org/apache/spark/shuffle/FileShuffleBlockResolver.scala @@ -18,7 +18,6 @@ package org.apache.spark.shuffle import java.io.File -import java.nio.ByteBuffer import java.util.concurrent.ConcurrentLinkedQueue import java.util.concurrent.atomic.AtomicInteger @@ -29,7 +28,7 @@ import org.apache.spark.executor.ShuffleWriteMetrics import org.apache.spark.network.buffer.{FileSegmentManagedBuffer, ManagedBuffer} import org.apache.spark.network.netty.SparkTransportConf import org.apache.spark.serializer.Serializer -import org.apache.spark.shuffle.FileShuffleBlockManager.ShuffleFileGroup +import org.apache.spark.shuffle.FileShuffleBlockResolver.ShuffleFileGroup import org.apache.spark.storage._ import org.apache.spark.util.{MetadataCleaner, MetadataCleanerType, TimeStampedHashMap} import org.apache.spark.util.collection.{PrimitiveKeyOpenHashMap, PrimitiveVector} @@ -64,9 +63,8 @@ private[spark] trait ShuffleWriterGroup { * files within a ShuffleFileGroups associated with the block's reducer. */ // Note: Changes to the format in this file should be kept in sync with -// org.apache.spark.network.shuffle.StandaloneShuffleBlockManager#getHashBasedShuffleBlockData(). -private[spark] -class FileShuffleBlockManager(conf: SparkConf) +// org.apache.spark.network.shuffle.ExternalShuffleBlockResolver#getHashBasedShuffleBlockData(). +private[spark] class FileShuffleBlockResolver(conf: SparkConf) extends ShuffleBlockResolver with Logging { private val transportConf = SparkTransportConf.fromSparkConf(conf) @@ -242,8 +240,7 @@ class FileShuffleBlockManager(conf: SparkConf) } } -private[spark] -object FileShuffleBlockManager { +private[spark] object FileShuffleBlockResolver { /** * A group of shuffle files, one per reducer. * A particular mapper will be assigned a single ShuffleFileGroup to write its output to. diff --git a/core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockManager.scala b/core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala similarity index 93% rename from core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockManager.scala rename to core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala index a1741e2875c16..d9c63b6e7bbb9 100644 --- a/core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockManager.scala +++ b/core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala @@ -18,7 +18,6 @@ package org.apache.spark.shuffle import java.io._ -import java.nio.ByteBuffer import com.google.common.io.ByteStreams @@ -28,7 +27,7 @@ import org.apache.spark.network.netty.SparkTransportConf import org.apache.spark.storage._ import org.apache.spark.util.Utils -import IndexShuffleBlockManager.NOOP_REDUCE_ID +import IndexShuffleBlockResolver.NOOP_REDUCE_ID /** * Create and maintain the shuffle blocks' mapping between logic block and physical file location. @@ -40,9 +39,8 @@ import IndexShuffleBlockManager.NOOP_REDUCE_ID * */ // Note: Changes to the format in this file should be kept in sync with -// org.apache.spark.network.shuffle.StandaloneShuffleBlockManager#getSortBasedShuffleBlockData(). -private[spark] -class IndexShuffleBlockManager(conf: SparkConf) extends ShuffleBlockResolver { +// org.apache.spark.network.shuffle.ExternalShuffleBlockResolver#getSortBasedShuffleBlockData(). +private[spark] class IndexShuffleBlockResolver(conf: SparkConf) extends ShuffleBlockResolver { private lazy val blockManager = SparkEnv.get.blockManager @@ -115,7 +113,7 @@ class IndexShuffleBlockManager(conf: SparkConf) extends ShuffleBlockResolver { override def stop(): Unit = {} } -private[spark] object IndexShuffleBlockManager { +private[spark] object IndexShuffleBlockResolver { // No-op reduce ID used in interactions with disk store and BlockObjectWriter. // The disk store currently expects puts to relate to a (map, reduce) pair, but in the sort // shuffle outputs for several reduces are glommed into a single file. diff --git a/core/src/main/scala/org/apache/spark/shuffle/hash/HashShuffleManager.scala b/core/src/main/scala/org/apache/spark/shuffle/hash/HashShuffleManager.scala index 2a7df8dd5bd83..c089088f409dd 100644 --- a/core/src/main/scala/org/apache/spark/shuffle/hash/HashShuffleManager.scala +++ b/core/src/main/scala/org/apache/spark/shuffle/hash/HashShuffleManager.scala @@ -26,7 +26,7 @@ import org.apache.spark.shuffle._ */ private[spark] class HashShuffleManager(conf: SparkConf) extends ShuffleManager { - private val fileShuffleBlockManager = new FileShuffleBlockManager(conf) + private val fileShuffleBlockResolver = new FileShuffleBlockResolver(conf) /* Register a shuffle with the manager and obtain a handle for it to pass to tasks. */ override def registerShuffle[K, V, C]( @@ -61,8 +61,8 @@ private[spark] class HashShuffleManager(conf: SparkConf) extends ShuffleManager shuffleBlockResolver.removeShuffle(shuffleId) } - override def shuffleBlockResolver: FileShuffleBlockManager = { - fileShuffleBlockManager + override def shuffleBlockResolver: FileShuffleBlockResolver = { + fileShuffleBlockResolver } /** Shut down this ShuffleManager. */ diff --git a/core/src/main/scala/org/apache/spark/shuffle/hash/HashShuffleWriter.scala b/core/src/main/scala/org/apache/spark/shuffle/hash/HashShuffleWriter.scala index cd27c9e07a3cd..897f0a5dc5bcc 100644 --- a/core/src/main/scala/org/apache/spark/shuffle/hash/HashShuffleWriter.scala +++ b/core/src/main/scala/org/apache/spark/shuffle/hash/HashShuffleWriter.scala @@ -25,7 +25,7 @@ import org.apache.spark.shuffle._ import org.apache.spark.storage.BlockObjectWriter private[spark] class HashShuffleWriter[K, V]( - shuffleBlockManager: FileShuffleBlockManager, + shuffleBlockResolver: FileShuffleBlockResolver, handle: BaseShuffleHandle[K, V, _], mapId: Int, context: TaskContext) @@ -45,7 +45,7 @@ private[spark] class HashShuffleWriter[K, V]( private val blockManager = SparkEnv.get.blockManager private val ser = Serializer.getSerializer(dep.serializer.getOrElse(null)) - private val shuffle = shuffleBlockManager.forMapTask(dep.shuffleId, mapId, numOutputSplits, ser, + private val shuffle = shuffleBlockResolver.forMapTask(dep.shuffleId, mapId, numOutputSplits, ser, writeMetrics) /** Write a bunch of records to this task's output */ diff --git a/core/src/main/scala/org/apache/spark/shuffle/sort/SortShuffleManager.scala b/core/src/main/scala/org/apache/spark/shuffle/sort/SortShuffleManager.scala index 0497036192154..15842941daaab 100644 --- a/core/src/main/scala/org/apache/spark/shuffle/sort/SortShuffleManager.scala +++ b/core/src/main/scala/org/apache/spark/shuffle/sort/SortShuffleManager.scala @@ -25,7 +25,7 @@ import org.apache.spark.shuffle.hash.HashShuffleReader private[spark] class SortShuffleManager(conf: SparkConf) extends ShuffleManager { - private val indexShuffleBlockManager = new IndexShuffleBlockManager(conf) + private val indexShuffleBlockResolver = new IndexShuffleBlockResolver(conf) private val shuffleMapNumber = new ConcurrentHashMap[Int, Int]() /** @@ -72,8 +72,8 @@ private[spark] class SortShuffleManager(conf: SparkConf) extends ShuffleManager true } - override def shuffleBlockResolver: IndexShuffleBlockManager = { - indexShuffleBlockManager + override def shuffleBlockResolver: IndexShuffleBlockResolver = { + indexShuffleBlockResolver } /** Shut down this ShuffleManager. */ diff --git a/core/src/main/scala/org/apache/spark/shuffle/sort/SortShuffleWriter.scala b/core/src/main/scala/org/apache/spark/shuffle/sort/SortShuffleWriter.scala index a066435df6fb0..add2656294ca2 100644 --- a/core/src/main/scala/org/apache/spark/shuffle/sort/SortShuffleWriter.scala +++ b/core/src/main/scala/org/apache/spark/shuffle/sort/SortShuffleWriter.scala @@ -20,12 +20,12 @@ package org.apache.spark.shuffle.sort import org.apache.spark.{MapOutputTracker, SparkEnv, Logging, TaskContext} import org.apache.spark.executor.ShuffleWriteMetrics import org.apache.spark.scheduler.MapStatus -import org.apache.spark.shuffle.{IndexShuffleBlockManager, ShuffleWriter, BaseShuffleHandle} +import org.apache.spark.shuffle.{IndexShuffleBlockResolver, ShuffleWriter, BaseShuffleHandle} import org.apache.spark.storage.ShuffleBlockId import org.apache.spark.util.collection.ExternalSorter private[spark] class SortShuffleWriter[K, V, C]( - shuffleBlockManager: IndexShuffleBlockManager, + shuffleBlockResolver: IndexShuffleBlockResolver, handle: BaseShuffleHandle[K, V, C], mapId: Int, context: TaskContext) @@ -65,10 +65,10 @@ private[spark] class SortShuffleWriter[K, V, C]( // Don't bother including the time to open the merged output file in the shuffle write time, // because it just opens a single file, so is typically too fast to measure accurately // (see SPARK-3570). - val outputFile = shuffleBlockManager.getDataFile(dep.shuffleId, mapId) - val blockId = ShuffleBlockId(dep.shuffleId, mapId, IndexShuffleBlockManager.NOOP_REDUCE_ID) + val outputFile = shuffleBlockResolver.getDataFile(dep.shuffleId, mapId) + val blockId = ShuffleBlockId(dep.shuffleId, mapId, IndexShuffleBlockResolver.NOOP_REDUCE_ID) val partitionLengths = sorter.writePartitionedFile(blockId, context, outputFile) - shuffleBlockManager.writeIndexFile(dep.shuffleId, mapId, partitionLengths) + shuffleBlockResolver.writeIndexFile(dep.shuffleId, mapId, partitionLengths) mapStatus = MapStatus(blockManager.shuffleServerId, partitionLengths) } @@ -84,7 +84,7 @@ private[spark] class SortShuffleWriter[K, V, C]( return Option(mapStatus) } else { // The map task failed, so delete our output data. - shuffleBlockManager.removeDataByMap(dep.shuffleId, mapId) + shuffleBlockResolver.removeDataByMap(dep.shuffleId, mapId) return None } } finally { diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/AllJobsResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/AllJobsResource.scala new file mode 100644 index 0000000000000..5783df5d8220c --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/AllJobsResource.scala @@ -0,0 +1,98 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import java.util.{Arrays, Date, List => JList} +import javax.ws.rs._ +import javax.ws.rs.core.MediaType + +import org.apache.spark.JobExecutionStatus +import org.apache.spark.ui.SparkUI +import org.apache.spark.ui.jobs.JobProgressListener +import org.apache.spark.ui.jobs.UIData.JobUIData + +@Produces(Array(MediaType.APPLICATION_JSON)) +private[v1] class AllJobsResource(ui: SparkUI) { + + @GET + def jobsList(@QueryParam("status") statuses: JList[JobExecutionStatus]): Seq[JobData] = { + val statusToJobs: Seq[(JobExecutionStatus, Seq[JobUIData])] = + AllJobsResource.getStatusToJobs(ui) + val adjStatuses: JList[JobExecutionStatus] = { + if (statuses.isEmpty) { + Arrays.asList(JobExecutionStatus.values(): _*) + } else { + statuses + } + } + val jobInfos = for { + (status, jobs) <- statusToJobs + job <- jobs if adjStatuses.contains(status) + } yield { + AllJobsResource.convertJobData(job, ui.jobProgressListener, false) + } + jobInfos.sortBy{- _.jobId} + } + +} + +private[v1] object AllJobsResource { + + def getStatusToJobs(ui: SparkUI): Seq[(JobExecutionStatus, Seq[JobUIData])] = { + val statusToJobs = ui.jobProgressListener.synchronized { + Seq( + JobExecutionStatus.RUNNING -> ui.jobProgressListener.activeJobs.values.toSeq, + JobExecutionStatus.SUCCEEDED -> ui.jobProgressListener.completedJobs.toSeq, + JobExecutionStatus.FAILED -> ui.jobProgressListener.failedJobs.reverse.toSeq + ) + } + statusToJobs + } + + def convertJobData( + job: JobUIData, + listener: JobProgressListener, + includeStageDetails: Boolean): JobData = { + listener.synchronized { + val lastStageInfo = listener.stageIdToInfo.get(job.stageIds.max) + val lastStageData = lastStageInfo.flatMap { s => + listener.stageIdToData.get((s.stageId, s.attemptId)) + } + val lastStageName = lastStageInfo.map { _.name }.getOrElse("(Unknown Stage Name)") + val lastStageDescription = lastStageData.flatMap { _.description } + new JobData( + jobId = job.jobId, + name = lastStageName, + description = lastStageDescription, + submissionTime = job.submissionTime.map{new Date(_)}, + completionTime = job.completionTime.map{new Date(_)}, + stageIds = job.stageIds, + jobGroup = job.jobGroup, + status = job.status, + numTasks = job.numTasks, + numActiveTasks = job.numActiveTasks, + numCompletedTasks = job.numCompletedTasks, + numSkippedTasks = job.numCompletedTasks, + numFailedTasks = job.numFailedTasks, + numActiveStages = job.numActiveStages, + numCompletedStages = job.completedStageIndices.size, + numSkippedStages = job.numSkippedStages, + numFailedStages = job.numFailedStages + ) + } + } +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/AllRDDResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/AllRDDResource.scala new file mode 100644 index 0000000000000..645ede26a0879 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/AllRDDResource.scala @@ -0,0 +1,104 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import javax.ws.rs.{GET, Produces} +import javax.ws.rs.core.MediaType + +import org.apache.spark.storage.{RDDInfo, StorageStatus, StorageUtils} +import org.apache.spark.ui.SparkUI +import org.apache.spark.ui.storage.StorageListener + +@Produces(Array(MediaType.APPLICATION_JSON)) +private[v1] class AllRDDResource(ui: SparkUI) { + + @GET + def rddList(): Seq[RDDStorageInfo] = { + val storageStatusList = ui.storageListener.storageStatusList + val rddInfos = ui.storageListener.rddInfoList + rddInfos.map{rddInfo => + AllRDDResource.getRDDStorageInfo(rddInfo.id, rddInfo, storageStatusList, + includeDetails = false) + } + } + +} + +private[spark] object AllRDDResource { + + def getRDDStorageInfo( + rddId: Int, + listener: StorageListener, + includeDetails: Boolean): Option[RDDStorageInfo] = { + val storageStatusList = listener.storageStatusList + listener.rddInfoList.find { _.id == rddId }.map { rddInfo => + getRDDStorageInfo(rddId, rddInfo, storageStatusList, includeDetails) + } + } + + def getRDDStorageInfo( + rddId: Int, + rddInfo: RDDInfo, + storageStatusList: Seq[StorageStatus], + includeDetails: Boolean): RDDStorageInfo = { + val workers = storageStatusList.map { (rddId, _) } + val blockLocations = StorageUtils.getRddBlockLocations(rddId, storageStatusList) + val blocks = storageStatusList + .flatMap { _.rddBlocksById(rddId) } + .sortWith { _._1.name < _._1.name } + .map { case (blockId, status) => + (blockId, status, blockLocations.get(blockId).getOrElse(Seq[String]("Unknown"))) + } + + val dataDistribution = if (includeDetails) { + Some(storageStatusList.map { status => + new RDDDataDistribution( + address = status.blockManagerId.hostPort, + memoryUsed = status.memUsedByRdd(rddId), + memoryRemaining = status.memRemaining, + diskUsed = status.diskUsedByRdd(rddId) + ) } ) + } else { + None + } + val partitions = if (includeDetails) { + Some(blocks.map { case (id, block, locations) => + new RDDPartitionInfo( + blockName = id.name, + storageLevel = block.storageLevel.description, + memoryUsed = block.memSize, + diskUsed = block.diskSize, + executors = locations + ) + } ) + } else { + None + } + + new RDDStorageInfo( + id = rddId, + name = rddInfo.name, + numPartitions = rddInfo.numPartitions, + numCachedPartitions = rddInfo.numCachedPartitions, + storageLevel = rddInfo.storageLevel.description, + memoryUsed = rddInfo.memSize, + diskUsed = rddInfo.diskSize, + dataDistribution = dataDistribution, + partitions = partitions + ) + } +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/AllStagesResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/AllStagesResource.scala new file mode 100644 index 0000000000000..50608588f09ae --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/AllStagesResource.scala @@ -0,0 +1,309 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import java.util.{Arrays, Date, List => JList} +import javax.ws.rs.{GET, PathParam, Produces, QueryParam} +import javax.ws.rs.core.MediaType + +import org.apache.spark.executor.{InputMetrics => InternalInputMetrics, OutputMetrics => InternalOutputMetrics, ShuffleReadMetrics => InternalShuffleReadMetrics, ShuffleWriteMetrics => InternalShuffleWriteMetrics, TaskMetrics => InternalTaskMetrics} +import org.apache.spark.scheduler.{AccumulableInfo => InternalAccumulableInfo, StageInfo} +import org.apache.spark.ui.SparkUI +import org.apache.spark.ui.jobs.UIData.{StageUIData, TaskUIData} +import org.apache.spark.util.Distribution + +@Produces(Array(MediaType.APPLICATION_JSON)) +private[v1] class AllStagesResource(ui: SparkUI) { + + @GET + def stageList(@QueryParam("status") statuses: JList[StageStatus]): Seq[StageData] = { + val listener = ui.jobProgressListener + val stageAndStatus = AllStagesResource.stagesAndStatus(ui) + val adjStatuses = { + if (statuses.isEmpty()) { + Arrays.asList(StageStatus.values(): _*) + } else { + statuses + } + } + for { + (status, stageList) <- stageAndStatus + stageInfo: StageInfo <- stageList if adjStatuses.contains(status) + stageUiData: StageUIData <- listener.synchronized { + listener.stageIdToData.get((stageInfo.stageId, stageInfo.attemptId)) + } + } yield { + AllStagesResource.stageUiToStageData(status, stageInfo, stageUiData, includeDetails = false) + } + } +} + +private[v1] object AllStagesResource { + def stageUiToStageData( + status: StageStatus, + stageInfo: StageInfo, + stageUiData: StageUIData, + includeDetails: Boolean): StageData = { + + val taskData = if (includeDetails) { + Some(stageUiData.taskData.map { case (k, v) => k -> convertTaskData(v) } ) + } else { + None + } + val executorSummary = if (includeDetails) { + Some(stageUiData.executorSummary.map { case (k, summary) => + k -> new ExecutorStageSummary( + taskTime = summary.taskTime, + failedTasks = summary.failedTasks, + succeededTasks = summary.succeededTasks, + inputBytes = summary.inputBytes, + outputBytes = summary.outputBytes, + shuffleRead = summary.shuffleRead, + shuffleWrite = summary.shuffleWrite, + memoryBytesSpilled = summary.memoryBytesSpilled, + diskBytesSpilled = summary.diskBytesSpilled + ) + }) + } else { + None + } + + val accumulableInfo = stageUiData.accumulables.values.map { convertAccumulableInfo }.toSeq + + new StageData( + status = status, + stageId = stageInfo.stageId, + attemptId = stageInfo.attemptId, + numActiveTasks = stageUiData.numActiveTasks, + numCompleteTasks = stageUiData.numCompleteTasks, + numFailedTasks = stageUiData.numFailedTasks, + executorRunTime = stageUiData.executorRunTime, + inputBytes = stageUiData.inputBytes, + inputRecords = stageUiData.inputRecords, + outputBytes = stageUiData.outputBytes, + outputRecords = stageUiData.outputRecords, + shuffleReadBytes = stageUiData.shuffleReadTotalBytes, + shuffleReadRecords = stageUiData.shuffleReadRecords, + shuffleWriteBytes = stageUiData.shuffleWriteBytes, + shuffleWriteRecords = stageUiData.shuffleWriteRecords, + memoryBytesSpilled = stageUiData.memoryBytesSpilled, + diskBytesSpilled = stageUiData.diskBytesSpilled, + schedulingPool = stageUiData.schedulingPool, + name = stageInfo.name, + details = stageInfo.details, + accumulatorUpdates = accumulableInfo, + tasks = taskData, + executorSummary = executorSummary + ) + } + + def stagesAndStatus(ui: SparkUI): Seq[(StageStatus, Seq[StageInfo])] = { + val listener = ui.jobProgressListener + listener.synchronized { + Seq( + StageStatus.ACTIVE -> listener.activeStages.values.toSeq, + StageStatus.COMPLETE -> listener.completedStages.reverse.toSeq, + StageStatus.FAILED -> listener.failedStages.reverse.toSeq, + StageStatus.PENDING -> listener.pendingStages.values.toSeq + ) + } + } + + def convertTaskData(uiData: TaskUIData): TaskData = { + new TaskData( + taskId = uiData.taskInfo.taskId, + index = uiData.taskInfo.index, + attempt = uiData.taskInfo.attempt, + launchTime = new Date(uiData.taskInfo.launchTime), + executorId = uiData.taskInfo.executorId, + host = uiData.taskInfo.host, + taskLocality = uiData.taskInfo.taskLocality.toString(), + speculative = uiData.taskInfo.speculative, + accumulatorUpdates = uiData.taskInfo.accumulables.map { convertAccumulableInfo }, + errorMessage = uiData.errorMessage, + taskMetrics = uiData.taskMetrics.map { convertUiTaskMetrics } + ) + } + + def taskMetricDistributions( + allTaskData: Iterable[TaskUIData], + quantiles: Array[Double]): TaskMetricDistributions = { + + val rawMetrics = allTaskData.flatMap{_.taskMetrics}.toSeq + + def metricQuantiles(f: InternalTaskMetrics => Double): IndexedSeq[Double] = + Distribution(rawMetrics.map { d => f(d) }).get.getQuantiles(quantiles) + + // We need to do a lot of similar munging to nested metrics here. For each one, + // we want (a) extract the values for nested metrics (b) make a distribution for each metric + // (c) shove the distribution into the right field in our return type and (d) only return + // a result if the option is defined for any of the tasks. MetricHelper is a little util + // to make it a little easier to deal w/ all of the nested options. Mostly it lets us just + // implement one "build" method, which just builds the quantiles for each field. + + val inputMetrics: Option[InputMetricDistributions] = + new MetricHelper[InternalInputMetrics, InputMetricDistributions](rawMetrics, quantiles) { + def getSubmetrics(raw: InternalTaskMetrics): Option[InternalInputMetrics] = { + raw.inputMetrics + } + + def build: InputMetricDistributions = new InputMetricDistributions( + bytesRead = submetricQuantiles(_.bytesRead), + recordsRead = submetricQuantiles(_.recordsRead) + ) + }.metricOption + + val outputMetrics: Option[OutputMetricDistributions] = + new MetricHelper[InternalOutputMetrics, OutputMetricDistributions](rawMetrics, quantiles) { + def getSubmetrics(raw:InternalTaskMetrics): Option[InternalOutputMetrics] = { + raw.outputMetrics + } + def build: OutputMetricDistributions = new OutputMetricDistributions( + bytesWritten = submetricQuantiles(_.bytesWritten), + recordsWritten = submetricQuantiles(_.recordsWritten) + ) + }.metricOption + + val shuffleReadMetrics: Option[ShuffleReadMetricDistributions] = + new MetricHelper[InternalShuffleReadMetrics, ShuffleReadMetricDistributions](rawMetrics, + quantiles) { + def getSubmetrics(raw: InternalTaskMetrics): Option[InternalShuffleReadMetrics] = { + raw.shuffleReadMetrics + } + def build: ShuffleReadMetricDistributions = new ShuffleReadMetricDistributions( + readBytes = submetricQuantiles(_.totalBytesRead), + readRecords = submetricQuantiles(_.recordsRead), + remoteBytesRead = submetricQuantiles(_.remoteBytesRead), + remoteBlocksFetched = submetricQuantiles(_.remoteBlocksFetched), + localBlocksFetched = submetricQuantiles(_.localBlocksFetched), + totalBlocksFetched = submetricQuantiles(_.totalBlocksFetched), + fetchWaitTime = submetricQuantiles(_.fetchWaitTime) + ) + }.metricOption + + val shuffleWriteMetrics: Option[ShuffleWriteMetricDistributions] = + new MetricHelper[InternalShuffleWriteMetrics, ShuffleWriteMetricDistributions](rawMetrics, + quantiles) { + def getSubmetrics(raw: InternalTaskMetrics): Option[InternalShuffleWriteMetrics] = { + raw.shuffleWriteMetrics + } + def build: ShuffleWriteMetricDistributions = new ShuffleWriteMetricDistributions( + writeBytes = submetricQuantiles(_.shuffleBytesWritten), + writeRecords = submetricQuantiles(_.shuffleRecordsWritten), + writeTime = submetricQuantiles(_.shuffleWriteTime) + ) + }.metricOption + + new TaskMetricDistributions( + quantiles = quantiles, + executorDeserializeTime = metricQuantiles(_.executorDeserializeTime), + executorRunTime = metricQuantiles(_.executorRunTime), + resultSize = metricQuantiles(_.resultSize), + jvmGcTime = metricQuantiles(_.jvmGCTime), + resultSerializationTime = metricQuantiles(_.resultSerializationTime), + memoryBytesSpilled = metricQuantiles(_.memoryBytesSpilled), + diskBytesSpilled = metricQuantiles(_.diskBytesSpilled), + inputMetrics = inputMetrics, + outputMetrics = outputMetrics, + shuffleReadMetrics = shuffleReadMetrics, + shuffleWriteMetrics = shuffleWriteMetrics + ) + } + + def convertAccumulableInfo(acc: InternalAccumulableInfo): AccumulableInfo = { + new AccumulableInfo(acc.id, acc.name, acc.update, acc.value) + } + + def convertUiTaskMetrics(internal: InternalTaskMetrics): TaskMetrics = { + new TaskMetrics( + executorDeserializeTime = internal.executorDeserializeTime, + executorRunTime = internal.executorRunTime, + resultSize = internal.resultSize, + jvmGcTime = internal.jvmGCTime, + resultSerializationTime = internal.resultSerializationTime, + memoryBytesSpilled = internal.memoryBytesSpilled, + diskBytesSpilled = internal.diskBytesSpilled, + inputMetrics = internal.inputMetrics.map { convertInputMetrics }, + outputMetrics = Option(internal.outputMetrics).flatten.map { convertOutputMetrics }, + shuffleReadMetrics = internal.shuffleReadMetrics.map { convertShuffleReadMetrics }, + shuffleWriteMetrics = internal.shuffleWriteMetrics.map { convertShuffleWriteMetrics } + ) + } + + def convertInputMetrics(internal: InternalInputMetrics): InputMetrics = { + new InputMetrics( + bytesRead = internal.bytesRead, + recordsRead = internal.recordsRead + ) + } + + def convertOutputMetrics(internal: InternalOutputMetrics): OutputMetrics = { + new OutputMetrics( + bytesWritten = internal.bytesWritten, + recordsWritten = internal.recordsWritten + ) + } + + def convertShuffleReadMetrics(internal: InternalShuffleReadMetrics): ShuffleReadMetrics = { + new ShuffleReadMetrics( + remoteBlocksFetched = internal.remoteBlocksFetched, + localBlocksFetched = internal.localBlocksFetched, + fetchWaitTime = internal.fetchWaitTime, + remoteBytesRead = internal.remoteBytesRead, + totalBlocksFetched = internal.totalBlocksFetched, + recordsRead = internal.recordsRead + ) + } + + def convertShuffleWriteMetrics(internal: InternalShuffleWriteMetrics): ShuffleWriteMetrics = { + new ShuffleWriteMetrics( + bytesWritten = internal.shuffleBytesWritten, + writeTime = internal.shuffleWriteTime, + recordsWritten = internal.shuffleRecordsWritten + ) + } +} + +/** + * Helper for getting distributions from nested metric types. Many of the metrics we want are + * contained in options inside TaskMetrics (eg., ShuffleWriteMetrics). This makes it easy to handle + * the options (returning None if the metrics are all empty), and extract the quantiles for each + * metric. After creating an instance, call metricOption to get the result type. + */ +private[v1] abstract class MetricHelper[I,O]( + rawMetrics: Seq[InternalTaskMetrics], + quantiles: Array[Double]) { + + def getSubmetrics(raw: InternalTaskMetrics): Option[I] + + def build: O + + val data: Seq[I] = rawMetrics.flatMap(getSubmetrics) + + /** applies the given function to all input metrics, and returns the quantiles */ + def submetricQuantiles(f: I => Double): IndexedSeq[Double] = { + Distribution(data.map { d => f(d) }).get.getQuantiles(quantiles) + } + + def metricOption: Option[O] = { + if (data.isEmpty) { + None + } else { + Some(build) + } + } +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/ApplicationListResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/ApplicationListResource.scala new file mode 100644 index 0000000000000..17b521f3e1d41 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/ApplicationListResource.scala @@ -0,0 +1,94 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import java.util.{Arrays, Date, List => JList} +import javax.ws.rs.{DefaultValue, GET, Produces, QueryParam} +import javax.ws.rs.core.MediaType + +import org.apache.spark.deploy.history.ApplicationHistoryInfo +import org.apache.spark.deploy.master.{ApplicationInfo => InternalApplicationInfo} + +@Produces(Array(MediaType.APPLICATION_JSON)) +private[v1] class ApplicationListResource(uiRoot: UIRoot) { + + @GET + def appList( + @QueryParam("status") status: JList[ApplicationStatus], + @DefaultValue("2010-01-01") @QueryParam("minDate") minDate: SimpleDateParam, + @DefaultValue("3000-01-01") @QueryParam("maxDate") maxDate: SimpleDateParam) + : Iterator[ApplicationInfo] = { + val allApps = uiRoot.getApplicationInfoList + val adjStatus = { + if (status.isEmpty) { + Arrays.asList(ApplicationStatus.values(): _*) + } else { + status + } + } + val includeCompleted = adjStatus.contains(ApplicationStatus.COMPLETED) + val includeRunning = adjStatus.contains(ApplicationStatus.RUNNING) + allApps.filter { app => + val anyRunning = app.attempts.exists(!_.completed) + // if any attempt is still running, we consider the app to also still be running + val statusOk = (!anyRunning && includeCompleted) || + (anyRunning && includeRunning) + // keep the app if *any* attempts fall in the right time window + val dateOk = app.attempts.exists { attempt => + attempt.startTime.getTime >= minDate.timestamp && + attempt.startTime.getTime <= maxDate.timestamp + } + statusOk && dateOk + } + } +} + +private[spark] object ApplicationsListResource { + def appHistoryInfoToPublicAppInfo(app: ApplicationHistoryInfo): ApplicationInfo = { + new ApplicationInfo( + id = app.id, + name = app.name, + attempts = app.attempts.map { internalAttemptInfo => + new ApplicationAttemptInfo( + attemptId = internalAttemptInfo.attemptId, + startTime = new Date(internalAttemptInfo.startTime), + endTime = new Date(internalAttemptInfo.endTime), + sparkUser = internalAttemptInfo.sparkUser, + completed = internalAttemptInfo.completed + ) + } + ) + } + + def convertApplicationInfo( + internal: InternalApplicationInfo, + completed: Boolean): ApplicationInfo = { + // standalone application info always has just one attempt + new ApplicationInfo( + id = internal.id, + name = internal.desc.name, + attempts = Seq(new ApplicationAttemptInfo( + attemptId = None, + startTime = new Date(internal.startTime), + endTime = new Date(internal.endTime), + sparkUser = internal.desc.user, + completed = completed + )) + ) + } + +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/ExecutorListResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/ExecutorListResource.scala new file mode 100644 index 0000000000000..8ad4656b4dada --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/ExecutorListResource.scala @@ -0,0 +1,36 @@ +/* +* Licensed to the Apache Software Foundation (ASF) under one or more +* contributor license agreements. See the NOTICE file distributed with +* this work for additional information regarding copyright ownership. +* The ASF licenses this file to You under the Apache License, Version 2.0 +* (the "License"); you may not use this file except in compliance with +* the License. You may obtain a copy of the License at +* +* http://www.apache.org/licenses/LICENSE-2.0 +* +* Unless required by applicable law or agreed to in writing, software +* distributed under the License is distributed on an "AS IS" BASIS, +* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +* See the License for the specific language governing permissions and +* limitations under the License. +*/ +package org.apache.spark.status.api.v1 + +import javax.ws.rs.{GET, PathParam, Produces} +import javax.ws.rs.core.MediaType + +import org.apache.spark.ui.SparkUI +import org.apache.spark.ui.exec.ExecutorsPage + +@Produces(Array(MediaType.APPLICATION_JSON)) +private[v1] class ExecutorListResource(ui: SparkUI) { + + @GET + def executorList(): Seq[ExecutorSummary] = { + val listener = ui.executorsListener + val storageStatusList = listener.storageStatusList + (0 until storageStatusList.size).map { statusId => + ExecutorsPage.getExecInfo(listener, statusId) + } + } +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/JacksonMessageWriter.scala b/core/src/main/scala/org/apache/spark/status/api/v1/JacksonMessageWriter.scala new file mode 100644 index 0000000000000..202a5191ad57d --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/JacksonMessageWriter.scala @@ -0,0 +1,93 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import java.io.OutputStream +import java.lang.annotation.Annotation +import java.lang.reflect.Type +import java.text.SimpleDateFormat +import java.util.{Calendar, SimpleTimeZone} +import javax.ws.rs.Produces +import javax.ws.rs.core.{MediaType, MultivaluedMap} +import javax.ws.rs.ext.{MessageBodyWriter, Provider} + +import com.fasterxml.jackson.annotation.JsonInclude +import com.fasterxml.jackson.databind.{ObjectMapper, SerializationFeature} + +/** + * This class converts the POJO metric responses into json, using jackson. + * + * This doesn't follow the standard jersey-jackson plugin options, because we want to stick + * with an old version of jersey (since we have it from yarn anyway) and don't want to pull in lots + * of dependencies from a new plugin. + * + * Note that jersey automatically discovers this class based on its package and its annotations. + */ +@Provider +@Produces(Array(MediaType.APPLICATION_JSON)) +private[v1] class JacksonMessageWriter extends MessageBodyWriter[Object]{ + + val mapper = new ObjectMapper() { + override def writeValueAsString(t: Any): String = { + super.writeValueAsString(t) + } + } + mapper.registerModule(com.fasterxml.jackson.module.scala.DefaultScalaModule) + mapper.enable(SerializationFeature.INDENT_OUTPUT) + mapper.setSerializationInclusion(JsonInclude.Include.NON_NULL) + mapper.setDateFormat(JacksonMessageWriter.makeISODateFormat) + + override def isWriteable( + aClass: Class[_], + `type`: Type, + annotations: Array[Annotation], + mediaType: MediaType): Boolean = { + true + } + + override def writeTo( + t: Object, + aClass: Class[_], + `type`: Type, + annotations: Array[Annotation], + mediaType: MediaType, + multivaluedMap: MultivaluedMap[String, AnyRef], + outputStream: OutputStream): Unit = { + t match { + case ErrorWrapper(err) => outputStream.write(err.getBytes("utf-8")) + case _ => mapper.writeValue(outputStream, t) + } + } + + override def getSize( + t: Object, + aClass: Class[_], + `type`: Type, + annotations: Array[Annotation], + mediaType: MediaType): Long = { + -1L + } +} + +private[spark] object JacksonMessageWriter { + def makeISODateFormat: SimpleDateFormat = { + val iso8601 = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss.SSS'GMT'") + val cal = Calendar.getInstance(new SimpleTimeZone(0, "GMT")) + iso8601.setCalendar(cal) + iso8601 + } +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/JsonRootResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/JsonRootResource.scala new file mode 100644 index 0000000000000..c3ec45f54681b --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/JsonRootResource.scala @@ -0,0 +1,255 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import javax.servlet.ServletContext +import javax.ws.rs._ +import javax.ws.rs.core.{Context, Response} + +import com.sun.jersey.api.core.ResourceConfig +import com.sun.jersey.spi.container.servlet.ServletContainer +import org.eclipse.jetty.server.handler.ContextHandler +import org.eclipse.jetty.servlet.{ServletContextHandler, ServletHolder} + +import org.apache.spark.SecurityManager +import org.apache.spark.ui.SparkUI + +/** + * Main entry point for serving spark application metrics as json, using JAX-RS. + * + * Each resource should have endpoints that return **public** classes defined in api.scala. Mima + * binary compatibility checks ensure that we don't inadvertently make changes that break the api. + * The returned objects are automatically converted to json by jackson with JacksonMessageWriter. + * In addition, there are a number of tests in HistoryServerSuite that compare the json to "golden + * files". Any changes and additions should be reflected there as well -- see the notes in + * HistoryServerSuite. + */ +@Path("/v1") +private[v1] class JsonRootResource extends UIRootFromServletContext { + + @Path("applications") + def getApplicationList(): ApplicationListResource = { + new ApplicationListResource(uiRoot) + } + + @Path("applications/{appId}") + def getApplication(): OneApplicationResource = { + new OneApplicationResource(uiRoot) + } + + @Path("applications/{appId}/{attemptId}/jobs") + def getJobs( + @PathParam("appId") appId: String, + @PathParam("attemptId") attemptId: String): AllJobsResource = { + uiRoot.withSparkUI(appId, Some(attemptId)) { ui => + new AllJobsResource(ui) + } + } + + @Path("applications/{appId}/jobs") + def getJobs(@PathParam("appId") appId: String): AllJobsResource = { + uiRoot.withSparkUI(appId, None) { ui => + new AllJobsResource(ui) + } + } + + @Path("applications/{appId}/jobs/{jobId: \\d+}") + def getJob(@PathParam("appId") appId: String): OneJobResource = { + uiRoot.withSparkUI(appId, None) { ui => + new OneJobResource(ui) + } + } + + @Path("applications/{appId}/{attemptId}/jobs/{jobId: \\d+}") + def getJob( + @PathParam("appId") appId: String, + @PathParam("attemptId") attemptId: String): OneJobResource = { + uiRoot.withSparkUI(appId, Some(attemptId)) { ui => + new OneJobResource(ui) + } + } + + @Path("applications/{appId}/executors") + def getExecutors(@PathParam("appId") appId: String): ExecutorListResource = { + uiRoot.withSparkUI(appId, None) { ui => + new ExecutorListResource(ui) + } + } + + @Path("applications/{appId}/{attemptId}/executors") + def getExecutors( + @PathParam("appId") appId: String, + @PathParam("attemptId") attemptId: String): ExecutorListResource = { + uiRoot.withSparkUI(appId, Some(attemptId)) { ui => + new ExecutorListResource(ui) + } + } + + + @Path("applications/{appId}/stages") + def getStages(@PathParam("appId") appId: String): AllStagesResource= { + uiRoot.withSparkUI(appId, None) { ui => + new AllStagesResource(ui) + } + } + + @Path("applications/{appId}/{attemptId}/stages") + def getStages( + @PathParam("appId") appId: String, + @PathParam("attemptId") attemptId: String): AllStagesResource= { + uiRoot.withSparkUI(appId, Some(attemptId)) { ui => + new AllStagesResource(ui) + } + } + + @Path("applications/{appId}/stages/{stageId: \\d+}") + def getStage(@PathParam("appId") appId: String): OneStageResource= { + uiRoot.withSparkUI(appId, None) { ui => + new OneStageResource(ui) + } + } + + @Path("applications/{appId}/{attemptId}/stages/{stageId: \\d+}") + def getStage( + @PathParam("appId") appId: String, + @PathParam("attemptId") attemptId: String): OneStageResource = { + uiRoot.withSparkUI(appId, Some(attemptId)) { ui => + new OneStageResource(ui) + } + } + + @Path("applications/{appId}/storage/rdd") + def getRdds(@PathParam("appId") appId: String): AllRDDResource = { + uiRoot.withSparkUI(appId, None) { ui => + new AllRDDResource(ui) + } + } + + @Path("applications/{appId}/{attemptId}/storage/rdd") + def getRdds( + @PathParam("appId") appId: String, + @PathParam("attemptId") attemptId: String): AllRDDResource = { + uiRoot.withSparkUI(appId, Some(attemptId)) { ui => + new AllRDDResource(ui) + } + } + + @Path("applications/{appId}/storage/rdd/{rddId: \\d+}") + def getRdd(@PathParam("appId") appId: String): OneRDDResource = { + uiRoot.withSparkUI(appId, None) { ui => + new OneRDDResource(ui) + } + } + + @Path("applications/{appId}/{attemptId}/storage/rdd/{rddId: \\d+}") + def getRdd( + @PathParam("appId") appId: String, + @PathParam("attemptId") attemptId: String): OneRDDResource = { + uiRoot.withSparkUI(appId, Some(attemptId)) { ui => + new OneRDDResource(ui) + } + } + +} + +private[spark] object JsonRootResource { + + def getJsonServlet(uiRoot: UIRoot): ServletContextHandler = { + val jerseyContext = new ServletContextHandler(ServletContextHandler.NO_SESSIONS) + jerseyContext.setContextPath("/json") + val holder:ServletHolder = new ServletHolder(classOf[ServletContainer]) + holder.setInitParameter("com.sun.jersey.config.property.resourceConfigClass", + "com.sun.jersey.api.core.PackagesResourceConfig") + holder.setInitParameter("com.sun.jersey.config.property.packages", + "org.apache.spark.status.api.v1") + holder.setInitParameter(ResourceConfig.PROPERTY_CONTAINER_REQUEST_FILTERS, + classOf[SecurityFilter].getCanonicalName) + UIRootFromServletContext.setUiRoot(jerseyContext, uiRoot) + jerseyContext.addServlet(holder, "/*") + jerseyContext + } +} + +/** + * This trait is shared by the all the root containers for application UI information -- + * the HistoryServer, the Master UI, and the application UI. This provides the common + * interface needed for them all to expose application info as json. + */ +private[spark] trait UIRoot { + def getSparkUI(appKey: String): Option[SparkUI] + def getApplicationInfoList: Iterator[ApplicationInfo] + + /** + * Get the spark UI with the given appID, and apply a function + * to it. If there is no such app, throw an appropriate exception + */ + def withSparkUI[T](appId: String, attemptId: Option[String])(f: SparkUI => T): T = { + val appKey = attemptId.map(appId + "/" + _).getOrElse(appId) + getSparkUI(appKey) match { + case Some(ui) => + f(ui) + case None => throw new NotFoundException("no such app: " + appId) + } + } + def securityManager: SecurityManager +} + +private[v1] object UIRootFromServletContext { + + private val attribute = getClass.getCanonicalName + + def setUiRoot(contextHandler: ContextHandler, uiRoot: UIRoot): Unit = { + contextHandler.setAttribute(attribute, uiRoot) + } + + def getUiRoot(context: ServletContext): UIRoot = { + context.getAttribute(attribute).asInstanceOf[UIRoot] + } +} + +private[v1] trait UIRootFromServletContext { + @Context + var servletContext: ServletContext = _ + + def uiRoot: UIRoot = UIRootFromServletContext.getUiRoot(servletContext) +} + +private[v1] class NotFoundException(msg: String) extends WebApplicationException( + new NoSuchElementException(msg), + Response + .status(Response.Status.NOT_FOUND) + .entity(ErrorWrapper(msg)) + .build() +) + +private[v1] class BadParameterException(msg: String) extends WebApplicationException( + new IllegalArgumentException(msg), + Response + .status(Response.Status.BAD_REQUEST) + .entity(ErrorWrapper(msg)) + .build() +) { + def this(param: String, exp: String, actual: String) = { + this(raw"""Bad value for parameter "$param". Expected a $exp, got "$actual"""") + } +} + +/** + * Signal to JacksonMessageWriter to not convert the message into json (which would result in an + * extra set of quotes). + */ +private[v1] case class ErrorWrapper(s: String) diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/OneApplicationResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/OneApplicationResource.scala new file mode 100644 index 0000000000000..b5ef72649e295 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/OneApplicationResource.scala @@ -0,0 +1,31 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import javax.ws.rs.core.MediaType +import javax.ws.rs.{Produces, PathParam, GET} + +@Produces(Array(MediaType.APPLICATION_JSON)) +private[v1] class OneApplicationResource(uiRoot: UIRoot) { + + @GET + def getApp(@PathParam("appId") appId: String): ApplicationInfo = { + val apps = uiRoot.getApplicationInfoList.find { _.id == appId } + apps.getOrElse(throw new NotFoundException("unknown app: " + appId)) + } + +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/OneJobResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/OneJobResource.scala new file mode 100644 index 0000000000000..6d8a60d480aed --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/OneJobResource.scala @@ -0,0 +1,41 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import javax.ws.rs.{PathParam, GET, Produces} +import javax.ws.rs.core.MediaType + +import org.apache.spark.JobExecutionStatus +import org.apache.spark.ui.SparkUI +import org.apache.spark.ui.jobs.UIData.JobUIData + +@Produces(Array(MediaType.APPLICATION_JSON)) +private[v1] class OneJobResource(ui: SparkUI) { + + @GET + def oneJob(@PathParam("jobId") jobId: Int): JobData = { + val statusToJobs: Seq[(JobExecutionStatus, Seq[JobUIData])] = + AllJobsResource.getStatusToJobs(ui) + val jobOpt = statusToJobs.map {_._2} .flatten.find { jobInfo => jobInfo.jobId == jobId} + jobOpt.map { job => + AllJobsResource.convertJobData(job, ui.jobProgressListener, false) + }.getOrElse { + throw new NotFoundException("unknown job: " + jobId) + } + } + +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/OneRDDResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/OneRDDResource.scala new file mode 100644 index 0000000000000..07b224fac4786 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/OneRDDResource.scala @@ -0,0 +1,34 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import javax.ws.rs.{PathParam, GET, Produces} +import javax.ws.rs.core.MediaType + +import org.apache.spark.ui.SparkUI + +@Produces(Array(MediaType.APPLICATION_JSON)) +private[v1] class OneRDDResource(ui: SparkUI) { + + @GET + def rddData(@PathParam("rddId") rddId: Int): RDDStorageInfo = { + AllRDDResource.getRDDStorageInfo(rddId, ui.storageListener, true).getOrElse( + throw new NotFoundException(s"no rdd found w/ id $rddId") + ) + } + +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/OneStageResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/OneStageResource.scala new file mode 100644 index 0000000000000..fd24aea63a8a1 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/OneStageResource.scala @@ -0,0 +1,150 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import javax.ws.rs._ +import javax.ws.rs.core.MediaType + +import org.apache.spark.SparkException +import org.apache.spark.scheduler.StageInfo +import org.apache.spark.status.api.v1.StageStatus._ +import org.apache.spark.status.api.v1.TaskSorting._ +import org.apache.spark.ui.SparkUI +import org.apache.spark.ui.jobs.JobProgressListener +import org.apache.spark.ui.jobs.UIData.StageUIData + +@Produces(Array(MediaType.APPLICATION_JSON)) +private[v1] class OneStageResource(ui: SparkUI) { + + @GET + @Path("") + def stageData(@PathParam("stageId") stageId: Int): Seq[StageData] = { + withStage(stageId){ stageAttempts => + stageAttempts.map { stage => + AllStagesResource.stageUiToStageData(stage.status, stage.info, stage.ui, + includeDetails = true) + } + } + } + + @GET + @Path("/{stageAttemptId: \\d+}") + def oneAttemptData( + @PathParam("stageId") stageId: Int, + @PathParam("stageAttemptId") stageAttemptId: Int): StageData = { + withStageAttempt(stageId, stageAttemptId) { stage => + AllStagesResource.stageUiToStageData(stage.status, stage.info, stage.ui, + includeDetails = true) + } + } + + @GET + @Path("/{stageAttemptId: \\d+}/taskSummary") + def taskSummary( + @PathParam("stageId") stageId: Int, + @PathParam("stageAttemptId") stageAttemptId: Int, + @DefaultValue("0.05,0.25,0.5,0.75,0.95") @QueryParam("quantiles") quantileString: String) + : TaskMetricDistributions = { + withStageAttempt(stageId, stageAttemptId) { stage => + val quantiles = quantileString.split(",").map { s => + try { + s.toDouble + } catch { + case nfe: NumberFormatException => + throw new BadParameterException("quantiles", "double", s) + } + } + AllStagesResource.taskMetricDistributions(stage.ui.taskData.values, quantiles) + } + } + + @GET + @Path("/{stageAttemptId: \\d+}/taskList") + def taskList( + @PathParam("stageId") stageId: Int, + @PathParam("stageAttemptId") stageAttemptId: Int, + @DefaultValue("0") @QueryParam("offset") offset: Int, + @DefaultValue("20") @QueryParam("length") length: Int, + @DefaultValue("ID") @QueryParam("sortBy") sortBy: TaskSorting): Seq[TaskData] = { + withStageAttempt(stageId, stageAttemptId) { stage => + val tasks = stage.ui.taskData.values.map{AllStagesResource.convertTaskData}.toIndexedSeq + .sorted(OneStageResource.ordering(sortBy)) + tasks.slice(offset, offset + length) + } + } + + private case class StageStatusInfoUi(status: StageStatus, info: StageInfo, ui: StageUIData) + + private def withStage[T](stageId: Int)(f: Seq[StageStatusInfoUi] => T): T = { + val stageAttempts = findStageStatusUIData(ui.jobProgressListener, stageId) + if (stageAttempts.isEmpty) { + throw new NotFoundException("unknown stage: " + stageId) + } else { + f(stageAttempts) + } + } + + private def findStageStatusUIData( + listener: JobProgressListener, + stageId: Int): Seq[StageStatusInfoUi] = { + listener.synchronized { + def getStatusInfoUi(status: StageStatus, infos: Seq[StageInfo]): Seq[StageStatusInfoUi] = { + infos.filter { _.stageId == stageId }.map { info => + val ui = listener.stageIdToData.getOrElse((info.stageId, info.attemptId), + // this is an internal error -- we should always have uiData + throw new SparkException( + s"no stage ui data found for stage: ${info.stageId}:${info.attemptId}") + ) + StageStatusInfoUi(status, info, ui) + } + } + getStatusInfoUi(ACTIVE, listener.activeStages.values.toSeq) ++ + getStatusInfoUi(COMPLETE, listener.completedStages) ++ + getStatusInfoUi(FAILED, listener.failedStages) ++ + getStatusInfoUi(PENDING, listener.pendingStages.values.toSeq) + } + } + + private def withStageAttempt[T]( + stageId: Int, + stageAttemptId: Int) + (f: StageStatusInfoUi => T): T = { + withStage(stageId) { attempts => + val oneAttempt = attempts.find { stage => stage.info.attemptId == stageAttemptId } + oneAttempt match { + case Some(stage) => + f(stage) + case None => + val stageAttempts = attempts.map { _.info.attemptId } + throw new NotFoundException(s"unknown attempt for stage $stageId. " + + s"Found attempts: ${stageAttempts.mkString("[", ",", "]")}") + } + } + } +} + +object OneStageResource { + def ordering(taskSorting: TaskSorting): Ordering[TaskData] = { + val extractor: (TaskData => Long) = td => + taskSorting match { + case ID => td.taskId + case INCREASING_RUNTIME => td.taskMetrics.map{_.executorRunTime}.getOrElse(-1L) + case DECREASING_RUNTIME => -td.taskMetrics.map{_.executorRunTime}.getOrElse(-1L) + } + Ordering.by(extractor) + } +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/SecurityFilter.scala b/core/src/main/scala/org/apache/spark/status/api/v1/SecurityFilter.scala new file mode 100644 index 0000000000000..95fbd96ade5ab --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/SecurityFilter.scala @@ -0,0 +1,38 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import javax.ws.rs.WebApplicationException +import javax.ws.rs.core.Response + +import com.sun.jersey.spi.container.{ContainerRequest, ContainerRequestFilter} + +private[v1] class SecurityFilter extends ContainerRequestFilter with UIRootFromServletContext { + def filter(req: ContainerRequest): ContainerRequest = { + val user = Option(req.getUserPrincipal).map { _.getName }.orNull + if (uiRoot.securityManager.checkUIViewPermissions(user)) { + req + } else { + throw new WebApplicationException( + Response + .status(Response.Status.FORBIDDEN) + .entity(raw"""user "$user"is not authorized""") + .build() + ) + } + } +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/SimpleDateParam.scala b/core/src/main/scala/org/apache/spark/status/api/v1/SimpleDateParam.scala new file mode 100644 index 0000000000000..cee29786c3019 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/SimpleDateParam.scala @@ -0,0 +1,55 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import java.text.SimpleDateFormat +import java.util.TimeZone +import javax.ws.rs.WebApplicationException +import javax.ws.rs.core.Response +import javax.ws.rs.core.Response.Status + +import scala.util.Try + +private[v1] class SimpleDateParam(val originalValue: String) { + val timestamp: Long = { + SimpleDateParam.formats.collectFirst { + case fmt if Try(fmt.parse(originalValue)).isSuccess => + fmt.parse(originalValue).getTime() + }.getOrElse( + throw new WebApplicationException( + Response + .status(Status.BAD_REQUEST) + .entity("Couldn't parse date: " + originalValue) + .build() + ) + ) + } +} + +private[v1] object SimpleDateParam { + + val formats: Seq[SimpleDateFormat] = { + + val gmtDay = new SimpleDateFormat("yyyy-MM-dd") + gmtDay.setTimeZone(TimeZone.getTimeZone("GMT")) + + Seq( + new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss.SSSz"), + gmtDay + ) + } +} diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/api.scala b/core/src/main/scala/org/apache/spark/status/api/v1/api.scala new file mode 100644 index 0000000000000..ef3c8570d8186 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/status/api/v1/api.scala @@ -0,0 +1,228 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import java.util.Date + +import scala.collection.Map + +import org.apache.spark.JobExecutionStatus + +class ApplicationInfo private[spark]( + val id: String, + val name: String, + val attempts: Seq[ApplicationAttemptInfo]) + +class ApplicationAttemptInfo private[spark]( + val attemptId: Option[String], + val startTime: Date, + val endTime: Date, + val sparkUser: String, + val completed: Boolean = false) + +class ExecutorStageSummary private[spark]( + val taskTime : Long, + val failedTasks : Int, + val succeededTasks : Int, + val inputBytes : Long, + val outputBytes : Long, + val shuffleRead : Long, + val shuffleWrite : Long, + val memoryBytesSpilled : Long, + val diskBytesSpilled : Long) + +class ExecutorSummary private[spark]( + val id: String, + val hostPort: String, + val rddBlocks: Int, + val memoryUsed: Long, + val diskUsed: Long, + val activeTasks: Int, + val failedTasks: Int, + val completedTasks: Int, + val totalTasks: Int, + val totalDuration: Long, + val totalInputBytes: Long, + val totalShuffleRead: Long, + val totalShuffleWrite: Long, + val maxMemory: Long, + val executorLogs: Map[String, String]) + +class JobData private[spark]( + val jobId: Int, + val name: String, + val description: Option[String], + val submissionTime: Option[Date], + val completionTime: Option[Date], + val stageIds: Seq[Int], + val jobGroup: Option[String], + val status: JobExecutionStatus, + val numTasks: Int, + val numActiveTasks: Int, + val numCompletedTasks: Int, + val numSkippedTasks: Int, + val numFailedTasks: Int, + val numActiveStages: Int, + val numCompletedStages: Int, + val numSkippedStages: Int, + val numFailedStages: Int) + +// Q: should Tachyon size go in here as well? currently the UI only shows it on the overall storage +// page ... does anybody pay attention to it? +class RDDStorageInfo private[spark]( + val id: Int, + val name: String, + val numPartitions: Int, + val numCachedPartitions: Int, + val storageLevel: String, + val memoryUsed: Long, + val diskUsed: Long, + val dataDistribution: Option[Seq[RDDDataDistribution]], + val partitions: Option[Seq[RDDPartitionInfo]]) + +class RDDDataDistribution private[spark]( + val address: String, + val memoryUsed: Long, + val memoryRemaining: Long, + val diskUsed: Long) + +class RDDPartitionInfo private[spark]( + val blockName: String, + val storageLevel: String, + val memoryUsed: Long, + val diskUsed: Long, + val executors: Seq[String]) + +class StageData private[spark]( + val status: StageStatus, + val stageId: Int, + val attemptId: Int, + val numActiveTasks: Int , + val numCompleteTasks: Int, + val numFailedTasks: Int, + + val executorRunTime: Long, + + val inputBytes: Long, + val inputRecords: Long, + val outputBytes: Long, + val outputRecords: Long, + val shuffleReadBytes: Long, + val shuffleReadRecords: Long, + val shuffleWriteBytes: Long, + val shuffleWriteRecords: Long, + val memoryBytesSpilled: Long, + val diskBytesSpilled: Long, + + val name: String, + val details: String, + val schedulingPool: String, + + val accumulatorUpdates: Seq[AccumulableInfo], + val tasks: Option[Map[Long, TaskData]], + val executorSummary:Option[Map[String,ExecutorStageSummary]]) + +class TaskData private[spark]( + val taskId: Long, + val index: Int, + val attempt: Int, + val launchTime: Date, + val executorId: String, + val host: String, + val taskLocality: String, + val speculative: Boolean, + val accumulatorUpdates: Seq[AccumulableInfo], + val errorMessage: Option[String] = None, + val taskMetrics: Option[TaskMetrics] = None) + +class TaskMetrics private[spark]( + val executorDeserializeTime: Long, + val executorRunTime: Long, + val resultSize: Long, + val jvmGcTime: Long, + val resultSerializationTime: Long, + val memoryBytesSpilled: Long, + val diskBytesSpilled: Long, + val inputMetrics: Option[InputMetrics], + val outputMetrics: Option[OutputMetrics], + val shuffleReadMetrics: Option[ShuffleReadMetrics], + val shuffleWriteMetrics: Option[ShuffleWriteMetrics]) + +class InputMetrics private[spark]( + val bytesRead: Long, + val recordsRead: Long) + +class OutputMetrics private[spark]( + val bytesWritten: Long, + val recordsWritten: Long) + +class ShuffleReadMetrics private[spark]( + val remoteBlocksFetched: Int, + val localBlocksFetched: Int, + val fetchWaitTime: Long, + val remoteBytesRead: Long, + val totalBlocksFetched: Int, + val recordsRead: Long) + +class ShuffleWriteMetrics private[spark]( + val bytesWritten: Long, + val writeTime: Long, + val recordsWritten: Long) + +class TaskMetricDistributions private[spark]( + val quantiles: IndexedSeq[Double], + + val executorDeserializeTime: IndexedSeq[Double], + val executorRunTime: IndexedSeq[Double], + val resultSize: IndexedSeq[Double], + val jvmGcTime: IndexedSeq[Double], + val resultSerializationTime: IndexedSeq[Double], + val memoryBytesSpilled: IndexedSeq[Double], + val diskBytesSpilled: IndexedSeq[Double], + + val inputMetrics: Option[InputMetricDistributions], + val outputMetrics: Option[OutputMetricDistributions], + val shuffleReadMetrics: Option[ShuffleReadMetricDistributions], + val shuffleWriteMetrics: Option[ShuffleWriteMetricDistributions]) + +class InputMetricDistributions private[spark]( + val bytesRead: IndexedSeq[Double], + val recordsRead: IndexedSeq[Double]) + +class OutputMetricDistributions private[spark]( + val bytesWritten: IndexedSeq[Double], + val recordsWritten: IndexedSeq[Double]) + +class ShuffleReadMetricDistributions private[spark]( + val readBytes: IndexedSeq[Double], + val readRecords: IndexedSeq[Double], + val remoteBlocksFetched: IndexedSeq[Double], + val localBlocksFetched: IndexedSeq[Double], + val fetchWaitTime: IndexedSeq[Double], + val remoteBytesRead: IndexedSeq[Double], + val totalBlocksFetched: IndexedSeq[Double]) + +class ShuffleWriteMetricDistributions private[spark]( + val writeBytes: IndexedSeq[Double], + val writeRecords: IndexedSeq[Double], + val writeTime: IndexedSeq[Double]) + +class AccumulableInfo private[spark]( + val id: Long, + val name: String, + val update: Option[String], + val value: String) diff --git a/core/src/main/scala/org/apache/spark/storage/BlockId.scala b/core/src/main/scala/org/apache/spark/storage/BlockId.scala index c186fd360fef6..524f6970992a5 100644 --- a/core/src/main/scala/org/apache/spark/storage/BlockId.scala +++ b/core/src/main/scala/org/apache/spark/storage/BlockId.scala @@ -54,7 +54,7 @@ case class RDDBlockId(rddId: Int, splitIndex: Int) extends BlockId { } // Format of the shuffle block ids (including data and index) should be kept in sync with -// org.apache.spark.network.shuffle.StandaloneShuffleBlockManager#getBlockData(). +// org.apache.spark.network.shuffle.ExternalShuffleBlockResolver#getBlockData(). @DeveloperApi case class ShuffleBlockId(shuffleId: Int, mapId: Int, reduceId: Int) extends BlockId { override def name: String = "shuffle_" + shuffleId + "_" + mapId + "_" + reduceId diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManager.scala b/core/src/main/scala/org/apache/spark/storage/BlockManager.scala index a46fecd2274ef..cc794e5c90ffa 100644 --- a/core/src/main/scala/org/apache/spark/storage/BlockManager.scala +++ b/core/src/main/scala/org/apache/spark/storage/BlockManager.scala @@ -431,10 +431,11 @@ private[spark] class BlockManager( // As an optimization for map output fetches, if the block is for a shuffle, return it // without acquiring a lock; the disk store never deletes (recent) items so this should work if (blockId.isShuffle) { - val shuffleBlockManager = shuffleManager.shuffleBlockResolver + val shuffleBlockResolver = shuffleManager.shuffleBlockResolver // TODO: This should gracefully handle case where local block is not available. Currently // downstream code will throw an exception. - Option(shuffleBlockManager.getBlockData(blockId.asInstanceOf[ShuffleBlockId]).nioByteBuffer()) + Option( + shuffleBlockResolver.getBlockData(blockId.asInstanceOf[ShuffleBlockId]).nioByteBuffer()) } else { doGetLocal(blockId, asBlockResult = false).asInstanceOf[Option[ByteBuffer]] } diff --git a/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala b/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala index 5764c16902c66..2a4447705fa65 100644 --- a/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala +++ b/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala @@ -55,7 +55,7 @@ private[spark] class DiskBlockManager(blockManager: BlockManager, conf: SparkCon /** Looks up a file by hashing it into one of our local subdirectories. */ // This method should be kept in sync with - // org.apache.spark.network.shuffle.StandaloneShuffleBlockManager#getFile(). + // org.apache.spark.network.shuffle.ExternalShuffleBlockResolver#getFile(). def getFile(filename: String): File = { // Figure out which local directory it hashes to, and which subdirectory in that val hash = Utils.nonNegativeHash(filename) diff --git a/core/src/main/scala/org/apache/spark/storage/StorageStatusListener.scala b/core/src/main/scala/org/apache/spark/storage/StorageStatusListener.scala index 7d75929b96f75..ec711480ebf30 100644 --- a/core/src/main/scala/org/apache/spark/storage/StorageStatusListener.scala +++ b/core/src/main/scala/org/apache/spark/storage/StorageStatusListener.scala @@ -25,13 +25,17 @@ import org.apache.spark.scheduler._ /** * :: DeveloperApi :: * A SparkListener that maintains executor storage status. + * + * This class is thread-safe (unlike JobProgressListener) */ @DeveloperApi class StorageStatusListener extends SparkListener { // This maintains only blocks that are cached (i.e. storage level is not StorageLevel.NONE) private[storage] val executorIdToStorageStatus = mutable.Map[String, StorageStatus]() - def storageStatusList: Seq[StorageStatus] = executorIdToStorageStatus.values.toSeq + def storageStatusList: Seq[StorageStatus] = synchronized { + executorIdToStorageStatus.values.toSeq + } /** Update storage status list to reflect updated block statuses */ private def updateStorageStatus(execId: String, updatedBlocks: Seq[(BlockId, BlockStatus)]) { diff --git a/core/src/main/scala/org/apache/spark/ui/SparkUI.scala b/core/src/main/scala/org/apache/spark/ui/SparkUI.scala index a5271f0574e6c..bfe4a180e8a6f 100644 --- a/core/src/main/scala/org/apache/spark/ui/SparkUI.scala +++ b/core/src/main/scala/org/apache/spark/ui/SparkUI.scala @@ -17,6 +17,9 @@ package org.apache.spark.ui +import java.util.Date + +import org.apache.spark.status.api.v1.{ApplicationAttemptInfo, ApplicationInfo, JsonRootResource, UIRoot} import org.apache.spark.{Logging, SecurityManager, SparkConf, SparkContext} import org.apache.spark.scheduler._ import org.apache.spark.storage.StorageStatusListener @@ -33,7 +36,7 @@ import org.apache.spark.ui.scope.RDDOperationGraphListener private[spark] class SparkUI private ( val sc: Option[SparkContext], val conf: SparkConf, - val securityManager: SecurityManager, + securityManager: SecurityManager, val environmentListener: EnvironmentListener, val storageStatusListener: StorageStatusListener, val executorsListener: ExecutorsListener, @@ -41,22 +44,27 @@ private[spark] class SparkUI private ( val storageListener: StorageListener, val operationGraphListener: RDDOperationGraphListener, var appName: String, - val basePath: String) + val basePath: String, + val startTime: Long) extends WebUI(securityManager, SparkUI.getUIPort(conf), conf, basePath, "SparkUI") - with Logging { + with Logging + with UIRoot { val killEnabled = sc.map(_.conf.getBoolean("spark.ui.killEnabled", true)).getOrElse(false) + + val stagesTab = new StagesTab(this) + /** Initialize all components of the server. */ def initialize() { attachTab(new JobsTab(this)) - val stagesTab = new StagesTab(this) attachTab(stagesTab) attachTab(new StorageTab(this)) attachTab(new EnvironmentTab(this)) attachTab(new ExecutorsTab(this)) attachHandler(createStaticHandler(SparkUI.STATIC_RESOURCE_DIR, "/static")) attachHandler(createRedirectHandler("/", "/jobs", basePath = basePath)) + attachHandler(JsonRootResource.getJsonServlet(this)) // This should be POST only, but, the YARN AM proxy won't proxy POSTs attachHandler(createRedirectHandler( "/stages/stage/kill", "/stages", stagesTab.handleKillRequest, @@ -83,6 +91,24 @@ private[spark] class SparkUI private ( private[spark] def appUIHostPort = publicHostName + ":" + boundPort private[spark] def appUIAddress = s"http://$appUIHostPort" + + def getSparkUI(appId: String): Option[SparkUI] = { + if (appId == appName) Some(this) else None + } + + def getApplicationInfoList: Iterator[ApplicationInfo] = { + Iterator(new ApplicationInfo( + id = appName, + name = appName, + attempts = Seq(new ApplicationAttemptInfo( + attemptId = None, + startTime = new Date(startTime), + endTime = new Date(-1), + sparkUser = "", + completed = false + )) + )) + } } private[spark] abstract class SparkUITab(parent: SparkUI, prefix: String) @@ -109,9 +135,10 @@ private[spark] object SparkUI { listenerBus: SparkListenerBus, jobProgressListener: JobProgressListener, securityManager: SecurityManager, - appName: String): SparkUI = { + appName: String, + startTime: Long): SparkUI = { create(Some(sc), conf, listenerBus, securityManager, appName, - jobProgressListener = Some(jobProgressListener)) + jobProgressListener = Some(jobProgressListener), startTime = startTime) } def createHistoryUI( @@ -119,8 +146,9 @@ private[spark] object SparkUI { listenerBus: SparkListenerBus, securityManager: SecurityManager, appName: String, - basePath: String): SparkUI = { - create(None, conf, listenerBus, securityManager, appName, basePath) + basePath: String, + startTime: Long): SparkUI = { + create(None, conf, listenerBus, securityManager, appName, basePath, startTime = startTime) } /** @@ -137,7 +165,8 @@ private[spark] object SparkUI { securityManager: SecurityManager, appName: String, basePath: String = "", - jobProgressListener: Option[JobProgressListener] = None): SparkUI = { + jobProgressListener: Option[JobProgressListener] = None, + startTime: Long): SparkUI = { val _jobProgressListener: JobProgressListener = jobProgressListener.getOrElse { val listener = new JobProgressListener(conf) @@ -159,6 +188,6 @@ private[spark] object SparkUI { new SparkUI(sc, conf, securityManager, environmentListener, storageStatusListener, executorsListener, _jobProgressListener, storageListener, operationGraphListener, - appName, basePath) + appName, basePath, startTime) } } diff --git a/core/src/main/scala/org/apache/spark/ui/ToolTips.scala b/core/src/main/scala/org/apache/spark/ui/ToolTips.scala index 24f3236456248..063e2a1f8b18e 100644 --- a/core/src/main/scala/org/apache/spark/ui/ToolTips.scala +++ b/core/src/main/scala/org/apache/spark/ui/ToolTips.scala @@ -57,4 +57,23 @@ private[spark] object ToolTips { val GC_TIME = """Time that the executor spent paused for Java garbage collection while the task was running.""" + + val JOB_TIMELINE = + """Shows when jobs started and ended and when executors joined or left. Drag to scroll. + Click Enable Zooming and use mouse wheel to zoom in/out.""" + + val STAGE_TIMELINE = + """Shows when stages started and ended and when executors joined or left. Drag to scroll. + Click Enable Zooming and use mouse wheel to zoom in/out.""" + + val JOB_DAG = + """Shows a graph of stages executed for this job, each of which can contain + multiple RDD operations (e.g. map() and filter()), and of RDDs inside each operation + (shown as dots).""" + + val STAGE_DAG = + """Shows a graph of RDD operations in this stage, and RDDs inside each one. A stage can run + multiple operations (e.g. two map() functions) if they can be pipelined. Some operations + also create multiple RDDs internally. Cached RDDs are shown in green. + """ } diff --git a/core/src/main/scala/org/apache/spark/ui/UIUtils.scala b/core/src/main/scala/org/apache/spark/ui/UIUtils.scala index 97eed13c2d780..6a0f5c5d16daa 100644 --- a/core/src/main/scala/org/apache/spark/ui/UIUtils.scala +++ b/core/src/main/scala/org/apache/spark/ui/UIUtils.scala @@ -156,10 +156,10 @@ private[spark] object UIUtils extends Logging { def commonHeaderNodes: Seq[Node] = { - - - - + + + + @@ -250,7 +250,7 @@ private[spark] object UIUtils extends Logging {

- {org.apache.spark.SPARK_VERSION} {title} @@ -350,7 +350,10 @@ private[spark] object UIUtils extends Logging {
- DAG visualization + + DAG Visualization +
diff --git a/core/src/main/scala/org/apache/spark/ui/WebUI.scala b/core/src/main/scala/org/apache/spark/ui/WebUI.scala index f9860d1a5ce76..384f2ad26e281 100644 --- a/core/src/main/scala/org/apache/spark/ui/WebUI.scala +++ b/core/src/main/scala/org/apache/spark/ui/WebUI.scala @@ -37,7 +37,7 @@ import org.apache.spark.{Logging, SecurityManager, SparkConf} * pages. The use of tabs is optional, however; a WebUI may choose to include pages directly. */ private[spark] abstract class WebUI( - securityManager: SecurityManager, + val securityManager: SecurityManager, port: Int, conf: SparkConf, basePath: String = "", @@ -77,15 +77,9 @@ private[spark] abstract class WebUI( val pagePath = "/" + page.prefix val renderHandler = createServletHandler(pagePath, (request: HttpServletRequest) => page.render(request), securityManager, basePath) - val renderJsonHandler = createServletHandler(pagePath.stripSuffix("/") + "/json", - (request: HttpServletRequest) => page.renderJson(request), securityManager, basePath) attachHandler(renderHandler) - attachHandler(renderJsonHandler) pageToHandlers.getOrElseUpdate(page, ArrayBuffer[ServletContextHandler]()) .append(renderHandler) - pageToHandlers.getOrElseUpdate(page, ArrayBuffer[ServletContextHandler]()) - .append(renderJsonHandler) - } /** Attach a handler to this UI. */ diff --git a/core/src/main/scala/org/apache/spark/ui/exec/ExecutorsPage.scala b/core/src/main/scala/org/apache/spark/ui/exec/ExecutorsPage.scala index 956608d7c0cbe..b247e4cdc3bd4 100644 --- a/core/src/main/scala/org/apache/spark/ui/exec/ExecutorsPage.scala +++ b/core/src/main/scala/org/apache/spark/ui/exec/ExecutorsPage.scala @@ -22,11 +22,11 @@ import javax.servlet.http.HttpServletRequest import scala.xml.Node +import org.apache.spark.status.api.v1.ExecutorSummary import org.apache.spark.ui.{ToolTips, UIUtils, WebUIPage} import org.apache.spark.util.Utils -/** Summary information about an executor to display in the UI. */ -// Needs to be private[ui] because of a false positive MiMa failure. +// This isn't even used anymore -- but we need to keep it b/c of a MiMa false positive private[ui] case class ExecutorSummaryInfo( id: String, hostPort: String, @@ -44,6 +44,7 @@ private[ui] case class ExecutorSummaryInfo( maxMemory: Long, executorLogs: Map[String, String]) + private[ui] class ExecutorsPage( parent: ExecutorsTab, threadDumpEnabled: Boolean) @@ -55,7 +56,8 @@ private[ui] class ExecutorsPage( val maxMem = storageStatusList.map(_.maxMem).sum val memUsed = storageStatusList.map(_.memUsed).sum val diskUsed = storageStatusList.map(_.diskUsed).sum - val execInfo = for (statusId <- 0 until storageStatusList.size) yield getExecInfo(statusId) + val execInfo = for (statusId <- 0 until storageStatusList.size) yield + ExecutorsPage.getExecInfo(listener, statusId) val execInfoSorted = execInfo.sortBy(_.id) val logsExist = execInfo.filter(_.executorLogs.nonEmpty).nonEmpty @@ -111,7 +113,7 @@ private[ui] class ExecutorsPage( } /** Render an HTML row representing an executor */ - private def execRow(info: ExecutorSummaryInfo, logsExist: Boolean): Seq[Node] = { + private def execRow(info: ExecutorSummary, logsExist: Boolean): Seq[Node] = { val maximumMemory = info.maxMemory val memoryUsed = info.memoryUsed val diskUsed = info.diskUsed @@ -170,8 +172,11 @@ private[ui] class ExecutorsPage( } +} + +private[spark] object ExecutorsPage { /** Represent an executor's info as a map given a storage status index */ - private def getExecInfo(statusId: Int): ExecutorSummaryInfo = { + def getExecInfo(listener: ExecutorsListener, statusId: Int): ExecutorSummary = { val status = listener.storageStatusList(statusId) val execId = status.blockManagerId.executorId val hostPort = status.blockManagerId.hostPort @@ -189,7 +194,7 @@ private[ui] class ExecutorsPage( val totalShuffleWrite = listener.executorToShuffleWrite.getOrElse(execId, 0L) val executorLogs = listener.executorToLogUrls.getOrElse(execId, Map.empty) - new ExecutorSummaryInfo( + new ExecutorSummary( execId, hostPort, rddBlocks, diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala b/core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala index f6abf27db49dd..e010ebef3b34a 100644 --- a/core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala +++ b/core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala @@ -18,12 +18,12 @@ package org.apache.spark.ui.jobs import scala.collection.mutable.{HashMap, ListBuffer} -import scala.xml.{Node, NodeSeq, Unparsed} +import scala.xml.{Node, NodeSeq, Unparsed, Utility} import java.util.Date import javax.servlet.http.HttpServletRequest -import org.apache.spark.ui.{UIUtils, WebUIPage} +import org.apache.spark.ui.{ToolTips, UIUtils, WebUIPage} import org.apache.spark.ui.jobs.UIData.{ExecutorUIData, JobUIData} import org.apache.spark.JobExecutionStatus @@ -81,6 +81,9 @@ private[ui] class AllJobsPage(parent: JobsTab) extends WebUIPage("") { case JobExecutionStatus.RUNNING => "running" } + // The timeline library treats contents as HTML, so we have to escape them; for the + // data-title attribute string we have to escape them twice since that's in a string. + val escapedDesc = Utility.escape(displayJobDescription) val jobEventJsonAsStr = s""" |{ @@ -90,16 +93,17 @@ private[ui] class AllJobsPage(parent: JobsTab) extends WebUIPage("") { | 'end': new Date(${completionTime}), | 'content': '
' + + | 'Status: ${status}
' + + | 'Submitted: ${UIUtils.formatDate(new Date(submissionTime))}' + | '${ if (status != JobExecutionStatus.RUNNING) { - s"""
Completion Time: ${UIUtils.formatDate(new Date(completionTime))}""" + s"""
Completed: ${UIUtils.formatDate(new Date(completionTime))}""" } else { "" } }">' + - | '${displayJobDescription} (Job ${jobId})
' + | '${escapedDesc} (Job ${jobId})
' |} """.stripMargin jobEventJsonAsStr @@ -179,13 +183,15 @@ private[ui] class AllJobsPage(parent: JobsTab) extends WebUIPage("") { - Event timeline + + Event Timeline + ++ ++ @@ -271,13 +277,19 @@ private[ui] class AllJobsPage(parent: JobsTab) extends WebUIPage("") { val shouldShowCompletedJobs = completedJobs.nonEmpty val shouldShowFailedJobs = failedJobs.nonEmpty + val completedJobNumStr = if (completedJobs.size == listener.numCompletedJobs) { + s"${completedJobs.size}" + } else { + s"${listener.numCompletedJobs}, only showing ${completedJobs.size}" + } + val summary: NodeSeq =
    {if (parent.sc.isDefined) { // Total duration is not meaningful unless the UI is live
  • - Total Duration: + Total Uptime: {UIUtils.formatDuration(System.currentTimeMillis() - startTime)}
    • }} @@ -295,9 +307,9 @@ private[ui] class AllJobsPage(parent: JobsTab) extends WebUIPage("") { } { if (shouldShowCompletedJobs) { -
  • +
  • Completed Jobs: - {completedJobs.size} + {completedJobNumStr}
    • } } @@ -305,7 +317,7 @@ private[ui] class AllJobsPage(parent: JobsTab) extends WebUIPage("") { if (shouldShowFailedJobs) {
  • Failed Jobs: - {failedJobs.size} + {listener.numFailedJobs}
    • } } @@ -322,7 +334,7 @@ private[ui] class AllJobsPage(parent: JobsTab) extends WebUIPage("") { activeJobsTable } if (shouldShowCompletedJobs) { - content ++=

    Completed Jobs ({completedJobs.size})

    ++ + content ++=

    Completed Jobs ({completedJobNumStr})

    ++ completedJobsTable } if (shouldShowFailedJobs) { @@ -330,9 +342,8 @@ private[ui] class AllJobsPage(parent: JobsTab) extends WebUIPage("") { failedJobsTable } - val helpText = """A job is triggered by an action, like "count()" or "saveAsTextFile()".""" + - " Click on a job's title to see information about the stages of tasks associated with" + - " the job." + val helpText = """A job is triggered by an action, like count() or saveAsTextFile().""" + + " Click on a job to see information about the stages of tasks inside it." UIUtils.headerSparkPage("Spark Jobs", content, parent, helpText = Some(helpText)) } diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/AllStagesPage.scala b/core/src/main/scala/org/apache/spark/ui/jobs/AllStagesPage.scala index 236bc8ea92879..5e52942b64f3f 100644 --- a/core/src/main/scala/org/apache/spark/ui/jobs/AllStagesPage.scala +++ b/core/src/main/scala/org/apache/spark/ui/jobs/AllStagesPage.scala @@ -64,22 +64,15 @@ private[ui] class AllStagesPage(parent: StagesTab) extends WebUIPage("") { val shouldShowCompletedStages = completedStages.nonEmpty val shouldShowFailedStages = failedStages.nonEmpty + val completedStageNumStr = if (numCompletedStages == completedStages.size) { + s"$numCompletedStages" + } else { + s"$numCompletedStages, only showing ${completedStages.size}" + } + val summary: NodeSeq =
      - { - if (sc.isDefined) { - // Total duration is not meaningful unless the UI is live -
    • - Total Duration: - {UIUtils.formatDuration(now - sc.get.startTime)} -
      • - } - } -
    • - Scheduling Mode: - {listener.schedulingMode.map(_.toString).getOrElse("Unknown")} -
      • { if (shouldShowActiveStages) {
    • @@ -98,9 +91,9 @@ private[ui] class AllStagesPage(parent: StagesTab) extends WebUIPage("") { } { if (shouldShowCompletedStages) { -
    • +
    • Completed Stages: - {numCompletedStages} + {completedStageNumStr}
      • } } @@ -132,14 +125,14 @@ private[ui] class AllStagesPage(parent: StagesTab) extends WebUIPage("") { pendingStagesTable.toNodeSeq } if (shouldShowCompletedStages) { - content ++=

      Completed Stages ({numCompletedStages})

      ++ + content ++=

      Completed Stages ({completedStageNumStr})

      ++ completedStagesTable.toNodeSeq } if (shouldShowFailedStages) { content ++=

      Failed Stages ({numFailedStages})

      ++ failedStagesTable.toNodeSeq } - UIUtils.headerSparkPage("Spark Stages (for all jobs)", content, parent) + UIUtils.headerSparkPage("Stages for All Jobs", content, parent) } } } diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala b/core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala index 96cc3d78d0f15..2cad0a796913e 100644 --- a/core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala +++ b/core/src/main/scala/org/apache/spark/ui/jobs/JobPage.scala @@ -20,13 +20,13 @@ package org.apache.spark.ui.jobs import java.util.Date import scala.collection.mutable.{Buffer, HashMap, ListBuffer} -import scala.xml.{NodeSeq, Node, Unparsed} +import scala.xml.{NodeSeq, Node, Unparsed, Utility} import javax.servlet.http.HttpServletRequest import org.apache.spark.JobExecutionStatus import org.apache.spark.scheduler.StageInfo -import org.apache.spark.ui.{UIUtils, WebUIPage} +import org.apache.spark.ui.{ToolTips, UIUtils, WebUIPage} import org.apache.spark.ui.jobs.UIData.ExecutorUIData /** Page showing statistics and stage list for a given job */ @@ -64,6 +64,9 @@ private[ui] class JobPage(parent: JobsTab) extends WebUIPage("job") { val submissionTime = stage.submissionTime.get val completionTime = stage.completionTime.getOrElse(System.currentTimeMillis()) + // The timeline library treats contents as HTML, so we have to escape them; for the + // data-title attribute string we have to escape them twice since that's in a string. + val escapedName = Utility.escape(name) s""" |{ | 'className': 'stage job-timeline-object ${status}', @@ -72,17 +75,17 @@ private[ui] class JobPage(parent: JobsTab) extends WebUIPage("job") { | 'end': new Date(${completionTime}), | 'content': '
      ' + | 'Status: ${status.toUpperCase}
      ' + - | 'Submission Time: ${UIUtils.formatDate(new Date(submissionTime))}' + + | 'Submitted: ${UIUtils.formatDate(new Date(submissionTime))}' + | '${ if (status != "running") { - s"""
      Completion Time: ${UIUtils.formatDate(new Date(completionTime))}""" + s"""
      Completed: ${UIUtils.formatDate(new Date(completionTime))}""" } else { "" } }">' + - | '${name} (Stage ${stageId}.${attemptId})
      ', + | '${escapedName} (Stage ${stageId}.${attemptId})
    ', |} """.stripMargin } @@ -161,13 +164,15 @@ private[ui] class JobPage(parent: JobsTab) extends WebUIPage("job") { - Event timeline + + Event Timeline + ++ ++ @@ -187,7 +192,7 @@ private[ui] class JobPage(parent: JobsTab) extends WebUIPage("job") { val jobDataOption = listener.jobIdToData.get(jobId) if (jobDataOption.isEmpty) { val content = -
    +

    No information to display for job {jobId}

    return UIUtils.headerSparkPage( diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala b/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala index 8f9aa9fdec819..246e191d64776 100644 --- a/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala +++ b/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala @@ -74,6 +74,8 @@ class JobProgressListener(conf: SparkConf) extends SparkListener with Logging { // JobProgressListener's retention limits. var numCompletedStages = 0 var numFailedStages = 0 + var numCompletedJobs = 0 + var numFailedJobs = 0 // Misc: val executorIdToBlockManagerId = HashMap[ExecutorId, BlockManagerId]() @@ -217,10 +219,12 @@ class JobProgressListener(conf: SparkConf) extends SparkListener with Logging { completedJobs += jobData trimJobsIfNecessary(completedJobs) jobData.status = JobExecutionStatus.SUCCEEDED + numCompletedJobs += 1 case JobFailed(exception) => failedJobs += jobData trimJobsIfNecessary(failedJobs) jobData.status = JobExecutionStatus.FAILED + numFailedJobs += 1 } for (stageId <- jobData.stageIds) { stageIdToActiveJobIds.get(stageId).foreach { jobsUsingStage => diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/PoolPage.scala b/core/src/main/scala/org/apache/spark/ui/jobs/PoolPage.scala index d725b9d8565ac..f3e0b38523f32 100644 --- a/core/src/main/scala/org/apache/spark/ui/jobs/PoolPage.scala +++ b/core/src/main/scala/org/apache/spark/ui/jobs/PoolPage.scala @@ -21,7 +21,7 @@ import javax.servlet.http.HttpServletRequest import scala.xml.Node -import org.apache.spark.scheduler.{Schedulable, StageInfo} +import org.apache.spark.scheduler.StageInfo import org.apache.spark.ui.{WebUIPage, UIUtils} /** Page showing specific pool details */ diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala b/core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala index 6c4305873cbd9..8f7b1c2f09665 100644 --- a/core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala +++ b/core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala @@ -25,11 +25,11 @@ import scala.xml.{Elem, Node, Unparsed} import org.apache.commons.lang3.StringEscapeUtils import org.apache.spark.executor.TaskMetrics +import org.apache.spark.scheduler.{AccumulableInfo, TaskInfo} import org.apache.spark.ui.{ToolTips, WebUIPage, UIUtils} import org.apache.spark.ui.jobs.UIData._ import org.apache.spark.ui.scope.RDDOperationGraph import org.apache.spark.util.{Utils, Distribution} -import org.apache.spark.scheduler.{AccumulableInfo, TaskInfo} /** Page showing statistics and task list for a given stage */ private[ui] class StagePage(parent: StagesTab) extends WebUIPage("stage") { @@ -52,14 +52,22 @@ private[ui] class StagePage(parent: StagesTab) extends WebUIPage("stage") { val stageAttemptId = parameterAttempt.toInt val stageDataOption = progressListener.stageIdToData.get((stageId, stageAttemptId)) - if (stageDataOption.isEmpty || stageDataOption.get.taskData.isEmpty) { + val stageHeader = s"Details for Stage $stageId (Attempt $stageAttemptId)" + if (stageDataOption.isEmpty) { + val content = +
    +

    No information to display for Stage {stageId} (Attempt {stageAttemptId})

    +
    + return UIUtils.headerSparkPage(stageHeader, content, parent) + + } + if (stageDataOption.get.taskData.isEmpty) { val content =

    Summary Metrics

    No tasks have started yet

    Tasks

    No tasks have started yet
    - return UIUtils.headerSparkPage( - s"Details for Stage $stageId (Attempt $stageAttemptId)", content, parent) + return UIUtils.headerSparkPage(stageHeader, content, parent) } val stageData = stageDataOption.get @@ -73,7 +81,7 @@ private[ui] class StagePage(parent: StagesTab) extends WebUIPage("stage") {
    • - Total task time across all tasks: + Total Time Across All Tasks: {UIUtils.formatDuration(stageData.executorRunTime)}
      • {if (stageData.hasInput) { @@ -90,25 +98,25 @@ private[ui] class StagePage(parent: StagesTab) extends WebUIPage("stage") { }} {if (stageData.hasShuffleRead) {
    • - Shuffle read: + Shuffle Read: {s"${Utils.bytesToString(stageData.shuffleReadTotalBytes)} / " + s"${stageData.shuffleReadRecords}"}
      • }} {if (stageData.hasShuffleWrite) {
    • - Shuffle write: + Shuffle Write: {s"${Utils.bytesToString(stageData.shuffleWriteBytes)} / " + s"${stageData.shuffleWriteRecords}"}
      • }} {if (stageData.hasBytesSpilled) {
    • - Shuffle spill (memory): + Shuffle Spill (Memory): {Utils.bytesToString(stageData.memoryBytesSpilled)}
    • - Shuffle spill (disk): + Shuffle Spill (Disk): {Utils.bytesToString(stageData.diskBytesSpilled)}
      • }} @@ -119,10 +127,10 @@ private[ui] class StagePage(parent: StagesTab) extends WebUIPage("stage") {
      - Show additional metrics + Show Additional Metrics @@ -86,19 +77,19 @@ private[ui] class RDDPage(parent: StorageTab) extends WebUIPage("rdd") {
      -

      Data Distribution on {workers.size} Executors

      +

      Data Distribution on {rddStorageInfo.dataDistribution.size} Executors

      {workerTable}
      -

      {blocks.size} Partitions

      +

      {rddStorageInfo.partitions.size} Partitions

      {blockTable}
      ; - UIUtils.headerSparkPage("RDD Storage Info for " + rddInfo.name, content, parent) + UIUtils.headerSparkPage("RDD Storage Info for " + rddStorageInfo.name, content, parent) } /** Header fields for the worker table */ @@ -116,34 +107,32 @@ private[ui] class RDDPage(parent: StorageTab) extends WebUIPage("rdd") { "Executors") /** Render an HTML row representing a worker */ - private def workerRow(worker: (Int, StorageStatus)): Seq[Node] = { - val (rddId, status) = worker + private def workerRow(worker: RDDDataDistribution): Seq[Node] = { - {status.blockManagerId.host + ":" + status.blockManagerId.port} + {worker.address} - {Utils.bytesToString(status.memUsedByRdd(rddId))} - ({Utils.bytesToString(status.memRemaining)} Remaining) + {Utils.bytesToString(worker.memoryUsed)} + ({Utils.bytesToString(worker.memoryRemaining)} Remaining) - {Utils.bytesToString(status.diskUsedByRdd(rddId))} + {Utils.bytesToString(worker.diskUsed)} } /** Render an HTML row representing a block */ - private def blockRow(row: (BlockId, BlockStatus, Seq[String])): Seq[Node] = { - val (id, block, locations) = row + private def blockRow(row: RDDPartitionInfo): Seq[Node] = { - {id} + {row.blockName} - {block.storageLevel.description} + {row.storageLevel} - - {Utils.bytesToString(block.memSize)} + + {Utils.bytesToString(row.memoryUsed)} - - {Utils.bytesToString(block.diskSize)} + + {Utils.bytesToString(row.diskUsed)} - {locations.map(l => {l}
      )} + {row.executors.map(l => {l}
      )} } diff --git a/core/src/main/scala/org/apache/spark/ui/storage/StoragePage.scala b/core/src/main/scala/org/apache/spark/ui/storage/StoragePage.scala index 59dc6b547c1d8..07db783c572cf 100644 --- a/core/src/main/scala/org/apache/spark/ui/storage/StoragePage.scala +++ b/core/src/main/scala/org/apache/spark/ui/storage/StoragePage.scala @@ -22,7 +22,7 @@ import javax.servlet.http.HttpServletRequest import scala.xml.Node import org.apache.spark.storage.RDDInfo -import org.apache.spark.ui.{WebUIPage, UIUtils} +import org.apache.spark.ui.{UIUtils, WebUIPage} import org.apache.spark.util.Utils /** Page showing list of RDD's currently stored in the cluster */ diff --git a/core/src/main/scala/org/apache/spark/ui/storage/StorageTab.scala b/core/src/main/scala/org/apache/spark/ui/storage/StorageTab.scala index 045bd784990d1..0351749700962 100644 --- a/core/src/main/scala/org/apache/spark/ui/storage/StorageTab.scala +++ b/core/src/main/scala/org/apache/spark/ui/storage/StorageTab.scala @@ -35,6 +35,8 @@ private[ui] class StorageTab(parent: SparkUI) extends SparkUITab(parent, "storag /** * :: DeveloperApi :: * A SparkListener that prepares information to be displayed on the BlockManagerUI. + * + * This class is thread-safe (unlike JobProgressListener) */ @DeveloperApi class StorageListener(storageStatusListener: StorageStatusListener) extends SparkListener { @@ -43,7 +45,9 @@ class StorageListener(storageStatusListener: StorageStatusListener) extends Spar def storageStatusList: Seq[StorageStatus] = storageStatusListener.storageStatusList /** Filter RDD info to include only those with cached partitions */ - def rddInfoList: Seq[RDDInfo] = _rddInfoMap.values.filter(_.numCachedPartitions > 0).toSeq + def rddInfoList: Seq[RDDInfo] = synchronized { + _rddInfoMap.values.filter(_.numCachedPartitions > 0).toSeq + } /** Update the storage info of the RDDs whose blocks are among the given updated blocks */ private def updateRDDInfo(updatedBlocks: Seq[(BlockId, BlockStatus)]): Unit = { diff --git a/core/src/test/resources/HistoryServerExpectations/application_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/application_list_json_expectation.json new file mode 100644 index 0000000000000..ce4fe80b66aa5 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/application_list_json_expectation.json @@ -0,0 +1,53 @@ +[ { + "id" : "local-1430917381534", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-05-06T13:03:00.893GMT", + "endTime" : "2015-05-06T13:03:11.398GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +}, { + "id" : "local-1426533911241", + "name" : "Spark shell", + "attempts" : [ { + "attemptId" : "2", + "startTime" : "2015-03-17T23:11:50.242GMT", + "endTime" : "2015-03-17T23:12:25.177GMT", + "sparkUser" : "irashid", + "completed" : true + }, { + "attemptId" : "1", + "startTime" : "2015-03-16T19:25:10.242GMT", + "endTime" : "2015-03-16T19:25:45.177GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +}, { + "id" : "local-1425081759269", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-02-28T00:02:38.277GMT", + "endTime" : "2015-02-28T00:02:46.912GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +}, { + "id" : "local-1422981780767", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-02-03T16:42:59.720GMT", + "endTime" : "2015-02-03T16:43:08.731GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +}, { + "id" : "local-1422981759269", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-02-03T16:42:38.277GMT", + "endTime" : "2015-02-03T16:42:46.912GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/complete_stage_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/complete_stage_list_json_expectation.json new file mode 100644 index 0000000000000..31ac9beea8788 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/complete_stage_list_json_expectation.json @@ -0,0 +1,67 @@ +[ { + "status" : "COMPLETE", + "stageId" : 3, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 8, + "numFailedTasks" : 0, + "executorRunTime" : 162, + "inputBytes" : 160, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 0, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "count at :17", + "details" : "org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line19.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line19.$read$$iwC$$iwC$$iwC.(:22)\n$line19.$read$$iwC$$iwC.(:24)\n$line19.$read$$iwC.(:26)\n$line19.$read.(:28)\n$line19.$read$.(:32)\n$line19.$read$.()\n$line19.$eval$.(:7)\n$line19.$eval$.()\n$line19.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ ] +}, { + "status" : "COMPLETE", + "stageId" : 1, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 8, + "numFailedTasks" : 0, + "executorRunTime" : 3476, + "inputBytes" : 28000128, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 13180, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "map at :14", + "details" : "org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ ] +}, { + "status" : "COMPLETE", + "stageId" : 0, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 8, + "numFailedTasks" : 0, + "executorRunTime" : 4338, + "inputBytes" : 0, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 0, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "count at :15", + "details" : "org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ ] +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/completed_app_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/completed_app_list_json_expectation.json new file mode 100644 index 0000000000000..ce4fe80b66aa5 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/completed_app_list_json_expectation.json @@ -0,0 +1,53 @@ +[ { + "id" : "local-1430917381534", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-05-06T13:03:00.893GMT", + "endTime" : "2015-05-06T13:03:11.398GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +}, { + "id" : "local-1426533911241", + "name" : "Spark shell", + "attempts" : [ { + "attemptId" : "2", + "startTime" : "2015-03-17T23:11:50.242GMT", + "endTime" : "2015-03-17T23:12:25.177GMT", + "sparkUser" : "irashid", + "completed" : true + }, { + "attemptId" : "1", + "startTime" : "2015-03-16T19:25:10.242GMT", + "endTime" : "2015-03-16T19:25:45.177GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +}, { + "id" : "local-1425081759269", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-02-28T00:02:38.277GMT", + "endTime" : "2015-02-28T00:02:46.912GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +}, { + "id" : "local-1422981780767", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-02-03T16:42:59.720GMT", + "endTime" : "2015-02-03T16:43:08.731GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +}, { + "id" : "local-1422981759269", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-02-03T16:42:38.277GMT", + "endTime" : "2015-02-03T16:42:46.912GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/executor_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/executor_list_json_expectation.json new file mode 100644 index 0000000000000..cb622e147249e --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/executor_list_json_expectation.json @@ -0,0 +1,17 @@ +[ { + "id" : "", + "hostPort" : "localhost:57971", + "rddBlocks" : 8, + "memoryUsed" : 28000128, + "diskUsed" : 0, + "activeTasks" : 0, + "failedTasks" : 1, + "completedTasks" : 31, + "totalTasks" : 32, + "totalDuration" : 8820, + "totalInputBytes" : 28000288, + "totalShuffleRead" : 0, + "totalShuffleWrite" : 13180, + "maxMemory" : 278302556, + "executorLogs" : { } +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/failed_stage_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/failed_stage_list_json_expectation.json new file mode 100644 index 0000000000000..bff6a4f69d077 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/failed_stage_list_json_expectation.json @@ -0,0 +1,23 @@ +[ { + "status" : "FAILED", + "stageId" : 2, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 7, + "numFailedTasks" : 1, + "executorRunTime" : 278, + "inputBytes" : 0, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 0, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "count at :20", + "details" : "org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line11.$read$$iwC$$iwC$$iwC$$iwC.(:20)\n$line11.$read$$iwC$$iwC$$iwC.(:25)\n$line11.$read$$iwC$$iwC.(:27)\n$line11.$read$$iwC.(:29)\n$line11.$read.(:31)\n$line11.$read$.(:35)\n$line11.$read$.()\n$line11.$eval$.(:7)\n$line11.$eval$.()\n$line11.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ ] +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/job_list_from_multi_attempt_app_json_1__expectation.json b/core/src/test/resources/HistoryServerExpectations/job_list_from_multi_attempt_app_json_1__expectation.json new file mode 100644 index 0000000000000..2e92e1fa0ec23 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/job_list_from_multi_attempt_app_json_1__expectation.json @@ -0,0 +1,15 @@ +[ { + "jobId" : 0, + "name" : "foreach at :15", + "stageIds" : [ 0 ], + "status" : "SUCCEEDED", + "numTasks" : 8, + "numActiveTasks" : 0, + "numCompletedTasks" : 8, + "numSkippedTasks" : 8, + "numFailedTasks" : 0, + "numActiveStages" : 0, + "numCompletedStages" : 1, + "numSkippedStages" : 0, + "numFailedStages" : 0 +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/job_list_from_multi_attempt_app_json_2__expectation.json b/core/src/test/resources/HistoryServerExpectations/job_list_from_multi_attempt_app_json_2__expectation.json new file mode 100644 index 0000000000000..2e92e1fa0ec23 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/job_list_from_multi_attempt_app_json_2__expectation.json @@ -0,0 +1,15 @@ +[ { + "jobId" : 0, + "name" : "foreach at :15", + "stageIds" : [ 0 ], + "status" : "SUCCEEDED", + "numTasks" : 8, + "numActiveTasks" : 0, + "numCompletedTasks" : 8, + "numSkippedTasks" : 8, + "numFailedTasks" : 0, + "numActiveStages" : 0, + "numCompletedStages" : 1, + "numSkippedStages" : 0, + "numFailedStages" : 0 +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/job_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/job_list_json_expectation.json new file mode 100644 index 0000000000000..cab4750270dfa --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/job_list_json_expectation.json @@ -0,0 +1,43 @@ +[ { + "jobId" : 2, + "name" : "count at :17", + "stageIds" : [ 3 ], + "status" : "SUCCEEDED", + "numTasks" : 8, + "numActiveTasks" : 0, + "numCompletedTasks" : 8, + "numSkippedTasks" : 8, + "numFailedTasks" : 0, + "numActiveStages" : 0, + "numCompletedStages" : 1, + "numSkippedStages" : 0, + "numFailedStages" : 0 +}, { + "jobId" : 1, + "name" : "count at :20", + "stageIds" : [ 1, 2 ], + "status" : "FAILED", + "numTasks" : 16, + "numActiveTasks" : 0, + "numCompletedTasks" : 15, + "numSkippedTasks" : 15, + "numFailedTasks" : 1, + "numActiveStages" : 0, + "numCompletedStages" : 1, + "numSkippedStages" : 0, + "numFailedStages" : 1 +}, { + "jobId" : 0, + "name" : "count at :15", + "stageIds" : [ 0 ], + "status" : "SUCCEEDED", + "numTasks" : 8, + "numActiveTasks" : 0, + "numCompletedTasks" : 8, + "numSkippedTasks" : 8, + "numFailedTasks" : 0, + "numActiveStages" : 0, + "numCompletedStages" : 1, + "numSkippedStages" : 0, + "numFailedStages" : 0 +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/maxDate2_app_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/maxDate2_app_list_json_expectation.json new file mode 100644 index 0000000000000..483632a3956ed --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/maxDate2_app_list_json_expectation.json @@ -0,0 +1,10 @@ +[ { + "id" : "local-1422981759269", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-02-03T16:42:38.277GMT", + "endTime" : "2015-02-03T16:42:46.912GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/maxDate_app_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/maxDate_app_list_json_expectation.json new file mode 100644 index 0000000000000..4b85690fd9199 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/maxDate_app_list_json_expectation.json @@ -0,0 +1,19 @@ +[ { + "id" : "local-1422981780767", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-02-03T16:42:59.720GMT", + "endTime" : "2015-02-03T16:43:08.731GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +}, { + "id" : "local-1422981759269", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-02-03T16:42:38.277GMT", + "endTime" : "2015-02-03T16:42:46.912GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/minDate_app_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/minDate_app_list_json_expectation.json new file mode 100644 index 0000000000000..dca86fe5f7e6a --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/minDate_app_list_json_expectation.json @@ -0,0 +1,35 @@ +[ { + "id" : "local-1430917381534", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-05-06T13:03:00.893GMT", + "endTime" : "2015-05-06T13:03:11.398GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +}, { + "id" : "local-1426533911241", + "name" : "Spark shell", + "attempts" : [ { + "attemptId" : "2", + "startTime" : "2015-03-17T23:11:50.242GMT", + "endTime" : "2015-03-17T23:12:25.177GMT", + "sparkUser" : "irashid", + "completed" : true + }, { + "attemptId" : "1", + "startTime" : "2015-03-16T19:25:10.242GMT", + "endTime" : "2015-03-16T19:25:45.177GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +}, { + "id" : "local-1425081759269", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-02-28T00:02:38.277GMT", + "endTime" : "2015-02-28T00:02:46.912GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/one_app_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/one_app_json_expectation.json new file mode 100644 index 0000000000000..07489ad96414a --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/one_app_json_expectation.json @@ -0,0 +1,10 @@ +{ + "id" : "local-1422981780767", + "name" : "Spark shell", + "attempts" : [ { + "startTime" : "2015-02-03T16:42:59.720GMT", + "endTime" : "2015-02-03T16:43:08.731GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +} \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/one_app_multi_attempt_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/one_app_multi_attempt_json_expectation.json new file mode 100644 index 0000000000000..8f3d7160c723f --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/one_app_multi_attempt_json_expectation.json @@ -0,0 +1,17 @@ +{ + "id" : "local-1426533911241", + "name" : "Spark shell", + "attempts" : [ { + "attemptId" : "2", + "startTime" : "2015-03-17T23:11:50.242GMT", + "endTime" : "2015-03-17T23:12:25.177GMT", + "sparkUser" : "irashid", + "completed" : true + }, { + "attemptId" : "1", + "startTime" : "2015-03-16T19:25:10.242GMT", + "endTime" : "2015-03-16T19:25:45.177GMT", + "sparkUser" : "irashid", + "completed" : true + } ] +} \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/one_job_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/one_job_json_expectation.json new file mode 100644 index 0000000000000..4a29072bdb6e4 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/one_job_json_expectation.json @@ -0,0 +1,15 @@ +{ + "jobId" : 0, + "name" : "count at :15", + "stageIds" : [ 0 ], + "status" : "SUCCEEDED", + "numTasks" : 8, + "numActiveTasks" : 0, + "numCompletedTasks" : 8, + "numSkippedTasks" : 8, + "numFailedTasks" : 0, + "numActiveStages" : 0, + "numCompletedStages" : 1, + "numSkippedStages" : 0, + "numFailedStages" : 0 +} \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/one_rdd_storage_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/one_rdd_storage_json_expectation.json new file mode 100644 index 0000000000000..38b5328ffbb03 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/one_rdd_storage_json_expectation.json @@ -0,0 +1,64 @@ +{ + "id" : 0, + "name" : "0", + "numPartitions" : 8, + "numCachedPartitions" : 8, + "storageLevel" : "Memory Deserialized 1x Replicated", + "memoryUsed" : 28000128, + "diskUsed" : 0, + "dataDistribution" : [ { + "address" : "localhost:57971", + "memoryUsed" : 28000128, + "memoryRemaining" : 250302428, + "diskUsed" : 0 + } ], + "partitions" : [ { + "blockName" : "rdd_0_0", + "storageLevel" : "Memory Deserialized 1x Replicated", + "memoryUsed" : 3500016, + "diskUsed" : 0, + "executors" : [ "localhost:57971" ] + }, { + "blockName" : "rdd_0_1", + "storageLevel" : "Memory Deserialized 1x Replicated", + "memoryUsed" : 3500016, + "diskUsed" : 0, + "executors" : [ "localhost:57971" ] + }, { + "blockName" : "rdd_0_2", + "storageLevel" : "Memory Deserialized 1x Replicated", + "memoryUsed" : 3500016, + "diskUsed" : 0, + "executors" : [ "localhost:57971" ] + }, { + "blockName" : "rdd_0_3", + "storageLevel" : "Memory Deserialized 1x Replicated", + "memoryUsed" : 3500016, + "diskUsed" : 0, + "executors" : [ "localhost:57971" ] + }, { + "blockName" : "rdd_0_4", + "storageLevel" : "Memory Deserialized 1x Replicated", + "memoryUsed" : 3500016, + "diskUsed" : 0, + "executors" : [ "localhost:57971" ] + }, { + "blockName" : "rdd_0_5", + "storageLevel" : "Memory Deserialized 1x Replicated", + "memoryUsed" : 3500016, + "diskUsed" : 0, + "executors" : [ "localhost:57971" ] + }, { + "blockName" : "rdd_0_6", + "storageLevel" : "Memory Deserialized 1x Replicated", + "memoryUsed" : 3500016, + "diskUsed" : 0, + "executors" : [ "localhost:57971" ] + }, { + "blockName" : "rdd_0_7", + "storageLevel" : "Memory Deserialized 1x Replicated", + "memoryUsed" : 3500016, + "diskUsed" : 0, + "executors" : [ "localhost:57971" ] + } ] +} \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/one_stage_attempt_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/one_stage_attempt_json_expectation.json new file mode 100644 index 0000000000000..111cb8163eb3d --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/one_stage_attempt_json_expectation.json @@ -0,0 +1,270 @@ +{ + "status" : "COMPLETE", + "stageId" : 1, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 8, + "numFailedTasks" : 0, + "executorRunTime" : 3476, + "inputBytes" : 28000128, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 13180, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "map at :14", + "details" : "org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ ], + "tasks" : { + "8" : { + "taskId" : 8, + "index" : 0, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.829GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 1, + "executorRunTime" : 435, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 94000, + "recordsWritten" : 0 + } + } + }, + "11" : { + "taskId" : 11, + "index" : 3, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.830GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 434, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1647, + "writeTime" : 83000, + "recordsWritten" : 0 + } + } + }, + "14" : { + "taskId" : 14, + "index" : 6, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.832GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 434, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 88000, + "recordsWritten" : 0 + } + } + }, + "13" : { + "taskId" : 13, + "index" : 5, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.831GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 434, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 73000, + "recordsWritten" : 0 + } + } + }, + "10" : { + "taskId" : 10, + "index" : 2, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.830GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 434, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 76000, + "recordsWritten" : 0 + } + } + }, + "9" : { + "taskId" : 9, + "index" : 1, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.830GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 1, + "executorRunTime" : 436, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 98000, + "recordsWritten" : 0 + } + } + }, + "12" : { + "taskId" : 12, + "index" : 4, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.831GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 434, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1645, + "writeTime" : 101000, + "recordsWritten" : 0 + } + } + }, + "15" : { + "taskId" : 15, + "index" : 7, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.833GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 1, + "executorRunTime" : 435, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 79000, + "recordsWritten" : 0 + } + } + } + }, + "executorSummary" : { + "" : { + "taskTime" : 3624, + "failedTasks" : 0, + "succeededTasks" : 8, + "inputBytes" : 28000128, + "outputBytes" : 0, + "shuffleRead" : 0, + "shuffleWrite" : 13180, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } + } +} \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/one_stage_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/one_stage_json_expectation.json new file mode 100644 index 0000000000000..ef339f89afa45 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/one_stage_json_expectation.json @@ -0,0 +1,270 @@ +[ { + "status" : "COMPLETE", + "stageId" : 1, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 8, + "numFailedTasks" : 0, + "executorRunTime" : 3476, + "inputBytes" : 28000128, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 13180, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "map at :14", + "details" : "org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ ], + "tasks" : { + "8" : { + "taskId" : 8, + "index" : 0, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.829GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 1, + "executorRunTime" : 435, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 94000, + "recordsWritten" : 0 + } + } + }, + "11" : { + "taskId" : 11, + "index" : 3, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.830GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 434, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1647, + "writeTime" : 83000, + "recordsWritten" : 0 + } + } + }, + "14" : { + "taskId" : 14, + "index" : 6, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.832GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 434, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 88000, + "recordsWritten" : 0 + } + } + }, + "13" : { + "taskId" : 13, + "index" : 5, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.831GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 434, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 73000, + "recordsWritten" : 0 + } + } + }, + "10" : { + "taskId" : 10, + "index" : 2, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.830GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 434, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 76000, + "recordsWritten" : 0 + } + } + }, + "9" : { + "taskId" : 9, + "index" : 1, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.830GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 1, + "executorRunTime" : 436, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 98000, + "recordsWritten" : 0 + } + } + }, + "12" : { + "taskId" : 12, + "index" : 4, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.831GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 434, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1645, + "writeTime" : 101000, + "recordsWritten" : 0 + } + } + }, + "15" : { + "taskId" : 15, + "index" : 7, + "attempt" : 0, + "launchTime" : "2015-02-03T16:43:05.833GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 1, + "executorRunTime" : 435, + "resultSize" : 1902, + "jvmGcTime" : 19, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 3500016, + "recordsRead" : 0 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1648, + "writeTime" : 79000, + "recordsWritten" : 0 + } + } + } + }, + "executorSummary" : { + "" : { + "taskTime" : 3624, + "failedTasks" : 0, + "succeededTasks" : 8, + "inputBytes" : 28000128, + "outputBytes" : 0, + "shuffleRead" : 0, + "shuffleWrite" : 13180, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } + } +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/rdd_list_storage_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/rdd_list_storage_json_expectation.json new file mode 100644 index 0000000000000..f79a31022d214 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/rdd_list_storage_json_expectation.json @@ -0,0 +1,9 @@ +[ { + "id" : 0, + "name" : "0", + "numPartitions" : 8, + "numCachedPartitions" : 8, + "storageLevel" : "Memory Deserialized 1x Replicated", + "memoryUsed" : 28000128, + "diskUsed" : 0 +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/running_app_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/running_app_list_json_expectation.json new file mode 100644 index 0000000000000..8878e547a7984 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/running_app_list_json_expectation.json @@ -0,0 +1 @@ +[ ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_list_json_expectation.json new file mode 100644 index 0000000000000..056fac7088594 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_list_json_expectation.json @@ -0,0 +1,89 @@ +[ { + "status" : "COMPLETE", + "stageId" : 3, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 8, + "numFailedTasks" : 0, + "executorRunTime" : 162, + "inputBytes" : 160, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 0, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "count at :17", + "details" : "org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line19.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line19.$read$$iwC$$iwC$$iwC.(:22)\n$line19.$read$$iwC$$iwC.(:24)\n$line19.$read$$iwC.(:26)\n$line19.$read.(:28)\n$line19.$read$.(:32)\n$line19.$read$.()\n$line19.$eval$.(:7)\n$line19.$eval$.()\n$line19.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ ] +}, { + "status" : "COMPLETE", + "stageId" : 1, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 8, + "numFailedTasks" : 0, + "executorRunTime" : 3476, + "inputBytes" : 28000128, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 13180, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "map at :14", + "details" : "org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ ] +}, { + "status" : "COMPLETE", + "stageId" : 0, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 8, + "numFailedTasks" : 0, + "executorRunTime" : 4338, + "inputBytes" : 0, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 0, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "count at :15", + "details" : "org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ ] +}, { + "status" : "FAILED", + "stageId" : 2, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 7, + "numFailedTasks" : 1, + "executorRunTime" : 278, + "inputBytes" : 0, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 0, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "count at :20", + "details" : "org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line11.$read$$iwC$$iwC$$iwC$$iwC.(:20)\n$line11.$read$$iwC$$iwC$$iwC.(:25)\n$line11.$read$$iwC$$iwC.(:27)\n$line11.$read$$iwC.(:29)\n$line11.$read.(:31)\n$line11.$read$.(:35)\n$line11.$read$.()\n$line11.$eval$.(:7)\n$line11.$eval$.()\n$line11.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ ] +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_list_with_accumulable_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_list_with_accumulable_json_expectation.json new file mode 100644 index 0000000000000..79ccacd309693 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_list_with_accumulable_json_expectation.json @@ -0,0 +1,27 @@ +[ { + "status" : "COMPLETE", + "stageId" : 0, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 8, + "numFailedTasks" : 0, + "executorRunTime" : 120, + "inputBytes" : 0, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 0, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "foreach at :15", + "details" : "org.apache.spark.rdd.RDD.foreach(RDD.scala:765)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "value" : "5050" + } ] +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_task_list_expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_task_list_expectation.json new file mode 100644 index 0000000000000..f2cb29b31c85f --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_task_list_expectation.json @@ -0,0 +1,561 @@ +[ { + "taskId" : 0, + "index" : 0, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.494GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 32, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 49294, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 3842811, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 1, + "index" : 1, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.502GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 350, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 3934399, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 2, + "index" : 2, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.503GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 32, + "executorRunTime" : 348, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 89885, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 3, + "index" : 3, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.504GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 1311694, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 4, + "index" : 4, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.504GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 83022, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 5, + "index" : 5, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.505GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 30, + "executorRunTime" : 350, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 3675510, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 6, + "index" : 6, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.505GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 29, + "executorRunTime" : 351, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 4016617, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 7, + "index" : 7, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.506GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 2579051, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 8, + "index" : 8, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.914GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 80, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 121551, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 9, + "index" : 9, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.915GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 9, + "executorRunTime" : 84, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60489, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 101664, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 10, + "index" : 10, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.916GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 8, + "executorRunTime" : 73, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 94709, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 11, + "index" : 11, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.918GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 6, + "executorRunTime" : 75, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 94507, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 12, + "index" : 12, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.923GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 9, + "executorRunTime" : 77, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 102476, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 13, + "index" : 13, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.924GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 9, + "executorRunTime" : 76, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95004, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 14, + "index" : 14, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.925GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 6, + "executorRunTime" : 83, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95646, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 15, + "index" : 15, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.928GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 76, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 602780, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 16, + "index" : 16, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.001GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 10, + "executorRunTime" : 84, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 108320, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 17, + "index" : 17, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.005GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 11, + "executorRunTime" : 91, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 99944, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 18, + "index" : 18, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.010GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 10, + "executorRunTime" : 92, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 100836, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 19, + "index" : 19, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.012GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 84, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95788, + "recordsWritten" : 10 + } + } +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_task_list_from_multi_attempt_app_json_1__expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_task_list_from_multi_attempt_app_json_1__expectation.json new file mode 100644 index 0000000000000..c3febc5fc9447 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_task_list_from_multi_attempt_app_json_1__expectation.json @@ -0,0 +1,193 @@ +[ { + "taskId" : 0, + "index" : 0, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.515GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "78", + "value" : "5050" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 14, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 1, + "index" : 1, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.521GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "247", + "value" : "2175" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 14, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 2, + "index" : 2, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.522GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "378", + "value" : "378" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 13, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 3, + "index" : 3, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.522GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "572", + "value" : "950" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 13, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 4, + "index" : 4, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.522GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "678", + "value" : "2853" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 5, + "index" : 5, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.523GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "897", + "value" : "3750" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 6, + "index" : 6, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.523GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "978", + "value" : "1928" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 7, + "index" : 7, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.524GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "1222", + "value" : "4972" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_task_list_from_multi_attempt_app_json_2__expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_task_list_from_multi_attempt_app_json_2__expectation.json new file mode 100644 index 0000000000000..56d667d88917c --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_task_list_from_multi_attempt_app_json_2__expectation.json @@ -0,0 +1,193 @@ +[ { + "taskId" : 0, + "index" : 0, + "attempt" : 0, + "launchTime" : "2015-03-17T23:12:16.515GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "78", + "value" : "5050" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 14, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 1, + "index" : 1, + "attempt" : 0, + "launchTime" : "2015-03-17T23:12:16.521GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "247", + "value" : "2175" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 14, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 2, + "index" : 2, + "attempt" : 0, + "launchTime" : "2015-03-17T23:12:16.522GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "378", + "value" : "378" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 13, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 3, + "index" : 3, + "attempt" : 0, + "launchTime" : "2015-03-17T23:12:16.522GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "572", + "value" : "950" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 13, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 4, + "index" : 4, + "attempt" : 0, + "launchTime" : "2015-03-17T23:12:16.522GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "678", + "value" : "2853" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 5, + "index" : 5, + "attempt" : 0, + "launchTime" : "2015-03-17T23:12:16.523GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "897", + "value" : "3750" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 6, + "index" : 6, + "attempt" : 0, + "launchTime" : "2015-03-17T23:12:16.523GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "978", + "value" : "1928" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +}, { + "taskId" : 7, + "index" : 7, + "attempt" : 0, + "launchTime" : "2015-03-17T23:12:16.524GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "1222", + "value" : "4972" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__offset___length_expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__offset___length_expectation.json new file mode 100644 index 0000000000000..e5ec3bc4c7126 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__offset___length_expectation.json @@ -0,0 +1,1401 @@ +[ { + "taskId" : 10, + "index" : 10, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.916GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 8, + "executorRunTime" : 73, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 94709, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 11, + "index" : 11, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.918GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 6, + "executorRunTime" : 75, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 94507, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 12, + "index" : 12, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.923GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 9, + "executorRunTime" : 77, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 102476, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 13, + "index" : 13, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.924GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 9, + "executorRunTime" : 76, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95004, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 14, + "index" : 14, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.925GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 6, + "executorRunTime" : 83, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95646, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 15, + "index" : 15, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.928GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 76, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 602780, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 16, + "index" : 16, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.001GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 10, + "executorRunTime" : 84, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 108320, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 17, + "index" : 17, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.005GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 11, + "executorRunTime" : 91, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 99944, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 18, + "index" : 18, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.010GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 10, + "executorRunTime" : 92, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 100836, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 19, + "index" : 19, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.012GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 84, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95788, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 20, + "index" : 20, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.014GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 83, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 97716, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 21, + "index" : 21, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.015GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 88, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 100270, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 22, + "index" : 22, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.018GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 93, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 143427, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 23, + "index" : 23, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.031GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 65, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 91844, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 24, + "index" : 24, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.098GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 43, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 157194, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 25, + "index" : 25, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.103GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 49, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 94134, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 26, + "index" : 26, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.105GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 6, + "executorRunTime" : 38, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 108213, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 27, + "index" : 27, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.110GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 32, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 102019, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 28, + "index" : 28, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.113GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 29, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 104299, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 29, + "index" : 29, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.114GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 39, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 114938, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 30, + "index" : 30, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.118GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 4, + "executorRunTime" : 34, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 119770, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 31, + "index" : 31, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.127GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 36, + "executorRunTime" : 24, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 92619, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 32, + "index" : 32, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.148GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 89603, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 33, + "index" : 33, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.149GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 43, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 118329, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 34, + "index" : 34, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.156GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 6, + "executorRunTime" : 27, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 127746, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 35, + "index" : 35, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.161GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 35, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 160963, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 36, + "index" : 36, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.164GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 29, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 123855, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 37, + "index" : 37, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.165GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 4, + "executorRunTime" : 32, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 111869, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 38, + "index" : 38, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.166GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 31, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 131158, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 39, + "index" : 39, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.180GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 98748, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 40, + "index" : 40, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.197GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 4, + "executorRunTime" : 14, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 94792, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 41, + "index" : 41, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.200GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 16, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 90765, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 42, + "index" : 42, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.203GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 10, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 103713, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 43, + "index" : 43, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.204GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 16, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 171516, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 44, + "index" : 44, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.205GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 18, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 98293, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 45, + "index" : 45, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.206GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 19, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 92985, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 46, + "index" : 46, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.210GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 1, + "executorRunTime" : 31, + "resultSize" : 2065, + "jvmGcTime" : 6, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 113322, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 47, + "index" : 47, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.212GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 18, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 103015, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 48, + "index" : 48, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.220GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 24, + "resultSize" : 2065, + "jvmGcTime" : 6, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 139844, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 49, + "index" : 49, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.223GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 7, + "executorRunTime" : 23, + "resultSize" : 2065, + "jvmGcTime" : 6, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 94984, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 50, + "index" : 50, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.240GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 4, + "executorRunTime" : 18, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 90836, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 51, + "index" : 51, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.242GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 96013, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 52, + "index" : 52, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.243GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 18, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 89664, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 53, + "index" : 53, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.244GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 6, + "executorRunTime" : 18, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 92835, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 54, + "index" : 54, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.244GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 18, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 90506, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 55, + "index" : 55, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.246GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 4, + "executorRunTime" : 21, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 108309, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 56, + "index" : 56, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.249GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 20, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 90329, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 57, + "index" : 57, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.257GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 16, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 96849, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 58, + "index" : 58, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.263GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 16, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 97521, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 59, + "index" : 59, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.265GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 100753, + "recordsWritten" : 10 + } + } +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__sortBy_expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__sortBy_expectation.json new file mode 100644 index 0000000000000..5657123a2db15 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__sortBy_expectation.json @@ -0,0 +1,561 @@ +[ { + "taskId" : 6, + "index" : 6, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.505GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 29, + "executorRunTime" : 351, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 4016617, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 5, + "index" : 5, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.505GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 30, + "executorRunTime" : 350, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 3675510, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 1, + "index" : 1, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.502GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 350, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 3934399, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 4, + "index" : 4, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.504GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 83022, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 7, + "index" : 7, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.506GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 2579051, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 3, + "index" : 3, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.504GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 1311694, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 0, + "index" : 0, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.494GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 32, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 49294, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 3842811, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 2, + "index" : 2, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.503GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 32, + "executorRunTime" : 348, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 89885, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 22, + "index" : 22, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.018GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 93, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 143427, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 18, + "index" : 18, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.010GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 10, + "executorRunTime" : 92, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 100836, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 17, + "index" : 17, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.005GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 11, + "executorRunTime" : 91, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 99944, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 21, + "index" : 21, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.015GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 88, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 100270, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 16, + "index" : 16, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.001GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 10, + "executorRunTime" : 84, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 108320, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 19, + "index" : 19, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.012GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 84, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95788, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 9, + "index" : 9, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.915GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 9, + "executorRunTime" : 84, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60489, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 101664, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 20, + "index" : 20, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.014GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 83, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 97716, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 14, + "index" : 14, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.925GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 6, + "executorRunTime" : 83, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95646, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 8, + "index" : 8, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.914GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 80, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 121551, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 12, + "index" : 12, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.923GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 9, + "executorRunTime" : 77, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 102476, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 13, + "index" : 13, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.924GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 9, + "executorRunTime" : 76, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95004, + "recordsWritten" : 10 + } + } +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__sortBy_short_names___runtime_expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__sortBy_short_names___runtime_expectation.json new file mode 100644 index 0000000000000..5657123a2db15 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__sortBy_short_names___runtime_expectation.json @@ -0,0 +1,561 @@ +[ { + "taskId" : 6, + "index" : 6, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.505GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 29, + "executorRunTime" : 351, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 4016617, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 5, + "index" : 5, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.505GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 30, + "executorRunTime" : 350, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 3675510, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 1, + "index" : 1, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.502GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 350, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 3934399, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 4, + "index" : 4, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.504GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 83022, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 7, + "index" : 7, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.506GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 2579051, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 3, + "index" : 3, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.504GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 31, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 1311694, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 0, + "index" : 0, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.494GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 32, + "executorRunTime" : 349, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 49294, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 3842811, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 2, + "index" : 2, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.503GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 32, + "executorRunTime" : 348, + "resultSize" : 2010, + "jvmGcTime" : 7, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 89885, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 22, + "index" : 22, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.018GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 93, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 143427, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 18, + "index" : 18, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.010GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 10, + "executorRunTime" : 92, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 100836, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 17, + "index" : 17, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.005GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 11, + "executorRunTime" : 91, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 99944, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 21, + "index" : 21, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.015GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 88, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 100270, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 16, + "index" : 16, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.001GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 10, + "executorRunTime" : 84, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 108320, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 19, + "index" : 19, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.012GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 5, + "executorRunTime" : 84, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95788, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 9, + "index" : 9, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.915GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 9, + "executorRunTime" : 84, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60489, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 101664, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 20, + "index" : 20, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.014GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 83, + "resultSize" : 2010, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 97716, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 14, + "index" : 14, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.925GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 6, + "executorRunTime" : 83, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95646, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 8, + "index" : 8, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.914GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 80, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 60488, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 121551, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 12, + "index" : 12, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.923GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 9, + "executorRunTime" : 77, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 102476, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 13, + "index" : 13, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:06.924GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 9, + "executorRunTime" : 76, + "resultSize" : 2010, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95004, + "recordsWritten" : 10 + } + } +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__sortBy_short_names__runtime_expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__sortBy_short_names__runtime_expectation.json new file mode 100644 index 0000000000000..72fe017e9f85d --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_task_list_w__sortBy_short_names__runtime_expectation.json @@ -0,0 +1,561 @@ +[ { + "taskId" : 40, + "index" : 40, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.197GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 4, + "executorRunTime" : 14, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 94792, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 86, + "index" : 86, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.374GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 16, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 95848, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 41, + "index" : 41, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.200GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 16, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 90765, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 68, + "index" : 68, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.306GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 16, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 101750, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 58, + "index" : 58, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.263GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 16, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 97521, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 43, + "index" : 43, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.204GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 16, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 171516, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 57, + "index" : 57, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.257GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 16, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 96849, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 59, + "index" : 59, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.265GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 100753, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 32, + "index" : 32, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.148GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 89603, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 87, + "index" : 87, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.374GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 102159, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 99, + "index" : 99, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.426GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70565, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 133964, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 63, + "index" : 63, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.276GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 20, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 102779, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 90, + "index" : 90, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.385GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 98472, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 39, + "index" : 39, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.180GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 98748, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 42, + "index" : 42, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.203GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 10, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 103713, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 51, + "index" : 51, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.242GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 2, + "executorRunTime" : 17, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 96013, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 50, + "index" : 50, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.240GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 4, + "executorRunTime" : 18, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 90836, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 53, + "index" : 53, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.244GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 6, + "executorRunTime" : 18, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 92835, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 44, + "index" : 44, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.205GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 3, + "executorRunTime" : 18, + "resultSize" : 2065, + "jvmGcTime" : 0, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 98293, + "recordsWritten" : 10 + } + } +}, { + "taskId" : 80, + "index" : 80, + "attempt" : 0, + "launchTime" : "2015-05-06T13:03:07.341GMT", + "executorId" : "driver", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ ], + "taskMetrics" : { + "executorDeserializeTime" : 13, + "executorRunTime" : 18, + "resultSize" : 2065, + "jvmGcTime" : 5, + "resultSerializationTime" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "inputMetrics" : { + "bytesRead" : 70564, + "recordsRead" : 10000 + }, + "shuffleWriteMetrics" : { + "bytesWritten" : 1710, + "writeTime" : 98069, + "recordsWritten" : 10 + } + } +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_task_summary_w__custom_quantiles_expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_task_summary_w__custom_quantiles_expectation.json new file mode 100644 index 0000000000000..bc3c302813de2 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_task_summary_w__custom_quantiles_expectation.json @@ -0,0 +1,19 @@ +{ + "quantiles" : [ 0.01, 0.5, 0.99 ], + "executorDeserializeTime" : [ 1.0, 3.0, 36.0 ], + "executorRunTime" : [ 16.0, 28.0, 351.0 ], + "resultSize" : [ 2010.0, 2065.0, 2065.0 ], + "jvmGcTime" : [ 0.0, 0.0, 7.0 ], + "resultSerializationTime" : [ 0.0, 0.0, 2.0 ], + "memoryBytesSpilled" : [ 0.0, 0.0, 0.0 ], + "diskBytesSpilled" : [ 0.0, 0.0, 0.0 ], + "inputMetrics" : { + "bytesRead" : [ 60488.0, 70564.0, 70565.0 ], + "recordsRead" : [ 10000.0, 10000.0, 10000.0 ] + }, + "shuffleWriteMetrics" : { + "writeBytes" : [ 1710.0, 1710.0, 1710.0 ], + "writeRecords" : [ 10.0, 10.0, 10.0 ], + "writeTime" : [ 89437.0, 102159.0, 4016617.0 ] + } +} \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_task_summary_w_shuffle_read_expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_task_summary_w_shuffle_read_expectation.json new file mode 100644 index 0000000000000..e084c839f1d5a --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_task_summary_w_shuffle_read_expectation.json @@ -0,0 +1,19 @@ +{ + "quantiles" : [ 0.05, 0.25, 0.5, 0.75, 0.95 ], + "executorDeserializeTime" : [ 1.0, 2.0, 2.0, 2.0, 3.0 ], + "executorRunTime" : [ 30.0, 74.0, 75.0, 76.0, 79.0 ], + "resultSize" : [ 1034.0, 1034.0, 1034.0, 1034.0, 1034.0 ], + "jvmGcTime" : [ 0.0, 0.0, 0.0, 0.0, 0.0 ], + "resultSerializationTime" : [ 0.0, 0.0, 0.0, 0.0, 0.0 ], + "memoryBytesSpilled" : [ 0.0, 0.0, 0.0, 0.0, 0.0 ], + "diskBytesSpilled" : [ 0.0, 0.0, 0.0, 0.0, 0.0 ], + "shuffleReadMetrics" : { + "readBytes" : [ 17100.0, 17100.0, 17100.0, 17100.0, 17100.0 ], + "readRecords" : [ 100.0, 100.0, 100.0, 100.0, 100.0 ], + "remoteBlocksFetched" : [ 0.0, 0.0, 0.0, 0.0, 0.0 ], + "localBlocksFetched" : [ 100.0, 100.0, 100.0, 100.0, 100.0 ], + "fetchWaitTime" : [ 0.0, 0.0, 0.0, 1.0, 1.0 ], + "remoteBytesRead" : [ 0.0, 0.0, 0.0, 0.0, 0.0 ], + "totalBlocksFetched" : [ 100.0, 100.0, 100.0, 100.0, 100.0 ] + } +} \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_task_summary_w_shuffle_write_expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_task_summary_w_shuffle_write_expectation.json new file mode 100644 index 0000000000000..6ac7811ce691b --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_task_summary_w_shuffle_write_expectation.json @@ -0,0 +1,19 @@ +{ + "quantiles" : [ 0.05, 0.25, 0.5, 0.75, 0.95 ], + "executorDeserializeTime" : [ 2.0, 2.0, 3.0, 7.0, 31.0 ], + "executorRunTime" : [ 16.0, 18.0, 28.0, 49.0, 349.0 ], + "resultSize" : [ 2010.0, 2065.0, 2065.0, 2065.0, 2065.0 ], + "jvmGcTime" : [ 0.0, 0.0, 0.0, 5.0, 7.0 ], + "resultSerializationTime" : [ 0.0, 0.0, 0.0, 0.0, 1.0 ], + "memoryBytesSpilled" : [ 0.0, 0.0, 0.0, 0.0, 0.0 ], + "diskBytesSpilled" : [ 0.0, 0.0, 0.0, 0.0, 0.0 ], + "inputMetrics" : { + "bytesRead" : [ 60488.0, 70564.0, 70564.0, 70564.0, 70564.0 ], + "recordsRead" : [ 10000.0, 10000.0, 10000.0, 10000.0, 10000.0 ] + }, + "shuffleWriteMetrics" : { + "writeBytes" : [ 1710.0, 1710.0, 1710.0, 1710.0, 1710.0 ], + "writeRecords" : [ 10.0, 10.0, 10.0, 10.0, 10.0 ], + "writeTime" : [ 90329.0, 95848.0, 102159.0, 121551.0, 2579051.0 ] + } +} \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/stage_with_accumulable_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/stage_with_accumulable_json_expectation.json new file mode 100644 index 0000000000000..32d5731676ad5 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/stage_with_accumulable_json_expectation.json @@ -0,0 +1,242 @@ +{ + "status" : "COMPLETE", + "stageId" : 0, + "attemptId" : 0, + "numActiveTasks" : 0, + "numCompleteTasks" : 8, + "numFailedTasks" : 0, + "executorRunTime" : 120, + "inputBytes" : 0, + "inputRecords" : 0, + "outputBytes" : 0, + "outputRecords" : 0, + "shuffleReadBytes" : 0, + "shuffleReadRecords" : 0, + "shuffleWriteBytes" : 0, + "shuffleWriteRecords" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0, + "name" : "foreach at :15", + "details" : "org.apache.spark.rdd.RDD.foreach(RDD.scala:765)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)", + "schedulingPool" : "default", + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "value" : "5050" + } ], + "tasks" : { + "2" : { + "taskId" : 2, + "index" : 2, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.522GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "378", + "value" : "378" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 13, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } + }, + "5" : { + "taskId" : 5, + "index" : 5, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.523GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "897", + "value" : "3750" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } + }, + "4" : { + "taskId" : 4, + "index" : 4, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.522GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "678", + "value" : "2853" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 1, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } + }, + "7" : { + "taskId" : 7, + "index" : 7, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.524GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "1222", + "value" : "4972" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } + }, + "1" : { + "taskId" : 1, + "index" : 1, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.521GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "247", + "value" : "2175" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 14, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } + }, + "3" : { + "taskId" : 3, + "index" : 3, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.522GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "572", + "value" : "950" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 13, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } + }, + "6" : { + "taskId" : 6, + "index" : 6, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.523GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "978", + "value" : "1928" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 12, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } + }, + "0" : { + "taskId" : 0, + "index" : 0, + "attempt" : 0, + "launchTime" : "2015-03-16T19:25:36.515GMT", + "executorId" : "", + "host" : "localhost", + "taskLocality" : "PROCESS_LOCAL", + "speculative" : false, + "accumulatorUpdates" : [ { + "id" : 1, + "name" : "my counter", + "update" : "78", + "value" : "5050" + } ], + "taskMetrics" : { + "executorDeserializeTime" : 14, + "executorRunTime" : 15, + "resultSize" : 697, + "jvmGcTime" : 0, + "resultSerializationTime" : 2, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } + } + }, + "executorSummary" : { + "" : { + "taskTime" : 418, + "failedTasks" : 0, + "succeededTasks" : 8, + "inputBytes" : 0, + "outputBytes" : 0, + "shuffleRead" : 0, + "shuffleWrite" : 0, + "memoryBytesSpilled" : 0, + "diskBytesSpilled" : 0 + } + } +} \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/succeeded_failed_job_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/succeeded_failed_job_list_json_expectation.json new file mode 100644 index 0000000000000..cab4750270dfa --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/succeeded_failed_job_list_json_expectation.json @@ -0,0 +1,43 @@ +[ { + "jobId" : 2, + "name" : "count at :17", + "stageIds" : [ 3 ], + "status" : "SUCCEEDED", + "numTasks" : 8, + "numActiveTasks" : 0, + "numCompletedTasks" : 8, + "numSkippedTasks" : 8, + "numFailedTasks" : 0, + "numActiveStages" : 0, + "numCompletedStages" : 1, + "numSkippedStages" : 0, + "numFailedStages" : 0 +}, { + "jobId" : 1, + "name" : "count at :20", + "stageIds" : [ 1, 2 ], + "status" : "FAILED", + "numTasks" : 16, + "numActiveTasks" : 0, + "numCompletedTasks" : 15, + "numSkippedTasks" : 15, + "numFailedTasks" : 1, + "numActiveStages" : 0, + "numCompletedStages" : 1, + "numSkippedStages" : 0, + "numFailedStages" : 1 +}, { + "jobId" : 0, + "name" : "count at :15", + "stageIds" : [ 0 ], + "status" : "SUCCEEDED", + "numTasks" : 8, + "numActiveTasks" : 0, + "numCompletedTasks" : 8, + "numSkippedTasks" : 8, + "numFailedTasks" : 0, + "numActiveStages" : 0, + "numCompletedStages" : 1, + "numSkippedStages" : 0, + "numFailedStages" : 0 +} ] \ No newline at end of file diff --git a/core/src/test/resources/HistoryServerExpectations/succeeded_job_list_json_expectation.json b/core/src/test/resources/HistoryServerExpectations/succeeded_job_list_json_expectation.json new file mode 100644 index 0000000000000..6fd25befbf7e8 --- /dev/null +++ b/core/src/test/resources/HistoryServerExpectations/succeeded_job_list_json_expectation.json @@ -0,0 +1,29 @@ +[ { + "jobId" : 2, + "name" : "count at :17", + "stageIds" : [ 3 ], + "status" : "SUCCEEDED", + "numTasks" : 8, + "numActiveTasks" : 0, + "numCompletedTasks" : 8, + "numSkippedTasks" : 8, + "numFailedTasks" : 0, + "numActiveStages" : 0, + "numCompletedStages" : 1, + "numSkippedStages" : 0, + "numFailedStages" : 0 +}, { + "jobId" : 0, + "name" : "count at :15", + "stageIds" : [ 0 ], + "status" : "SUCCEEDED", + "numTasks" : 8, + "numActiveTasks" : 0, + "numCompletedTasks" : 8, + "numSkippedTasks" : 8, + "numFailedTasks" : 0, + "numActiveStages" : 0, + "numCompletedStages" : 1, + "numSkippedStages" : 0, + "numFailedStages" : 0 +} ] \ No newline at end of file diff --git a/core/src/test/resources/spark-events/local-1422981759269/APPLICATION_COMPLETE b/core/src/test/resources/spark-events/local-1422981759269/APPLICATION_COMPLETE new file mode 100755 index 0000000000000..e69de29bb2d1d diff --git a/core/src/test/resources/spark-events/local-1422981759269/EVENT_LOG_1 b/core/src/test/resources/spark-events/local-1422981759269/EVENT_LOG_1 new file mode 100755 index 0000000000000..4794e56d1107a --- /dev/null +++ b/core/src/test/resources/spark-events/local-1422981759269/EVENT_LOG_1 @@ -0,0 +1,88 @@ +{"Event":"SparkListenerBlockManagerAdded","Block Manager ID":{"Executor ID":"","Host":"localhost","Port":57967},"Maximum Memory":278302556,"Timestamp":1422981759407} +{"Event":"SparkListenerEnvironmentUpdate","JVM Information":{"Java Home":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre","Java Version":"1.7.0_67 (Oracle Corporation)","Scala Version":"version 2.10.4"},"Spark Properties":{"spark.driver.host":"192.168.1.103","spark.eventLog.enabled":"true","spark.driver.port":"57965","spark.repl.class.uri":"http://192.168.1.103:57964","spark.jars":"","spark.app.name":"Spark shell","spark.scheduler.mode":"FIFO","spark.executor.id":"driver","spark.master":"local[*]","spark.fileserver.uri":"http://192.168.1.103:57966","spark.tachyonStore.folderName":"spark-fd6c823a-8a18-4113-8306-1fa7bb623a7f","spark.app.id":"local-1422981759269"},"System Properties":{"java.io.tmpdir":"/var/folders/36/m29jw1z95qv4ywb1c4n0rz000000gp/T/","line.separator":"\n","path.separator":":","sun.management.compiler":"HotSpot 64-Bit Tiered Compilers","SPARK_SUBMIT":"true","sun.cpu.endian":"little","java.specification.version":"1.7","java.vm.specification.name":"Java Virtual Machine Specification","java.vendor":"Oracle Corporation","java.vm.specification.version":"1.7","user.home":"/Users/irashid","file.encoding.pkg":"sun.io","sun.nio.ch.bugLevel":"","ftp.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","sun.arch.data.model":"64","sun.boot.library.path":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib","user.dir":"/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4","java.library.path":"/Users/irashid/Library/Java/Extensions:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java:.","sun.cpu.isalist":"","os.arch":"x86_64","java.vm.version":"24.65-b04","java.endorsed.dirs":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/endorsed","java.runtime.version":"1.7.0_67-b01","java.vm.info":"mixed mode","java.ext.dirs":"/Users/irashid/Library/Java/Extensions:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/ext:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java","java.runtime.name":"Java(TM) SE Runtime Environment","file.separator":"/","java.class.version":"51.0","java.specification.name":"Java Platform API Specification","sun.boot.class.path":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/resources.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/rt.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/sunrsasign.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/jsse.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/jce.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/charsets.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/jfr.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/classes","file.encoding":"UTF-8","user.timezone":"America/Chicago","java.specification.vendor":"Oracle Corporation","sun.java.launcher":"SUN_STANDARD","os.version":"10.9.5","sun.os.patch.level":"unknown","gopherProxySet":"false","java.vm.specification.vendor":"Oracle Corporation","user.country":"US","sun.jnu.encoding":"UTF-8","http.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","user.language":"en","socksNonProxyHosts":"local|*.local|169.254/16|*.169.254/16","java.vendor.url":"http://java.oracle.com/","java.awt.printerjob":"sun.lwawt.macosx.CPrinterJob","java.awt.graphicsenv":"sun.awt.CGraphicsEnvironment","awt.toolkit":"sun.lwawt.macosx.LWCToolkit","os.name":"Mac OS X","java.vm.vendor":"Oracle Corporation","java.vendor.url.bug":"http://bugreport.sun.com/bugreport/","user.name":"irashid","java.vm.name":"Java HotSpot(TM) 64-Bit Server VM","sun.java.command":"org.apache.spark.deploy.SparkSubmit --class org.apache.spark.repl.Main --conf spark.eventLog.enabled=true spark-shell","java.home":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre","java.version":"1.7.0_67","sun.io.unicode.encoding":"UnicodeBig"},"Classpath Entries":{"/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/spark-assembly-1.2.0-hadoop2.4.0.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-api-jdo-3.2.6.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-rdbms-3.2.9.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-core-3.2.10.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/conf":"System Classpath"}} +{"Event":"SparkListenerApplicationStart","App Name":"Spark shell","App ID":"local-1422981759269","Timestamp":1422981758277,"User":"irashid"} +{"Event":"SparkListenerJobStart","Job ID":0,"Stage Infos":[{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"count at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[0]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"count at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1422981762075,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1422981762081,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1422981762081,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1422981762082,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1422981762083,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1422981762084,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1422981762084,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1422981762085,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1422981762084,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981762632,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":521,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_6","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1422981762081,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981762633,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":520,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_2","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1422981762082,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981762634,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":521,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_3","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1422981762084,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981762634,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":522,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_5","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1422981762083,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981762635,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":522,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_4","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1422981762075,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981762636,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":11,"Executor Run Time":522,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_0","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1422981762085,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981762636,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":9,"Executor Run Time":521,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_7","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1422981762081,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981762637,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":11,"Executor Run Time":522,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_1","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"count at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":8,"Memory Size":28000128,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1422981762069,"Completion Time":1422981762637,"Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":0,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerJobStart","Job ID":1,"Stage Infos":[{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"map at :14","Number of Tasks":8,"RDD Info":[{"RDD ID":1,"Name":"1","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]},{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"first at :17","Number of Tasks":1,"RDD Info":[{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.first(RDD.scala:1093)\n$line11.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line11.$read$$iwC$$iwC$$iwC.(:22)\n$line11.$read$$iwC$$iwC.(:24)\n$line11.$read$$iwC.(:26)\n$line11.$read.(:28)\n$line11.$read$.(:32)\n$line11.$read$.()\n$line11.$eval$.(:7)\n$line11.$eval$.()\n$line11.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[1,2]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"map at :14","Number of Tasks":8,"RDD Info":[{"RDD ID":1,"Name":"1","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":8,"Index":0,"Attempt":0,"Launch Time":1422981763578,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":9,"Index":1,"Attempt":0,"Launch Time":1422981763578,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":10,"Index":2,"Attempt":0,"Launch Time":1422981763579,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":11,"Index":3,"Attempt":0,"Launch Time":1422981763579,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":12,"Index":4,"Attempt":0,"Launch Time":1422981763580,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":13,"Index":5,"Attempt":0,"Launch Time":1422981763580,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":14,"Index":6,"Attempt":0,"Launch Time":1422981763581,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":15,"Index":7,"Attempt":0,"Launch Time":1422981763581,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":10,"Index":2,"Attempt":0,"Launch Time":1422981763579,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764001,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":406,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":138000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":9,"Index":1,"Attempt":0,"Launch Time":1422981763578,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764002,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":106000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":12,"Index":4,"Attempt":0,"Launch Time":1422981763580,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764002,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1645,"Shuffle Write Time":99000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":8,"Index":0,"Attempt":0,"Launch Time":1422981763578,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764003,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":123000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":15,"Index":7,"Attempt":0,"Launch Time":1422981763581,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764003,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":406,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":108000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":11,"Index":3,"Attempt":0,"Launch Time":1422981763579,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764004,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1647,"Shuffle Write Time":97000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":14,"Index":6,"Attempt":0,"Launch Time":1422981763581,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764004,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":132000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":13,"Index":5,"Attempt":0,"Launch Time":1422981763580,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764005,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":81000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"map at :14","Number of Tasks":8,"RDD Info":[{"RDD ID":1,"Name":"1","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1422981763578,"Completion Time":1422981764005,"Accumulables":[]}} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"first at :17","Number of Tasks":1,"RDD Info":[{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.first(RDD.scala:1093)\n$line11.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line11.$read$$iwC$$iwC$$iwC.(:22)\n$line11.$read$$iwC$$iwC.(:24)\n$line11.$read$$iwC.(:26)\n$line11.$read.(:28)\n$line11.$read$.(:32)\n$line11.$read$.()\n$line11.$eval$.(:7)\n$line11.$eval$.()\n$line11.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":2,"Stage Attempt ID":0,"Task Info":{"Task ID":16,"Index":0,"Attempt":0,"Launch Time":1422981764014,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":2,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":16,"Index":0,"Attempt":0,"Launch Time":1422981764014,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764045,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":0,"Executor Run Time":28,"Result Size":1013,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"first at :17","Number of Tasks":1,"RDD Info":[{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.first(RDD.scala:1093)\n$line11.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line11.$read$$iwC$$iwC$$iwC.(:22)\n$line11.$read$$iwC$$iwC.(:24)\n$line11.$read$$iwC.(:26)\n$line11.$read.(:28)\n$line11.$read$.(:32)\n$line11.$read$.()\n$line11.$eval$.(:7)\n$line11.$eval$.()\n$line11.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1422981764014,"Completion Time":1422981764045,"Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":1,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerJobStart","Job ID":2,"Stage Infos":[{"Stage ID":3,"Stage Attempt ID":0,"Stage Name":"map at :14","Number of Tasks":8,"RDD Info":[{"RDD ID":1,"Name":"1","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]},{"Stage ID":4,"Stage Attempt ID":0,"Stage Name":"saveAsTextFile at :19","Number of Tasks":8,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1164)\n$line13.$read$$iwC$$iwC$$iwC$$iwC.(:19)\n$line13.$read$$iwC$$iwC$$iwC.(:24)\n$line13.$read$$iwC$$iwC.(:26)\n$line13.$read$$iwC.(:28)\n$line13.$read.(:30)\n$line13.$read$.(:34)\n$line13.$read$.()\n$line13.$eval$.(:7)\n$line13.$eval$.()\n$line13.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[3,4]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":4,"Stage Attempt ID":0,"Stage Name":"saveAsTextFile at :19","Number of Tasks":8,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1164)\n$line13.$read$$iwC$$iwC$$iwC$$iwC.(:19)\n$line13.$read$$iwC$$iwC$$iwC.(:24)\n$line13.$read$$iwC$$iwC.(:26)\n$line13.$read$$iwC.(:28)\n$line13.$read.(:30)\n$line13.$read$.(:34)\n$line13.$read$.()\n$line13.$eval$.(:7)\n$line13.$eval$.()\n$line13.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":17,"Index":0,"Attempt":0,"Launch Time":1422981764396,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":18,"Index":1,"Attempt":0,"Launch Time":1422981764396,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":19,"Index":2,"Attempt":0,"Launch Time":1422981764397,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":20,"Index":3,"Attempt":0,"Launch Time":1422981764397,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":21,"Index":4,"Attempt":0,"Launch Time":1422981764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":22,"Index":5,"Attempt":0,"Launch Time":1422981764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":23,"Index":6,"Attempt":0,"Launch Time":1422981764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":24,"Index":7,"Attempt":0,"Launch Time":1422981764399,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":24,"Index":7,"Attempt":0,"Launch Time":1422981764399,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764642,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":240,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":19,"Index":2,"Attempt":0,"Launch Time":1422981764397,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764643,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":241,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":21,"Index":4,"Attempt":0,"Launch Time":1422981764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764643,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":240,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":22,"Index":5,"Attempt":0,"Launch Time":1422981764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764645,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":241,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":23,"Index":6,"Attempt":0,"Launch Time":1422981764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764645,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":241,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":17,"Index":0,"Attempt":0,"Launch Time":1422981764396,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764646,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":243,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":18,"Index":1,"Attempt":0,"Launch Time":1422981764396,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764646,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":243,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":20,"Index":3,"Attempt":0,"Launch Time":1422981764397,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981764648,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":247,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":4,"Stage Attempt ID":0,"Stage Name":"saveAsTextFile at :19","Number of Tasks":8,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1164)\n$line13.$read$$iwC$$iwC$$iwC$$iwC.(:19)\n$line13.$read$$iwC$$iwC$$iwC.(:24)\n$line13.$read$$iwC$$iwC.(:26)\n$line13.$read$$iwC.(:28)\n$line13.$read.(:30)\n$line13.$read$.(:34)\n$line13.$read$.()\n$line13.$eval$.(:7)\n$line13.$eval$.()\n$line13.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1422981764396,"Completion Time":1422981764648,"Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":2,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerJobStart","Job ID":3,"Stage Infos":[{"Stage ID":5,"Stage Attempt ID":0,"Stage Name":"count at :17","Number of Tasks":8,"RDD Info":[{"RDD ID":5,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":4,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line15.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line15.$read$$iwC$$iwC$$iwC.(:22)\n$line15.$read$$iwC$$iwC.(:24)\n$line15.$read$$iwC.(:26)\n$line15.$read.(:28)\n$line15.$read$.(:32)\n$line15.$read$.()\n$line15.$eval$.(:7)\n$line15.$eval$.()\n$line15.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[5]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":5,"Stage Attempt ID":0,"Stage Name":"count at :17","Number of Tasks":8,"RDD Info":[{"RDD ID":5,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":4,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line15.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line15.$read$$iwC$$iwC$$iwC.(:22)\n$line15.$read$$iwC$$iwC.(:24)\n$line15.$read$$iwC.(:26)\n$line15.$read.(:28)\n$line15.$read$.(:32)\n$line15.$read$.()\n$line15.$eval$.(:7)\n$line15.$eval$.()\n$line15.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":25,"Index":0,"Attempt":0,"Launch Time":1422981765026,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":26,"Index":1,"Attempt":0,"Launch Time":1422981765026,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":27,"Index":2,"Attempt":0,"Launch Time":1422981765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":28,"Index":3,"Attempt":0,"Launch Time":1422981765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":29,"Index":4,"Attempt":0,"Launch Time":1422981765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":30,"Index":5,"Attempt":0,"Launch Time":1422981765028,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":31,"Index":6,"Attempt":0,"Launch Time":1422981765028,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":32,"Index":7,"Attempt":0,"Launch Time":1422981765029,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":27,"Index":2,"Attempt":0,"Launch Time":1422981765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981765045,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":13,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":30,"Index":5,"Attempt":0,"Launch Time":1422981765028,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981765046,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":13,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":25,"Index":0,"Attempt":0,"Launch Time":1422981765026,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981765046,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":12,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":32}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":29,"Index":4,"Attempt":0,"Launch Time":1422981765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981765047,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":13,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":28,"Index":3,"Attempt":0,"Launch Time":1422981765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981765047,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":12,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":32,"Index":7,"Attempt":0,"Launch Time":1422981765029,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981765048,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":13,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":31,"Index":6,"Attempt":0,"Launch Time":1422981765028,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981765048,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":14,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":26,"Index":1,"Attempt":0,"Launch Time":1422981765026,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981765049,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":12,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":32}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":5,"Stage Attempt ID":0,"Stage Name":"count at :17","Number of Tasks":8,"RDD Info":[{"RDD ID":5,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":4,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line15.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line15.$read$$iwC$$iwC$$iwC.(:22)\n$line15.$read$$iwC$$iwC.(:24)\n$line15.$read$$iwC.(:26)\n$line15.$read.(:28)\n$line15.$read$.(:32)\n$line15.$read$.()\n$line15.$eval$.(:7)\n$line15.$eval$.()\n$line15.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1422981765026,"Completion Time":1422981765050,"Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":3,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerApplicationEnd","Timestamp":1422981766912} diff --git a/core/src/test/resources/spark-events/local-1422981759269/SPARK_VERSION_1.2.0 b/core/src/test/resources/spark-events/local-1422981759269/SPARK_VERSION_1.2.0 new file mode 100755 index 0000000000000..e69de29bb2d1d diff --git a/core/src/test/resources/spark-events/local-1422981780767/APPLICATION_COMPLETE b/core/src/test/resources/spark-events/local-1422981780767/APPLICATION_COMPLETE new file mode 100755 index 0000000000000..e69de29bb2d1d diff --git a/core/src/test/resources/spark-events/local-1422981780767/EVENT_LOG_1 b/core/src/test/resources/spark-events/local-1422981780767/EVENT_LOG_1 new file mode 100755 index 0000000000000..f14a000bf2c28 --- /dev/null +++ b/core/src/test/resources/spark-events/local-1422981780767/EVENT_LOG_1 @@ -0,0 +1,82 @@ +{"Event":"SparkListenerBlockManagerAdded","Block Manager ID":{"Executor ID":"","Host":"localhost","Port":57971},"Maximum Memory":278302556,"Timestamp":1422981780906} +{"Event":"SparkListenerEnvironmentUpdate","JVM Information":{"Java Home":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre","Java Version":"1.7.0_67 (Oracle Corporation)","Scala Version":"version 2.10.4"},"Spark Properties":{"spark.driver.host":"192.168.1.103","spark.eventLog.enabled":"true","spark.driver.port":"57969","spark.repl.class.uri":"http://192.168.1.103:57968","spark.jars":"","spark.app.name":"Spark shell","spark.scheduler.mode":"FIFO","spark.executor.id":"driver","spark.master":"local[*]","spark.fileserver.uri":"http://192.168.1.103:57970","spark.tachyonStore.folderName":"spark-3f19daee-844c-41d0-a3fc-5e3e508f9731","spark.app.id":"local-1422981780767"},"System Properties":{"java.io.tmpdir":"/var/folders/36/m29jw1z95qv4ywb1c4n0rz000000gp/T/","line.separator":"\n","path.separator":":","sun.management.compiler":"HotSpot 64-Bit Tiered Compilers","SPARK_SUBMIT":"true","sun.cpu.endian":"little","java.specification.version":"1.7","java.vm.specification.name":"Java Virtual Machine Specification","java.vendor":"Oracle Corporation","java.vm.specification.version":"1.7","user.home":"/Users/irashid","file.encoding.pkg":"sun.io","sun.nio.ch.bugLevel":"","ftp.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","sun.arch.data.model":"64","sun.boot.library.path":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib","user.dir":"/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4","java.library.path":"/Users/irashid/Library/Java/Extensions:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java:.","sun.cpu.isalist":"","os.arch":"x86_64","java.vm.version":"24.65-b04","java.endorsed.dirs":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/endorsed","java.runtime.version":"1.7.0_67-b01","java.vm.info":"mixed mode","java.ext.dirs":"/Users/irashid/Library/Java/Extensions:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/ext:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java","java.runtime.name":"Java(TM) SE Runtime Environment","file.separator":"/","java.class.version":"51.0","java.specification.name":"Java Platform API Specification","sun.boot.class.path":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/resources.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/rt.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/sunrsasign.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/jsse.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/jce.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/charsets.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/jfr.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/classes","file.encoding":"UTF-8","user.timezone":"America/Chicago","java.specification.vendor":"Oracle Corporation","sun.java.launcher":"SUN_STANDARD","os.version":"10.9.5","sun.os.patch.level":"unknown","gopherProxySet":"false","java.vm.specification.vendor":"Oracle Corporation","user.country":"US","sun.jnu.encoding":"UTF-8","http.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","user.language":"en","socksNonProxyHosts":"local|*.local|169.254/16|*.169.254/16","java.vendor.url":"http://java.oracle.com/","java.awt.printerjob":"sun.lwawt.macosx.CPrinterJob","java.awt.graphicsenv":"sun.awt.CGraphicsEnvironment","awt.toolkit":"sun.lwawt.macosx.LWCToolkit","os.name":"Mac OS X","java.vm.vendor":"Oracle Corporation","java.vendor.url.bug":"http://bugreport.sun.com/bugreport/","user.name":"irashid","java.vm.name":"Java HotSpot(TM) 64-Bit Server VM","sun.java.command":"org.apache.spark.deploy.SparkSubmit --class org.apache.spark.repl.Main --conf spark.eventLog.enabled=true spark-shell","java.home":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre","java.version":"1.7.0_67","sun.io.unicode.encoding":"UnicodeBig"},"Classpath Entries":{"/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/spark-assembly-1.2.0-hadoop2.4.0.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-api-jdo-3.2.6.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-rdbms-3.2.9.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-core-3.2.10.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/conf":"System Classpath"}} +{"Event":"SparkListenerApplicationStart","App Name":"Spark shell","App ID":"local-1422981780767","Timestamp":1422981779720,"User":"irashid"} +{"Event":"SparkListenerJobStart","Job ID":0,"Stage Infos":[{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"count at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[0]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"count at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1422981784234,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1422981784240,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1422981784240,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1422981784241,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1422981784241,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1422981784242,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1422981784242,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1422981784243,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1422981784241,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981784812,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":11,"Executor Run Time":543,"Result Size":1268,"JVM GC Time":25,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_3","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1422981784240,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981784814,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":542,"Result Size":1268,"JVM GC Time":25,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_1","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1422981784234,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981784816,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":542,"Result Size":1268,"JVM GC Time":25,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_0","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1422981784243,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981784816,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":11,"Executor Run Time":543,"Result Size":1268,"JVM GC Time":25,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_7","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1422981784242,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981784817,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":541,"Result Size":1268,"JVM GC Time":25,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_5","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1422981784241,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981784817,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":11,"Executor Run Time":542,"Result Size":1268,"JVM GC Time":25,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_4","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1422981784242,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981784818,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":11,"Executor Run Time":543,"Result Size":1268,"JVM GC Time":25,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_6","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1422981784240,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981784818,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":11,"Executor Run Time":542,"Result Size":1268,"JVM GC Time":25,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_2","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"count at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":8,"Memory Size":28000128,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1422981784228,"Completion Time":1422981784819,"Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":0,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerJobStart","Job ID":1,"Stage Infos":[{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"map at :14","Number of Tasks":8,"RDD Info":[{"RDD ID":1,"Name":"1","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]},{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"count at :20","Number of Tasks":8,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line11.$read$$iwC$$iwC$$iwC$$iwC.(:20)\n$line11.$read$$iwC$$iwC$$iwC.(:25)\n$line11.$read$$iwC$$iwC.(:27)\n$line11.$read$$iwC.(:29)\n$line11.$read.(:31)\n$line11.$read$.(:35)\n$line11.$read$.()\n$line11.$eval$.(:7)\n$line11.$eval$.()\n$line11.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[1,2]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"map at :14","Number of Tasks":8,"RDD Info":[{"RDD ID":1,"Name":"1","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":8,"Index":0,"Attempt":0,"Launch Time":1422981785829,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":9,"Index":1,"Attempt":0,"Launch Time":1422981785830,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":10,"Index":2,"Attempt":0,"Launch Time":1422981785830,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":11,"Index":3,"Attempt":0,"Launch Time":1422981785830,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":12,"Index":4,"Attempt":0,"Launch Time":1422981785831,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":13,"Index":5,"Attempt":0,"Launch Time":1422981785831,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":14,"Index":6,"Attempt":0,"Launch Time":1422981785832,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":15,"Index":7,"Attempt":0,"Launch Time":1422981785833,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":14,"Index":6,"Attempt":0,"Launch Time":1422981785832,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786282,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":434,"Result Size":1902,"JVM GC Time":19,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":88000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":8,"Index":0,"Attempt":0,"Launch Time":1422981785829,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786283,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":435,"Result Size":1902,"JVM GC Time":19,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":94000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":15,"Index":7,"Attempt":0,"Launch Time":1422981785833,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786283,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":435,"Result Size":1902,"JVM GC Time":19,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":79000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":13,"Index":5,"Attempt":0,"Launch Time":1422981785831,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786283,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":434,"Result Size":1902,"JVM GC Time":19,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":73000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":11,"Index":3,"Attempt":0,"Launch Time":1422981785830,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786284,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":434,"Result Size":1902,"JVM GC Time":19,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1647,"Shuffle Write Time":83000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":9,"Index":1,"Attempt":0,"Launch Time":1422981785830,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786284,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":436,"Result Size":1902,"JVM GC Time":19,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":98000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":12,"Index":4,"Attempt":0,"Launch Time":1422981785831,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786285,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":434,"Result Size":1902,"JVM GC Time":19,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1645,"Shuffle Write Time":101000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":10,"Index":2,"Attempt":0,"Launch Time":1422981785830,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786286,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":434,"Result Size":1902,"JVM GC Time":19,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":76000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"map at :14","Number of Tasks":8,"RDD Info":[{"RDD ID":1,"Name":"1","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1422981785829,"Completion Time":1422981786286,"Accumulables":[]}} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"count at :20","Number of Tasks":8,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line11.$read$$iwC$$iwC$$iwC$$iwC.(:20)\n$line11.$read$$iwC$$iwC$$iwC.(:25)\n$line11.$read$$iwC$$iwC.(:27)\n$line11.$read$$iwC.(:29)\n$line11.$read.(:31)\n$line11.$read$.(:35)\n$line11.$read$.()\n$line11.$eval$.(:7)\n$line11.$eval$.()\n$line11.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":2,"Stage Attempt ID":0,"Task Info":{"Task ID":16,"Index":0,"Attempt":0,"Launch Time":1422981786296,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":2,"Stage Attempt ID":0,"Task Info":{"Task ID":17,"Index":1,"Attempt":0,"Launch Time":1422981786297,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":2,"Stage Attempt ID":0,"Task Info":{"Task ID":18,"Index":2,"Attempt":0,"Launch Time":1422981786297,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":2,"Stage Attempt ID":0,"Task Info":{"Task ID":19,"Index":3,"Attempt":0,"Launch Time":1422981786297,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":2,"Stage Attempt ID":0,"Task Info":{"Task ID":20,"Index":4,"Attempt":0,"Launch Time":1422981786298,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":2,"Stage Attempt ID":0,"Task Info":{"Task ID":21,"Index":5,"Attempt":0,"Launch Time":1422981786298,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":2,"Stage Attempt ID":0,"Task Info":{"Task ID":22,"Index":6,"Attempt":0,"Launch Time":1422981786298,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":2,"Stage Attempt ID":0,"Task Info":{"Task ID":23,"Index":7,"Attempt":0,"Launch Time":1422981786299,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":2,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":20,"Index":4,"Attempt":0,"Launch Time":1422981786298,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786337,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":34,"Result Size":862,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":2,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":21,"Index":5,"Attempt":0,"Launch Time":1422981786298,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786339,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":35,"Result Size":862,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":2,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":17,"Index":1,"Attempt":0,"Launch Time":1422981786297,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786340,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":35,"Result Size":862,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":1,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":2,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":18,"Index":2,"Attempt":0,"Launch Time":1422981786297,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786340,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":34,"Result Size":862,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":2,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":16,"Index":0,"Attempt":0,"Launch Time":1422981786296,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786340,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":35,"Result Size":862,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":2,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":23,"Index":7,"Attempt":0,"Launch Time":1422981786299,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786341,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":35,"Result Size":862,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":2,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":22,"Index":6,"Attempt":0,"Launch Time":1422981786298,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786342,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":34,"Result Size":862,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":2,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"ExceptionFailure","Class Name":"java.lang.RuntimeException","Description":"got a 3, failing","Stack Trace":[{"Declaring Class":"$line11.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$1","Method Name":"apply","File Name":"","Line Number":18},{"Declaring Class":"$line11.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$1","Method Name":"apply","File Name":"","Line Number":17},{"Declaring Class":"scala.collection.Iterator$$anon$11","Method Name":"next","File Name":"Iterator.scala","Line Number":328},{"Declaring Class":"org.apache.spark.util.Utils$","Method Name":"getIteratorSize","File Name":"Utils.scala","Line Number":1311},{"Declaring Class":"org.apache.spark.rdd.RDD$$anonfun$count$1","Method Name":"apply","File Name":"RDD.scala","Line Number":910},{"Declaring Class":"org.apache.spark.rdd.RDD$$anonfun$count$1","Method Name":"apply","File Name":"RDD.scala","Line Number":910},{"Declaring Class":"org.apache.spark.SparkContext$$anonfun$runJob$4","Method Name":"apply","File Name":"SparkContext.scala","Line Number":1314},{"Declaring Class":"org.apache.spark.SparkContext$$anonfun$runJob$4","Method Name":"apply","File Name":"SparkContext.scala","Line Number":1314},{"Declaring Class":"org.apache.spark.scheduler.ResultTask","Method Name":"runTask","File Name":"ResultTask.scala","Line Number":61},{"Declaring Class":"org.apache.spark.scheduler.Task","Method Name":"run","File Name":"Task.scala","Line Number":56},{"Declaring Class":"org.apache.spark.executor.Executor$TaskRunner","Method Name":"run","File Name":"Executor.scala","Line Number":196},{"Declaring Class":"java.util.concurrent.ThreadPoolExecutor","Method Name":"runWorker","File Name":"ThreadPoolExecutor.java","Line Number":1145},{"Declaring Class":"java.util.concurrent.ThreadPoolExecutor$Worker","Method Name":"run","File Name":"ThreadPoolExecutor.java","Line Number":615},{"Declaring Class":"java.lang.Thread","Method Name":"run","File Name":"Thread.java","Line Number":745}],"Full Stack Trace":"java.lang.RuntimeException: got a 3, failing\n\tat $line11.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(:18)\n\tat $line11.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(:17)\n\tat scala.collection.Iterator$$anon$11.next(Iterator.scala:328)\n\tat org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1311)\n\tat org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:910)\n\tat org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:910)\n\tat org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1314)\n\tat org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1314)\n\tat org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)\n\tat org.apache.spark.scheduler.Task.run(Task.scala:56)\n\tat org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)\n\tat java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)\n\tat java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)\n\tat java.lang.Thread.run(Thread.java:745)\n","Metrics":{"Host Name":"localhost","Executor Deserialize Time":0,"Executor Run Time":36,"Result Size":0,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}},"Task Info":{"Task ID":19,"Index":3,"Attempt":0,"Launch Time":1422981786297,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981786343,"Failed":true,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":0,"Executor Run Time":36,"Result Size":0,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"count at :20","Number of Tasks":8,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line11.$read$$iwC$$iwC$$iwC$$iwC.(:20)\n$line11.$read$$iwC$$iwC$$iwC.(:25)\n$line11.$read$$iwC$$iwC.(:27)\n$line11.$read$$iwC.(:29)\n$line11.$read.(:31)\n$line11.$read$.(:35)\n$line11.$read$.()\n$line11.$eval$.(:7)\n$line11.$eval$.()\n$line11.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1422981786296,"Completion Time":1422981786347,"Failure Reason":"Job aborted due to stage failure: Task 3 in stage 2.0 failed 1 times, most recent failure: Lost task 3.0 in stage 2.0 (TID 19, localhost): java.lang.RuntimeException: got a 3, failing\n\tat $line11.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(:18)\n\tat $line11.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(:17)\n\tat scala.collection.Iterator$$anon$11.next(Iterator.scala:328)\n\tat org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1311)\n\tat org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:910)\n\tat org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:910)\n\tat org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1314)\n\tat org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1314)\n\tat org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)\n\tat org.apache.spark.scheduler.Task.run(Task.scala:56)\n\tat org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)\n\tat java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)\n\tat java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)\n\tat java.lang.Thread.run(Thread.java:745)\n\nDriver stacktrace:","Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":1,"Job Result":{"Result":"JobFailed","Exception":{"Message":"Job aborted due to stage failure: Task 3 in stage 2.0 failed 1 times, most recent failure: Lost task 3.0 in stage 2.0 (TID 19, localhost): java.lang.RuntimeException: got a 3, failing\n\tat $line11.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(:18)\n\tat $line11.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(:17)\n\tat scala.collection.Iterator$$anon$11.next(Iterator.scala:328)\n\tat org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1311)\n\tat org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:910)\n\tat org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:910)\n\tat org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1314)\n\tat org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1314)\n\tat org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)\n\tat org.apache.spark.scheduler.Task.run(Task.scala:56)\n\tat org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)\n\tat java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)\n\tat java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)\n\tat java.lang.Thread.run(Thread.java:745)\n\nDriver stacktrace:","Stack Trace":[{"Declaring Class":"org.apache.spark.scheduler.DAGScheduler","Method Name":"org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages","File Name":"DAGScheduler.scala","Line Number":1214},{"Declaring Class":"org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1","Method Name":"apply","File Name":"DAGScheduler.scala","Line Number":1203},{"Declaring Class":"org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1","Method Name":"apply","File Name":"DAGScheduler.scala","Line Number":1202},{"Declaring Class":"scala.collection.mutable.ResizableArray$class","Method Name":"foreach","File Name":"ResizableArray.scala","Line Number":59},{"Declaring Class":"scala.collection.mutable.ArrayBuffer","Method Name":"foreach","File Name":"ArrayBuffer.scala","Line Number":47},{"Declaring Class":"org.apache.spark.scheduler.DAGScheduler","Method Name":"abortStage","File Name":"DAGScheduler.scala","Line Number":1202},{"Declaring Class":"org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1","Method Name":"apply","File Name":"DAGScheduler.scala","Line Number":696},{"Declaring Class":"org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1","Method Name":"apply","File Name":"DAGScheduler.scala","Line Number":696},{"Declaring Class":"scala.Option","Method Name":"foreach","File Name":"Option.scala","Line Number":236},{"Declaring Class":"org.apache.spark.scheduler.DAGScheduler","Method Name":"handleTaskSetFailed","File Name":"DAGScheduler.scala","Line Number":696},{"Declaring Class":"org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2","Method Name":"applyOrElse","File Name":"DAGScheduler.scala","Line Number":1420},{"Declaring Class":"akka.actor.Actor$class","Method Name":"aroundReceive","File Name":"Actor.scala","Line Number":465},{"Declaring Class":"org.apache.spark.scheduler.DAGSchedulerEventProcessActor","Method Name":"aroundReceive","File Name":"DAGScheduler.scala","Line Number":1375},{"Declaring Class":"akka.actor.ActorCell","Method Name":"receiveMessage","File Name":"ActorCell.scala","Line Number":516},{"Declaring Class":"akka.actor.ActorCell","Method Name":"invoke","File Name":"ActorCell.scala","Line Number":487},{"Declaring Class":"akka.dispatch.Mailbox","Method Name":"processMailbox","File Name":"Mailbox.scala","Line Number":238},{"Declaring Class":"akka.dispatch.Mailbox","Method Name":"run","File Name":"Mailbox.scala","Line Number":220},{"Declaring Class":"akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask","Method Name":"exec","File Name":"AbstractDispatcher.scala","Line Number":393},{"Declaring Class":"scala.concurrent.forkjoin.ForkJoinTask","Method Name":"doExec","File Name":"ForkJoinTask.java","Line Number":260},{"Declaring Class":"scala.concurrent.forkjoin.ForkJoinPool$WorkQueue","Method Name":"runTask","File Name":"ForkJoinPool.java","Line Number":1339},{"Declaring Class":"scala.concurrent.forkjoin.ForkJoinPool","Method Name":"runWorker","File Name":"ForkJoinPool.java","Line Number":1979},{"Declaring Class":"scala.concurrent.forkjoin.ForkJoinWorkerThread","Method Name":"run","File Name":"ForkJoinWorkerThread.java","Line Number":107}]}}} +{"Event":"SparkListenerJobStart","Job ID":2,"Stage Infos":[{"Stage ID":3,"Stage Attempt ID":0,"Stage Name":"count at :17","Number of Tasks":8,"RDD Info":[{"RDD ID":6,"Name":"/Users/irashid/spark-examples/tmp_data/sums_2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":5,"Name":"/Users/irashid/spark-examples/tmp_data/sums_2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line19.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line19.$read$$iwC$$iwC$$iwC.(:22)\n$line19.$read$$iwC$$iwC.(:24)\n$line19.$read$$iwC.(:26)\n$line19.$read.(:28)\n$line19.$read$.(:32)\n$line19.$read$.()\n$line19.$eval$.(:7)\n$line19.$eval$.()\n$line19.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[3]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":3,"Stage Attempt ID":0,"Stage Name":"count at :17","Number of Tasks":8,"RDD Info":[{"RDD ID":6,"Name":"/Users/irashid/spark-examples/tmp_data/sums_2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":5,"Name":"/Users/irashid/spark-examples/tmp_data/sums_2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line19.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line19.$read$$iwC$$iwC$$iwC.(:22)\n$line19.$read$$iwC$$iwC.(:24)\n$line19.$read$$iwC.(:26)\n$line19.$read.(:28)\n$line19.$read$.(:32)\n$line19.$read$.()\n$line19.$eval$.(:7)\n$line19.$eval$.()\n$line19.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":3,"Stage Attempt ID":0,"Task Info":{"Task ID":24,"Index":0,"Attempt":0,"Launch Time":1422981787191,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":3,"Stage Attempt ID":0,"Task Info":{"Task ID":25,"Index":1,"Attempt":0,"Launch Time":1422981787191,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":3,"Stage Attempt ID":0,"Task Info":{"Task ID":26,"Index":2,"Attempt":0,"Launch Time":1422981787192,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":3,"Stage Attempt ID":0,"Task Info":{"Task ID":27,"Index":3,"Attempt":0,"Launch Time":1422981787192,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":3,"Stage Attempt ID":0,"Task Info":{"Task ID":28,"Index":4,"Attempt":0,"Launch Time":1422981787193,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":3,"Stage Attempt ID":0,"Task Info":{"Task ID":29,"Index":5,"Attempt":0,"Launch Time":1422981787193,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":3,"Stage Attempt ID":0,"Task Info":{"Task ID":30,"Index":6,"Attempt":0,"Launch Time":1422981787194,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":3,"Stage Attempt ID":0,"Task Info":{"Task ID":31,"Index":7,"Attempt":0,"Launch Time":1422981787194,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":3,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":25,"Index":1,"Attempt":0,"Launch Time":1422981787191,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981787222,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":20,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":32}}} +{"Event":"SparkListenerTaskEnd","Stage ID":3,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":24,"Index":0,"Attempt":0,"Launch Time":1422981787191,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981787223,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":20,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":32}}} +{"Event":"SparkListenerTaskEnd","Stage ID":3,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":26,"Index":2,"Attempt":0,"Launch Time":1422981787192,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981787223,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":4,"Executor Run Time":22,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":3,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":31,"Index":7,"Attempt":0,"Launch Time":1422981787194,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981787223,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":19,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":3,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":29,"Index":5,"Attempt":0,"Launch Time":1422981787193,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981787224,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":19,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":3,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":27,"Index":3,"Attempt":0,"Launch Time":1422981787192,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981787224,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":6,"Executor Run Time":19,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":3,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":28,"Index":4,"Attempt":0,"Launch Time":1422981787193,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981787225,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":22,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":3,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":30,"Index":6,"Attempt":0,"Launch Time":1422981787194,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1422981787225,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":21,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":3,"Stage Attempt ID":0,"Stage Name":"count at :17","Number of Tasks":8,"RDD Info":[{"RDD ID":6,"Name":"/Users/irashid/spark-examples/tmp_data/sums_2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":5,"Name":"/Users/irashid/spark-examples/tmp_data/sums_2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line19.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line19.$read$$iwC$$iwC$$iwC.(:22)\n$line19.$read$$iwC$$iwC.(:24)\n$line19.$read$$iwC.(:26)\n$line19.$read.(:28)\n$line19.$read$.(:32)\n$line19.$read$.()\n$line19.$eval$.(:7)\n$line19.$eval$.()\n$line19.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1422981787191,"Completion Time":1422981787226,"Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":2,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerApplicationEnd","Timestamp":1422981788731} diff --git a/core/src/test/resources/spark-events/local-1422981780767/SPARK_VERSION_1.2.0 b/core/src/test/resources/spark-events/local-1422981780767/SPARK_VERSION_1.2.0 new file mode 100755 index 0000000000000..e69de29bb2d1d diff --git a/core/src/test/resources/spark-events/local-1425081759269/APPLICATION_COMPLETE b/core/src/test/resources/spark-events/local-1425081759269/APPLICATION_COMPLETE new file mode 100755 index 0000000000000..e69de29bb2d1d diff --git a/core/src/test/resources/spark-events/local-1425081759269/EVENT_LOG_1 b/core/src/test/resources/spark-events/local-1425081759269/EVENT_LOG_1 new file mode 100755 index 0000000000000..9745b36b09e44 --- /dev/null +++ b/core/src/test/resources/spark-events/local-1425081759269/EVENT_LOG_1 @@ -0,0 +1,88 @@ +{"Event":"SparkListenerBlockManagerAdded","Block Manager ID":{"Executor ID":"","Host":"localhost","Port":57967},"Maximum Memory":278302556,"Timestamp":1425081759407} +{"Event":"SparkListenerEnvironmentUpdate","JVM Information":{"Java Home":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre","Java Version":"1.7.0_67 (Oracle Corporation)","Scala Version":"version 2.10.4"},"Spark Properties":{"spark.driver.host":"192.168.1.103","spark.eventLog.enabled":"true","spark.driver.port":"57965","spark.repl.class.uri":"http://192.168.1.103:57964","spark.jars":"","spark.app.name":"Spark shell","spark.scheduler.mode":"FIFO","spark.executor.id":"driver","spark.master":"local[*]","spark.fileserver.uri":"http://192.168.1.103:57966","spark.tachyonStore.folderName":"spark-fd6c823a-8a18-4113-8306-1fa7bb623a7f","spark.app.id":"local-1425081759269"},"System Properties":{"java.io.tmpdir":"/var/folders/36/m29jw1z95qv4ywb1c4n0rz000000gp/T/","line.separator":"\n","path.separator":":","sun.management.compiler":"HotSpot 64-Bit Tiered Compilers","SPARK_SUBMIT":"true","sun.cpu.endian":"little","java.specification.version":"1.7","java.vm.specification.name":"Java Virtual Machine Specification","java.vendor":"Oracle Corporation","java.vm.specification.version":"1.7","user.home":"/Users/irashid","file.encoding.pkg":"sun.io","sun.nio.ch.bugLevel":"","ftp.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","sun.arch.data.model":"64","sun.boot.library.path":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib","user.dir":"/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4","java.library.path":"/Users/irashid/Library/Java/Extensions:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java:.","sun.cpu.isalist":"","os.arch":"x86_64","java.vm.version":"24.65-b04","java.endorsed.dirs":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/endorsed","java.runtime.version":"1.7.0_67-b01","java.vm.info":"mixed mode","java.ext.dirs":"/Users/irashid/Library/Java/Extensions:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/ext:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java","java.runtime.name":"Java(TM) SE Runtime Environment","file.separator":"/","java.class.version":"51.0","java.specification.name":"Java Platform API Specification","sun.boot.class.path":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/resources.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/rt.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/sunrsasign.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/jsse.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/jce.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/charsets.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/lib/jfr.jar:/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre/classes","file.encoding":"UTF-8","user.timezone":"America/Chicago","java.specification.vendor":"Oracle Corporation","sun.java.launcher":"SUN_STANDARD","os.version":"10.9.5","sun.os.patch.level":"unknown","gopherProxySet":"false","java.vm.specification.vendor":"Oracle Corporation","user.country":"US","sun.jnu.encoding":"UTF-8","http.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","user.language":"en","socksNonProxyHosts":"local|*.local|169.254/16|*.169.254/16","java.vendor.url":"http://java.oracle.com/","java.awt.printerjob":"sun.lwawt.macosx.CPrinterJob","java.awt.graphicsenv":"sun.awt.CGraphicsEnvironment","awt.toolkit":"sun.lwawt.macosx.LWCToolkit","os.name":"Mac OS X","java.vm.vendor":"Oracle Corporation","java.vendor.url.bug":"http://bugreport.sun.com/bugreport/","user.name":"irashid","java.vm.name":"Java HotSpot(TM) 64-Bit Server VM","sun.java.command":"org.apache.spark.deploy.SparkSubmit --class org.apache.spark.repl.Main --conf spark.eventLog.enabled=true spark-shell","java.home":"/Library/Java/JavaVirtualMachines/jdk1.7.0_67.jdk/Contents/Home/jre","java.version":"1.7.0_67","sun.io.unicode.encoding":"UnicodeBig"},"Classpath Entries":{"/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/spark-assembly-1.2.0-hadoop2.4.0.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-api-jdo-3.2.6.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-rdbms-3.2.9.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-core-3.2.10.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/conf":"System Classpath"}} +{"Event":"SparkListenerApplicationStart","App Name":"Spark shell","App ID":"local-1425081759269","Timestamp":1425081758277,"User":"irashid"} +{"Event":"SparkListenerJobStart","Job ID":0,"Stage Infos":[{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"count at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[0]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"count at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1425081762075,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1425081762081,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1425081762081,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1425081762082,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1425081762083,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1425081762084,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1425081762084,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1425081762085,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1425081762084,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081762632,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":521,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_6","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1425081762081,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081762633,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":520,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_2","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1425081762082,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081762634,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":521,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_3","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1425081762084,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081762634,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":522,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_5","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1425081762083,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081762635,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":522,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_4","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1425081762075,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081762636,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":11,"Executor Run Time":522,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_0","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1425081762085,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081762636,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":9,"Executor Run Time":521,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_7","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1425081762081,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081762637,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":11,"Executor Run Time":522,"Result Size":1268,"JVM GC Time":20,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Updated Blocks":[{"Block ID":"rdd_0_1","Status":{"Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Memory Size":3500016,"Tachyon Size":0,"Disk Size":0}}]}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"count at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":8,"Memory Size":28000128,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1425081762069,"Completion Time":1425081762637,"Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":0,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerJobStart","Job ID":1,"Stage Infos":[{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"map at :14","Number of Tasks":8,"RDD Info":[{"RDD ID":1,"Name":"1","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]},{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"first at :17","Number of Tasks":1,"RDD Info":[{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.first(RDD.scala:1093)\n$line11.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line11.$read$$iwC$$iwC$$iwC.(:22)\n$line11.$read$$iwC$$iwC.(:24)\n$line11.$read$$iwC.(:26)\n$line11.$read.(:28)\n$line11.$read$.(:32)\n$line11.$read$.()\n$line11.$eval$.(:7)\n$line11.$eval$.()\n$line11.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[1,2]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"map at :14","Number of Tasks":8,"RDD Info":[{"RDD ID":1,"Name":"1","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":8,"Index":0,"Attempt":0,"Launch Time":1425081763578,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":9,"Index":1,"Attempt":0,"Launch Time":1425081763578,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":10,"Index":2,"Attempt":0,"Launch Time":1425081763579,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":11,"Index":3,"Attempt":0,"Launch Time":1425081763579,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":12,"Index":4,"Attempt":0,"Launch Time":1425081763580,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":13,"Index":5,"Attempt":0,"Launch Time":1425081763580,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":14,"Index":6,"Attempt":0,"Launch Time":1425081763581,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":15,"Index":7,"Attempt":0,"Launch Time":1425081763581,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":10,"Index":2,"Attempt":0,"Launch Time":1425081763579,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764001,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":406,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":138000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":9,"Index":1,"Attempt":0,"Launch Time":1425081763578,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764002,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":106000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":12,"Index":4,"Attempt":0,"Launch Time":1425081763580,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764002,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1645,"Shuffle Write Time":99000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":8,"Index":0,"Attempt":0,"Launch Time":1425081763578,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764003,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":123000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":15,"Index":7,"Attempt":0,"Launch Time":1425081763581,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764003,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":406,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":108000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":11,"Index":3,"Attempt":0,"Launch Time":1425081763579,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764004,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1647,"Shuffle Write Time":97000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":14,"Index":6,"Attempt":0,"Launch Time":1425081763581,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764004,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":132000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":13,"Index":5,"Attempt":0,"Launch Time":1425081763580,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764005,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":407,"Result Size":1902,"JVM GC Time":18,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1648,"Shuffle Write Time":81000},"Input Metrics":{"Data Read Method":"Memory","Bytes Read":3500016}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"map at :14","Number of Tasks":8,"RDD Info":[{"RDD ID":1,"Name":"1","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1425081763578,"Completion Time":1425081764005,"Accumulables":[]}} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"first at :17","Number of Tasks":1,"RDD Info":[{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.first(RDD.scala:1093)\n$line11.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line11.$read$$iwC$$iwC$$iwC.(:22)\n$line11.$read$$iwC$$iwC.(:24)\n$line11.$read$$iwC.(:26)\n$line11.$read.(:28)\n$line11.$read$.(:32)\n$line11.$read$.()\n$line11.$eval$.(:7)\n$line11.$eval$.()\n$line11.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":2,"Stage Attempt ID":0,"Task Info":{"Task ID":16,"Index":0,"Attempt":0,"Launch Time":1425081764014,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":2,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":16,"Index":0,"Attempt":0,"Launch Time":1425081764014,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764045,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":0,"Executor Run Time":28,"Result Size":1013,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"first at :17","Number of Tasks":1,"RDD Info":[{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.first(RDD.scala:1093)\n$line11.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line11.$read$$iwC$$iwC$$iwC.(:22)\n$line11.$read$$iwC$$iwC.(:24)\n$line11.$read$$iwC.(:26)\n$line11.$read.(:28)\n$line11.$read$.(:32)\n$line11.$read$.()\n$line11.$eval$.(:7)\n$line11.$eval$.()\n$line11.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1425081764014,"Completion Time":1425081764045,"Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":1,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerJobStart","Job ID":2,"Stage Infos":[{"Stage ID":3,"Stage Attempt ID":0,"Stage Name":"map at :14","Number of Tasks":8,"RDD Info":[{"RDD ID":1,"Name":"1","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":true,"Use Tachyon":false,"Deserialized":true,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:271)\n$line10.$read$$iwC$$iwC$$iwC$$iwC.(:14)\n$line10.$read$$iwC$$iwC$$iwC.(:19)\n$line10.$read$$iwC$$iwC.(:21)\n$line10.$read$$iwC.(:23)\n$line10.$read.(:25)\n$line10.$read$.(:29)\n$line10.$read$.()\n$line10.$eval$.(:7)\n$line10.$eval$.()\n$line10.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]},{"Stage ID":4,"Stage Attempt ID":0,"Stage Name":"saveAsTextFile at :19","Number of Tasks":8,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1164)\n$line13.$read$$iwC$$iwC$$iwC$$iwC.(:19)\n$line13.$read$$iwC$$iwC$$iwC.(:24)\n$line13.$read$$iwC$$iwC.(:26)\n$line13.$read$$iwC.(:28)\n$line13.$read.(:30)\n$line13.$read$.(:34)\n$line13.$read$.()\n$line13.$eval$.(:7)\n$line13.$eval$.()\n$line13.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[3,4]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":4,"Stage Attempt ID":0,"Stage Name":"saveAsTextFile at :19","Number of Tasks":8,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1164)\n$line13.$read$$iwC$$iwC$$iwC$$iwC.(:19)\n$line13.$read$$iwC$$iwC$$iwC.(:24)\n$line13.$read$$iwC$$iwC.(:26)\n$line13.$read$$iwC.(:28)\n$line13.$read.(:30)\n$line13.$read$.(:34)\n$line13.$read$.()\n$line13.$eval$.(:7)\n$line13.$eval$.()\n$line13.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":17,"Index":0,"Attempt":0,"Launch Time":1425081764396,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":18,"Index":1,"Attempt":0,"Launch Time":1425081764396,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":19,"Index":2,"Attempt":0,"Launch Time":1425081764397,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":20,"Index":3,"Attempt":0,"Launch Time":1425081764397,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":21,"Index":4,"Attempt":0,"Launch Time":1425081764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":22,"Index":5,"Attempt":0,"Launch Time":1425081764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":23,"Index":6,"Attempt":0,"Launch Time":1425081764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":4,"Stage Attempt ID":0,"Task Info":{"Task ID":24,"Index":7,"Attempt":0,"Launch Time":1425081764399,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":24,"Index":7,"Attempt":0,"Launch Time":1425081764399,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764642,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":240,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":19,"Index":2,"Attempt":0,"Launch Time":1425081764397,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764643,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":241,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":21,"Index":4,"Attempt":0,"Launch Time":1425081764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764643,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":240,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":22,"Index":5,"Attempt":0,"Launch Time":1425081764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764645,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":241,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":23,"Index":6,"Attempt":0,"Launch Time":1425081764398,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764645,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":241,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":17,"Index":0,"Attempt":0,"Launch Time":1425081764396,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764646,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":243,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":18,"Index":1,"Attempt":0,"Launch Time":1425081764396,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764646,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":243,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerTaskEnd","Stage ID":4,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":20,"Index":3,"Attempt":0,"Launch Time":1425081764397,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081764648,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":247,"Result Size":824,"JVM GC Time":31,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":8,"Fetch Wait Time":0,"Remote Bytes Read":0}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":4,"Stage Attempt ID":0,"Stage Name":"saveAsTextFile at :19","Number of Tasks":8,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1164)\n$line13.$read$$iwC$$iwC$$iwC$$iwC.(:19)\n$line13.$read$$iwC$$iwC$$iwC.(:24)\n$line13.$read$$iwC$$iwC.(:26)\n$line13.$read$$iwC.(:28)\n$line13.$read.(:30)\n$line13.$read$.(:34)\n$line13.$read$.()\n$line13.$eval$.(:7)\n$line13.$eval$.()\n$line13.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1425081764396,"Completion Time":1425081764648,"Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":2,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerJobStart","Job ID":3,"Stage Infos":[{"Stage ID":5,"Stage Attempt ID":0,"Stage Name":"count at :17","Number of Tasks":8,"RDD Info":[{"RDD ID":5,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":4,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line15.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line15.$read$$iwC$$iwC$$iwC.(:22)\n$line15.$read$$iwC$$iwC.(:24)\n$line15.$read$$iwC.(:26)\n$line15.$read.(:28)\n$line15.$read$.(:32)\n$line15.$read$.()\n$line15.$eval$.(:7)\n$line15.$eval$.()\n$line15.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[5]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":5,"Stage Attempt ID":0,"Stage Name":"count at :17","Number of Tasks":8,"RDD Info":[{"RDD ID":5,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":4,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line15.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line15.$read$$iwC$$iwC$$iwC.(:22)\n$line15.$read$$iwC$$iwC.(:24)\n$line15.$read$$iwC.(:26)\n$line15.$read.(:28)\n$line15.$read$.(:32)\n$line15.$read$.()\n$line15.$eval$.(:7)\n$line15.$eval$.()\n$line15.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":25,"Index":0,"Attempt":0,"Launch Time":1425081765026,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":26,"Index":1,"Attempt":0,"Launch Time":1425081765026,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":27,"Index":2,"Attempt":0,"Launch Time":1425081765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":28,"Index":3,"Attempt":0,"Launch Time":1425081765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":29,"Index":4,"Attempt":0,"Launch Time":1425081765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":30,"Index":5,"Attempt":0,"Launch Time":1425081765028,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":31,"Index":6,"Attempt":0,"Launch Time":1425081765028,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":32,"Index":7,"Attempt":0,"Launch Time":1425081765029,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":27,"Index":2,"Attempt":0,"Launch Time":1425081765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081765045,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":13,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":30,"Index":5,"Attempt":0,"Launch Time":1425081765028,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081765046,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":13,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":25,"Index":0,"Attempt":0,"Launch Time":1425081765026,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081765046,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":12,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":32}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":29,"Index":4,"Attempt":0,"Launch Time":1425081765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081765047,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":13,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":28,"Index":3,"Attempt":0,"Launch Time":1425081765027,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081765047,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":12,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":32,"Index":7,"Attempt":0,"Launch Time":1425081765029,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081765048,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":13,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":31,"Index":6,"Attempt":0,"Launch Time":1425081765028,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081765048,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":14,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":16}}} +{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":26,"Index":1,"Attempt":0,"Launch Time":1425081765026,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1425081765049,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":12,"Result Size":1812,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":32}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":5,"Stage Attempt ID":0,"Stage Name":"count at :17","Number of Tasks":8,"RDD Info":[{"RDD ID":5,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":4,"Name":"/Users/irashid/spark-examples/tmp_data/sums","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.count(RDD.scala:910)\n$line15.$read$$iwC$$iwC$$iwC$$iwC.(:17)\n$line15.$read$$iwC$$iwC$$iwC.(:22)\n$line15.$read$$iwC$$iwC.(:24)\n$line15.$read$$iwC.(:26)\n$line15.$read.(:28)\n$line15.$read$.(:32)\n$line15.$read$.()\n$line15.$eval$.(:7)\n$line15.$eval$.()\n$line15.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:606)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1425081765026,"Completion Time":1425081765050,"Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":3,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerApplicationEnd","Timestamp":1425081766912} diff --git a/core/src/test/resources/spark-events/local-1425081759269/SPARK_VERSION_1.2.0 b/core/src/test/resources/spark-events/local-1425081759269/SPARK_VERSION_1.2.0 new file mode 100755 index 0000000000000..e69de29bb2d1d diff --git a/core/src/test/resources/spark-events/local-1426533911241/APPLICATION_COMPLETE b/core/src/test/resources/spark-events/local-1426533911241/APPLICATION_COMPLETE new file mode 100755 index 0000000000000..e69de29bb2d1d diff --git a/core/src/test/resources/spark-events/local-1426533911241/EVENT_LOG_1 b/core/src/test/resources/spark-events/local-1426533911241/EVENT_LOG_1 new file mode 100755 index 0000000000000..9ef5bd5d92de5 --- /dev/null +++ b/core/src/test/resources/spark-events/local-1426533911241/EVENT_LOG_1 @@ -0,0 +1,24 @@ +{"Event":"SparkListenerBlockManagerAdded","Block Manager ID":{"Executor ID":"","Host":"localhost","Port":58610},"Maximum Memory":278019440,"Timestamp":1426533911361} +{"Event":"SparkListenerEnvironmentUpdate","JVM Information":{"Java Home":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre","Java Version":"1.8.0_25 (Oracle Corporation)","Scala Version":"version 2.10.4"},"Spark Properties":{"spark.driver.host":"192.168.1.105","spark.eventLog.enabled":"true","spark.driver.port":"58608","spark.repl.class.uri":"http://192.168.1.105:58607","spark.jars":"","spark.app.name":"Spark shell","spark.scheduler.mode":"FIFO","spark.executor.id":"driver","spark.master":"local[*]","spark.fileserver.uri":"http://192.168.1.105:58609","spark.tachyonStore.folderName":"spark-5e9b7f26-8e97-4b43-82d6-25c141530da9","spark.app.id":"local-1426533911241"},"System Properties":{"java.io.tmpdir":"/var/folders/36/m29jw1z95qv4ywb1c4n0rz000000gp/T/","line.separator":"\n","path.separator":":","sun.management.compiler":"HotSpot 64-Bit Tiered Compilers","SPARK_SUBMIT":"true","sun.cpu.endian":"little","java.specification.version":"1.8","java.vm.specification.name":"Java Virtual Machine Specification","java.vendor":"Oracle Corporation","java.vm.specification.version":"1.8","user.home":"/Users/irashid","file.encoding.pkg":"sun.io","sun.nio.ch.bugLevel":"","ftp.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","sun.arch.data.model":"64","sun.boot.library.path":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib","user.dir":"/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4","java.library.path":"/Users/irashid/Library/Java/Extensions:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java:.","sun.cpu.isalist":"","os.arch":"x86_64","java.vm.version":"25.25-b02","java.endorsed.dirs":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/endorsed","java.runtime.version":"1.8.0_25-b17","java.vm.info":"mixed mode","java.ext.dirs":"/Users/irashid/Library/Java/Extensions:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java","java.runtime.name":"Java(TM) SE Runtime Environment","file.separator":"/","java.class.version":"52.0","java.specification.name":"Java Platform API Specification","sun.boot.class.path":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/resources.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/rt.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/sunrsasign.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jsse.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jce.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/charsets.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jfr.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/classes","file.encoding":"UTF-8","user.timezone":"America/Chicago","java.specification.vendor":"Oracle Corporation","sun.java.launcher":"SUN_STANDARD","os.version":"10.9.5","sun.os.patch.level":"unknown","gopherProxySet":"false","java.vm.specification.vendor":"Oracle Corporation","user.country":"US","sun.jnu.encoding":"UTF-8","http.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","user.language":"en","socksNonProxyHosts":"local|*.local|169.254/16|*.169.254/16","java.vendor.url":"http://java.oracle.com/","java.awt.printerjob":"sun.lwawt.macosx.CPrinterJob","java.awt.graphicsenv":"sun.awt.CGraphicsEnvironment","awt.toolkit":"sun.lwawt.macosx.LWCToolkit","os.name":"Mac OS X","java.vm.vendor":"Oracle Corporation","java.vendor.url.bug":"http://bugreport.sun.com/bugreport/","user.name":"irashid","java.vm.name":"Java HotSpot(TM) 64-Bit Server VM","sun.java.command":"org.apache.spark.deploy.SparkSubmit --class org.apache.spark.repl.Main --conf spark.eventLog.enabled=true spark-shell","java.home":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre","java.version":"1.8.0_25","sun.io.unicode.encoding":"UnicodeBig"},"Classpath Entries":{"/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/spark-assembly-1.2.0-hadoop2.4.0.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-api-jdo-3.2.6.jar":"System Classpath","/etc/hadoop":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-rdbms-3.2.9.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-core-3.2.10.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/conf":"System Classpath"}} +{"Event":"SparkListenerApplicationStart","App Name":"Spark shell","App ID":"local-1426533911241","Timestamp":1426533910242,"User":"irashid","App Attempt ID":"1"} +{"Event":"SparkListenerJobStart","Job ID":0,"Stage Infos":[{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"foreach at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.foreach(RDD.scala:765)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[0]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"foreach at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.foreach(RDD.scala:765)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1426533936515,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1426533936521,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1426533936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1426533936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1426533936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1426533936523,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1426533936523,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1426533936524,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1426533936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426533936570,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"378","Value":"378"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":13,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1426533936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426533936572,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"572","Value":"950"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":13,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1426533936523,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426533936574,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"978","Value":"1928"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1426533936521,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426533936574,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"247","Value":"2175"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":14,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1426533936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426533936574,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"678","Value":"2853"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1426533936523,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426533936575,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"897","Value":"3750"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1426533936524,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426533936575,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"1222","Value":"4972"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1426533936515,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426533936576,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"78","Value":"5050"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":14,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"foreach at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.foreach(RDD.scala:765)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1426533936103,"Completion Time":1426533936579,"Accumulables":[{"ID":1,"Name":"my counter","Value":"5050"}]}} +{"Event":"SparkListenerJobEnd","Job ID":0,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerApplicationEnd","Timestamp":1426533945177} diff --git a/core/src/test/resources/spark-events/local-1426533911241/SPARK_VERSION_1.2.0 b/core/src/test/resources/spark-events/local-1426533911241/SPARK_VERSION_1.2.0 new file mode 100755 index 0000000000000..e69de29bb2d1d diff --git a/core/src/test/resources/spark-events/local-1426633911242/APPLICATION_COMPLETE b/core/src/test/resources/spark-events/local-1426633911242/APPLICATION_COMPLETE new file mode 100755 index 0000000000000..e69de29bb2d1d diff --git a/core/src/test/resources/spark-events/local-1426633911242/EVENT_LOG_1 b/core/src/test/resources/spark-events/local-1426633911242/EVENT_LOG_1 new file mode 100755 index 0000000000000..e7043282107d3 --- /dev/null +++ b/core/src/test/resources/spark-events/local-1426633911242/EVENT_LOG_1 @@ -0,0 +1,24 @@ +{"Event":"SparkListenerBlockManagerAdded","Block Manager ID":{"Executor ID":"","Host":"localhost","Port":58610},"Maximum Memory":278019440,"Timestamp":1426633911361} +{"Event":"SparkListenerEnvironmentUpdate","JVM Information":{"Java Home":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre","Java Version":"1.8.0_25 (Oracle Corporation)","Scala Version":"version 2.10.4"},"Spark Properties":{"spark.driver.host":"192.168.1.105","spark.eventLog.enabled":"true","spark.driver.port":"58608","spark.repl.class.uri":"http://192.168.1.105:58607","spark.jars":"","spark.app.name":"Spark shell","spark.scheduler.mode":"FIFO","spark.executor.id":"driver","spark.master":"local[*]","spark.fileserver.uri":"http://192.168.1.105:58609","spark.tachyonStore.folderName":"spark-5e9b7f26-8e97-4b43-82d6-25c141530da9","spark.app.id":"local-1426633911241"},"System Properties":{"java.io.tmpdir":"/var/folders/36/m29jw1z95qv4ywb1c4n0rz000000gp/T/","line.separator":"\n","path.separator":":","sun.management.compiler":"HotSpot 64-Bit Tiered Compilers","SPARK_SUBMIT":"true","sun.cpu.endian":"little","java.specification.version":"1.8","java.vm.specification.name":"Java Virtual Machine Specification","java.vendor":"Oracle Corporation","java.vm.specification.version":"1.8","user.home":"/Users/irashid","file.encoding.pkg":"sun.io","sun.nio.ch.bugLevel":"","ftp.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","sun.arch.data.model":"64","sun.boot.library.path":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib","user.dir":"/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4","java.library.path":"/Users/irashid/Library/Java/Extensions:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java:.","sun.cpu.isalist":"","os.arch":"x86_64","java.vm.version":"25.25-b02","java.endorsed.dirs":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/endorsed","java.runtime.version":"1.8.0_25-b17","java.vm.info":"mixed mode","java.ext.dirs":"/Users/irashid/Library/Java/Extensions:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java","java.runtime.name":"Java(TM) SE Runtime Environment","file.separator":"/","java.class.version":"52.0","java.specification.name":"Java Platform API Specification","sun.boot.class.path":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/resources.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/rt.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/sunrsasign.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jsse.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jce.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/charsets.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jfr.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/classes","file.encoding":"UTF-8","user.timezone":"America/Chicago","java.specification.vendor":"Oracle Corporation","sun.java.launcher":"SUN_STANDARD","os.version":"10.9.5","sun.os.patch.level":"unknown","gopherProxySet":"false","java.vm.specification.vendor":"Oracle Corporation","user.country":"US","sun.jnu.encoding":"UTF-8","http.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","user.language":"en","socksNonProxyHosts":"local|*.local|169.254/16|*.169.254/16","java.vendor.url":"http://java.oracle.com/","java.awt.printerjob":"sun.lwawt.macosx.CPrinterJob","java.awt.graphicsenv":"sun.awt.CGraphicsEnvironment","awt.toolkit":"sun.lwawt.macosx.LWCToolkit","os.name":"Mac OS X","java.vm.vendor":"Oracle Corporation","java.vendor.url.bug":"http://bugreport.sun.com/bugreport/","user.name":"irashid","java.vm.name":"Java HotSpot(TM) 64-Bit Server VM","sun.java.command":"org.apache.spark.deploy.SparkSubmit --class org.apache.spark.repl.Main --conf spark.eventLog.enabled=true spark-shell","java.home":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre","java.version":"1.8.0_25","sun.io.unicode.encoding":"UnicodeBig"},"Classpath Entries":{"/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/spark-assembly-1.2.0-hadoop2.4.0.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-api-jdo-3.2.6.jar":"System Classpath","/etc/hadoop":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-rdbms-3.2.9.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/lib/datanucleus-core-3.2.10.jar":"System Classpath","/Users/irashid/spark-examples/releases/spark-1.2.0-bin-hadoop2.4/conf":"System Classpath"}} +{"Event":"SparkListenerApplicationStart","App Name":"Spark shell","App ID":"local-1426533911241","Timestamp":1426633910242,"User":"irashid","App Attempt ID":"2"} +{"Event":"SparkListenerJobStart","Job ID":0,"Stage Infos":[{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"foreach at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.foreach(RDD.scala:765)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}],"Stage IDs":[0]} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"foreach at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.foreach(RDD.scala:765)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1426633936515,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1426633936521,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1426633936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1426633936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1426633936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1426633936523,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1426633936523,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1426633936524,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1426633936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426633936570,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"378","Value":"378"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":13,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1426633936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426633936572,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"572","Value":"950"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":13,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1426633936523,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426633936574,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"978","Value":"1928"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1426633936521,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426633936574,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"247","Value":"2175"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":14,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1426633936522,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426633936574,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"678","Value":"2853"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1426633936523,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426633936575,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"897","Value":"3750"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1426633936524,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426633936575,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"1222","Value":"4972"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1426633936515,"Executor ID":"","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1426633936576,"Failed":false,"Accumulables":[{"ID":1,"Name":"my counter","Update":"78","Value":"5050"}]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":14,"Executor Run Time":15,"Result Size":697,"JVM GC Time":0,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"foreach at :15","Number of Tasks":8,"RDD Info":[{"RDD ID":0,"Name":"0","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":8,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.foreach(RDD.scala:765)\n$line9.$read$$iwC$$iwC$$iwC$$iwC.(:15)\n$line9.$read$$iwC$$iwC$$iwC.(:20)\n$line9.$read$$iwC$$iwC.(:22)\n$line9.$read$$iwC.(:24)\n$line9.$read.(:26)\n$line9.$read$.(:30)\n$line9.$read$.()\n$line9.$eval$.(:7)\n$line9.$eval$.()\n$line9.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)\norg.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)\norg.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)\norg.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)","Submission Time":1426633936103,"Completion Time":1426633936579,"Accumulables":[{"ID":1,"Name":"my counter","Value":"5050"}]}} +{"Event":"SparkListenerJobEnd","Job ID":0,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerApplicationEnd","Timestamp":1426633945177} diff --git a/core/src/test/resources/spark-events/local-1426633911242/SPARK_VERSION_1.2.0 b/core/src/test/resources/spark-events/local-1426633911242/SPARK_VERSION_1.2.0 new file mode 100755 index 0000000000000..e69de29bb2d1d diff --git a/core/src/test/resources/spark-events/local-1430917381534 b/core/src/test/resources/spark-events/local-1430917381534 new file mode 100755 index 0000000000000..24ac478073e3d --- /dev/null +++ b/core/src/test/resources/spark-events/local-1430917381534 @@ -0,0 +1,231 @@ +{"Event":"SparkListenerLogStart","Spark Version":"1.4.0-SNAPSHOT"} +{"Event":"SparkListenerBlockManagerAdded","Block Manager ID":{"Executor ID":"driver","Host":"localhost","Port":61103},"Maximum Memory":278019440,"Timestamp":1430917381651} +{"Event":"SparkListenerEnvironmentUpdate","JVM Information":{"Java Home":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre","Java Version":"1.8.0_25 (Oracle Corporation)","Scala Version":"version 2.10.4"},"Spark Properties":{"spark.driver.host":"192.168.1.102","spark.eventLog.enabled":"true","spark.driver.port":"61101","spark.repl.class.uri":"http://192.168.1.102:61100","spark.jars":"","spark.app.name":"Spark shell","spark.scheduler.mode":"FIFO","spark.executor.id":"driver","spark.master":"local[*]","spark.eventLog.dir":"/Users/irashid/github/kraps/core/src/test/resources/spark-events","spark.fileserver.uri":"http://192.168.1.102:61102","spark.tachyonStore.folderName":"spark-aaaf41b3-d1dd-447f-8951-acf51490758b","spark.app.id":"local-1430917381534"},"System Properties":{"java.io.tmpdir":"/var/folders/36/m29jw1z95qv4ywb1c4n0rz000000gp/T/","line.separator":"\n","path.separator":":","sun.management.compiler":"HotSpot 64-Bit Tiered Compilers","SPARK_SUBMIT":"true","sun.cpu.endian":"little","java.specification.version":"1.8","java.vm.specification.name":"Java Virtual Machine Specification","java.vendor":"Oracle Corporation","java.vm.specification.version":"1.8","user.home":"/Users/irashid","file.encoding.pkg":"sun.io","sun.nio.ch.bugLevel":"","ftp.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","sun.arch.data.model":"64","sun.boot.library.path":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib","user.dir":"/Users/irashid/github/spark","java.library.path":"/Users/irashid/Library/Java/Extensions:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java:.","sun.cpu.isalist":"","os.arch":"x86_64","java.vm.version":"25.25-b02","java.endorsed.dirs":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/endorsed","java.runtime.version":"1.8.0_25-b17","java.vm.info":"mixed mode","java.ext.dirs":"/Users/irashid/Library/Java/Extensions:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext:/Library/Java/Extensions:/Network/Library/Java/Extensions:/System/Library/Java/Extensions:/usr/lib/java","java.runtime.name":"Java(TM) SE Runtime Environment","file.separator":"/","java.class.version":"52.0","scala.usejavacp":"true","java.specification.name":"Java Platform API Specification","sun.boot.class.path":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/resources.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/rt.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/sunrsasign.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jsse.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jce.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/charsets.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jfr.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/classes","file.encoding":"UTF-8","user.timezone":"America/Chicago","java.specification.vendor":"Oracle Corporation","sun.java.launcher":"SUN_STANDARD","os.version":"10.9.5","sun.os.patch.level":"unknown","gopherProxySet":"false","java.vm.specification.vendor":"Oracle Corporation","user.country":"US","sun.jnu.encoding":"UTF-8","http.nonProxyHosts":"local|*.local|169.254/16|*.169.254/16","user.language":"en","socksNonProxyHosts":"local|*.local|169.254/16|*.169.254/16","java.vendor.url":"http://java.oracle.com/","java.awt.printerjob":"sun.lwawt.macosx.CPrinterJob","java.awt.graphicsenv":"sun.awt.CGraphicsEnvironment","awt.toolkit":"sun.lwawt.macosx.LWCToolkit","os.name":"Mac OS X","java.vm.vendor":"Oracle Corporation","java.vendor.url.bug":"http://bugreport.sun.com/bugreport/","user.name":"irashid","java.vm.name":"Java HotSpot(TM) 64-Bit Server VM","sun.java.command":"org.apache.spark.deploy.SparkSubmit --conf spark.eventLog.enabled=true --conf spark.eventLog.dir=/Users/irashid/github/kraps/core/src/test/resources/spark-events --class org.apache.spark.repl.Main spark-shell","java.home":"/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre","java.version":"1.8.0_25","sun.io.unicode.encoding":"UnicodeBig"},"Classpath Entries":{"/etc/hadoop":"System Classpath","/Users/irashid/github/spark/lib_managed/jars/datanucleus-rdbms-3.2.9.jar":"System Classpath","/Users/irashid/github/spark/conf/":"System Classpath","/Users/irashid/github/spark/assembly/target/scala-2.10/spark-assembly-1.4.0-SNAPSHOT-hadoop2.5.0.jar":"System Classpath","/Users/irashid/github/spark/lib_managed/jars/datanucleus-core-3.2.10.jar":"System Classpath","/Users/irashid/github/spark/lib_managed/jars/datanucleus-api-jdo-3.2.6.jar":"System Classpath"}} +{"Event":"SparkListenerApplicationStart","App Name":"Spark shell","App ID":"local-1430917381534","Timestamp":1430917380893,"User":"irashid"} +{"Event":"SparkListenerJobStart","Job ID":0,"Submission Time":1430917386422,"Stage Infos":[{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"map at :26","Number of Tasks":100,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"/Users/irashid/spark-examples/tmp_data/raw_data","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":1,"Name":"/Users/irashid/spark-examples/tmp_data/raw_data","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:287)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:26)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:31)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:33)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC.(:35)\n$line20.$read$$iwC$$iwC$$iwC$$iwC.(:37)\n$line20.$read$$iwC$$iwC$$iwC.(:39)\n$line20.$read$$iwC$$iwC.(:41)\n$line20.$read$$iwC.(:43)\n$line20.$read.(:45)\n$line20.$read$.(:49)\n$line20.$read$.()\n$line20.$eval$.(:7)\n$line20.$eval$.()\n$line20.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)","Accumulables":[]},{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"collect at :26","Number of Tasks":10,"RDD Info":[{"RDD ID":4,"Name":"4","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":10,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.collect(RDD.scala:819)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:26)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:31)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:33)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC.(:35)\n$line20.$read$$iwC$$iwC$$iwC$$iwC.(:37)\n$line20.$read$$iwC$$iwC$$iwC.(:39)\n$line20.$read$$iwC$$iwC.(:41)\n$line20.$read$$iwC.(:43)\n$line20.$read.(:45)\n$line20.$read$.(:49)\n$line20.$read$.()\n$line20.$eval$.(:7)\n$line20.$eval$.()\n$line20.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)","Accumulables":[]}],"Stage IDs":[0,1],"Properties":{}} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"map at :26","Number of Tasks":100,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"/Users/irashid/spark-examples/tmp_data/raw_data","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":1,"Name":"/Users/irashid/spark-examples/tmp_data/raw_data","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:287)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:26)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:31)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:33)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC.(:35)\n$line20.$read$$iwC$$iwC$$iwC$$iwC.(:37)\n$line20.$read$$iwC$$iwC$$iwC.(:39)\n$line20.$read$$iwC$$iwC.(:41)\n$line20.$read$$iwC.(:43)\n$line20.$read.(:45)\n$line20.$read$.(:49)\n$line20.$read$.()\n$line20.$eval$.(:7)\n$line20.$eval$.()\n$line20.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)","Accumulables":[]},"Properties":{}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1430917386494,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1430917386502,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1430917386503,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1430917386504,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1430917386504,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1430917386505,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1430917386505,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1430917386506,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":8,"Index":8,"Attempt":0,"Launch Time":1430917386914,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":9,"Index":9,"Attempt":0,"Launch Time":1430917386915,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":10,"Index":10,"Attempt":0,"Launch Time":1430917386916,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":11,"Index":11,"Attempt":0,"Launch Time":1430917386918,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":5,"Index":5,"Attempt":0,"Launch Time":1430917386505,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917386919,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":30,"Executor Run Time":350,"Result Size":2010,"JVM GC Time":7,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":3675510,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":60488,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":2,"Index":2,"Attempt":0,"Launch Time":1430917386503,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917386922,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":32,"Executor Run Time":348,"Result Size":2010,"JVM GC Time":7,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":89885,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":60488,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":1,"Index":1,"Attempt":0,"Launch Time":1430917386502,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917386923,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":31,"Executor Run Time":350,"Result Size":2010,"JVM GC Time":7,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":3934399,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":60488,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":4,"Index":4,"Attempt":0,"Launch Time":1430917386504,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917386923,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":31,"Executor Run Time":349,"Result Size":2010,"JVM GC Time":7,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":83022,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":60488,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":12,"Index":12,"Attempt":0,"Launch Time":1430917386923,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387016,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":6,"Index":6,"Attempt":0,"Launch Time":1430917386505,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917386924,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":29,"Executor Run Time":351,"Result Size":2010,"JVM GC Time":7,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":4016617,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":60488,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":13,"Index":13,"Attempt":0,"Launch Time":1430917386924,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387062,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":14,"Index":14,"Attempt":0,"Launch Time":1430917386925,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387019,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":3,"Index":3,"Attempt":0,"Launch Time":1430917386504,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917386927,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":31,"Executor Run Time":349,"Result Size":2010,"JVM GC Time":7,"Result Serialization Time":2,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":1311694,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":60488,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":15,"Index":15,"Attempt":0,"Launch Time":1430917386928,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387011,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Launch Time":1430917386494,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917386929,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":32,"Executor Run Time":349,"Result Size":2010,"JVM GC Time":7,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":3842811,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":49294,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":7,"Index":7,"Attempt":0,"Launch Time":1430917386506,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917386929,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":31,"Executor Run Time":349,"Result Size":2010,"JVM GC Time":7,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":2579051,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":60488,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":16,"Index":16,"Attempt":0,"Launch Time":1430917387001,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387099,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":8,"Index":8,"Attempt":0,"Launch Time":1430917386914,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387002,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":80,"Result Size":2010,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":121551,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":60488,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":17,"Index":17,"Attempt":0,"Launch Time":1430917387005,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387128,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":11,"Index":11,"Attempt":0,"Launch Time":1430917386918,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387007,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":6,"Executor Run Time":75,"Result Size":2010,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":94507,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":18,"Index":18,"Attempt":0,"Launch Time":1430917387010,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387115,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":15,"Index":15,"Attempt":0,"Launch Time":1430917386928,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387011,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":76,"Result Size":2010,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":602780,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":19,"Index":19,"Attempt":0,"Launch Time":1430917387012,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387106,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":20,"Index":20,"Attempt":0,"Launch Time":1430917387014,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387104,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":21,"Index":21,"Attempt":0,"Launch Time":1430917387015,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387111,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":10,"Index":10,"Attempt":0,"Launch Time":1430917386916,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387015,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":8,"Executor Run Time":73,"Result Size":2010,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":94709,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":9,"Index":9,"Attempt":0,"Launch Time":1430917386915,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387016,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":9,"Executor Run Time":84,"Result Size":2010,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":101664,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":60489,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":12,"Index":12,"Attempt":0,"Launch Time":1430917386923,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387016,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":9,"Executor Run Time":77,"Result Size":2010,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":102476,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":22,"Index":22,"Attempt":0,"Launch Time":1430917387018,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387119,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":14,"Index":14,"Attempt":0,"Launch Time":1430917386925,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387019,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":6,"Executor Run Time":83,"Result Size":2010,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":95646,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":23,"Index":23,"Attempt":0,"Launch Time":1430917387031,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387115,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":13,"Index":13,"Attempt":0,"Launch Time":1430917386924,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387062,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":9,"Executor Run Time":76,"Result Size":2010,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":95004,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":24,"Index":24,"Attempt":0,"Launch Time":1430917387098,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":16,"Index":16,"Attempt":0,"Launch Time":1430917387001,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387099,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":84,"Result Size":2010,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":108320,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":25,"Index":25,"Attempt":0,"Launch Time":1430917387103,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":20,"Index":20,"Attempt":0,"Launch Time":1430917387014,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387104,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":83,"Result Size":2010,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":97716,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":26,"Index":26,"Attempt":0,"Launch Time":1430917387105,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":19,"Index":19,"Attempt":0,"Launch Time":1430917387012,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387106,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":84,"Result Size":2010,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":95788,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":27,"Index":27,"Attempt":0,"Launch Time":1430917387110,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":21,"Index":21,"Attempt":0,"Launch Time":1430917387015,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387111,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":88,"Result Size":2010,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":100270,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":28,"Index":28,"Attempt":0,"Launch Time":1430917387113,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":29,"Index":29,"Attempt":0,"Launch Time":1430917387114,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":23,"Index":23,"Attempt":0,"Launch Time":1430917387031,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387115,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":65,"Result Size":2010,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":91844,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":18,"Index":18,"Attempt":0,"Launch Time":1430917387010,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387115,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":92,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":100836,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":30,"Index":30,"Attempt":0,"Launch Time":1430917387118,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":22,"Index":22,"Attempt":0,"Launch Time":1430917387018,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387119,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":93,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":143427,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":31,"Index":31,"Attempt":0,"Launch Time":1430917387127,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":17,"Index":17,"Attempt":0,"Launch Time":1430917387005,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387128,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":11,"Executor Run Time":91,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":99944,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":32,"Index":32,"Attempt":0,"Launch Time":1430917387148,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":33,"Index":33,"Attempt":0,"Launch Time":1430917387149,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":24,"Index":24,"Attempt":0,"Launch Time":1430917387098,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387150,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":43,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":157194,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":27,"Index":27,"Attempt":0,"Launch Time":1430917387110,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387151,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":32,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":102019,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":34,"Index":34,"Attempt":0,"Launch Time":1430917387156,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":26,"Index":26,"Attempt":0,"Launch Time":1430917387105,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387157,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":6,"Executor Run Time":38,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":108213,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":35,"Index":35,"Attempt":0,"Launch Time":1430917387161,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":28,"Index":28,"Attempt":0,"Launch Time":1430917387113,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387162,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":29,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":104299,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":36,"Index":36,"Attempt":0,"Launch Time":1430917387164,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":25,"Index":25,"Attempt":0,"Launch Time":1430917387103,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387164,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":49,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":94134,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":37,"Index":37,"Attempt":0,"Launch Time":1430917387165,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":38,"Index":38,"Attempt":0,"Launch Time":1430917387166,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":29,"Index":29,"Attempt":0,"Launch Time":1430917387114,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387166,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":39,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":114938,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":39,"Index":39,"Attempt":0,"Launch Time":1430917387180,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":30,"Index":30,"Attempt":0,"Launch Time":1430917387118,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387180,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":4,"Executor Run Time":34,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":119770,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":32,"Index":32,"Attempt":0,"Launch Time":1430917387148,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387181,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":17,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":89603,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":40,"Index":40,"Attempt":0,"Launch Time":1430917387197,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":34,"Index":34,"Attempt":0,"Launch Time":1430917387156,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387198,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":6,"Executor Run Time":27,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":127746,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":41,"Index":41,"Attempt":0,"Launch Time":1430917387200,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":31,"Index":31,"Attempt":0,"Launch Time":1430917387127,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387201,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":36,"Executor Run Time":24,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":92619,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":42,"Index":42,"Attempt":0,"Launch Time":1430917387203,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":36,"Index":36,"Attempt":0,"Launch Time":1430917387164,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387204,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":29,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":123855,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":43,"Index":43,"Attempt":0,"Launch Time":1430917387204,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":44,"Index":44,"Attempt":0,"Launch Time":1430917387205,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":45,"Index":45,"Attempt":0,"Launch Time":1430917387206,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":37,"Index":37,"Attempt":0,"Launch Time":1430917387165,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387207,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":4,"Executor Run Time":32,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":111869,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":33,"Index":33,"Attempt":0,"Launch Time":1430917387149,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387207,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":43,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":118329,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":46,"Index":46,"Attempt":0,"Launch Time":1430917387210,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":35,"Index":35,"Attempt":0,"Launch Time":1430917387161,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387211,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":35,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":160963,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":47,"Index":47,"Attempt":0,"Launch Time":1430917387212,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":39,"Index":39,"Attempt":0,"Launch Time":1430917387180,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387212,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":17,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":98748,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":38,"Index":38,"Attempt":0,"Launch Time":1430917387166,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387213,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":31,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":131158,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":48,"Index":48,"Attempt":0,"Launch Time":1430917387220,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":40,"Index":40,"Attempt":0,"Launch Time":1430917387197,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387221,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":4,"Executor Run Time":14,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":94792,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":49,"Index":49,"Attempt":0,"Launch Time":1430917387223,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":41,"Index":41,"Attempt":0,"Launch Time":1430917387200,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387224,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":16,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":90765,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":50,"Index":50,"Attempt":0,"Launch Time":1430917387240,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":44,"Index":44,"Attempt":0,"Launch Time":1430917387205,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387242,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":18,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":98293,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":51,"Index":51,"Attempt":0,"Launch Time":1430917387242,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":52,"Index":52,"Attempt":0,"Launch Time":1430917387243,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":43,"Index":43,"Attempt":0,"Launch Time":1430917387204,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387243,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":16,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":171516,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":45,"Index":45,"Attempt":0,"Launch Time":1430917387206,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387243,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":19,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":92985,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":53,"Index":53,"Attempt":0,"Launch Time":1430917387244,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":54,"Index":54,"Attempt":0,"Launch Time":1430917387244,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":42,"Index":42,"Attempt":0,"Launch Time":1430917387203,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387245,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":10,"Executor Run Time":17,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":103713,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":47,"Index":47,"Attempt":0,"Launch Time":1430917387212,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387245,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":18,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":103015,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":55,"Index":55,"Attempt":0,"Launch Time":1430917387246,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":56,"Index":56,"Attempt":0,"Launch Time":1430917387249,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":48,"Index":48,"Attempt":0,"Launch Time":1430917387220,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387250,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":24,"Result Size":2065,"JVM GC Time":6,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":139844,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":46,"Index":46,"Attempt":0,"Launch Time":1430917387210,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387253,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":31,"Result Size":2065,"JVM GC Time":6,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":113322,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":57,"Index":57,"Attempt":0,"Launch Time":1430917387257,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":49,"Index":49,"Attempt":0,"Launch Time":1430917387223,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387257,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":7,"Executor Run Time":23,"Result Size":2065,"JVM GC Time":6,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":94984,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":58,"Index":58,"Attempt":0,"Launch Time":1430917387263,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":51,"Index":51,"Attempt":0,"Launch Time":1430917387242,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387263,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":17,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":96013,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":59,"Index":59,"Attempt":0,"Launch Time":1430917387265,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":50,"Index":50,"Attempt":0,"Launch Time":1430917387240,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387266,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":4,"Executor Run Time":18,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":90836,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":60,"Index":60,"Attempt":0,"Launch Time":1430917387269,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":61,"Index":61,"Attempt":0,"Launch Time":1430917387270,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":52,"Index":52,"Attempt":0,"Launch Time":1430917387243,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387271,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":18,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":89664,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":62,"Index":62,"Attempt":0,"Launch Time":1430917387272,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":53,"Index":53,"Attempt":0,"Launch Time":1430917387244,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387273,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":6,"Executor Run Time":18,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":92835,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":63,"Index":63,"Attempt":0,"Launch Time":1430917387276,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":55,"Index":55,"Attempt":0,"Launch Time":1430917387246,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387276,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":4,"Executor Run Time":21,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":108309,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":64,"Index":64,"Attempt":0,"Launch Time":1430917387277,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":57,"Index":57,"Attempt":0,"Launch Time":1430917387257,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387278,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":16,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":96849,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":65,"Index":65,"Attempt":0,"Launch Time":1430917387279,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":56,"Index":56,"Attempt":0,"Launch Time":1430917387249,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387280,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":20,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":90329,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":66,"Index":66,"Attempt":0,"Launch Time":1430917387285,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":58,"Index":58,"Attempt":0,"Launch Time":1430917387263,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387286,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":16,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":97521,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":67,"Index":67,"Attempt":0,"Launch Time":1430917387288,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":59,"Index":59,"Attempt":0,"Launch Time":1430917387265,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387288,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":17,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":100753,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":54,"Index":54,"Attempt":0,"Launch Time":1430917387244,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387303,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":18,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":90506,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":68,"Index":68,"Attempt":0,"Launch Time":1430917387306,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":60,"Index":60,"Attempt":0,"Launch Time":1430917387269,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387307,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":8,"Executor Run Time":28,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":156916,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":69,"Index":69,"Attempt":0,"Launch Time":1430917387308,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":62,"Index":62,"Attempt":0,"Launch Time":1430917387272,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387309,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":32,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":100396,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":70,"Index":70,"Attempt":0,"Launch Time":1430917387311,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":64,"Index":64,"Attempt":0,"Launch Time":1430917387277,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387311,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":25,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":104087,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":71,"Index":71,"Attempt":0,"Launch Time":1430917387313,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":72,"Index":72,"Attempt":0,"Launch Time":1430917387314,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":61,"Index":61,"Attempt":0,"Launch Time":1430917387270,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387315,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":4,"Executor Run Time":36,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":100426,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":73,"Index":73,"Attempt":0,"Launch Time":1430917387316,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":63,"Index":63,"Attempt":0,"Launch Time":1430917387276,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387316,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":20,"Executor Run Time":17,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":102779,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":74,"Index":74,"Attempt":0,"Launch Time":1430917387318,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":66,"Index":66,"Attempt":0,"Launch Time":1430917387285,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387319,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":27,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":100823,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":65,"Index":65,"Attempt":0,"Launch Time":1430917387279,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387321,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":27,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":99123,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":75,"Index":75,"Attempt":0,"Launch Time":1430917387323,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":67,"Index":67,"Attempt":0,"Launch Time":1430917387288,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387323,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":14,"Executor Run Time":19,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":92741,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":76,"Index":76,"Attempt":0,"Launch Time":1430917387327,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":68,"Index":68,"Attempt":0,"Launch Time":1430917387306,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387328,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":16,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":101750,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":77,"Index":77,"Attempt":0,"Launch Time":1430917387329,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":69,"Index":69,"Attempt":0,"Launch Time":1430917387308,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387331,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":18,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":89437,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":78,"Index":78,"Attempt":0,"Launch Time":1430917387338,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":71,"Index":71,"Attempt":0,"Launch Time":1430917387313,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387339,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":22,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":183323,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":79,"Index":79,"Attempt":0,"Launch Time":1430917387339,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":70,"Index":70,"Attempt":0,"Launch Time":1430917387311,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387340,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":24,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":105933,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":80,"Index":80,"Attempt":0,"Launch Time":1430917387341,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":74,"Index":74,"Attempt":0,"Launch Time":1430917387318,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387341,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":18,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":98047,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":81,"Index":81,"Attempt":0,"Launch Time":1430917387342,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":72,"Index":72,"Attempt":0,"Launch Time":1430917387314,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387343,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":22,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":139584,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":82,"Index":82,"Attempt":0,"Launch Time":1430917387349,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":75,"Index":75,"Attempt":0,"Launch Time":1430917387323,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387359,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":20,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":134733,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":83,"Index":83,"Attempt":0,"Launch Time":1430917387360,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":73,"Index":73,"Attempt":0,"Launch Time":1430917387316,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387360,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":16,"Executor Run Time":25,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":197728,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":84,"Index":84,"Attempt":0,"Launch Time":1430917387368,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":77,"Index":77,"Attempt":0,"Launch Time":1430917387329,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387368,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":30,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":104879,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":85,"Index":85,"Attempt":0,"Launch Time":1430917387371,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":76,"Index":76,"Attempt":0,"Launch Time":1430917387327,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387371,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":38,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":117198,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":86,"Index":86,"Attempt":0,"Launch Time":1430917387374,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":87,"Index":87,"Attempt":0,"Launch Time":1430917387374,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":79,"Index":79,"Attempt":0,"Launch Time":1430917387339,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387375,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":28,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":760569,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":80,"Index":80,"Attempt":0,"Launch Time":1430917387341,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387375,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":13,"Executor Run Time":18,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":98069,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":88,"Index":88,"Attempt":0,"Launch Time":1430917387376,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":78,"Index":78,"Attempt":0,"Launch Time":1430917387338,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387377,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":31,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":94029,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":89,"Index":89,"Attempt":0,"Launch Time":1430917387384,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":82,"Index":82,"Attempt":0,"Launch Time":1430917387349,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387385,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":23,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":103837,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":90,"Index":90,"Attempt":0,"Launch Time":1430917387385,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":81,"Index":81,"Attempt":0,"Launch Time":1430917387342,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387386,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":38,"Result Size":2065,"JVM GC Time":5,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":102935,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":91,"Index":91,"Attempt":0,"Launch Time":1430917387394,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":84,"Index":84,"Attempt":0,"Launch Time":1430917387368,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387395,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":22,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":97176,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":92,"Index":92,"Attempt":0,"Launch Time":1430917387400,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":85,"Index":85,"Attempt":0,"Launch Time":1430917387371,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387401,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":19,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":103743,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":93,"Index":93,"Attempt":0,"Launch Time":1430917387402,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":86,"Index":86,"Attempt":0,"Launch Time":1430917387374,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387402,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":16,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":95848,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":94,"Index":94,"Attempt":0,"Launch Time":1430917387404,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":83,"Index":83,"Attempt":0,"Launch Time":1430917387360,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387405,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":37,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":134049,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":95,"Index":95,"Attempt":0,"Launch Time":1430917387406,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":96,"Index":96,"Attempt":0,"Launch Time":1430917387406,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":97,"Index":97,"Attempt":0,"Launch Time":1430917387407,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":88,"Index":88,"Attempt":0,"Launch Time":1430917387376,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387407,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":19,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":94269,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":90,"Index":90,"Attempt":0,"Launch Time":1430917387385,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387408,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":17,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":98472,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":98,"Index":98,"Attempt":0,"Launch Time":1430917387410,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":87,"Index":87,"Attempt":0,"Launch Time":1430917387374,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387410,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":12,"Executor Run Time":17,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":102159,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":89,"Index":89,"Attempt":0,"Launch Time":1430917387384,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387417,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":18,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":97226,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":99,"Index":99,"Attempt":0,"Launch Time":1430917387426,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":91,"Index":91,"Attempt":0,"Launch Time":1430917387394,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387427,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":8,"Executor Run Time":21,"Result Size":2065,"JVM GC Time":4,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":98301,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":94,"Index":94,"Attempt":0,"Launch Time":1430917387404,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387441,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":5,"Executor Run Time":22,"Result Size":2065,"JVM GC Time":4,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":102455,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":92,"Index":92,"Attempt":0,"Launch Time":1430917387400,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387442,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":31,"Result Size":2065,"JVM GC Time":4,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":114766,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":96,"Index":96,"Attempt":0,"Launch Time":1430917387406,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387443,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":26,"Result Size":2065,"JVM GC Time":4,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":100678,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":93,"Index":93,"Attempt":0,"Launch Time":1430917387402,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387443,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":32,"Result Size":2065,"JVM GC Time":4,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":95818,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":95,"Index":95,"Attempt":0,"Launch Time":1430917387406,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387444,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":28,"Result Size":2065,"JVM GC Time":4,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":117803,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":98,"Index":98,"Attempt":0,"Launch Time":1430917387410,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387444,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":7,"Executor Run Time":22,"Result Size":2065,"JVM GC Time":4,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":105039,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":99,"Index":99,"Attempt":0,"Launch Time":1430917387426,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387448,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":17,"Result Size":2065,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":133964,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70565,"Records Read":10000}}} +{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":97,"Index":97,"Attempt":0,"Launch Time":1430917387407,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387450,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":38,"Result Size":2065,"JVM GC Time":4,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Write Metrics":{"Shuffle Bytes Written":1710,"Shuffle Write Time":131987,"Shuffle Records Written":10},"Input Metrics":{"Data Read Method":"Hadoop","Bytes Read":70564,"Records Read":10000}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"map at :26","Number of Tasks":100,"RDD Info":[{"RDD ID":3,"Name":"3","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":2,"Name":"2","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":0,"Name":"/Users/irashid/spark-examples/tmp_data/raw_data","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0},{"RDD ID":1,"Name":"/Users/irashid/spark-examples/tmp_data/raw_data","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":100,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.map(RDD.scala:287)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:26)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:31)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:33)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC.(:35)\n$line20.$read$$iwC$$iwC$$iwC$$iwC.(:37)\n$line20.$read$$iwC$$iwC$$iwC.(:39)\n$line20.$read$$iwC$$iwC.(:41)\n$line20.$read$$iwC.(:43)\n$line20.$read.(:45)\n$line20.$read$.(:49)\n$line20.$read$.()\n$line20.$eval$.(:7)\n$line20.$eval$.()\n$line20.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)","Submission Time":1430917386485,"Completion Time":1430917387451,"Accumulables":[]}} +{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"collect at :26","Number of Tasks":10,"RDD Info":[{"RDD ID":4,"Name":"4","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":10,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.collect(RDD.scala:819)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:26)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:31)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:33)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC.(:35)\n$line20.$read$$iwC$$iwC$$iwC$$iwC.(:37)\n$line20.$read$$iwC$$iwC$$iwC.(:39)\n$line20.$read$$iwC$$iwC.(:41)\n$line20.$read$$iwC.(:43)\n$line20.$read.(:45)\n$line20.$read$.(:49)\n$line20.$read$.()\n$line20.$eval$.(:7)\n$line20.$eval$.()\n$line20.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)","Accumulables":[]},"Properties":{}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":100,"Index":0,"Attempt":0,"Launch Time":1430917387462,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":101,"Index":1,"Attempt":0,"Launch Time":1430917387464,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":102,"Index":2,"Attempt":0,"Launch Time":1430917387465,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":103,"Index":3,"Attempt":0,"Launch Time":1430917387465,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":104,"Index":4,"Attempt":0,"Launch Time":1430917387465,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":105,"Index":5,"Attempt":0,"Launch Time":1430917387466,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":106,"Index":6,"Attempt":0,"Launch Time":1430917387466,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":107,"Index":7,"Attempt":0,"Launch Time":1430917387466,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":108,"Index":8,"Attempt":0,"Launch Time":1430917387546,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":103,"Index":3,"Attempt":0,"Launch Time":1430917387465,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387546,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":75,"Result Size":1034,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":100,"Fetch Wait Time":0,"Remote Bytes Read":0,"Local Bytes Read":17100,"Total Records Read":100}}} +{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":109,"Index":9,"Attempt":0,"Launch Time":1430917387546,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Accumulables":[]}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":105,"Index":5,"Attempt":0,"Launch Time":1430917387466,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387547,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":76,"Result Size":1034,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":100,"Fetch Wait Time":0,"Remote Bytes Read":0,"Local Bytes Read":17100,"Total Records Read":100}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":100,"Index":0,"Attempt":0,"Launch Time":1430917387462,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387548,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":74,"Result Size":1034,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":100,"Fetch Wait Time":0,"Remote Bytes Read":0,"Local Bytes Read":17100,"Total Records Read":100}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":107,"Index":7,"Attempt":0,"Launch Time":1430917387466,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387548,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":76,"Result Size":1034,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":100,"Fetch Wait Time":0,"Remote Bytes Read":0,"Local Bytes Read":17100,"Total Records Read":100}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":101,"Index":1,"Attempt":0,"Launch Time":1430917387464,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387548,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":1,"Executor Run Time":76,"Result Size":1034,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":100,"Fetch Wait Time":1,"Remote Bytes Read":0,"Local Bytes Read":17100,"Total Records Read":100}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":106,"Index":6,"Attempt":0,"Launch Time":1430917387466,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387549,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":75,"Result Size":1034,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":100,"Fetch Wait Time":0,"Remote Bytes Read":0,"Local Bytes Read":17100,"Total Records Read":100}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":104,"Index":4,"Attempt":0,"Launch Time":1430917387465,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387549,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":3,"Executor Run Time":74,"Result Size":1034,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":100,"Fetch Wait Time":1,"Remote Bytes Read":0,"Local Bytes Read":17100,"Total Records Read":100}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":102,"Index":2,"Attempt":0,"Launch Time":1430917387465,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387550,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":79,"Result Size":1034,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":100,"Fetch Wait Time":0,"Remote Bytes Read":0,"Local Bytes Read":17100,"Total Records Read":100}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":108,"Index":8,"Attempt":0,"Launch Time":1430917387546,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387583,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":31,"Result Size":1034,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":100,"Fetch Wait Time":0,"Remote Bytes Read":0,"Local Bytes Read":17100,"Total Records Read":100}}} +{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":109,"Index":9,"Attempt":0,"Launch Time":1430917387546,"Executor ID":"driver","Host":"localhost","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1430917387585,"Failed":false,"Accumulables":[]},"Task Metrics":{"Host Name":"localhost","Executor Deserialize Time":2,"Executor Run Time":30,"Result Size":1034,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":100,"Fetch Wait Time":1,"Remote Bytes Read":0,"Local Bytes Read":17100,"Total Records Read":100}}} +{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"collect at :26","Number of Tasks":10,"RDD Info":[{"RDD ID":4,"Name":"4","Storage Level":{"Use Disk":false,"Use Memory":false,"Use Tachyon":false,"Deserialized":false,"Replication":1},"Number of Partitions":10,"Number of Cached Partitions":0,"Memory Size":0,"Tachyon Size":0,"Disk Size":0}],"Details":"org.apache.spark.rdd.RDD.collect(RDD.scala:819)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:26)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:31)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.(:33)\n$line20.$read$$iwC$$iwC$$iwC$$iwC$$iwC.(:35)\n$line20.$read$$iwC$$iwC$$iwC$$iwC.(:37)\n$line20.$read$$iwC$$iwC$$iwC.(:39)\n$line20.$read$$iwC$$iwC.(:41)\n$line20.$read$$iwC.(:43)\n$line20.$read.(:45)\n$line20.$read$.(:49)\n$line20.$read$.()\n$line20.$eval$.(:7)\n$line20.$eval$.()\n$line20.$eval.$print()\nsun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\nsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\nsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.lang.reflect.Method.invoke(Method.java:483)\norg.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)","Submission Time":1430917387462,"Completion Time":1430917387585,"Accumulables":[]}} +{"Event":"SparkListenerJobEnd","Job ID":0,"Completion Time":1430917387589,"Job Result":{"Result":"JobSucceeded"}} +{"Event":"SparkListenerApplicationEnd","Timestamp":1430917391398} diff --git a/core/src/test/scala/org/apache/spark/JsonTestUtils.scala b/core/src/test/scala/org/apache/spark/JsonTestUtils.scala new file mode 100644 index 0000000000000..ba367cd476146 --- /dev/null +++ b/core/src/test/scala/org/apache/spark/JsonTestUtils.scala @@ -0,0 +1,34 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark + +import org.json4s._ +import org.json4s.jackson.JsonMethods + +trait JsonTestUtils { + def assertValidDataInJson(validateJson: JValue, expectedJson: JValue) { + val Diff(c, a, d) = validateJson.diff(expectedJson) + val validatePretty = JsonMethods.pretty(validateJson) + val expectedPretty = JsonMethods.pretty(expectedJson) + val errorMessage = s"Expected:\n$expectedPretty\nFound:\n$validatePretty" + import org.scalactic.TripleEquals._ + assert(c === JNothing, s"$errorMessage\nChanged:\n${JsonMethods.pretty(c)}") + assert(a === JNothing, s"$errorMessage\nAdded:\n${JsonMethods.pretty(a)}") + assert(d === JNothing, s"$errorMessage\nDeleted:\n${JsonMethods.pretty(d)}") + } + +} diff --git a/core/src/test/scala/org/apache/spark/deploy/JsonProtocolSuite.scala b/core/src/test/scala/org/apache/spark/deploy/JsonProtocolSuite.scala index b58d62567afe1..e04a79284175c 100644 --- a/core/src/test/scala/org/apache/spark/deploy/JsonProtocolSuite.scala +++ b/core/src/test/scala/org/apache/spark/deploy/JsonProtocolSuite.scala @@ -28,9 +28,9 @@ import org.scalatest.FunSuite import org.apache.spark.deploy.DeployMessages.{MasterStateResponse, WorkerStateResponse} import org.apache.spark.deploy.master.{ApplicationInfo, DriverInfo, RecoveryState, WorkerInfo} import org.apache.spark.deploy.worker.{DriverRunner, ExecutorRunner} -import org.apache.spark.{SecurityManager, SparkConf} +import org.apache.spark.{JsonTestUtils, SecurityManager, SparkConf} -class JsonProtocolSuite extends FunSuite { +class JsonProtocolSuite extends FunSuite with JsonTestUtils { test("writeApplicationInfo") { val output = JsonProtocol.writeApplicationInfo(createAppInfo()) @@ -136,16 +136,6 @@ class JsonProtocolSuite extends FunSuite { case e: JsonParseException => fail("Invalid Json detected", e) } } - - def assertValidDataInJson(validateJson: JValue, expectedJson: JValue) { - val Diff(c, a, d) = validateJson diff expectedJson - val validatePretty = JsonMethods.pretty(validateJson) - val expectedPretty = JsonMethods.pretty(expectedJson) - val errorMessage = s"Expected:\n$expectedPretty\nFound:\n$validatePretty" - assert(c === JNothing, s"$errorMessage\nChanged:\n${JsonMethods.pretty(c)}") - assert(a === JNothing, s"$errorMessage\nAdded:\n${JsonMethods.pretty(a)}") - assert(d === JNothing, s"$errorMessage\nDelected:\n${JsonMethods.pretty(d)}") - } } object JsonConstants { diff --git a/core/src/test/scala/org/apache/spark/deploy/history/HistoryServerSuite.scala b/core/src/test/scala/org/apache/spark/deploy/history/HistoryServerSuite.scala index 71ba9c18257b8..318ab5dbc4804 100644 --- a/core/src/test/scala/org/apache/spark/deploy/history/HistoryServerSuite.scala +++ b/core/src/test/scala/org/apache/spark/deploy/history/HistoryServerSuite.scala @@ -14,22 +14,164 @@ * See the License for the specific language governing permissions and * limitations under the License. */ - package org.apache.spark.deploy.history -import javax.servlet.http.HttpServletRequest - -import scala.collection.mutable +import java.io.{File, FileInputStream, FileWriter, IOException} +import java.net.{HttpURLConnection, URL} +import javax.servlet.http.{HttpServletRequest, HttpServletResponse} -import org.apache.hadoop.fs.Path -import org.mockito.Mockito.{when} -import org.scalatest.FunSuite -import org.scalatest.Matchers +import org.apache.commons.io.{FileUtils, IOUtils} +import org.mockito.Mockito.when +import org.scalatest.{BeforeAndAfter, FunSuite, Matchers} import org.scalatest.mock.MockitoSugar +import org.apache.spark.{JsonTestUtils, SecurityManager, SparkConf} import org.apache.spark.ui.SparkUI -class HistoryServerSuite extends FunSuite with Matchers with MockitoSugar { +/** + * A collection of tests against the historyserver, including comparing responses from the json + * metrics api to a set of known "golden files". If new endpoints / parameters are added, + * cases should be added to this test suite. The expected outcomes can be genered by running + * the HistoryServerSuite.main. Note that this will blindly generate new expectation files matching + * the current behavior -- the developer must verify that behavior is correct. + * + * Similarly, if the behavior is changed, HistoryServerSuite.main can be run to update the + * expectations. However, in general this should be done with extreme caution, as the metrics + * are considered part of Spark's public api. + */ +class HistoryServerSuite extends FunSuite with BeforeAndAfter with Matchers with MockitoSugar + with JsonTestUtils { + + private val logDir = new File("src/test/resources/spark-events") + private val expRoot = new File("src/test/resources/HistoryServerExpectations/") + + private var provider: FsHistoryProvider = null + private var server: HistoryServer = null + private var port: Int = -1 + + def init(): Unit = { + val conf = new SparkConf() + .set("spark.history.fs.logDirectory", logDir.getAbsolutePath) + .set("spark.history.fs.updateInterval", "0") + .set("spark.testing", "true") + provider = new FsHistoryProvider(conf) + provider.checkForLogs() + val securityManager = new SecurityManager(conf) + + server = new HistoryServer(conf, provider, securityManager, 18080) + server.initialize() + server.bind() + port = server.boundPort + } + + def stop(): Unit = { + server.stop() + } + + before { + init() + } + + after{ + stop() + } + + val cases = Seq( + "application list json" -> "applications", + "completed app list json" -> "applications?status=completed", + "running app list json" -> "applications?status=running", + "minDate app list json" -> "applications?minDate=2015-02-10", + "maxDate app list json" -> "applications?maxDate=2015-02-10", + "maxDate2 app list json" -> "applications?maxDate=2015-02-03T10:42:40.000CST", + "one app json" -> "applications/local-1422981780767", + "one app multi-attempt json" -> "applications/local-1426533911241", + "job list json" -> "applications/local-1422981780767/jobs", + "job list from multi-attempt app json(1)" -> "applications/local-1426533911241/1/jobs", + "job list from multi-attempt app json(2)" -> "applications/local-1426533911241/2/jobs", + "one job json" -> "applications/local-1422981780767/jobs/0", + "succeeded job list json" -> "applications/local-1422981780767/jobs?status=succeeded", + "succeeded&failed job list json" -> + "applications/local-1422981780767/jobs?status=succeeded&status=failed", + "executor list json" -> "applications/local-1422981780767/executors", + "stage list json" -> "applications/local-1422981780767/stages", + "complete stage list json" -> "applications/local-1422981780767/stages?status=complete", + "failed stage list json" -> "applications/local-1422981780767/stages?status=failed", + "one stage json" -> "applications/local-1422981780767/stages/1", + "one stage attempt json" -> "applications/local-1422981780767/stages/1/0", + + "stage task summary w shuffle write" + -> "applications/local-1430917381534/stages/0/0/taskSummary", + "stage task summary w shuffle read" + -> "applications/local-1430917381534/stages/1/0/taskSummary", + "stage task summary w/ custom quantiles" -> + "applications/local-1430917381534/stages/0/0/taskSummary?quantiles=0.01,0.5,0.99", + + "stage task list" -> "applications/local-1430917381534/stages/0/0/taskList", + "stage task list w/ offset & length" -> + "applications/local-1430917381534/stages/0/0/taskList?offset=10&length=50", + "stage task list w/ sortBy" -> + "applications/local-1430917381534/stages/0/0/taskList?sortBy=DECREASING_RUNTIME", + "stage task list w/ sortBy short names: -runtime" -> + "applications/local-1430917381534/stages/0/0/taskList?sortBy=-runtime", + "stage task list w/ sortBy short names: runtime" -> + "applications/local-1430917381534/stages/0/0/taskList?sortBy=runtime", + + "stage list with accumulable json" -> "applications/local-1426533911241/1/stages", + "stage with accumulable json" -> "applications/local-1426533911241/1/stages/0/0", + "stage task list from multi-attempt app json(1)" -> + "applications/local-1426533911241/1/stages/0/0/taskList", + "stage task list from multi-attempt app json(2)" -> + "applications/local-1426533911241/2/stages/0/0/taskList", + + "rdd list storage json" -> "applications/local-1422981780767/storage/rdd", + "one rdd storage json" -> "applications/local-1422981780767/storage/rdd/0" + ) + + // run a bunch of characterization tests -- just verify the behavior is the same as what is saved + // in the test resource folder + cases.foreach { case (name, path) => + test(name) { + val (code, jsonOpt, errOpt) = getContentAndCode(path) + code should be (HttpServletResponse.SC_OK) + jsonOpt should be ('defined) + errOpt should be (None) + val json = jsonOpt.get + val exp = IOUtils.toString(new FileInputStream( + new File(expRoot, HistoryServerSuite.sanitizePath(name) + "_expectation.json"))) + // compare the ASTs so formatting differences don't cause failures + import org.json4s._ + import org.json4s.jackson.JsonMethods._ + val jsonAst = parse(json) + val expAst = parse(exp) + assertValidDataInJson(jsonAst, expAst) + } + } + + test("response codes on bad paths") { + val badAppId = getContentAndCode("applications/foobar") + badAppId._1 should be (HttpServletResponse.SC_NOT_FOUND) + badAppId._3 should be (Some("unknown app: foobar")) + + val badStageId = getContentAndCode("applications/local-1422981780767/stages/12345") + badStageId._1 should be (HttpServletResponse.SC_NOT_FOUND) + badStageId._3 should be (Some("unknown stage: 12345")) + + val badStageAttemptId = getContentAndCode("applications/local-1422981780767/stages/1/1") + badStageAttemptId._1 should be (HttpServletResponse.SC_NOT_FOUND) + badStageAttemptId._3 should be (Some("unknown attempt for stage 1. Found attempts: [0]")) + + val badStageId2 = getContentAndCode("applications/local-1422981780767/stages/flimflam") + badStageId2._1 should be (HttpServletResponse.SC_NOT_FOUND) + // will take some mucking w/ jersey to get a better error msg in this case + + val badQuantiles = getContentAndCode( + "applications/local-1430917381534/stages/0/0/taskSummary?quantiles=foo,0.1") + badQuantiles._1 should be (HttpServletResponse.SC_BAD_REQUEST) + badQuantiles._3 should be (Some("Bad value for parameter \"quantiles\". Expected a double, " + + "got \"foo\"")) + + getContentAndCode("foobar")._1 should be (HttpServletResponse.SC_NOT_FOUND) + } test("generate history page with relative links") { val historyServer = mock[HistoryServer] @@ -54,4 +196,75 @@ class HistoryServerSuite extends FunSuite with Matchers with MockitoSugar { } yield (attrs.toString) justHrefs should contain(link) } + + def getContentAndCode(path: String, port: Int = port): (Int, Option[String], Option[String]) = { + HistoryServerSuite.getContentAndCode(new URL(s"http://localhost:$port/json/v1/$path")) + } + + def getUrl(path: String): String = { + HistoryServerSuite.getUrl(new URL(s"http://localhost:$port/json/v1/$path")) + } + + def generateExpectation(name: String, path: String): Unit = { + val json = getUrl(path) + val file = new File(expRoot, HistoryServerSuite.sanitizePath(name) + "_expectation.json") + val out = new FileWriter(file) + out.write(json) + out.close() + } +} + +object HistoryServerSuite { + def main(args: Array[String]): Unit = { + // generate the "expected" results for the characterization tests. Just blindly assume the + // current behavior is correct, and write out the returned json to the test/resource files + + val suite = new HistoryServerSuite + FileUtils.deleteDirectory(suite.expRoot) + suite.expRoot.mkdirs() + try { + suite.init() + suite.cases.foreach { case (name, path) => + suite.generateExpectation(name, path) + } + } finally { + suite.stop() + } + } + + def getContentAndCode(url: URL): (Int, Option[String], Option[String]) = { + val connection = url.openConnection().asInstanceOf[HttpURLConnection] + connection.setRequestMethod("GET") + connection.connect() + val code = connection.getResponseCode() + val inString = try { + val in = Option(connection.getInputStream()) + in.map(IOUtils.toString) + } catch { + case io: IOException => None + } + val errString = try { + val err = Option(connection.getErrorStream()) + err.map(IOUtils.toString) + } catch { + case io: IOException => None + } + (code, inString, errString) + } + + + def sanitizePath(path: String): String = { + // this doesn't need to be perfect, just good enough to avoid collisions + path.replaceAll("\\W", "_") + } + + def getUrl(path: URL): String = { + val (code, resultOpt, error) = getContentAndCode(path) + if (code == 200) { + resultOpt.get + } else { + throw new RuntimeException( + "got code: " + code + " when getting " + path + " w/ error: " + error) + } + } } diff --git a/core/src/test/scala/org/apache/spark/deploy/master/CustomRecoveryModeFactory.scala b/core/src/test/scala/org/apache/spark/deploy/master/CustomRecoveryModeFactory.scala new file mode 100644 index 0000000000000..f4e56632e426a --- /dev/null +++ b/core/src/test/scala/org/apache/spark/deploy/master/CustomRecoveryModeFactory.scala @@ -0,0 +1,110 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// This file is placed in different package to make sure all of these components work well +// when they are outside of org.apache.spark. +package other.supplier + +import scala.collection.mutable +import scala.reflect.ClassTag + +import akka.serialization.Serialization + +import org.apache.spark.SparkConf +import org.apache.spark.deploy.master._ + +class CustomRecoveryModeFactory( + conf: SparkConf, + serialization: Serialization +) extends StandaloneRecoveryModeFactory(conf, serialization) { + + CustomRecoveryModeFactory.instantiationAttempts += 1 + + /** + * PersistenceEngine defines how the persistent data(Information about worker, driver etc..) + * is handled for recovery. + * + */ + override def createPersistenceEngine(): PersistenceEngine = + new CustomPersistenceEngine(serialization) + + /** + * Create an instance of LeaderAgent that decides who gets elected as master. + */ + override def createLeaderElectionAgent(master: LeaderElectable): LeaderElectionAgent = + new CustomLeaderElectionAgent(master) +} + +object CustomRecoveryModeFactory { + @volatile var instantiationAttempts = 0 +} + +class CustomPersistenceEngine(serialization: Serialization) extends PersistenceEngine { + val data = mutable.HashMap[String, Array[Byte]]() + + CustomPersistenceEngine.lastInstance = Some(this) + + /** + * Defines how the object is serialized and persisted. Implementation will + * depend on the store used. + */ + override def persist(name: String, obj: Object): Unit = { + CustomPersistenceEngine.persistAttempts += 1 + serialization.serialize(obj) match { + case util.Success(bytes) => data += name -> bytes + case util.Failure(cause) => throw new RuntimeException(cause) + } + } + + /** + * Defines how the object referred by its name is removed from the store. + */ + override def unpersist(name: String): Unit = { + CustomPersistenceEngine.unpersistAttempts += 1 + data -= name + } + + /** + * Gives all objects, matching a prefix. This defines how objects are + * read/deserialized back. + */ + override def read[T: ClassTag](prefix: String): Seq[T] = { + CustomPersistenceEngine.readAttempts += 1 + val clazz = implicitly[ClassTag[T]].runtimeClass.asInstanceOf[Class[T]] + val results = for ((name, bytes) <- data; if name.startsWith(prefix)) + yield serialization.deserialize(bytes, clazz) + + results.find(_.isFailure).foreach { + case util.Failure(cause) => throw new RuntimeException(cause) + } + + results.flatMap(_.toOption).toSeq + } +} + +object CustomPersistenceEngine { + @volatile var persistAttempts = 0 + @volatile var unpersistAttempts = 0 + @volatile var readAttempts = 0 + + @volatile var lastInstance: Option[CustomPersistenceEngine] = None +} + +class CustomLeaderElectionAgent(val masterActor: LeaderElectable) extends LeaderElectionAgent { + masterActor.electedLeader() +} + diff --git a/core/src/test/scala/org/apache/spark/deploy/master/MasterSuite.scala b/core/src/test/scala/org/apache/spark/deploy/master/MasterSuite.scala index 34c74d87f0a62..0faa8f650e5e1 100644 --- a/core/src/test/scala/org/apache/spark/deploy/master/MasterSuite.scala +++ b/core/src/test/scala/org/apache/spark/deploy/master/MasterSuite.scala @@ -17,12 +17,20 @@ package org.apache.spark.deploy.master +import java.util.Date + +import scala.concurrent.Await +import scala.concurrent.duration._ +import scala.language.postfixOps + import akka.actor.Address -import org.scalatest.FunSuite +import org.scalatest.{FunSuite, Matchers} +import other.supplier.{CustomPersistenceEngine, CustomRecoveryModeFactory} -import org.apache.spark.{SSLOptions, SparkConf, SparkException} +import org.apache.spark.deploy._ +import org.apache.spark.{SparkConf, SparkException} -class MasterSuite extends FunSuite { +class MasterSuite extends FunSuite with Matchers { test("toAkkaUrl") { val conf = new SparkConf(loadDefaults = false) @@ -63,4 +71,90 @@ class MasterSuite extends FunSuite { } assert("Invalid master URL: spark://1.2. 3.4:1234" === e.getMessage) } + + test("can use a custom recovery mode factory") { + val conf = new SparkConf(loadDefaults = false) + conf.set("spark.deploy.recoveryMode", "CUSTOM") + conf.set("spark.deploy.recoveryMode.factory", + classOf[CustomRecoveryModeFactory].getCanonicalName) + + val instantiationAttempts = CustomRecoveryModeFactory.instantiationAttempts + + val commandToPersist = new Command( + mainClass = "", + arguments = Nil, + environment = Map.empty, + classPathEntries = Nil, + libraryPathEntries = Nil, + javaOpts = Nil + ) + + val appToPersist = new ApplicationInfo( + startTime = 0, + id = "test_app", + desc = new ApplicationDescription( + name = "", + maxCores = None, + memoryPerExecutorMB = 0, + command = commandToPersist, + appUiUrl = "", + eventLogDir = None, + eventLogCodec = None, + coresPerExecutor = None), + submitDate = new Date(), + driver = null, + defaultCores = 0 + ) + + val driverToPersist = new DriverInfo( + startTime = 0, + id = "test_driver", + desc = new DriverDescription( + jarUrl = "", + mem = 0, + cores = 0, + supervise = false, + command = commandToPersist + ), + submitDate = new Date() + ) + + val workerToPersist = new WorkerInfo( + id = "test_worker", + host = "127.0.0.1", + port = 10000, + cores = 0, + memory = 0, + actor = null, + webUiPort = 0, + publicAddress = "" + ) + + val (actorSystem, port, uiPort, restPort) = + Master.startSystemAndActor("127.0.0.1", 7077, 8080, conf) + + try { + Await.result(actorSystem.actorSelection("/user/Master").resolveOne(10 seconds), 10 seconds) + + CustomPersistenceEngine.lastInstance.isDefined shouldBe true + val persistenceEngine = CustomPersistenceEngine.lastInstance.get + + persistenceEngine.addApplication(appToPersist) + persistenceEngine.addDriver(driverToPersist) + persistenceEngine.addWorker(workerToPersist) + + val (apps, drivers, workers) = persistenceEngine.readPersistedData() + + apps.map(_.id) should contain(appToPersist.id) + drivers.map(_.id) should contain(driverToPersist.id) + workers.map(_.id) should contain(workerToPersist.id) + + } finally { + actorSystem.shutdown() + actorSystem.awaitTermination() + } + + CustomRecoveryModeFactory.instantiationAttempts should be > instantiationAttempts + } + } diff --git a/core/src/test/scala/org/apache/spark/serializer/KryoSerializerSuite.scala b/core/src/test/scala/org/apache/spark/serializer/KryoSerializerSuite.scala index 778a7eee73b23..c7369de24b81f 100644 --- a/core/src/test/scala/org/apache/spark/serializer/KryoSerializerSuite.scala +++ b/core/src/test/scala/org/apache/spark/serializer/KryoSerializerSuite.scala @@ -32,6 +32,36 @@ class KryoSerializerSuite extends FunSuite with SharedSparkContext { conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer") conf.set("spark.kryo.registrator", classOf[MyRegistrator].getName) + test("configuration limits") { + val conf1 = conf.clone() + val kryoBufferProperty = "spark.kryoserializer.buffer" + val kryoBufferMaxProperty = "spark.kryoserializer.buffer.max" + conf1.set(kryoBufferProperty, "64k") + conf1.set(kryoBufferMaxProperty, "64m") + new KryoSerializer(conf1).newInstance() + // 2048m = 2097152k + conf1.set(kryoBufferProperty, "2097151k") + conf1.set(kryoBufferMaxProperty, "64m") + // should not throw exception when kryoBufferMaxProperty < kryoBufferProperty + new KryoSerializer(conf1).newInstance() + conf1.set(kryoBufferMaxProperty, "2097151k") + new KryoSerializer(conf1).newInstance() + val conf2 = conf.clone() + conf2.set(kryoBufferProperty, "2048m") + val thrown1 = intercept[IllegalArgumentException](new KryoSerializer(conf2).newInstance()) + assert(thrown1.getMessage.contains(kryoBufferProperty)) + val conf3 = conf.clone() + conf3.set(kryoBufferMaxProperty, "2048m") + val thrown2 = intercept[IllegalArgumentException](new KryoSerializer(conf3).newInstance()) + assert(thrown2.getMessage.contains(kryoBufferMaxProperty)) + val conf4 = conf.clone() + conf4.set(kryoBufferProperty, "2g") + conf4.set(kryoBufferMaxProperty, "3g") + val thrown3 = intercept[IllegalArgumentException](new KryoSerializer(conf4).newInstance()) + assert(thrown3.getMessage.contains(kryoBufferProperty)) + assert(!thrown3.getMessage.contains(kryoBufferMaxProperty)) + } + test("basic types") { val ser = new KryoSerializer(conf).newInstance() def check[T: ClassTag](t: T) { diff --git a/core/src/test/scala/org/apache/spark/shuffle/hash/HashShuffleManagerSuite.scala b/core/src/test/scala/org/apache/spark/shuffle/hash/HashShuffleManagerSuite.scala index 84384bb48999a..0537bf66ad020 100644 --- a/core/src/test/scala/org/apache/spark/shuffle/hash/HashShuffleManagerSuite.scala +++ b/core/src/test/scala/org/apache/spark/shuffle/hash/HashShuffleManagerSuite.scala @@ -27,7 +27,7 @@ import org.apache.spark.{SparkEnv, SparkContext, LocalSparkContext, SparkConf} import org.apache.spark.executor.ShuffleWriteMetrics import org.apache.spark.network.buffer.{FileSegmentManagedBuffer, ManagedBuffer} import org.apache.spark.serializer.JavaSerializer -import org.apache.spark.shuffle.FileShuffleBlockManager +import org.apache.spark.shuffle.FileShuffleBlockResolver import org.apache.spark.storage.{ShuffleBlockId, FileSegment} class HashShuffleManagerSuite extends FunSuite with LocalSparkContext { @@ -53,10 +53,10 @@ class HashShuffleManagerSuite extends FunSuite with LocalSparkContext { sc = new SparkContext("local", "test", conf) - val shuffleBlockManager = - SparkEnv.get.shuffleManager.shuffleBlockResolver.asInstanceOf[FileShuffleBlockManager] + val shuffleBlockResolver = + SparkEnv.get.shuffleManager.shuffleBlockResolver.asInstanceOf[FileShuffleBlockResolver] - val shuffle1 = shuffleBlockManager.forMapTask(1, 1, 1, new JavaSerializer(conf), + val shuffle1 = shuffleBlockResolver.forMapTask(1, 1, 1, new JavaSerializer(conf), new ShuffleWriteMetrics) for (writer <- shuffle1.writers) { writer.write("test1", "value") @@ -69,7 +69,7 @@ class HashShuffleManagerSuite extends FunSuite with LocalSparkContext { val shuffle1Segment = shuffle1.writers(0).fileSegment() shuffle1.releaseWriters(success = true) - val shuffle2 = shuffleBlockManager.forMapTask(1, 2, 1, new JavaSerializer(conf), + val shuffle2 = shuffleBlockResolver.forMapTask(1, 2, 1, new JavaSerializer(conf), new ShuffleWriteMetrics) for (writer <- shuffle2.writers) { @@ -88,7 +88,7 @@ class HashShuffleManagerSuite extends FunSuite with LocalSparkContext { // of block based on remaining data in file : which could mess things up when there is // concurrent read and writes happening to the same shuffle group. - val shuffle3 = shuffleBlockManager.forMapTask(1, 3, 1, new JavaSerializer(testConf), + val shuffle3 = shuffleBlockResolver.forMapTask(1, 3, 1, new JavaSerializer(testConf), new ShuffleWriteMetrics) for (writer <- shuffle3.writers) { writer.write("test3", "value") @@ -98,10 +98,10 @@ class HashShuffleManagerSuite extends FunSuite with LocalSparkContext { writer.commitAndClose() } // check before we register. - checkSegments(shuffle2Segment, shuffleBlockManager.getBlockData(ShuffleBlockId(1, 2, 0))) + checkSegments(shuffle2Segment, shuffleBlockResolver.getBlockData(ShuffleBlockId(1, 2, 0))) shuffle3.releaseWriters(success = true) - checkSegments(shuffle2Segment, shuffleBlockManager.getBlockData(ShuffleBlockId(1, 2, 0))) - shuffleBlockManager.removeShuffle(1) + checkSegments(shuffle2Segment, shuffleBlockResolver.getBlockData(ShuffleBlockId(1, 2, 0))) + shuffleBlockResolver.removeShuffle(1) } def writeToFile(file: File, numBytes: Int) { diff --git a/core/src/test/scala/org/apache/spark/status/api/v1/SimpleDateParamTest.scala b/core/src/test/scala/org/apache/spark/status/api/v1/SimpleDateParamTest.scala new file mode 100644 index 0000000000000..5274df904d395 --- /dev/null +++ b/core/src/test/scala/org/apache/spark/status/api/v1/SimpleDateParamTest.scala @@ -0,0 +1,29 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.status.api.v1 + +import org.scalatest.{Matchers, FunSuite} + +class SimpleDateParamTest extends FunSuite with Matchers { + + test("date parsing") { + new SimpleDateParam("2015-02-20T23:21:17.190GMT").timestamp should be (1424474477190L) + new SimpleDateParam("2015-02-20T17:21:17.190CST").timestamp should be (1424474477190L) + new SimpleDateParam("2015-02-20").timestamp should be (1424390400000L) // GMT + } + +} diff --git a/core/src/test/scala/org/apache/spark/ui/UISeleniumSuite.scala b/core/src/test/scala/org/apache/spark/ui/UISeleniumSuite.scala index d53d7f3ba5ae7..117b2c3960820 100644 --- a/core/src/test/scala/org/apache/spark/ui/UISeleniumSuite.scala +++ b/core/src/test/scala/org/apache/spark/ui/UISeleniumSuite.scala @@ -18,11 +18,13 @@ package org.apache.spark.ui import java.net.{HttpURLConnection, URL} -import javax.servlet.http.HttpServletRequest +import javax.servlet.http.{HttpServletResponse, HttpServletRequest} import scala.collection.JavaConversions._ import scala.xml.Node +import org.json4s._ +import org.json4s.jackson.JsonMethods import org.openqa.selenium.htmlunit.HtmlUnitDriver import org.openqa.selenium.{By, WebDriver} import org.scalatest._ @@ -33,8 +35,9 @@ import org.scalatest.time.SpanSugar._ import org.apache.spark.LocalSparkContext._ import org.apache.spark._ import org.apache.spark.api.java.StorageLevels +import org.apache.spark.deploy.history.HistoryServerSuite import org.apache.spark.shuffle.FetchFailedException - +import org.apache.spark.status.api.v1.{JacksonMessageWriter, StageStatus} /** * Selenium tests for the Spark Web UI. @@ -42,6 +45,8 @@ import org.apache.spark.shuffle.FetchFailedException class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with BeforeAndAfterAll { implicit var webDriver: WebDriver = _ + implicit val formats = DefaultFormats + override def beforeAll(): Unit = { webDriver = new HtmlUnitDriver @@ -76,28 +81,42 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before val rdd = sc.parallelize(Seq(1, 2, 3)) rdd.persist(StorageLevels.DISK_ONLY).count() eventually(timeout(5 seconds), interval(50 milliseconds)) { - go to (ui.appUIAddress.stripSuffix("/") + "/storage") + goToUi(ui, "/storage") val tableRowText = findAll(cssSelector("#storage-by-rdd-table td")).map(_.text).toSeq tableRowText should contain (StorageLevels.DISK_ONLY.description) } eventually(timeout(5 seconds), interval(50 milliseconds)) { - go to (ui.appUIAddress.stripSuffix("/") + "/storage/rdd/?id=0") + goToUi(ui, "/storage/rdd/?id=0") val tableRowText = findAll(cssSelector("#rdd-storage-by-block-table td")).map(_.text).toSeq tableRowText should contain (StorageLevels.DISK_ONLY.description) } + val storageJson = getJson(ui, "storage/rdd") + storageJson.children.length should be (1) + (storageJson \ "storageLevel").extract[String] should be (StorageLevels.DISK_ONLY.description) + val rddJson = getJson(ui, "storage/rdd/0") + (rddJson \ "storageLevel").extract[String] should be (StorageLevels.DISK_ONLY.description) + rdd.unpersist() rdd.persist(StorageLevels.MEMORY_ONLY).count() eventually(timeout(5 seconds), interval(50 milliseconds)) { - go to (ui.appUIAddress.stripSuffix("/") + "/storage") + goToUi(ui, "/storage") val tableRowText = findAll(cssSelector("#storage-by-rdd-table td")).map(_.text).toSeq tableRowText should contain (StorageLevels.MEMORY_ONLY.description) } eventually(timeout(5 seconds), interval(50 milliseconds)) { - go to (ui.appUIAddress.stripSuffix("/") + "/storage/rdd/?id=0") + goToUi(ui, "/storage/rdd/?id=0") val tableRowText = findAll(cssSelector("#rdd-storage-by-block-table td")).map(_.text).toSeq tableRowText should contain (StorageLevels.MEMORY_ONLY.description) } + + val updatedStorageJson = getJson(ui, "storage/rdd") + updatedStorageJson.children.length should be (1) + (updatedStorageJson \ "storageLevel").extract[String] should be ( + StorageLevels.MEMORY_ONLY.description) + val updatedRddJson = getJson(ui, "storage/rdd/0") + (updatedRddJson \ "storageLevel").extract[String] should be ( + StorageLevels.MEMORY_ONLY.description) } } @@ -108,10 +127,13 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before sc.parallelize(1 to 10).map { x => throw new Exception()}.collect() } eventually(timeout(5 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/stages") + goToUi(sc, "/stages") find(id("active")) should be(None) // Since we hide empty tables find(id("failed")).get.text should be("Failed Stages (1)") } + val stageJson = getJson(sc.ui.get, "stages") + stageJson.children.length should be (1) + (stageJson \ "status").extract[String] should be (StageStatus.FAILED.name()) // Regression test for SPARK-2105 class NotSerializable @@ -120,12 +142,15 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before sc.parallelize(1 to 10).map { x => unserializableObject}.collect() } eventually(timeout(5 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/stages") + goToUi(sc, "/stages") find(id("active")) should be(None) // Since we hide empty tables // The failure occurs before the stage becomes active, hence we should still show only one // failed stage, not two: find(id("failed")).get.text should be("Failed Stages (1)") } + + val updatedStageJson = getJson(sc.ui.get, "stages") + updatedStageJson should be (stageJson) } } @@ -138,7 +163,7 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before withSpark(newSparkContext(killEnabled = true)) { sc => runSlowJob(sc) eventually(timeout(5 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/stages") + goToUi(sc, "/stages") assert(hasKillLink) } } @@ -146,7 +171,7 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before withSpark(newSparkContext(killEnabled = false)) { sc => runSlowJob(sc) eventually(timeout(5 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/stages") + goToUi(sc, "/stages") assert(!hasKillLink) } } @@ -157,7 +182,7 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before // If no job has been run in a job group, then "(Job Group)" should not appear in the header sc.parallelize(Seq(1, 2, 3)).count() eventually(timeout(5 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/jobs") + goToUi(sc, "/jobs") val tableHeaders = findAll(cssSelector("th")).map(_.text).toSeq tableHeaders should not contain "Job Id (Job Group)" } @@ -165,10 +190,22 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before sc.setJobGroup("my-job-group", "my-job-group-description") sc.parallelize(Seq(1, 2, 3)).count() eventually(timeout(5 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/jobs") + goToUi(sc, "/jobs") val tableHeaders = findAll(cssSelector("th")).map(_.text).toSeq tableHeaders should contain ("Job Id (Job Group)") } + + val jobJson = getJson(sc.ui.get, "jobs") + for { + job @ JObject(_) <- jobJson + JInt(jobId) <- job \ "jobId" + jobGroup = job \ "jobGroup" + } { + jobId.toInt match { + case 0 => jobGroup should be (JNothing) + case 1 => jobGroup should be (JString("my-job-group")) + } + } } } @@ -195,7 +232,7 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before } mappedData.count() eventually(timeout(5 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/jobs") + goToUi(sc, "/jobs") find(cssSelector(".stage-progress-cell")).get.text should be ("2/2 (1 failed)") // Ideally, the following test would pass, but currently we overcount completed tasks // if task recomputations occur: @@ -204,6 +241,32 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before // of completed tasks may be higher: find(cssSelector(".progress-cell .progress")).get.text should be ("3/2 (1 failed)") } + val jobJson = getJson(sc.ui.get, "jobs") + (jobJson \ "numTasks").extract[Int]should be (2) + (jobJson \ "numCompletedTasks").extract[Int] should be (3) + (jobJson \ "numFailedTasks").extract[Int] should be (1) + (jobJson \ "numCompletedStages").extract[Int] should be (2) + (jobJson \ "numFailedStages").extract[Int] should be (1) + val stageJson = getJson(sc.ui.get, "stages") + + for { + stage @ JObject(_) <- stageJson + JString(status) <- stage \ "status" + JInt(stageId) <- stage \ "stageId" + JInt(attemptId) <- stage \ "attemptId" + } { + val exp = if (attemptId == 0 && stageId == 1) StageStatus.FAILED else StageStatus.COMPLETE + status should be (exp.name()) + } + + for { + stageId <- 0 to 1 + attemptId <- 0 to 1 + } { + val exp = if (attemptId == 0 && stageId == 1) StageStatus.FAILED else StageStatus.COMPLETE + val stageJson = getJson(sc.ui.get, s"stages/$stageId/$attemptId") + (stageJson \ "status").extract[String] should be (exp.name()) + } } } @@ -218,7 +281,7 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before // Start the job: rdd.countAsync() eventually(timeout(10 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/jobs/job/?id=0") + goToUi(sc, "/jobs/job/?id=0") find(id("active")).get.text should be ("Active Stages (1)") find(id("pending")).get.text should be ("Pending Stages (2)") // Essentially, we want to check that none of the stage rows show @@ -244,7 +307,7 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before rdd.count() rdd.count() eventually(timeout(10 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/jobs") + goToUi(sc, "/jobs") // The completed jobs table should have two rows. The first row will be the most recent job: val firstRow = find(cssSelector("tbody tr")).get.underlying val firstRowColumns = firstRow.findElements(By.tagName("td")) @@ -271,7 +334,7 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before rdd.count() rdd.count() eventually(timeout(10 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/jobs/job/?id=1") + goToUi(sc, "/jobs/job/?id=1") find(id("pending")) should be (None) find(id("active")) should be (None) find(id("failed")) should be (None) @@ -299,7 +362,7 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before rdd.count() rdd.count() eventually(timeout(10 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/jobs") + goToUi(sc, "/jobs") findAll(cssSelector("tbody tr a")).foreach { link => link.text.toLowerCase should include ("count") link.text.toLowerCase should not include "unknown" @@ -321,7 +384,7 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before } sparkUI.attachTab(newTab) eventually(timeout(10 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/")) + goToUi(sc, "") find(cssSelector("""ul li a[href*="jobs"]""")) should not be(None) find(cssSelector("""ul li a[href*="stages"]""")) should not be(None) find(cssSelector("""ul li a[href*="storage"]""")) should not be(None) @@ -330,12 +393,12 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before } eventually(timeout(10 seconds), interval(50 milliseconds)) { // check whether new page exists - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/foo") + goToUi(sc, "/foo") find(cssSelector("b")).get.text should include ("html magic") } sparkUI.detachTab(newTab) eventually(timeout(10 seconds), interval(50 milliseconds)) { - go to (sc.ui.get.appUIAddress.stripSuffix("/")) + goToUi(sc, "") find(cssSelector("""ul li a[href*="jobs"]""")) should not be(None) find(cssSelector("""ul li a[href*="stages"]""")) should not be(None) find(cssSelector("""ul li a[href*="storage"]""")) should not be(None) @@ -344,7 +407,7 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before } eventually(timeout(10 seconds), interval(50 milliseconds)) { // check new page not exist - go to (sc.ui.get.appUIAddress.stripSuffix("/") + "/foo") + goToUi(sc, "/foo") find(cssSelector("b")) should be(None) } } @@ -371,4 +434,163 @@ class UISeleniumSuite extends FunSuite with WebBrowser with Matchers with Before } } } + + test("stage & job retention") { + val conf = new SparkConf() + .setMaster("local") + .setAppName("test") + .set("spark.ui.enabled", "true") + .set("spark.ui.port", "0") + .set("spark.ui.retainedStages", "3") + .set("spark.ui.retainedJobs", "2") + val sc = new SparkContext(conf) + assert(sc.ui.isDefined) + + withSpark(sc) { sc => + // run a few jobs & stages ... + (0 until 5).foreach { idx => + // NOTE: if we reverse the order, things don't really behave nicely + // we lose the stage for a job we keep, and then the job doesn't know + // about its last stage + sc.parallelize(idx to (idx + 3)).map(identity).groupBy(identity).map(identity) + .groupBy(identity).count() + sc.parallelize(idx to (idx + 3)).collect() + } + + val expJobInfo = Seq( + ("9", "collect"), + ("8", "count") + ) + + eventually(timeout(1 second), interval(50 milliseconds)) { + goToUi(sc, "/jobs") + // The completed jobs table should have two rows. The first row will be the most recent job: + find("completed-summary").get.text should be ("Completed Jobs: 10, only showing 2") + find("completed").get.text should be ("Completed Jobs (10, only showing 2)") + val rows = findAll(cssSelector("tbody tr")).toIndexedSeq.map{_.underlying} + rows.size should be (expJobInfo.size) + for { + (row, idx) <- rows.zipWithIndex + columns = row.findElements(By.tagName("td")) + id = columns(0).getText() + description = columns(1).getText() + } { + id should be (expJobInfo(idx)._1) + description should include (expJobInfo(idx)._2) + } + } + + val jobsJson = getJson(sc.ui.get, "jobs") + jobsJson.children.size should be (expJobInfo.size) + for { + (job @ JObject(_),idx) <- jobsJson.children.zipWithIndex + id = (job \ "jobId").extract[String] + name = (job \ "name").extract[String] + } { + withClue(s"idx = $idx; id = $id; name = ${name.substring(0,20)}") { + id should be (expJobInfo(idx)._1) + name should include (expJobInfo(idx)._2) + } + } + + // what about when we query for a job that did exist, but has been cleared? + goToUi(sc, "/jobs/job/?id=7") + find("no-info").get.text should be ("No information to display for job 7") + + val badJob = HistoryServerSuite.getContentAndCode(jsonUrl(sc.ui.get, "jobs/7")) + badJob._1 should be (HttpServletResponse.SC_NOT_FOUND) + badJob._2 should be (None) + badJob._3 should be (Some("unknown job: 7")) + + val expStageInfo = Seq( + ("19", "collect"), + ("18", "count"), + ("17", "groupBy") + ) + + eventually(timeout(1 second), interval(50 milliseconds)) { + goToUi(sc, "/stages") + find("completed-summary").get.text should be ("Completed Stages: 20, only showing 3") + find("completed").get.text should be ("Completed Stages (20, only showing 3)") + val rows = findAll(cssSelector("tbody tr")).toIndexedSeq.map{_.underlying} + rows.size should be (3) + for { + (row, idx) <- rows.zipWithIndex + columns = row.findElements(By.tagName("td")) + id = columns(0).getText() + description = columns(1).getText() + } { + id should be (expStageInfo(idx)._1) + description should include (expStageInfo(idx)._2) + } + } + + val stagesJson = getJson(sc.ui.get, "stages") + stagesJson.children.size should be (3) + for { + (stage @ JObject(_), idx) <- stagesJson.children.zipWithIndex + id = (stage \ "stageId").extract[String] + name = (stage \ "name").extract[String] + } { + id should be (expStageInfo(idx)._1) + name should include (expStageInfo(idx)._2) + } + + // nonexistent stage + + goToUi(sc, "/stages/stage/?id=12&attempt=0") + find("no-info").get.text should be ("No information to display for Stage 12 (Attempt 0)") + val badStage = HistoryServerSuite.getContentAndCode(jsonUrl(sc.ui.get,"stages/12/0")) + badStage._1 should be (HttpServletResponse.SC_NOT_FOUND) + badStage._2 should be (None) + badStage._3 should be (Some("unknown stage: 12")) + + val badAttempt = HistoryServerSuite.getContentAndCode(jsonUrl(sc.ui.get,"stages/19/15")) + badAttempt._1 should be (HttpServletResponse.SC_NOT_FOUND) + badAttempt._2 should be (None) + badAttempt._3 should be (Some("unknown attempt for stage 19. Found attempts: [0]")) + + val badStageAttemptList = HistoryServerSuite.getContentAndCode( + jsonUrl(sc.ui.get, "stages/12")) + badStageAttemptList._1 should be (HttpServletResponse.SC_NOT_FOUND) + badStageAttemptList._2 should be (None) + badStageAttemptList._3 should be (Some("unknown stage: 12")) + } + } + + test("live UI json application list") { + withSpark(newSparkContext()) { sc => + val appListRawJson = HistoryServerSuite.getUrl(new URL( + sc.ui.get.appUIAddress + "/json/v1/applications")) + val appListJsonAst = JsonMethods.parse(appListRawJson) + appListJsonAst.children.length should be (1) + val attempts = (appListJsonAst \ "attempts").children + attempts.size should be (1) + (attempts(0) \ "completed").extract[Boolean] should be (false) + parseDate(attempts(0) \ "startTime") should be (sc.startTime) + parseDate(attempts(0) \ "endTime") should be (-1) + val oneAppJsonAst = getJson(sc.ui.get, "") + oneAppJsonAst should be (appListJsonAst.children(0)) + } + } + + def goToUi(sc: SparkContext, path: String): Unit = { + goToUi(sc.ui.get, path) + } + + def goToUi(ui: SparkUI, path: String): Unit = { + go to (ui.appUIAddress.stripSuffix("/") + path) + } + + def parseDate(json: JValue): Long = { + JacksonMessageWriter.makeISODateFormat.parse(json.extract[String]).getTime + } + + def getJson(ui: SparkUI, path: String): JValue = { + JsonMethods.parse(HistoryServerSuite.getUrl(jsonUrl(ui, path))) + } + + def jsonUrl(ui: SparkUI, path: String): URL = { + new URL(ui.appUIAddress + "/json/v1/applications/test/" + path) + } } diff --git a/docs/monitoring.md b/docs/monitoring.md index 8a85928d6d44d..1e0fc150862fb 100644 --- a/docs/monitoring.md +++ b/docs/monitoring.md @@ -174,6 +174,80 @@ making it easy to identify slow tasks, data skew, etc. Note that the history server only displays completed Spark jobs. One way to signal the completion of a Spark job is to stop the Spark Context explicitly (`sc.stop()`), or in Python using the `with SparkContext() as sc:` to handle the Spark Context setup and tear down, and still show the job history on the UI. +## REST API + +In addition to viewing the metrics in the UI, they are also available as JSON. This gives developers +an easy way to create new visualizations and monitoring tools for Spark. The JSON is available for +both running applications, and in the history server. The endpoints are mounted at `/json/v1`. Eg., +for the history server, they would typically be accessible at `http://:18080/json/v1`, and +for a running application, at `http://localhost:4040/json/v1`. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
      EndpointMeaning
      /applicationsA list of all applications
      /applications/[app-id]/jobsA list of all jobs for a given application
      /applications/[app-id]/jobs/[job-id]Details for the given job
      /applications/[app-id]/stagesA list of all stages for a given application
      /applications/[app-id]/stages/[stage-id]A list of all attempts for the given stage
      /applications/[app-id]/stages/[stage-id]/[stage-attempt-id]Details for the given stage attempt
      /applications/[app-id]/stages/[stage-id]/[stage-attempt-id]/taskSummarySummary metrics of all tasks in the given stage attempt
      /applications/[app-id]/stages/[stage-id]/[stage-attempt-id]/taskListA list of all tasks for the given stage attempt
      /applications/[app-id]/executorsA list of all executors for the given application
      /applications/[app-id]/storage/rddA list of stored RDDs for the given application
      /applications/[app-id]/storage/rdd/[rdd-id]Details for the storage status of a given RDD
      + +When running on Yarn, each application has multiple attempts, so `[app-id]` is actually +`[app-id]/[attempt-id]` in all cases. + +These endpoints have been strongly versioned to make it easier to develop applications on top. + In particular, Spark guarantees: + +* Endpoints will never be removed from one version +* Individual fields will never be removed for any given endpoint +* New endpoints may be added +* New fields may be added to existing endpoints +* New versions of the api may be added in the future at a separate endpoint (eg., `json/v2`). New versions are *not* required to be backwards compatible. +* Api versions may be dropped, but only after at least one minor release of co-existing with a new api version + +Note that even when examining the UI of a running applications, the `applications/[app-id]` portion is +still required, though there is only one application available. Eg. to see the list of jobs for the +running app, you would go to `http://localhost:4040/json/v1/applications/[app-id]/jobs`. This is to +keep the paths consistent in both modes. + # Metrics Spark has a configurable metrics system based on the diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala index 63e190c8aae53..9e6177ca27e4a 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala @@ -31,7 +31,7 @@ import org.apache.spark.sql.types.DataType * which is available at [[http://en.wikipedia.org/wiki/Polynomial_expansion]], "In mathematics, an * expansion of a product of sums expresses it as a sum of products by using the fact that * multiplication distributes over addition". Take a 2-variable feature vector as an example: - * `(x, y)`, if we want to expand it with degree 2, then we get `(x, y, x * x, x * y, y * y)`. + * `(x, y)`, if we want to expand it with degree 2, then we get `(x, x * x, y, x * y, y * y)`. */ @AlphaComponent class PolynomialExpansion extends UnaryTransformer[Vector, Vector, PolynomialExpansion] { diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala index 2863b7621526e..649c217b16590 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala @@ -42,7 +42,7 @@ class Tokenizer extends UnaryTransformer[String, Seq[String], Tokenizer] { /** * :: AlphaComponent :: - * A regex based tokenizer that extracts tokens either by repeatedly matching the regex(default) + * A regex based tokenizer that extracts tokens either by repeatedly matching the regex(default) * or using it to split the text (set matching to false). Optional parameters also allow filtering * tokens using a minimal length. * It returns an array of strings that can be empty. diff --git a/network/shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java b/network/shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java index 46ca9708621b9..e4faaf8854fc7 100644 --- a/network/shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java +++ b/network/shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java @@ -46,18 +46,18 @@ public class ExternalShuffleBlockHandler extends RpcHandler { private final Logger logger = LoggerFactory.getLogger(ExternalShuffleBlockHandler.class); - private final ExternalShuffleBlockManager blockManager; + private final ExternalShuffleBlockResolver blockManager; private final OneForOneStreamManager streamManager; public ExternalShuffleBlockHandler(TransportConf conf) { - this(new OneForOneStreamManager(), new ExternalShuffleBlockManager(conf)); + this(new OneForOneStreamManager(), new ExternalShuffleBlockResolver(conf)); } /** Enables mocking out the StreamManager and BlockManager. */ @VisibleForTesting ExternalShuffleBlockHandler( OneForOneStreamManager streamManager, - ExternalShuffleBlockManager blockManager) { + ExternalShuffleBlockResolver blockManager) { this.streamManager = streamManager; this.blockManager = blockManager; } diff --git a/network/shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockManager.java b/network/shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java similarity index 95% rename from network/shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockManager.java rename to network/shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java index 93e6fdd7161fa..dd08e24cade23 100644 --- a/network/shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockManager.java +++ b/network/shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java @@ -44,13 +44,13 @@ * Manages converting shuffle BlockIds into physical segments of local files, from a process outside * of Executors. Each Executor must register its own configuration about where it stores its files * (local dirs) and how (shuffle manager). The logic for retrieval of individual files is replicated - * from Spark's FileShuffleBlockManager and IndexShuffleBlockManager. + * from Spark's FileShuffleBlockResolver and IndexShuffleBlockResolver. * * Executors with shuffle file consolidation are not currently supported, as the index is stored in - * the Executor's memory, unlike the IndexShuffleBlockManager. + * the Executor's memory, unlike the IndexShuffleBlockResolver. */ -public class ExternalShuffleBlockManager { - private static final Logger logger = LoggerFactory.getLogger(ExternalShuffleBlockManager.class); +public class ExternalShuffleBlockResolver { + private static final Logger logger = LoggerFactory.getLogger(ExternalShuffleBlockResolver.class); // Map containing all registered executors' metadata. private final ConcurrentMap executors; @@ -60,7 +60,7 @@ public class ExternalShuffleBlockManager { private final TransportConf conf; - public ExternalShuffleBlockManager(TransportConf conf) { + public ExternalShuffleBlockResolver(TransportConf conf) { this(conf, Executors.newSingleThreadExecutor( // Add `spark` prefix because it will run in NM in Yarn mode. NettyUtils.createThreadFactory("spark-shuffle-directory-cleaner"))); @@ -68,7 +68,7 @@ public ExternalShuffleBlockManager(TransportConf conf) { // Allows tests to have more control over when directories are cleaned up. @VisibleForTesting - ExternalShuffleBlockManager(TransportConf conf, Executor directoryCleaner) { + ExternalShuffleBlockResolver(TransportConf conf, Executor directoryCleaner) { this.conf = conf; this.executors = Maps.newConcurrentMap(); this.directoryCleaner = directoryCleaner; @@ -168,7 +168,7 @@ private void deleteExecutorDirs(String[] dirs) { /** * Hash-based shuffle data is simply stored as one file per block. - * This logic is from FileShuffleBlockManager. + * This logic is from FileShuffleBlockResolver. */ // TODO: Support consolidated hash shuffle files private ManagedBuffer getHashBasedShuffleBlockData(ExecutorShuffleInfo executor, String blockId) { @@ -178,7 +178,7 @@ private ManagedBuffer getHashBasedShuffleBlockData(ExecutorShuffleInfo executor, /** * Sort-based shuffle data uses an index called "shuffle_ShuffleId_MapId_0.index" into a data file - * called "shuffle_ShuffleId_MapId_0.data". This logic is from IndexShuffleBlockManager, + * called "shuffle_ShuffleId_MapId_0.data". This logic is from IndexShuffleBlockResolver, * and the block id format is from ShuffleDataBlockId and ShuffleIndexBlockId. */ private ManagedBuffer getSortBasedShuffleBlockData( diff --git a/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandlerSuite.java b/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandlerSuite.java index 3f9fe1681cf27..73374cdc77a23 100644 --- a/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandlerSuite.java +++ b/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandlerSuite.java @@ -45,14 +45,14 @@ public class ExternalShuffleBlockHandlerSuite { TransportClient client = mock(TransportClient.class); OneForOneStreamManager streamManager; - ExternalShuffleBlockManager blockManager; + ExternalShuffleBlockResolver blockResolver; RpcHandler handler; @Before public void beforeEach() { streamManager = mock(OneForOneStreamManager.class); - blockManager = mock(ExternalShuffleBlockManager.class); - handler = new ExternalShuffleBlockHandler(streamManager, blockManager); + blockResolver = mock(ExternalShuffleBlockResolver.class); + handler = new ExternalShuffleBlockHandler(streamManager, blockResolver); } @Test @@ -62,7 +62,7 @@ public void testRegisterExecutor() { ExecutorShuffleInfo config = new ExecutorShuffleInfo(new String[] {"/a", "/b"}, 16, "sort"); byte[] registerMessage = new RegisterExecutor("app0", "exec1", config).toByteArray(); handler.receive(client, registerMessage, callback); - verify(blockManager, times(1)).registerExecutor("app0", "exec1", config); + verify(blockResolver, times(1)).registerExecutor("app0", "exec1", config); verify(callback, times(1)).onSuccess((byte[]) any()); verify(callback, never()).onFailure((Throwable) any()); @@ -75,12 +75,12 @@ public void testOpenShuffleBlocks() { ManagedBuffer block0Marker = new NioManagedBuffer(ByteBuffer.wrap(new byte[3])); ManagedBuffer block1Marker = new NioManagedBuffer(ByteBuffer.wrap(new byte[7])); - when(blockManager.getBlockData("app0", "exec1", "b0")).thenReturn(block0Marker); - when(blockManager.getBlockData("app0", "exec1", "b1")).thenReturn(block1Marker); + when(blockResolver.getBlockData("app0", "exec1", "b0")).thenReturn(block0Marker); + when(blockResolver.getBlockData("app0", "exec1", "b1")).thenReturn(block1Marker); byte[] openBlocks = new OpenBlocks("app0", "exec1", new String[] { "b0", "b1" }).toByteArray(); handler.receive(client, openBlocks, callback); - verify(blockManager, times(1)).getBlockData("app0", "exec1", "b0"); - verify(blockManager, times(1)).getBlockData("app0", "exec1", "b1"); + verify(blockResolver, times(1)).getBlockData("app0", "exec1", "b0"); + verify(blockResolver, times(1)).getBlockData("app0", "exec1", "b1"); ArgumentCaptor response = ArgumentCaptor.forClass(byte[].class); verify(callback, times(1)).onSuccess(response.capture()); diff --git a/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockManagerSuite.java b/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolverSuite.java similarity index 77% rename from network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockManagerSuite.java rename to network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolverSuite.java index dad6428a836fc..d02f4f0fdb682 100644 --- a/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockManagerSuite.java +++ b/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolverSuite.java @@ -30,7 +30,7 @@ import static org.junit.Assert.*; -public class ExternalShuffleBlockManagerSuite { +public class ExternalShuffleBlockResolverSuite { static String sortBlock0 = "Hello!"; static String sortBlock1 = "World!"; @@ -60,29 +60,29 @@ public static void afterAll() { @Test public void testBadRequests() { - ExternalShuffleBlockManager manager = new ExternalShuffleBlockManager(conf); + ExternalShuffleBlockResolver resolver = new ExternalShuffleBlockResolver(conf); // Unregistered executor try { - manager.getBlockData("app0", "exec1", "shuffle_1_1_0"); + resolver.getBlockData("app0", "exec1", "shuffle_1_1_0"); fail("Should have failed"); } catch (RuntimeException e) { assertTrue("Bad error message: " + e, e.getMessage().contains("not registered")); } // Invalid shuffle manager - manager.registerExecutor("app0", "exec2", dataContext.createExecutorInfo("foobar")); + resolver.registerExecutor("app0", "exec2", dataContext.createExecutorInfo("foobar")); try { - manager.getBlockData("app0", "exec2", "shuffle_1_1_0"); + resolver.getBlockData("app0", "exec2", "shuffle_1_1_0"); fail("Should have failed"); } catch (UnsupportedOperationException e) { // pass } // Nonexistent shuffle block - manager.registerExecutor("app0", "exec3", + resolver.registerExecutor("app0", "exec3", dataContext.createExecutorInfo("org.apache.spark.shuffle.sort.SortShuffleManager")); try { - manager.getBlockData("app0", "exec3", "shuffle_1_1_0"); + resolver.getBlockData("app0", "exec3", "shuffle_1_1_0"); fail("Should have failed"); } catch (Exception e) { // pass @@ -91,18 +91,18 @@ public void testBadRequests() { @Test public void testSortShuffleBlocks() throws IOException { - ExternalShuffleBlockManager manager = new ExternalShuffleBlockManager(conf); - manager.registerExecutor("app0", "exec0", + ExternalShuffleBlockResolver resolver = new ExternalShuffleBlockResolver(conf); + resolver.registerExecutor("app0", "exec0", dataContext.createExecutorInfo("org.apache.spark.shuffle.sort.SortShuffleManager")); InputStream block0Stream = - manager.getBlockData("app0", "exec0", "shuffle_0_0_0").createInputStream(); + resolver.getBlockData("app0", "exec0", "shuffle_0_0_0").createInputStream(); String block0 = CharStreams.toString(new InputStreamReader(block0Stream)); block0Stream.close(); assertEquals(sortBlock0, block0); InputStream block1Stream = - manager.getBlockData("app0", "exec0", "shuffle_0_0_1").createInputStream(); + resolver.getBlockData("app0", "exec0", "shuffle_0_0_1").createInputStream(); String block1 = CharStreams.toString(new InputStreamReader(block1Stream)); block1Stream.close(); assertEquals(sortBlock1, block1); @@ -110,18 +110,18 @@ public void testSortShuffleBlocks() throws IOException { @Test public void testHashShuffleBlocks() throws IOException { - ExternalShuffleBlockManager manager = new ExternalShuffleBlockManager(conf); - manager.registerExecutor("app0", "exec0", + ExternalShuffleBlockResolver resolver = new ExternalShuffleBlockResolver(conf); + resolver.registerExecutor("app0", "exec0", dataContext.createExecutorInfo("org.apache.spark.shuffle.hash.HashShuffleManager")); InputStream block0Stream = - manager.getBlockData("app0", "exec0", "shuffle_1_0_0").createInputStream(); + resolver.getBlockData("app0", "exec0", "shuffle_1_0_0").createInputStream(); String block0 = CharStreams.toString(new InputStreamReader(block0Stream)); block0Stream.close(); assertEquals(hashBlock0, block0); InputStream block1Stream = - manager.getBlockData("app0", "exec0", "shuffle_1_0_1").createInputStream(); + resolver.getBlockData("app0", "exec0", "shuffle_1_0_1").createInputStream(); String block1 = CharStreams.toString(new InputStreamReader(block1Stream)); block1Stream.close(); assertEquals(hashBlock1, block1); diff --git a/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleCleanupSuite.java b/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleCleanupSuite.java index 254e3a7a32b98..d9d9c1bf2f17a 100644 --- a/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleCleanupSuite.java +++ b/network/shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleCleanupSuite.java @@ -41,14 +41,15 @@ public class ExternalShuffleCleanupSuite { public void noCleanupAndCleanup() throws IOException { TestShuffleDataContext dataContext = createSomeData(); - ExternalShuffleBlockManager manager = new ExternalShuffleBlockManager(conf, sameThreadExecutor); - manager.registerExecutor("app", "exec0", dataContext.createExecutorInfo("shuffleMgr")); - manager.applicationRemoved("app", false /* cleanup */); + ExternalShuffleBlockResolver resolver = + new ExternalShuffleBlockResolver(conf, sameThreadExecutor); + resolver.registerExecutor("app", "exec0", dataContext.createExecutorInfo("shuffleMgr")); + resolver.applicationRemoved("app", false /* cleanup */); assertStillThere(dataContext); - manager.registerExecutor("app", "exec1", dataContext.createExecutorInfo("shuffleMgr")); - manager.applicationRemoved("app", true /* cleanup */); + resolver.registerExecutor("app", "exec1", dataContext.createExecutorInfo("shuffleMgr")); + resolver.applicationRemoved("app", true /* cleanup */); assertCleanedUp(dataContext); } @@ -64,7 +65,7 @@ public void cleanupUsesExecutor() throws IOException { @Override public void execute(Runnable runnable) { cleanupCalled.set(true); } }; - ExternalShuffleBlockManager manager = new ExternalShuffleBlockManager(conf, noThreadExecutor); + ExternalShuffleBlockResolver manager = new ExternalShuffleBlockResolver(conf, noThreadExecutor); manager.registerExecutor("app", "exec0", dataContext.createExecutorInfo("shuffleMgr")); manager.applicationRemoved("app", true); @@ -81,11 +82,12 @@ public void cleanupMultipleExecutors() throws IOException { TestShuffleDataContext dataContext0 = createSomeData(); TestShuffleDataContext dataContext1 = createSomeData(); - ExternalShuffleBlockManager manager = new ExternalShuffleBlockManager(conf, sameThreadExecutor); + ExternalShuffleBlockResolver resolver = + new ExternalShuffleBlockResolver(conf, sameThreadExecutor); - manager.registerExecutor("app", "exec0", dataContext0.createExecutorInfo("shuffleMgr")); - manager.registerExecutor("app", "exec1", dataContext1.createExecutorInfo("shuffleMgr")); - manager.applicationRemoved("app", true); + resolver.registerExecutor("app", "exec0", dataContext0.createExecutorInfo("shuffleMgr")); + resolver.registerExecutor("app", "exec1", dataContext1.createExecutorInfo("shuffleMgr")); + resolver.applicationRemoved("app", true); assertCleanedUp(dataContext0); assertCleanedUp(dataContext1); @@ -96,25 +98,26 @@ public void cleanupOnlyRemovedApp() throws IOException { TestShuffleDataContext dataContext0 = createSomeData(); TestShuffleDataContext dataContext1 = createSomeData(); - ExternalShuffleBlockManager manager = new ExternalShuffleBlockManager(conf, sameThreadExecutor); + ExternalShuffleBlockResolver resolver = + new ExternalShuffleBlockResolver(conf, sameThreadExecutor); - manager.registerExecutor("app-0", "exec0", dataContext0.createExecutorInfo("shuffleMgr")); - manager.registerExecutor("app-1", "exec0", dataContext1.createExecutorInfo("shuffleMgr")); + resolver.registerExecutor("app-0", "exec0", dataContext0.createExecutorInfo("shuffleMgr")); + resolver.registerExecutor("app-1", "exec0", dataContext1.createExecutorInfo("shuffleMgr")); - manager.applicationRemoved("app-nonexistent", true); + resolver.applicationRemoved("app-nonexistent", true); assertStillThere(dataContext0); assertStillThere(dataContext1); - manager.applicationRemoved("app-0", true); + resolver.applicationRemoved("app-0", true); assertCleanedUp(dataContext0); assertStillThere(dataContext1); - manager.applicationRemoved("app-1", true); + resolver.applicationRemoved("app-1", true); assertCleanedUp(dataContext0); assertCleanedUp(dataContext1); // Make sure it's not an error to cleanup multiple times - manager.applicationRemoved("app-1", true); + resolver.applicationRemoved("app-1", true); assertCleanedUp(dataContext0); assertCleanedUp(dataContext1); } diff --git a/network/shuffle/src/test/java/org/apache/spark/network/shuffle/TestShuffleDataContext.java b/network/shuffle/src/test/java/org/apache/spark/network/shuffle/TestShuffleDataContext.java index 76639114df5d9..3fdde054ab6c7 100644 --- a/network/shuffle/src/test/java/org/apache/spark/network/shuffle/TestShuffleDataContext.java +++ b/network/shuffle/src/test/java/org/apache/spark/network/shuffle/TestShuffleDataContext.java @@ -29,7 +29,7 @@ /** * Manages some sort- and hash-based shuffle data, including the creation - * and cleanup of directories that can be read by the {@link ExternalShuffleBlockManager}. + * and cleanup of directories that can be read by the {@link ExternalShuffleBlockResolver}. */ public class TestShuffleDataContext { public final String[] localDirs; @@ -61,9 +61,9 @@ public void insertSortShuffleData(int shuffleId, int mapId, byte[][] blocks) thr String blockId = "shuffle_" + shuffleId + "_" + mapId + "_0"; OutputStream dataStream = new FileOutputStream( - ExternalShuffleBlockManager.getFile(localDirs, subDirsPerLocalDir, blockId + ".data")); + ExternalShuffleBlockResolver.getFile(localDirs, subDirsPerLocalDir, blockId + ".data")); DataOutputStream indexStream = new DataOutputStream(new FileOutputStream( - ExternalShuffleBlockManager.getFile(localDirs, subDirsPerLocalDir, blockId + ".index"))); + ExternalShuffleBlockResolver.getFile(localDirs, subDirsPerLocalDir, blockId + ".index"))); long offset = 0; indexStream.writeLong(offset); @@ -82,7 +82,7 @@ public void insertHashShuffleData(int shuffleId, int mapId, byte[][] blocks) thr for (int i = 0; i < blocks.length; i ++) { String blockId = "shuffle_" + shuffleId + "_" + mapId + "_" + i; Files.write(blocks[i], - ExternalShuffleBlockManager.getFile(localDirs, subDirsPerLocalDir, blockId)); + ExternalShuffleBlockResolver.getFile(localDirs, subDirsPerLocalDir, blockId)); } } diff --git a/pom.xml b/pom.xml index 12ad7c5be4e40..94cf28332cf47 100644 --- a/pom.xml +++ b/pom.xml @@ -623,6 +623,18 @@ + + com.sun.jersey + jersey-server + 1.9 + ${hadoop.deps.scope} + + + com.sun.jersey + jersey-core + 1.9 + ${hadoop.deps.scope} + org.scala-lang scala-compiler diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index 026855f8f6a5a..186345af0e60e 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -370,6 +370,7 @@ object Assembly { object PySparkAssembly { import sbtassembly.Plugin._ import AssemblyKeys._ + import java.util.zip.{ZipOutputStream, ZipEntry} lazy val settings = Seq( unmanagedJars in Compile += { BuildCommons.sparkHome / "python/lib/py4j-0.8.2.1-src.zip" }, @@ -377,16 +378,48 @@ object PySparkAssembly { // to be included in the assembly. We can't just add "python/" to the assembly's resource dir // list since that will copy unneeded / unwanted files. resourceGenerators in Compile <+= resourceManaged in Compile map { outDir: File => + val src = new File(BuildCommons.sparkHome, "python/pyspark") + + val zipFile = new File(BuildCommons.sparkHome , "python/lib/pyspark.zip") + zipFile.delete() + zipRecursive(src, zipFile) + val dst = new File(outDir, "pyspark") if (!dst.isDirectory()) { require(dst.mkdirs()) } - - val src = new File(BuildCommons.sparkHome, "python/pyspark") copy(src, dst) } ) + private def zipRecursive(source: File, destZipFile: File) = { + val destOutput = new ZipOutputStream(new FileOutputStream(destZipFile)) + addFilesToZipStream("", source, destOutput) + destOutput.flush() + destOutput.close() + } + + private def addFilesToZipStream(parent: String, source: File, output: ZipOutputStream): Unit = { + if (source.isDirectory()) { + output.putNextEntry(new ZipEntry(parent + source.getName())) + for (file <- source.listFiles()) { + addFilesToZipStream(parent + source.getName() + File.separator, file, output) + } + } else { + val in = new FileInputStream(source) + output.putNextEntry(new ZipEntry(parent + source.getName())) + val buf = new Array[Byte](8192) + var n = 0 + while (n != -1) { + n = in.read(buf) + if (n != -1) { + output.write(buf, 0, n) + } + } + in.close() + } + } + private def copy(src: File, dst: File): Seq[File] = { src.listFiles().flatMap { f => val child = new File(dst, f.getName()) diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py index 705a368192c24..f35bc1463d51b 100644 --- a/python/pyspark/ml/feature.py +++ b/python/pyspark/ml/feature.py @@ -16,61 +16,72 @@ # from pyspark.rdd import ignore_unicode_prefix -from pyspark.ml.param.shared import HasInputCol, HasInputCols, HasOutputCol, HasNumFeatures +from pyspark.ml.param.shared import * from pyspark.ml.util import keyword_only -from pyspark.ml.wrapper import JavaTransformer +from pyspark.ml.wrapper import JavaEstimator, JavaModel, JavaTransformer from pyspark.mllib.common import inherit_doc -__all__ = ['Tokenizer', 'HashingTF', 'VectorAssembler'] +__all__ = ['Binarizer', 'HashingTF', 'IDF', 'IDFModel', 'Normalizer', 'OneHotEncoder', + 'PolynomialExpansion', 'RegexTokenizer', 'StandardScaler', 'StandardScalerModel', + 'StringIndexer', 'StringIndexerModel', 'Tokenizer', 'VectorAssembler', 'VectorIndexer', + 'Word2Vec', 'Word2VecModel'] @inherit_doc -@ignore_unicode_prefix -class Tokenizer(JavaTransformer, HasInputCol, HasOutputCol): +class Binarizer(JavaTransformer, HasInputCol, HasOutputCol): """ - A tokenizer that converts the input string to lowercase and then - splits it by white spaces. + Binarize a column of continuous features given a threshold. - >>> from pyspark.sql import Row - >>> df = sc.parallelize([Row(text="a b c")]).toDF() - >>> tokenizer = Tokenizer(inputCol="text", outputCol="words") - >>> tokenizer.transform(df).head() - Row(text=u'a b c', words=[u'a', u'b', u'c']) - >>> # Change a parameter. - >>> tokenizer.setParams(outputCol="tokens").transform(df).head() - Row(text=u'a b c', tokens=[u'a', u'b', u'c']) - >>> # Temporarily modify a parameter. - >>> tokenizer.transform(df, {tokenizer.outputCol: "words"}).head() - Row(text=u'a b c', words=[u'a', u'b', u'c']) - >>> tokenizer.transform(df).head() - Row(text=u'a b c', tokens=[u'a', u'b', u'c']) - >>> # Must use keyword arguments to specify params. - >>> tokenizer.setParams("text") - Traceback (most recent call last): - ... - TypeError: Method setParams forces keyword arguments. + >>> df = sqlContext.createDataFrame([(0.5,)], ["values"]) + >>> binarizer = Binarizer(threshold=1.0, inputCol="values", outputCol="features") + >>> binarizer.transform(df).head().features + 0.0 + >>> binarizer.setParams(outputCol="freqs").transform(df).head().freqs + 0.0 + >>> params = {binarizer.threshold: -0.5, binarizer.outputCol: "vector"} + >>> binarizer.transform(df, params).head().vector + 1.0 """ - _java_class = "org.apache.spark.ml.feature.Tokenizer" + _java_class = "org.apache.spark.ml.feature.Binarizer" + # a placeholder to make it appear in the generated doc + threshold = Param(Params._dummy(), "threshold", + "threshold in binary classification prediction, in range [0, 1]") @keyword_only - def __init__(self, inputCol=None, outputCol=None): + def __init__(self, threshold=0.0, inputCol=None, outputCol=None): """ - __init__(self, inputCol=None, outputCol=None) + __init__(self, threshold=0.0, inputCol=None, outputCol=None) """ - super(Tokenizer, self).__init__() + super(Binarizer, self).__init__() + self.threshold = Param(self, "threshold", + "threshold in binary classification prediction, in range [0, 1]") + self._setDefault(threshold=0.0) kwargs = self.__init__._input_kwargs self.setParams(**kwargs) @keyword_only - def setParams(self, inputCol=None, outputCol=None): + def setParams(self, threshold=0.0, inputCol=None, outputCol=None): """ - setParams(self, inputCol="input", outputCol="output") - Sets params for this Tokenizer. + setParams(self, threshold=0.0, inputCol=None, outputCol=None) + Sets params for this Binarizer. """ kwargs = self.setParams._input_kwargs return self._set(**kwargs) + def setThreshold(self, value): + """ + Sets the value of :py:attr:`threshold`. + """ + self.paramMap[self.threshold] = value + return self + + def getThreshold(self): + """ + Gets the value of threshold or its default value. + """ + return self.getOrDefault(self.threshold) + @inherit_doc class HashingTF(JavaTransformer, HasInputCol, HasOutputCol, HasNumFeatures): @@ -78,8 +89,7 @@ class HashingTF(JavaTransformer, HasInputCol, HasOutputCol, HasNumFeatures): Maps a sequence of terms to their term frequencies using the hashing trick. - >>> from pyspark.sql import Row - >>> df = sc.parallelize([Row(words=["a", "b", "c"])]).toDF() + >>> df = sqlContext.createDataFrame([(["a", "b", "c"],)], ["words"]) >>> hashingTF = HashingTF(numFeatures=10, inputCol="words", outputCol="features") >>> hashingTF.transform(df).head().features SparseVector(10, {7: 1.0, 8: 1.0, 9: 1.0}) @@ -112,13 +122,520 @@ def setParams(self, numFeatures=1 << 18, inputCol=None, outputCol=None): return self._set(**kwargs) +@inherit_doc +class IDF(JavaEstimator, HasInputCol, HasOutputCol): + """ + Compute the Inverse Document Frequency (IDF) given a collection of documents. + + >>> from pyspark.mllib.linalg import DenseVector + >>> df = sqlContext.createDataFrame([(DenseVector([1.0, 2.0]),), + ... (DenseVector([0.0, 1.0]),), (DenseVector([3.0, 0.2]),)], ["tf"]) + >>> idf = IDF(minDocFreq=3, inputCol="tf", outputCol="idf") + >>> idf.fit(df).transform(df).head().idf + DenseVector([0.0, 0.0]) + >>> idf.setParams(outputCol="freqs").fit(df).transform(df).collect()[1].freqs + DenseVector([0.0, 0.0]) + >>> params = {idf.minDocFreq: 1, idf.outputCol: "vector"} + >>> idf.fit(df, params).transform(df).head().vector + DenseVector([0.2877, 0.0]) + """ + + _java_class = "org.apache.spark.ml.feature.IDF" + + # a placeholder to make it appear in the generated doc + minDocFreq = Param(Params._dummy(), "minDocFreq", + "minimum of documents in which a term should appear for filtering") + + @keyword_only + def __init__(self, minDocFreq=0, inputCol=None, outputCol=None): + """ + __init__(self, minDocFreq=0, inputCol=None, outputCol=None) + """ + super(IDF, self).__init__() + self.minDocFreq = Param(self, "minDocFreq", + "minimum of documents in which a term should appear for filtering") + self._setDefault(minDocFreq=0) + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, minDocFreq=0, inputCol=None, outputCol=None): + """ + setParams(self, minDocFreq=0, inputCol=None, outputCol=None) + Sets params for this IDF. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + def setMinDocFreq(self, value): + """ + Sets the value of :py:attr:`minDocFreq`. + """ + self.paramMap[self.minDocFreq] = value + return self + + def getMinDocFreq(self): + """ + Gets the value of minDocFreq or its default value. + """ + return self.getOrDefault(self.minDocFreq) + + +class IDFModel(JavaModel): + """ + Model fitted by IDF. + """ + + +@inherit_doc +class Normalizer(JavaTransformer, HasInputCol, HasOutputCol): + """ + Normalize a vector to have unit norm using the given p-norm. + + >>> from pyspark.mllib.linalg import Vectors + >>> svec = Vectors.sparse(4, {1: 4.0, 3: 3.0}) + >>> df = sqlContext.createDataFrame([(Vectors.dense([3.0, -4.0]), svec)], ["dense", "sparse"]) + >>> normalizer = Normalizer(p=2.0, inputCol="dense", outputCol="features") + >>> normalizer.transform(df).head().features + DenseVector([0.6, -0.8]) + >>> normalizer.setParams(inputCol="sparse", outputCol="freqs").transform(df).head().freqs + SparseVector(4, {1: 0.8, 3: 0.6}) + >>> params = {normalizer.p: 1.0, normalizer.inputCol: "dense", normalizer.outputCol: "vector"} + >>> normalizer.transform(df, params).head().vector + DenseVector([0.4286, -0.5714]) + """ + + # a placeholder to make it appear in the generated doc + p = Param(Params._dummy(), "p", "the p norm value.") + + _java_class = "org.apache.spark.ml.feature.Normalizer" + + @keyword_only + def __init__(self, p=2.0, inputCol=None, outputCol=None): + """ + __init__(self, p=2.0, inputCol=None, outputCol=None) + """ + super(Normalizer, self).__init__() + self.p = Param(self, "p", "the p norm value.") + self._setDefault(p=2.0) + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, p=2.0, inputCol=None, outputCol=None): + """ + setParams(self, p=2.0, inputCol=None, outputCol=None) + Sets params for this Normalizer. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + def setP(self, value): + """ + Sets the value of :py:attr:`p`. + """ + self.paramMap[self.p] = value + return self + + def getP(self): + """ + Gets the value of p or its default value. + """ + return self.getOrDefault(self.p) + + +@inherit_doc +class OneHotEncoder(JavaTransformer, HasInputCol, HasOutputCol): + """ + A one-hot encoder that maps a column of label indices to a column of binary vectors, with + at most a single one-value. By default, the binary vector has an element for each category, so + with 5 categories, an input value of 2.0 would map to an output vector of + (0.0, 0.0, 1.0, 0.0, 0.0). If includeFirst is set to false, the first category is omitted, so + the output vector for the previous example would be (0.0, 1.0, 0.0, 0.0) and an input value + of 0.0 would map to a vector of all zeros. Including the first category makes the vector columns + linearly dependent because they sum up to one. + + TODO: This method requires the use of StringIndexer first. Decouple them. + + >>> stringIndexer = StringIndexer(inputCol="label", outputCol="indexed") + >>> model = stringIndexer.fit(stringIndDf) + >>> td = model.transform(stringIndDf) + >>> encoder = OneHotEncoder(includeFirst=False, inputCol="indexed", outputCol="features") + >>> encoder.transform(td).head().features + SparseVector(2, {}) + >>> encoder.setParams(outputCol="freqs").transform(td).head().freqs + SparseVector(2, {}) + >>> params = {encoder.includeFirst: True, encoder.outputCol: "test"} + >>> encoder.transform(td, params).head().test + SparseVector(3, {0: 1.0}) + """ + + _java_class = "org.apache.spark.ml.feature.OneHotEncoder" + + # a placeholder to make it appear in the generated doc + includeFirst = Param(Params._dummy(), "includeFirst", "include first category") + + @keyword_only + def __init__(self, includeFirst=True, inputCol=None, outputCol=None): + """ + __init__(self, includeFirst=True, inputCol=None, outputCol=None) + """ + super(OneHotEncoder, self).__init__() + self.includeFirst = Param(self, "includeFirst", "include first category") + self._setDefault(includeFirst=True) + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, includeFirst=True, inputCol=None, outputCol=None): + """ + setParams(self, includeFirst=True, inputCol=None, outputCol=None) + Sets params for this OneHotEncoder. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + def setIncludeFirst(self, value): + """ + Sets the value of :py:attr:`includeFirst`. + """ + self.paramMap[self.includeFirst] = value + return self + + def getIncludeFirst(self): + """ + Gets the value of includeFirst or its default value. + """ + return self.getOrDefault(self.includeFirst) + + +@inherit_doc +class PolynomialExpansion(JavaTransformer, HasInputCol, HasOutputCol): + """ + Perform feature expansion in a polynomial space. As said in wikipedia of Polynomial Expansion, + which is available at `http://en.wikipedia.org/wiki/Polynomial_expansion`, "In mathematics, an + expansion of a product of sums expresses it as a sum of products by using the fact that + multiplication distributes over addition". Take a 2-variable feature vector as an example: + `(x, y)`, if we want to expand it with degree 2, then we get `(x, x * x, y, x * y, y * y)`. + + >>> from pyspark.mllib.linalg import Vectors + >>> df = sqlContext.createDataFrame([(Vectors.dense([0.5, 2.0]),)], ["dense"]) + >>> px = PolynomialExpansion(degree=2, inputCol="dense", outputCol="expanded") + >>> px.transform(df).head().expanded + DenseVector([0.5, 0.25, 2.0, 1.0, 4.0]) + >>> px.setParams(outputCol="test").transform(df).head().test + DenseVector([0.5, 0.25, 2.0, 1.0, 4.0]) + """ + + _java_class = "org.apache.spark.ml.feature.PolynomialExpansion" + + # a placeholder to make it appear in the generated doc + degree = Param(Params._dummy(), "degree", "the polynomial degree to expand (>= 1)") + + @keyword_only + def __init__(self, degree=2, inputCol=None, outputCol=None): + """ + __init__(self, degree=2, inputCol=None, outputCol=None) + """ + super(PolynomialExpansion, self).__init__() + self.degree = Param(self, "degree", "the polynomial degree to expand (>= 1)") + self._setDefault(degree=2) + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, degree=2, inputCol=None, outputCol=None): + """ + setParams(self, degree=2, inputCol=None, outputCol=None) + Sets params for this PolynomialExpansion. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + def setDegree(self, value): + """ + Sets the value of :py:attr:`degree`. + """ + self.paramMap[self.degree] = value + return self + + def getDegree(self): + """ + Gets the value of degree or its default value. + """ + return self.getOrDefault(self.degree) + + +@inherit_doc +@ignore_unicode_prefix +class RegexTokenizer(JavaTransformer, HasInputCol, HasOutputCol): + """ + A regex based tokenizer that extracts tokens either by repeatedly matching the regex(default) + or using it to split the text (set matching to false). Optional parameters also allow filtering + tokens using a minimal length. + It returns an array of strings that can be empty. + + >>> df = sqlContext.createDataFrame([("a b c",)], ["text"]) + >>> reTokenizer = RegexTokenizer(inputCol="text", outputCol="words") + >>> reTokenizer.transform(df).head() + Row(text=u'a b c', words=[u'a', u'b', u'c']) + >>> # Change a parameter. + >>> reTokenizer.setParams(outputCol="tokens").transform(df).head() + Row(text=u'a b c', tokens=[u'a', u'b', u'c']) + >>> # Temporarily modify a parameter. + >>> reTokenizer.transform(df, {reTokenizer.outputCol: "words"}).head() + Row(text=u'a b c', words=[u'a', u'b', u'c']) + >>> reTokenizer.transform(df).head() + Row(text=u'a b c', tokens=[u'a', u'b', u'c']) + >>> # Must use keyword arguments to specify params. + >>> reTokenizer.setParams("text") + Traceback (most recent call last): + ... + TypeError: Method setParams forces keyword arguments. + """ + + _java_class = "org.apache.spark.ml.feature.RegexTokenizer" + # a placeholder to make it appear in the generated doc + minTokenLength = Param(Params._dummy(), "minTokenLength", "minimum token length (>= 0)") + gaps = Param(Params._dummy(), "gaps", "Set regex to match gaps or tokens") + pattern = Param(Params._dummy(), "pattern", "regex pattern used for tokenizing") + + @keyword_only + def __init__(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+", + inputCol=None, outputCol=None): + """ + __init__(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+", + inputCol=None, outputCol=None) + """ + super(RegexTokenizer, self).__init__() + self.minTokenLength = Param(self, "minLength", "minimum token length (>= 0)") + self.gaps = Param(self, "gaps", "Set regex to match gaps or tokens") + self.pattern = Param(self, "pattern", "regex pattern used for tokenizing") + self._setDefault(minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+") + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+", + inputCol=None, outputCol=None): + """ + setParams(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+", + inputCol="input", outputCol="output") + Sets params for this RegexTokenizer. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + def setMinTokenLength(self, value): + """ + Sets the value of :py:attr:`minTokenLength`. + """ + self.paramMap[self.minTokenLength] = value + return self + + def getMinTokenLength(self): + """ + Gets the value of minTokenLength or its default value. + """ + return self.getOrDefault(self.minTokenLength) + + def setGaps(self, value): + """ + Sets the value of :py:attr:`gaps`. + """ + self.paramMap[self.gaps] = value + return self + + def getGaps(self): + """ + Gets the value of gaps or its default value. + """ + return self.getOrDefault(self.gaps) + + def setPattern(self, value): + """ + Sets the value of :py:attr:`pattern`. + """ + self.paramMap[self.pattern] = value + return self + + def getPattern(self): + """ + Gets the value of pattern or its default value. + """ + return self.getOrDefault(self.pattern) + + +@inherit_doc +class StandardScaler(JavaEstimator, HasInputCol, HasOutputCol): + """ + Standardizes features by removing the mean and scaling to unit variance using column summary + statistics on the samples in the training set. + + >>> from pyspark.mllib.linalg import Vectors + >>> df = sqlContext.createDataFrame([(Vectors.dense([0.0]),), (Vectors.dense([2.0]),)], ["a"]) + >>> standardScaler = StandardScaler(inputCol="a", outputCol="scaled") + >>> model = standardScaler.fit(df) + >>> model.transform(df).collect()[1].scaled + DenseVector([1.4142]) + """ + + _java_class = "org.apache.spark.ml.feature.StandardScaler" + + # a placeholder to make it appear in the generated doc + withMean = Param(Params._dummy(), "withMean", "Center data with mean") + withStd = Param(Params._dummy(), "withStd", "Scale to unit standard deviation") + + @keyword_only + def __init__(self, withMean=False, withStd=True, inputCol=None, outputCol=None): + """ + __init__(self, withMean=False, withStd=True, inputCol=None, outputCol=None) + """ + super(StandardScaler, self).__init__() + self.withMean = Param(self, "withMean", "Center data with mean") + self.withStd = Param(self, "withStd", "Scale to unit standard deviation") + self._setDefault(withMean=False, withStd=True) + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, withMean=False, withStd=True, inputCol=None, outputCol=None): + """ + setParams(self, withMean=False, withStd=True, inputCol=None, outputCol=None) + Sets params for this StandardScaler. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + def setWithMean(self, value): + """ + Sets the value of :py:attr:`withMean`. + """ + self.paramMap[self.withMean] = value + return self + + def getWithMean(self): + """ + Gets the value of withMean or its default value. + """ + return self.getOrDefault(self.withMean) + + def setWithStd(self, value): + """ + Sets the value of :py:attr:`withStd`. + """ + self.paramMap[self.withStd] = value + return self + + def getWithStd(self): + """ + Gets the value of withStd or its default value. + """ + return self.getOrDefault(self.withStd) + + +class StandardScalerModel(JavaModel): + """ + Model fitted by StandardScaler. + """ + + +@inherit_doc +class StringIndexer(JavaEstimator, HasInputCol, HasOutputCol): + """ + A label indexer that maps a string column of labels to an ML column of label indices. + If the input column is numeric, we cast it to string and index the string values. + The indices are in [0, numLabels), ordered by label frequencies. + So the most frequent label gets index 0. + + >>> stringIndexer = StringIndexer(inputCol="label", outputCol="indexed") + >>> model = stringIndexer.fit(stringIndDf) + >>> td = model.transform(stringIndDf) + >>> sorted(set([(i[0], i[1]) for i in td.select(td.id, td.indexed).collect()]), + ... key=lambda x: x[0]) + [(0, 0.0), (1, 2.0), (2, 1.0), (3, 0.0), (4, 0.0), (5, 1.0)] + """ + + _java_class = "org.apache.spark.ml.feature.StringIndexer" + + @keyword_only + def __init__(self, inputCol=None, outputCol=None): + """ + __init__(self, inputCol=None, outputCol=None) + """ + super(StringIndexer, self).__init__() + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, inputCol=None, outputCol=None): + """ + setParams(self, inputCol=None, outputCol=None) + Sets params for this StringIndexer. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + +class StringIndexerModel(JavaModel): + """ + Model fitted by StringIndexer. + """ + + +@inherit_doc +@ignore_unicode_prefix +class Tokenizer(JavaTransformer, HasInputCol, HasOutputCol): + """ + A tokenizer that converts the input string to lowercase and then + splits it by white spaces. + + >>> df = sqlContext.createDataFrame([("a b c",)], ["text"]) + >>> tokenizer = Tokenizer(inputCol="text", outputCol="words") + >>> tokenizer.transform(df).head() + Row(text=u'a b c', words=[u'a', u'b', u'c']) + >>> # Change a parameter. + >>> tokenizer.setParams(outputCol="tokens").transform(df).head() + Row(text=u'a b c', tokens=[u'a', u'b', u'c']) + >>> # Temporarily modify a parameter. + >>> tokenizer.transform(df, {tokenizer.outputCol: "words"}).head() + Row(text=u'a b c', words=[u'a', u'b', u'c']) + >>> tokenizer.transform(df).head() + Row(text=u'a b c', tokens=[u'a', u'b', u'c']) + >>> # Must use keyword arguments to specify params. + >>> tokenizer.setParams("text") + Traceback (most recent call last): + ... + TypeError: Method setParams forces keyword arguments. + """ + + _java_class = "org.apache.spark.ml.feature.Tokenizer" + + @keyword_only + def __init__(self, inputCol=None, outputCol=None): + """ + __init__(self, inputCol=None, outputCol=None) + """ + super(Tokenizer, self).__init__() + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, inputCol=None, outputCol=None): + """ + setParams(self, inputCol="input", outputCol="output") + Sets params for this Tokenizer. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + @inherit_doc class VectorAssembler(JavaTransformer, HasInputCols, HasOutputCol): """ A feature transformer that merges multiple columns into a vector column. - >>> from pyspark.sql import Row - >>> df = sc.parallelize([Row(a=1, b=0, c=3)]).toDF() + >>> df = sqlContext.createDataFrame([(1, 0, 3)], ["a", "b", "c"]) >>> vecAssembler = VectorAssembler(inputCols=["a", "b", "c"], outputCol="features") >>> vecAssembler.transform(df).head().features DenseVector([1.0, 0.0, 3.0]) @@ -137,7 +654,6 @@ def __init__(self, inputCols=None, outputCol=None): __init__(self, inputCols=None, outputCol=None) """ super(VectorAssembler, self).__init__() - self._setDefault() kwargs = self.__init__._input_kwargs self.setParams(**kwargs) @@ -151,10 +667,208 @@ def setParams(self, inputCols=None, outputCol=None): return self._set(**kwargs) +@inherit_doc +class VectorIndexer(JavaEstimator, HasInputCol, HasOutputCol): + """ + Class for indexing categorical feature columns in a dataset of [[Vector]]. + + This has 2 usage modes: + - Automatically identify categorical features (default behavior) + - This helps process a dataset of unknown vectors into a dataset with some continuous + features and some categorical features. The choice between continuous and categorical + is based upon a maxCategories parameter. + - Set maxCategories to the maximum number of categorical any categorical feature should + have. + - E.g.: Feature 0 has unique values {-1.0, 0.0}, and feature 1 values {1.0, 3.0, 5.0}. + If maxCategories = 2, then feature 0 will be declared categorical and use indices {0, 1}, + and feature 1 will be declared continuous. + - Index all features, if all features are categorical + - If maxCategories is set to be very large, then this will build an index of unique + values for all features. + - Warning: This can cause problems if features are continuous since this will collect ALL + unique values to the driver. + - E.g.: Feature 0 has unique values {-1.0, 0.0}, and feature 1 values {1.0, 3.0, 5.0}. + If maxCategories >= 3, then both features will be declared categorical. + + This returns a model which can transform categorical features to use 0-based indices. + + Index stability: + - This is not guaranteed to choose the same category index across multiple runs. + - If a categorical feature includes value 0, then this is guaranteed to map value 0 to + index 0. This maintains vector sparsity. + - More stability may be added in the future. + + TODO: Future extensions: The following functionality is planned for the future: + - Preserve metadata in transform; if a feature's metadata is already present, + do not recompute. + - Specify certain features to not index, either via a parameter or via existing metadata. + - Add warning if a categorical feature has only 1 category. + - Add option for allowing unknown categories. + + >>> from pyspark.mllib.linalg import Vectors + >>> df = sqlContext.createDataFrame([(Vectors.dense([-1.0, 0.0]),), + ... (Vectors.dense([0.0, 1.0]),), (Vectors.dense([0.0, 2.0]),)], ["a"]) + >>> indexer = VectorIndexer(maxCategories=2, inputCol="a", outputCol="indexed") + >>> model = indexer.fit(df) + >>> model.transform(df).head().indexed + DenseVector([1.0, 0.0]) + >>> indexer.setParams(outputCol="test").fit(df).transform(df).collect()[1].test + DenseVector([0.0, 1.0]) + >>> params = {indexer.maxCategories: 3, indexer.outputCol: "vector"} + >>> model2 = indexer.fit(df, params) + >>> model2.transform(df).head().vector + DenseVector([1.0, 0.0]) + """ + + _java_class = "org.apache.spark.ml.feature.VectorIndexer" + # a placeholder to make it appear in the generated doc + maxCategories = Param(Params._dummy(), "maxCategories", + "Threshold for the number of values a categorical feature can take " + + "(>= 2). If a feature is found to have > maxCategories values, then " + + "it is declared continuous.") + + @keyword_only + def __init__(self, maxCategories=20, inputCol=None, outputCol=None): + """ + __init__(self, maxCategories=20, inputCol=None, outputCol=None) + """ + super(VectorIndexer, self).__init__() + self.maxCategories = Param(self, "maxCategories", + "Threshold for the number of values a categorical feature " + + "can take (>= 2). If a feature is found to have " + + "> maxCategories values, then it is declared continuous.") + self._setDefault(maxCategories=20) + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, maxCategories=20, inputCol=None, outputCol=None): + """ + setParams(self, maxCategories=20, inputCol=None, outputCol=None) + Sets params for this VectorIndexer. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + def setMaxCategories(self, value): + """ + Sets the value of :py:attr:`maxCategories`. + """ + self.paramMap[self.maxCategories] = value + return self + + def getMaxCategories(self): + """ + Gets the value of maxCategories or its default value. + """ + return self.getOrDefault(self.maxCategories) + + +@inherit_doc +@ignore_unicode_prefix +class Word2Vec(JavaEstimator, HasStepSize, HasMaxIter, HasSeed, HasInputCol, HasOutputCol): + """ + Word2Vec trains a model of `Map(String, Vector)`, i.e. transforms a word into a code for further + natural language processing or machine learning process. + + >>> sent = ("a b " * 100 + "a c " * 10).split(" ") + >>> doc = sqlContext.createDataFrame([(sent,), (sent,)], ["sentence"]) + >>> model = Word2Vec(vectorSize=5, seed=42, inputCol="sentence", outputCol="model").fit(doc) + >>> model.transform(doc).head().model + DenseVector([-0.0422, -0.5138, -0.2546, 0.6885, 0.276]) + """ + + _java_class = "org.apache.spark.ml.feature.Word2Vec" + # a placeholder to make it appear in the generated doc + vectorSize = Param(Params._dummy(), "vectorSize", + "the dimension of codes after transforming from words") + numPartitions = Param(Params._dummy(), "numPartitions", + "number of partitions for sentences of words") + minCount = Param(Params._dummy(), "minCount", + "the minimum number of times a token must appear to be included in the " + + "word2vec model's vocabulary") + + @keyword_only + def __init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, + seed=42, inputCol=None, outputCol=None): + """ + __init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, + seed=42, inputCol=None, outputCol=None) + """ + super(Word2Vec, self).__init__() + self.vectorSize = Param(self, "vectorSize", + "the dimension of codes after transforming from words") + self.numPartitions = Param(self, "numPartitions", + "number of partitions for sentences of words") + self.minCount = Param(self, "minCount", + "the minimum number of times a token must appear to be included " + + "in the word2vec model's vocabulary") + self._setDefault(vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, + seed=42) + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, + seed=42, inputCol=None, outputCol=None): + """ + setParams(self, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, seed=42, + inputCol=None, outputCol=None) + Sets params for this Word2Vec. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + def setVectorSize(self, value): + """ + Sets the value of :py:attr:`vectorSize`. + """ + self.paramMap[self.vectorSize] = value + return self + + def getVectorSize(self): + """ + Gets the value of vectorSize or its default value. + """ + return self.getOrDefault(self.vectorSize) + + def setNumPartitions(self, value): + """ + Sets the value of :py:attr:`numPartitions`. + """ + self.paramMap[self.numPartitions] = value + return self + + def getNumPartitions(self): + """ + Gets the value of numPartitions or its default value. + """ + return self.getOrDefault(self.numPartitions) + + def setMinCount(self, value): + """ + Sets the value of :py:attr:`minCount`. + """ + self.paramMap[self.minCount] = value + return self + + def getMinCount(self): + """ + Gets the value of minCount or its default value. + """ + return self.getOrDefault(self.minCount) + + +class Word2VecModel(JavaModel): + """ + Model fitted by Word2Vec. + """ + + if __name__ == "__main__": import doctest from pyspark.context import SparkContext - from pyspark.sql import SQLContext + from pyspark.sql import Row, SQLContext globs = globals().copy() # The small batch size here ensures that we see multiple batches, # even in these small test examples: @@ -162,8 +876,11 @@ def setParams(self, inputCols=None, outputCol=None): sqlContext = SQLContext(sc) globs['sc'] = sc globs['sqlContext'] = sqlContext - (failure_count, test_count) = doctest.testmod( - globs=globs, optionflags=doctest.ELLIPSIS) + testData = sc.parallelize([Row(id=0, label="a"), Row(id=1, label="b"), + Row(id=2, label="c"), Row(id=3, label="a"), + Row(id=4, label="a"), Row(id=5, label="c")], 2) + globs['stringIndDf'] = sqlContext.createDataFrame(testData) + (failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS) sc.stop() if failure_count: exit(-1) diff --git a/python/pyspark/ml/param/_shared_params_code_gen.py b/python/pyspark/ml/param/_shared_params_code_gen.py index c1c8e921dda87..ee901f25847bc 100644 --- a/python/pyspark/ml/param/_shared_params_code_gen.py +++ b/python/pyspark/ml/param/_shared_params_code_gen.py @@ -97,7 +97,9 @@ def get$Name(self): ("inputCol", "input column name", None), ("inputCols", "input column names", None), ("outputCol", "output column name", None), - ("numFeatures", "number of features", None)] + ("seed", "random seed", None), + ("tol", "the convergence tolerance for iterative algorithms", None), + ("stepSize", "Step size to be used for each iteration of optimization.", None)] code = [] for name, doc, defaultValueStr in shared: code.append(_gen_param_code(name, doc, defaultValueStr)) diff --git a/python/pyspark/ml/param/shared.py b/python/pyspark/ml/param/shared.py index aaf80f00085bf..5e7529c1dcf1e 100644 --- a/python/pyspark/ml/param/shared.py +++ b/python/pyspark/ml/param/shared.py @@ -308,3 +308,92 @@ def getNumFeatures(self): Gets the value of numFeatures or its default value. """ return self.getOrDefault(self.numFeatures) + + +class HasSeed(Params): + """ + Mixin for param seed: random seed. + """ + + # a placeholder to make it appear in the generated doc + seed = Param(Params._dummy(), "seed", "random seed") + + def __init__(self): + super(HasSeed, self).__init__() + #: param for random seed + self.seed = Param(self, "seed", "random seed") + if None is not None: + self._setDefault(seed=None) + + def setSeed(self, value): + """ + Sets the value of :py:attr:`seed`. + """ + self.paramMap[self.seed] = value + return self + + def getSeed(self): + """ + Gets the value of seed or its default value. + """ + return self.getOrDefault(self.seed) + + +class HasTol(Params): + """ + Mixin for param tol: the convergence tolerance for iterative algorithms. + """ + + # a placeholder to make it appear in the generated doc + tol = Param(Params._dummy(), "tol", "the convergence tolerance for iterative algorithms") + + def __init__(self): + super(HasTol, self).__init__() + #: param for the convergence tolerance for iterative algorithms + self.tol = Param(self, "tol", "the convergence tolerance for iterative algorithms") + if None is not None: + self._setDefault(tol=None) + + def setTol(self, value): + """ + Sets the value of :py:attr:`tol`. + """ + self.paramMap[self.tol] = value + return self + + def getTol(self): + """ + Gets the value of tol or its default value. + """ + return self.getOrDefault(self.tol) + + +class HasStepSize(Params): + """ + Mixin for param stepSize: Step size to be used for each iteration of optimization.. + """ + + # a placeholder to make it appear in the generated doc + stepSize = Param(Params._dummy(), "stepSize", + "Step size to be used for each iteration of optimization.") + + def __init__(self): + super(HasStepSize, self).__init__() + #: param for Step size to be used for each iteration of optimization. + self.stepSize = Param(self, "stepSize", + "Step size to be used for each iteration of optimization.") + if None is not None: + self._setDefault(stepSize=None) + + def setStepSize(self, value): + """ + Sets the value of :py:attr:`stepSize`. + """ + self.paramMap[self.stepSize] = value + return self + + def getStepSize(self): + """ + Gets the value of stepSize or its default value. + """ + return self.getOrDefault(self.stepSize) diff --git a/python/pyspark/ml/tuning.py b/python/pyspark/ml/tuning.py index 1e04c37fca53e..28e3727f2c064 100644 --- a/python/pyspark/ml/tuning.py +++ b/python/pyspark/ml/tuning.py @@ -27,24 +27,22 @@ class ParamGridBuilder(object): - """ + r""" Builder for a param grid used in grid search-based model selection. - >>> from classification import LogisticRegression + >>> from pyspark.ml.classification import LogisticRegression >>> lr = LogisticRegression() - >>> output = ParamGridBuilder().baseOn({lr.labelCol: 'l'}) \ - .baseOn([lr.predictionCol, 'p']) \ - .addGrid(lr.regParam, [1.0, 2.0, 3.0]) \ - .addGrid(lr.maxIter, [1, 5]) \ - .addGrid(lr.featuresCol, ['f']) \ - .build() - >>> expected = [ \ -{lr.regParam: 1.0, lr.featuresCol: 'f', lr.maxIter: 1, lr.labelCol: 'l', lr.predictionCol: 'p'}, \ -{lr.regParam: 2.0, lr.featuresCol: 'f', lr.maxIter: 1, lr.labelCol: 'l', lr.predictionCol: 'p'}, \ -{lr.regParam: 3.0, lr.featuresCol: 'f', lr.maxIter: 1, lr.labelCol: 'l', lr.predictionCol: 'p'}, \ -{lr.regParam: 1.0, lr.featuresCol: 'f', lr.maxIter: 5, lr.labelCol: 'l', lr.predictionCol: 'p'}, \ -{lr.regParam: 2.0, lr.featuresCol: 'f', lr.maxIter: 5, lr.labelCol: 'l', lr.predictionCol: 'p'}, \ -{lr.regParam: 3.0, lr.featuresCol: 'f', lr.maxIter: 5, lr.labelCol: 'l', lr.predictionCol: 'p'}] + >>> output = ParamGridBuilder() \ + ... .baseOn({lr.labelCol: 'l'}) \ + ... .baseOn([lr.predictionCol, 'p']) \ + ... .addGrid(lr.regParam, [1.0, 2.0]) \ + ... .addGrid(lr.maxIter, [1, 5]) \ + ... .build() + >>> expected = [ + ... {lr.regParam: 1.0, lr.maxIter: 1, lr.labelCol: 'l', lr.predictionCol: 'p'}, + ... {lr.regParam: 2.0, lr.maxIter: 1, lr.labelCol: 'l', lr.predictionCol: 'p'}, + ... {lr.regParam: 1.0, lr.maxIter: 5, lr.labelCol: 'l', lr.predictionCol: 'p'}, + ... {lr.regParam: 2.0, lr.maxIter: 5, lr.labelCol: 'l', lr.predictionCol: 'p'}] >>> len(output) == len(expected) True >>> all([m in expected for m in output]) diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index cee804f5cc1f7..a9697999e82cb 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -1275,7 +1275,7 @@ def __init__(self, jc): # container operators __contains__ = _bin_op("contains") - __getitem__ = _bin_op("getItem") + __getitem__ = _bin_op("apply") # bitwise operators bitwiseOR = _bin_op("bitwiseOR") @@ -1308,19 +1308,19 @@ def getField(self, name): >>> from pyspark.sql import Row >>> df = sc.parallelize([Row(r=Row(a=1, b="b"))]).toDF() >>> df.select(df.r.getField("b")).show() - +---+ - |r.b| - +---+ - | b| - +---+ + +----+ + |r[b]| + +----+ + | b| + +----+ >>> df.select(df.r.a).show() - +---+ - |r.a| - +---+ - | 1| - +---+ + +----+ + |r[a]| + +----+ + | 1| + +----+ """ - return Column(self._jc.getField(name)) + return self[name] def __getattr__(self, item): if item.startswith("__"): diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index 45dfedce22add..7e63f4d6461f6 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -519,6 +519,13 @@ def test_access_nested_types(self): self.assertEqual("v", df.select(df.d["k"]).first()[0]) self.assertEqual("v", df.select(df.d.getItem("k")).first()[0]) + def test_field_accessor(self): + df = self.sc.parallelize([Row(l=[1], r=Row(a=1, b="b"), d={"k": "v"})]).toDF() + self.assertEqual(1, df.select(df.l[0]).first()[0]) + self.assertEqual(1, df.select(df.r["a"]).first()[0]) + self.assertEqual("b", df.select(df.r["b"]).first()[0]) + self.assertEqual("v", df.select(df.d["k"]).first()[0]) + def test_infer_long_type(self): longrow = [Row(f1='a', f2=100000000000000)] df = self.sc.parallelize(longrow).toDF() diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala index b06bfb2ce8c8e..fc36b9f1f20d2 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala @@ -375,9 +375,9 @@ class SqlParser extends AbstractSparkSQLParser with DataTypeParser { protected lazy val primary: PackratParser[Expression] = ( literal | expression ~ ("[" ~> expression <~ "]") ^^ - { case base ~ ordinal => GetItem(base, ordinal) } + { case base ~ ordinal => UnresolvedExtractValue(base, ordinal) } | (expression <~ ".") ~ ident ^^ - { case base ~ fieldName => UnresolvedGetField(base, fieldName) } + { case base ~ fieldName => UnresolvedExtractValue(base, Literal(fieldName)) } | cast | "(" ~> expression <~ ")" | function diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala index bb7913e186a85..ecbac57ea4d62 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala @@ -348,8 +348,8 @@ class Analyzer( withPosition(u) { q.resolveChildren(nameParts, resolver).getOrElse(u) } logDebug(s"Resolving $u to $result") result - case UnresolvedGetField(child, fieldName) if child.resolved => - GetField(child, fieldName, resolver) + case UnresolvedExtractValue(child, fieldExpr) if child.resolved => + ExtractValue(child, fieldExpr, resolver) } } diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala index eb736ac3290e8..2999c2ef3efe1 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala @@ -184,7 +184,17 @@ case class ResolvedStar(expressions: Seq[NamedExpression]) extends Star { override def toString: String = expressions.mkString("ResolvedStar(", ", ", ")") } -case class UnresolvedGetField(child: Expression, fieldName: String) extends UnaryExpression { +/** + * Extracts a value or values from an Expression + * + * @param child The expression to extract value from, + * can be Map, Array, Struct or array of Structs. + * @param extraction The expression to describe the extraction, + * can be key of Map, index of Array, field name of Struct. + */ +case class UnresolvedExtractValue(child: Expression, extraction: Expression) + extends UnaryExpression { + override def dataType: DataType = throw new UnresolvedException(this, "dataType") override def foldable: Boolean = throw new UnresolvedException(this, "foldable") override def nullable: Boolean = throw new UnresolvedException(this, "nullable") @@ -193,5 +203,5 @@ case class UnresolvedGetField(child: Expression, fieldName: String) extends Unar override def eval(input: Row = null): EvaluatedType = throw new TreeNodeException(this, s"No function to evaluate expression. type: ${this.nodeName}") - override def toString: String = s"$child.$fieldName" + override def toString: String = s"$child[$extraction]" } diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala index fa6cc7a1a36cf..4c0d70203c6f5 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala @@ -22,7 +22,7 @@ import java.sql.{Date, Timestamp} import scala.language.implicitConversions import scala.reflect.runtime.universe.{TypeTag, typeTag} -import org.apache.spark.sql.catalyst.analysis.{EliminateSubQueries, UnresolvedGetField, UnresolvedAttribute} +import org.apache.spark.sql.catalyst.analysis.{EliminateSubQueries, UnresolvedExtractValue, UnresolvedAttribute} import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.catalyst.plans.logical._ import org.apache.spark.sql.catalyst.plans.{Inner, JoinType} @@ -100,8 +100,9 @@ package object dsl { def isNull: Predicate = IsNull(expr) def isNotNull: Predicate = IsNotNull(expr) - def getItem(ordinal: Expression): Expression = GetItem(expr, ordinal) - def getField(fieldName: String): UnresolvedGetField = UnresolvedGetField(expr, fieldName) + def getItem(ordinal: Expression): UnresolvedExtractValue = UnresolvedExtractValue(expr, ordinal) + def getField(fieldName: String): UnresolvedExtractValue = + UnresolvedExtractValue(expr, Literal(fieldName)) def cast(to: DataType): Expression = Cast(expr, to) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExtractValue.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExtractValue.scala new file mode 100644 index 0000000000000..e05926cbfe74b --- /dev/null +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExtractValue.scala @@ -0,0 +1,206 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.catalyst.expressions + +import scala.collection.Map + +import org.apache.spark.sql.AnalysisException +import org.apache.spark.sql.catalyst.analysis._ +import org.apache.spark.sql.types._ + +object ExtractValue { + /** + * Returns the resolved `ExtractValue`. It will return one kind of concrete `ExtractValue`, + * depend on the type of `child` and `extraction`. + * + * `child` | `extraction` | concrete `ExtractValue` + * ---------------------------------------------------------------- + * Struct | Literal String | GetStructField + * Array[Struct] | Literal String | GetArrayStructFields + * Array | Integral type | GetArrayItem + * Map | Any type | GetMapValue + */ + def apply( + child: Expression, + extraction: Expression, + resolver: Resolver): ExtractValue = { + + (child.dataType, extraction) match { + case (StructType(fields), Literal(fieldName, StringType)) => + val ordinal = findField(fields, fieldName.toString, resolver) + GetStructField(child, fields(ordinal), ordinal) + case (ArrayType(StructType(fields), containsNull), Literal(fieldName, StringType)) => + val ordinal = findField(fields, fieldName.toString, resolver) + GetArrayStructFields(child, fields(ordinal), ordinal, containsNull) + case (_: ArrayType, _) if extraction.dataType.isInstanceOf[IntegralType] => + GetArrayItem(child, extraction) + case (_: MapType, _) => + GetMapValue(child, extraction) + case (otherType, _) => + val errorMsg = otherType match { + case StructType(_) | ArrayType(StructType(_), _) => + s"Field name should be String Literal, but it's $extraction" + case _: ArrayType => + s"Array index should be integral type, but it's ${extraction.dataType}" + case other => + s"Can't extract value from $child" + } + throw new AnalysisException(errorMsg) + } + } + + def unapply(g: ExtractValue): Option[(Expression, Expression)] = { + g match { + case o: ExtractValueWithOrdinal => Some((o.child, o.ordinal)) + case _ => Some((g.child, null)) + } + } + + /** + * Find the ordinal of StructField, report error if no desired field or over one + * desired fields are found. + */ + private def findField(fields: Array[StructField], fieldName: String, resolver: Resolver): Int = { + val checkField = (f: StructField) => resolver(f.name, fieldName) + val ordinal = fields.indexWhere(checkField) + if (ordinal == -1) { + throw new AnalysisException( + s"No such struct field $fieldName in ${fields.map(_.name).mkString(", ")}") + } else if (fields.indexWhere(checkField, ordinal + 1) != -1) { + throw new AnalysisException( + s"Ambiguous reference to fields ${fields.filter(checkField).mkString(", ")}") + } else { + ordinal + } + } +} + +trait ExtractValue extends UnaryExpression { + self: Product => + + type EvaluatedType = Any +} + +/** + * Returns the value of fields in the Struct `child`. + */ +case class GetStructField(child: Expression, field: StructField, ordinal: Int) + extends ExtractValue { + + override def dataType: DataType = field.dataType + override def nullable: Boolean = child.nullable || field.nullable + override def foldable: Boolean = child.foldable + override def toString: String = s"$child.${field.name}" + + override def eval(input: Row): Any = { + val baseValue = child.eval(input).asInstanceOf[Row] + if (baseValue == null) null else baseValue(ordinal) + } +} + +/** + * Returns the array of value of fields in the Array of Struct `child`. + */ +case class GetArrayStructFields( + child: Expression, + field: StructField, + ordinal: Int, + containsNull: Boolean) extends ExtractValue { + + override def dataType: DataType = ArrayType(field.dataType, containsNull) + override def nullable: Boolean = child.nullable + override def foldable: Boolean = child.foldable + override def toString: String = s"$child.${field.name}" + + override def eval(input: Row): Any = { + val baseValue = child.eval(input).asInstanceOf[Seq[Row]] + if (baseValue == null) null else { + baseValue.map { row => + if (row == null) null else row(ordinal) + } + } + } +} + +abstract class ExtractValueWithOrdinal extends ExtractValue { + self: Product => + + def ordinal: Expression + + /** `Null` is returned for invalid ordinals. */ + override def nullable: Boolean = true + override def foldable: Boolean = child.foldable && ordinal.foldable + override def toString: String = s"$child[$ordinal]" + override def children: Seq[Expression] = child :: ordinal :: Nil + + override def eval(input: Row): Any = { + val value = child.eval(input) + if (value == null) { + null + } else { + val o = ordinal.eval(input) + if (o == null) { + null + } else { + evalNotNull(value, o) + } + } + } + + protected def evalNotNull(value: Any, ordinal: Any): Any +} + +/** + * Returns the field at `ordinal` in the Array `child` + */ +case class GetArrayItem(child: Expression, ordinal: Expression) + extends ExtractValueWithOrdinal { + + override def dataType: DataType = child.dataType.asInstanceOf[ArrayType].elementType + + override lazy val resolved = childrenResolved && + child.dataType.isInstanceOf[ArrayType] && ordinal.dataType.isInstanceOf[IntegralType] + + protected def evalNotNull(value: Any, ordinal: Any) = { + // TODO: consider using Array[_] for ArrayType child to avoid + // boxing of primitives + val baseValue = value.asInstanceOf[Seq[_]] + val index = ordinal.asInstanceOf[Int] + if (index >= baseValue.size || index < 0) { + null + } else { + baseValue(index) + } + } +} + +/** + * Returns the value of key `ordinal` in Map `child` + */ +case class GetMapValue(child: Expression, ordinal: Expression) + extends ExtractValueWithOrdinal { + + override def dataType: DataType = child.dataType.asInstanceOf[MapType].valueType + + override lazy val resolved = childrenResolved && child.dataType.isInstanceOf[MapType] + + protected def evalNotNull(value: Any, ordinal: Any) = { + val baseValue = value.asInstanceOf[Map[Any, _]] + baseValue.get(ordinal).orNull + } +} diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypes.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypes.scala index fc1f69655963d..956a2429b0b61 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypes.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypes.scala @@ -17,139 +17,8 @@ package org.apache.spark.sql.catalyst.expressions -import scala.collection.Map - -import org.apache.spark.sql.AnalysisException -import org.apache.spark.sql.catalyst.analysis.Resolver import org.apache.spark.sql.types._ -/** - * Returns the item at `ordinal` in the Array `child` or the Key `ordinal` in Map `child`. - */ -case class GetItem(child: Expression, ordinal: Expression) extends Expression { - type EvaluatedType = Any - - val children: Seq[Expression] = child :: ordinal :: Nil - /** `Null` is returned for invalid ordinals. */ - override def nullable: Boolean = true - override def foldable: Boolean = child.foldable && ordinal.foldable - - override def dataType: DataType = child.dataType match { - case ArrayType(dt, _) => dt - case MapType(_, vt, _) => vt - } - override lazy val resolved = - childrenResolved && - (child.dataType.isInstanceOf[ArrayType] || child.dataType.isInstanceOf[MapType]) - - override def toString: String = s"$child[$ordinal]" - - override def eval(input: Row): Any = { - val value = child.eval(input) - if (value == null) { - null - } else { - val key = ordinal.eval(input) - if (key == null) { - null - } else { - if (child.dataType.isInstanceOf[ArrayType]) { - // TODO: consider using Array[_] for ArrayType child to avoid - // boxing of primitives - val baseValue = value.asInstanceOf[Seq[_]] - val o = key.asInstanceOf[Int] - if (o >= baseValue.size || o < 0) { - null - } else { - baseValue(o) - } - } else { - val baseValue = value.asInstanceOf[Map[Any, _]] - baseValue.get(key).orNull - } - } - } - } -} - - -trait GetField extends UnaryExpression { - self: Product => - - type EvaluatedType = Any - override def foldable: Boolean = child.foldable - override def toString: String = s"$child.${field.name}" - - def field: StructField -} - -object GetField { - /** - * Returns the resolved `GetField`, and report error if no desired field or over one - * desired fields are found. - */ - def apply( - expr: Expression, - fieldName: String, - resolver: Resolver): GetField = { - def findField(fields: Array[StructField]): Int = { - val checkField = (f: StructField) => resolver(f.name, fieldName) - val ordinal = fields.indexWhere(checkField) - if (ordinal == -1) { - throw new AnalysisException( - s"No such struct field $fieldName in ${fields.map(_.name).mkString(", ")}") - } else if (fields.indexWhere(checkField, ordinal + 1) != -1) { - throw new AnalysisException( - s"Ambiguous reference to fields ${fields.filter(checkField).mkString(", ")}") - } else { - ordinal - } - } - expr.dataType match { - case StructType(fields) => - val ordinal = findField(fields) - StructGetField(expr, fields(ordinal), ordinal) - case ArrayType(StructType(fields), containsNull) => - val ordinal = findField(fields) - ArrayGetField(expr, fields(ordinal), ordinal, containsNull) - case otherType => - throw new AnalysisException(s"GetField is not valid on fields of type $otherType") - } - } -} - -/** - * Returns the value of fields in the Struct `child`. - */ -case class StructGetField(child: Expression, field: StructField, ordinal: Int) extends GetField { - - override def dataType: DataType = field.dataType - override def nullable: Boolean = child.nullable || field.nullable - - override def eval(input: Row): Any = { - val baseValue = child.eval(input).asInstanceOf[Row] - if (baseValue == null) null else baseValue(ordinal) - } -} - -/** - * Returns the array of value of fields in the Array of Struct `child`. - */ -case class ArrayGetField(child: Expression, field: StructField, ordinal: Int, containsNull: Boolean) - extends GetField { - - override def dataType: DataType = ArrayType(field.dataType, containsNull) - override def nullable: Boolean = child.nullable - - override def eval(input: Row): Any = { - val baseValue = child.eval(input).asInstanceOf[Seq[Row]] - if (baseValue == null) null else { - baseValue.map { row => - if (row == null) null else row(ordinal) - } - } - } -} /** * Returns an Array containing the evaluation of all children expressions. diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala index e4a60f53d6c09..d7b2f203a6934 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala @@ -227,10 +227,8 @@ object NullPropagation extends Rule[LogicalPlan] { case e @ Count(Literal(null, _)) => Cast(Literal(0L), e.dataType) case e @ IsNull(c) if !c.nullable => Literal.create(false, BooleanType) case e @ IsNotNull(c) if !c.nullable => Literal.create(true, BooleanType) - case e @ GetItem(Literal(null, _), _) => Literal.create(null, e.dataType) - case e @ GetItem(_, Literal(null, _)) => Literal.create(null, e.dataType) - case e @ StructGetField(Literal(null, _), _, _) => Literal.create(null, e.dataType) - case e @ ArrayGetField(Literal(null, _), _, _, _) => Literal.create(null, e.dataType) + case e @ ExtractValue(Literal(null, _), _) => Literal.create(null, e.dataType) + case e @ ExtractValue(_, Literal(null, _)) => Literal.create(null, e.dataType) case e @ EqualNullSafe(Literal(null, _), r) => IsNull(r) case e @ EqualNullSafe(l, Literal(null, _)) => IsNull(l) case e @ Count(expr) if !expr.nullable => Count(Literal(1)) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala index 4574934d910db..cd54d04814ea4 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala @@ -160,7 +160,7 @@ object PartialAggregation { // resolving struct field accesses, because `GetField` is not a `NamedExpression`. // (Should we just turn `GetField` into a `NamedExpression`?) namedGroupingExpressions - .get(e.transform { case Alias(g: GetField, _) => g }) + .get(e.transform { case Alias(g: ExtractValue, _) => g }) .map(_.toAttribute) .getOrElse(e) }).asInstanceOf[Seq[NamedExpression]] diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala index ae4620a4e5abf..dbb12d56f9497 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala @@ -209,7 +209,8 @@ abstract class LogicalPlan extends QueryPlan[LogicalPlan] with Logging { // For example, consider "a.b.c", where "a" is resolved to an existing attribute. // Then this will add GetField("c", GetField("b", a)), and alias // the final expression as "c". - val fieldExprs = nestedFields.foldLeft(a: Expression)(GetField(_, _, resolver)) + val fieldExprs = nestedFields.foldLeft(a: Expression)((expr, fieldName) => + ExtractValue(expr, Literal(fieldName), resolver)) val aliasName = nestedFields.last Some(Alias(fieldExprs, aliasName)()) } catch { diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionEvaluationSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionEvaluationSuite.scala index 88d36d153ceea..04fd261d16aa3 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionEvaluationSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionEvaluationSuite.scala @@ -26,7 +26,7 @@ import org.scalatest.FunSuite import org.scalatest.Matchers._ import org.apache.spark.sql.catalyst.CatalystTypeConverters -import org.apache.spark.sql.catalyst.analysis.UnresolvedGetField +import org.apache.spark.sql.catalyst.analysis.UnresolvedExtractValue import org.apache.spark.sql.catalyst.dsl.expressions._ import org.apache.spark.sql.catalyst.expressions.mathfuncs._ import org.apache.spark.sql.types._ @@ -880,7 +880,7 @@ class ExpressionEvaluationSuite extends ExpressionEvaluationBaseSuite { val row = create_row( "^Ba*n", // 0 null.asInstanceOf[UTF8String], // 1 - create_row("aa", "bb"), // 2 + create_row("aa", "bb"), // 2 Map("aa"->"bb"), // 3 Seq("aa", "bb") // 4 ) @@ -891,54 +891,79 @@ class ExpressionEvaluationSuite extends ExpressionEvaluationBaseSuite { val typeMap = MapType(StringType, StringType) val typeArray = ArrayType(StringType) - checkEvaluation(GetItem(BoundReference(3, typeMap, true), + checkEvaluation(GetMapValue(BoundReference(3, typeMap, true), Literal("aa")), "bb", row) - checkEvaluation(GetItem(Literal.create(null, typeMap), Literal("aa")), null, row) + checkEvaluation(GetMapValue(Literal.create(null, typeMap), Literal("aa")), null, row) checkEvaluation( - GetItem(Literal.create(null, typeMap), Literal.create(null, StringType)), null, row) - checkEvaluation(GetItem(BoundReference(3, typeMap, true), + GetMapValue(Literal.create(null, typeMap), Literal.create(null, StringType)), null, row) + checkEvaluation(GetMapValue(BoundReference(3, typeMap, true), Literal.create(null, StringType)), null, row) - checkEvaluation(GetItem(BoundReference(4, typeArray, true), + checkEvaluation(GetArrayItem(BoundReference(4, typeArray, true), Literal(1)), "bb", row) - checkEvaluation(GetItem(Literal.create(null, typeArray), Literal(1)), null, row) + checkEvaluation(GetArrayItem(Literal.create(null, typeArray), Literal(1)), null, row) checkEvaluation( - GetItem(Literal.create(null, typeArray), Literal.create(null, IntegerType)), null, row) - checkEvaluation(GetItem(BoundReference(4, typeArray, true), + GetArrayItem(Literal.create(null, typeArray), Literal.create(null, IntegerType)), null, row) + checkEvaluation(GetArrayItem(BoundReference(4, typeArray, true), Literal.create(null, IntegerType)), null, row) - def quickBuildGetField(expr: Expression, fieldName: String): StructGetField = { + def getStructField(expr: Expression, fieldName: String): ExtractValue = { expr.dataType match { case StructType(fields) => val field = fields.find(_.name == fieldName).get - StructGetField(expr, field, fields.indexOf(field)) + GetStructField(expr, field, fields.indexOf(field)) } } - def quickResolve(u: UnresolvedGetField): StructGetField = { - quickBuildGetField(u.child, u.fieldName) + def quickResolve(u: UnresolvedExtractValue): ExtractValue = { + ExtractValue(u.child, u.extraction, _ == _) } - checkEvaluation(quickBuildGetField(BoundReference(2, typeS, nullable = true), "a"), "aa", row) - checkEvaluation(quickBuildGetField(Literal.create(null, typeS), "a"), null, row) + checkEvaluation(getStructField(BoundReference(2, typeS, nullable = true), "a"), "aa", row) + checkEvaluation(getStructField(Literal.create(null, typeS), "a"), null, row) val typeS_notNullable = StructType( StructField("a", StringType, nullable = false) :: StructField("b", StringType, nullable = false) :: Nil ) - assert(quickBuildGetField(BoundReference(2,typeS, nullable = true), "a").nullable === true) - assert(quickBuildGetField(BoundReference(2, typeS_notNullable, nullable = false), "a").nullable + assert(getStructField(BoundReference(2,typeS, nullable = true), "a").nullable === true) + assert(getStructField(BoundReference(2, typeS_notNullable, nullable = false), "a").nullable === false) - assert(quickBuildGetField(Literal.create(null, typeS), "a").nullable === true) - assert(quickBuildGetField(Literal.create(null, typeS_notNullable), "a").nullable === true) + assert(getStructField(Literal.create(null, typeS), "a").nullable === true) + assert(getStructField(Literal.create(null, typeS_notNullable), "a").nullable === true) - checkEvaluation('c.map(typeMap).at(3).getItem("aa"), "bb", row) - checkEvaluation('c.array(typeArray.elementType).at(4).getItem(1), "bb", row) + checkEvaluation(quickResolve('c.map(typeMap).at(3).getItem("aa")), "bb", row) + checkEvaluation(quickResolve('c.array(typeArray.elementType).at(4).getItem(1)), "bb", row) checkEvaluation(quickResolve('c.struct(typeS).at(2).getField("a")), "aa", row) } + test("error message of ExtractValue") { + val structType = StructType(StructField("a", StringType, true) :: Nil) + val arrayStructType = ArrayType(structType) + val arrayType = ArrayType(StringType) + val otherType = StringType + + def checkErrorMessage( + childDataType: DataType, + fieldDataType: DataType, + errorMesage: String): Unit = { + val e = intercept[org.apache.spark.sql.AnalysisException] { + ExtractValue( + Literal.create(null, childDataType), + Literal.create(null, fieldDataType), + _ == _) + } + assert(e.getMessage().contains(errorMesage)) + } + + checkErrorMessage(structType, IntegerType, "Field name should be String Literal") + checkErrorMessage(arrayStructType, BooleanType, "Field name should be String Literal") + checkErrorMessage(arrayType, StringType, "Array index should be integral type") + checkErrorMessage(otherType, StringType, "Can't extract value from") + } + test("arithmetic") { val row = create_row(1, 2, 3, null) val c1 = 'a.int.at(0) diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ConstantFoldingSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ConstantFoldingSuite.scala index 18f92150b0966..6b7d9a85c341b 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ConstantFoldingSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ConstantFoldingSuite.scala @@ -17,7 +17,7 @@ package org.apache.spark.sql.catalyst.optimizer -import org.apache.spark.sql.catalyst.analysis.{UnresolvedGetField, EliminateSubQueries} +import org.apache.spark.sql.catalyst.analysis.{UnresolvedExtractValue, EliminateSubQueries} import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, LogicalPlan} import org.apache.spark.sql.catalyst.plans.PlanTest @@ -180,10 +180,10 @@ class ConstantFoldingSuite extends PlanTest { IsNull(Literal(null)) as 'c1, IsNotNull(Literal(null)) as 'c2, - GetItem(Literal.create(null, ArrayType(IntegerType)), 1) as 'c3, - GetItem( + UnresolvedExtractValue(Literal.create(null, ArrayType(IntegerType)), 1) as 'c3, + UnresolvedExtractValue( Literal.create(Seq(1), ArrayType(IntegerType)), Literal.create(null, IntegerType)) as 'c4, - UnresolvedGetField( + UnresolvedExtractValue( Literal.create(null, StructType(Seq(StructField("a", IntegerType, true)))), "a") as 'c5, diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Column.scala b/sql/core/src/main/scala/org/apache/spark/sql/Column.scala index 8bbe11b412214..e6e475bb82f82 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/Column.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/Column.scala @@ -23,7 +23,7 @@ import org.apache.spark.annotation.Experimental import org.apache.spark.Logging import org.apache.spark.sql.functions.lit import org.apache.spark.sql.catalyst.expressions._ -import org.apache.spark.sql.catalyst.analysis.{UnresolvedAttribute, UnresolvedStar, UnresolvedGetField} +import org.apache.spark.sql.catalyst.analysis.{UnresolvedAttribute, UnresolvedStar, UnresolvedExtractValue} import org.apache.spark.sql.types._ @@ -67,6 +67,19 @@ class Column(protected[sql] val expr: Expression) extends Logging { override def hashCode: Int = this.expr.hashCode + /** + * Extracts a value or values from a complex type. + * The following types of extraction are supported: + * - Given an Array, an integer ordinal can be used to retrieve a single value. + * - Given a Map, a key of the correct type can be used to retrieve an individual value. + * - Given a Struct, a string fieldName can be used to extract that field. + * - Given an Array of Structs, a string fieldName can be used to extract filed + * of every struct in that array, and return an Array of fields + * + * @group expr_ops + */ + def apply(field: Any): Column = UnresolvedExtractValue(expr, Literal(field)) + /** * Unary minus, i.e. negate the expression. * {{{ @@ -529,14 +542,14 @@ class Column(protected[sql] val expr: Expression) extends Logging { * * @group expr_ops */ - def getItem(key: Any): Column = GetItem(expr, Literal(key)) + def getItem(key: Any): Column = UnresolvedExtractValue(expr, Literal(key)) /** * An expression that gets a field by name in a [[StructType]]. * * @group expr_ops */ - def getField(fieldName: String): Column = UnresolvedGetField(expr, fieldName) + def getField(fieldName: String): Column = UnresolvedExtractValue(expr, Literal(fieldName)) /** * An expression that returns a substring. diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala index 1515e9b843771..d2ca8dccae574 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala @@ -449,7 +449,7 @@ class DataFrameSuite extends QueryTest { testData.collect().map { case Row(key: Int, value: String) => Row(key, value, key + 1) }.toSeq) - assert(df.schema.map(_.name).toSeq === Seq("key", "value", "newCol")) + assert(df.schema.map(_.name) === Seq("key", "value", "newCol")) } test("replace column using withColumn") { @@ -484,7 +484,7 @@ class DataFrameSuite extends QueryTest { testData.collect().map { case Row(key: Int, value: String) => Row(key, value, key + 1) }.toSeq) - assert(df.schema.map(_.name).toSeq === Seq("key", "valueRenamed", "newCol")) + assert(df.schema.map(_.name) === Seq("key", "valueRenamed", "newCol")) } test("randomSplit") { @@ -593,4 +593,10 @@ class DataFrameSuite extends QueryTest { Row(new java.math.BigDecimal(2.0))) TestSQLContext.setConf(SQLConf.CODEGEN_ENABLED, originalValue.toString) } + + test("SPARK-7133: Implement struct, array, and map field accessor") { + assert(complexData.filter(complexData("a")(0) === 2).count() == 1) + assert(complexData.filter(complexData("m")("1") === 1).count() == 1) + assert(complexData.filter(complexData("s")("key") === 1).count() == 1) + } } diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala index f30b196734c40..04d40bbb2bced 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala @@ -1204,7 +1204,7 @@ https://cwiki.apache.org/confluence/display/Hive/Enhanced+Aggregation%2C+Cube%2C nodeToExpr(qualifier) match { case UnresolvedAttribute(qualifierName) => UnresolvedAttribute(qualifierName :+ cleanIdentifier(attr)) - case other => UnresolvedGetField(other, attr) + case other => UnresolvedExtractValue(other, Literal(attr)) } /* Stars (*) */ @@ -1329,7 +1329,7 @@ https://cwiki.apache.org/confluence/display/Hive/Enhanced+Aggregation%2C+Cube%2C /* Complex datatype manipulation */ case Token("[", child :: ordinal :: Nil) => - GetItem(nodeToExpr(child), nodeToExpr(ordinal)) + UnresolvedExtractValue(nodeToExpr(child), nodeToExpr(ordinal)) /* Other functions */ case Token("TOK_FUNCTION", Token(ARRAY(), Nil) :: children) => diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala index 20ecaf092e3f8..d21a7393478ce 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala +++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala @@ -468,6 +468,17 @@ private[spark] class Client( env("SPARK_YARN_USER_ENV") = userEnvs } + // if spark.submit.pyArchives is in sparkConf, append pyArchives to PYTHONPATH + // that can be passed on to the ApplicationMaster and the executors. + if (sparkConf.contains("spark.submit.pyArchives")) { + var pythonPath = sparkConf.get("spark.submit.pyArchives") + if (env.contains("PYTHONPATH")) { + pythonPath = Seq(env.get("PYTHONPATH"), pythonPath).mkString(File.pathSeparator) + } + env("PYTHONPATH") = pythonPath + sparkConf.setExecutorEnv("PYTHONPATH", pythonPath) + } + // In cluster mode, if the deprecated SPARK_JAVA_OPTS is set, we need to propagate it to // executors. But we can't just set spark.executor.extraJavaOptions, because the driver's // SparkContext will not let that set spark* system properties, which is expected behavior for @@ -1074,7 +1085,7 @@ object Client extends Logging { val hiveConf = hiveClass.getMethod("getConf").invoke(hive) val hiveConfClass = mirror.classLoader.loadClass("org.apache.hadoop.hive.conf.HiveConf") - val hiveConfGet = (param:String) => Option(hiveConfClass + val hiveConfGet = (param: String) => Option(hiveConfClass .getMethod("get", classOf[java.lang.String]) .invoke(hiveConf, param)) @@ -1096,7 +1107,7 @@ object Client extends Logging { val hive2Token = new Token[DelegationTokenIdentifier]() hive2Token.decodeFromUrlString(tokenStr) - credentials.addToken(new Text("hive.server2.delegation.token"),hive2Token) + credentials.addToken(new Text("hive.server2.delegation.token"), hive2Token) logDebug("Added hive.Server2.delegation.token to conf.") hiveClass.getMethod("closeCurrent").invoke(null) } else { @@ -1141,13 +1152,13 @@ object Client extends Logging { logInfo("Added HBase security token to credentials.") } catch { - case e:java.lang.NoSuchMethodException => + case e: java.lang.NoSuchMethodException => logInfo("HBase Method not found: " + e) - case e:java.lang.ClassNotFoundException => + case e: java.lang.ClassNotFoundException => logDebug("HBase Class not found: " + e) - case e:java.lang.NoClassDefFoundError => + case e: java.lang.NoClassDefFoundError => logDebug("HBase Class not found: " + e) - case e:Exception => + case e: Exception => logError("Exception when obtaining HBase security token: " + e) } }