Skip to content

Commit

Permalink
Merge branch 'master' of github.com:apache/spark
Browse files Browse the repository at this point in the history
  • Loading branch information
luhenry committed May 7, 2021
2 parents 37ea990 + cf2c4ba commit 9ee1d2d
Show file tree
Hide file tree
Showing 309 changed files with 20,141 additions and 17,875 deletions.
2 changes: 1 addition & 1 deletion .github/workflows/benchmark.yml
Original file line number Diff line number Diff line change
Expand Up @@ -91,7 +91,7 @@ jobs:
# To keep the directory structure and file permissions, tar them
# See also https://github.com/actions/upload-artifact#maintaining-file-permissions-and-case-sensitive-files
echo "Preparing the benchmark results:"
tar -cvf benchmark-results-${{ github.event.inputs.jdk }}.tar `git diff --name-only`
tar -cvf benchmark-results-${{ github.event.inputs.jdk }}.tar `git diff --name-only` `git ls-files --others --exclude-standard`
- name: Upload benchmark results
uses: actions/upload-artifact@v2
with:
Expand Down
31 changes: 18 additions & 13 deletions .github/workflows/build_and_test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -493,19 +493,6 @@ jobs:
steps:
- name: Checkout Spark repository
uses: actions/checkout@v2
- name: Cache TPC-DS generated data
id: cache-tpcds-sf-1
uses: actions/cache@v2
with:
path: ./tpcds-sf-1
key: tpcds-556111e35d400f56cb0625dc16e9063d54628320
- name: Checkout TPC-DS (SF=1) generated data repository
if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
uses: actions/checkout@v2
with:
repository: maropu/spark-tpcds-sf-1
ref: 556111e35d400f56cb0625dc16e9063d54628320
path: ./tpcds-sf-1
- name: Cache Scala, SBT and Maven
uses: actions/cache@v2
with:
Expand All @@ -528,6 +515,24 @@ jobs:
uses: actions/setup-java@v1
with:
java-version: 8
- name: Cache TPC-DS generated data
id: cache-tpcds-sf-1
uses: actions/cache@v2
with:
path: ./tpcds-sf-1
key: tpcds-${{ hashFiles('.github/workflows/build_and_test.yml', 'sql/core/src/test/scala/org/apache/spark/sql/TPCDSSchema.scala') }}
- name: Checkout tpcds-kit repository
if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
uses: actions/checkout@v2
with:
repository: databricks/tpcds-kit
path: ./tpcds-kit
- name: Build tpcds-kit
if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
run: cd tpcds-kit/tools && make OS=LINUX
- name: Generate TPC-DS (SF=1) table data
if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
run: build/sbt "sql/test:runMain org.apache.spark.sql.GenTPCDSData --dsdgenDir `pwd`/tpcds-kit/tools --location `pwd`/tpcds-sf-1 --scaleFactor 1 --numPartitions 1 --overwrite"
- name: Run TPC-DS queries
run: |
SPARK_TPCDS_DATA=`pwd`/tpcds-sf-1 build/sbt "sql/testOnly org.apache.spark.sql.TPCDSQueryTestSuite"
Expand Down
13 changes: 0 additions & 13 deletions LICENSE-binary
Original file line number Diff line number Diff line change
Expand Up @@ -218,7 +218,6 @@ javax.jdo:jdo-api
joda-time:joda-time
net.sf.opencsv:opencsv
org.apache.derby:derby
org.ehcache:ehcache
org.objenesis:objenesis
org.roaringbitmap:RoaringBitmap
org.scalanlp:breeze-macros_2.12
Expand Down Expand Up @@ -261,7 +260,6 @@ net.sf.supercsv:super-csv
org.apache.arrow:arrow-format
org.apache.arrow:arrow-memory
org.apache.arrow:arrow-vector
org.apache.commons:commons-configuration2
org.apache.commons:commons-crypto
org.apache.commons:commons-lang3
org.apache.hadoop:hadoop-annotations
Expand Down Expand Up @@ -296,7 +294,6 @@ org.apache.kerby:kerby-config
org.apache.kerby:kerby-pkix
org.apache.kerby:kerby-util
org.apache.kerby:kerby-xdr
org.apache.kerby:token-provider
org.apache.orc:orc-core
org.apache.orc:orc-mapreduce
org.mortbay.jetty:jetty
Expand All @@ -316,19 +313,15 @@ com.fasterxml.jackson.jaxrs:jackson-jaxrs-json-provider
com.fasterxml.jackson.module:jackson-module-jaxb-annotations
com.fasterxml.jackson.module:jackson-module-paranamer
com.fasterxml.jackson.module:jackson-module-scala_2.12
com.fasterxml.woodstox:woodstox-core
com.github.mifmif:generex
com.github.stephenc.jcip:jcip-annotations
com.google.code.findbugs:jsr305
com.google.code.gson:gson
com.google.flatbuffers:flatbuffers-java
com.google.guava:guava
com.google.inject:guice
com.google.inject.extensions:guice-servlet
com.nimbusds:nimbus-jose-jwt
com.twitter:parquet-hadoop-bundle
commons-cli:commons-cli
commons-daemon:commons-daemon
commons-dbcp:commons-dbcp
commons-io:commons-io
commons-lang:commons-lang
Expand All @@ -340,8 +333,6 @@ javax.inject:javax.inject
javax.validation:validation-api
log4j:apache-log4j-extras
log4j:log4j
net.minidev:accessors-smart
net.minidev:json-smart
net.sf.jpam:jpam
org.apache.avro:avro
org.apache.avro:avro-ipc
Expand All @@ -357,7 +348,6 @@ org.apache.directory.server:apacheds-i18n
org.apache.directory.server:apacheds-kerberos-codec
org.apache.htrace:htrace-core
org.apache.ivy:ivy
org.apache.geronimo.specs:geronimo-jcache_1.0_spec
org.apache.mesos:mesos
org.apache.parquet:parquet-column
org.apache.parquet:parquet-common
Expand Down Expand Up @@ -432,15 +422,13 @@ BSD 2-Clause
------------

com.github.luben:zstd-jni
dnsjava:dnsjava
javolution:javolution
com.esotericsoftware:kryo-shaded
com.esotericsoftware:minlog
com.esotericsoftware:reflectasm
com.google.protobuf:protobuf-java
org.codehaus.janino:commons-compiler
org.codehaus.janino:janino
org.codehaus.woodstox:stax2-api
jline:jline
org.jodd:jodd-core
com.github.wendykierp:JTransforms
Expand All @@ -456,7 +444,6 @@ org.antlr:ST4
org.antlr:stringtemplate
org.antlr:antlr4-runtime
antlr:antlr
com.google.re2j:re2j
com.thoughtworks.paranamer:paranamer
org.scala-lang:scala-compiler
org.scala-lang:scala-library
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,8 @@ package org.apache.spark.benchmark

import java.io.{File, FileOutputStream, OutputStream}

import org.apache.spark.internal.config.Tests.IS_TESTING

/**
* A base class for generate benchmark results to a file.
* For JDK9+, JDK major version number is added to the file names to distinguish the results.
Expand All @@ -42,14 +44,25 @@ abstract class BenchmarkBase {
}

def main(args: Array[String]): Unit = {
// turning this on so the behavior between running benchmark via `spark-submit` or SBT will
// be consistent, also allow users to turn on/off certain behavior such as
// `spark.sql.codegen.factoryMode`
System.setProperty(IS_TESTING.key, "true")
val regenerateBenchmarkFiles: Boolean = System.getenv("SPARK_GENERATE_BENCHMARK_FILES") == "1"
if (regenerateBenchmarkFiles) {
val version = System.getProperty("java.version").split("\\D+")(0).toInt
val jdkString = if (version > 8) s"-jdk$version" else ""
val resultFileName =
s"${this.getClass.getSimpleName.replace("$", "")}$jdkString$suffix-results.txt"
val prefix = Benchmarks.currentProjectRoot.map(_ + "/").getOrElse("")
val file = new File(s"${prefix}benchmarks/$resultFileName")
val dir = new File(s"${prefix}benchmarks/")
if (!dir.exists()) {
// scalastyle:off println
println(s"Creating ${dir.getAbsolutePath} for benchmark results.")
// scalastyle:on println
dir.mkdirs()
}
val file = new File(dir, resultFileName)
if (!file.exists()) {
file.createNewFile()
}
Expand Down
53 changes: 26 additions & 27 deletions dev/deps/spark-deps-hadoop-2.7-hive-2.3
Original file line number Diff line number Diff line change
Expand Up @@ -131,13 +131,12 @@ jaxb-api/2.2.11//jaxb-api-2.2.11.jar
jaxb-runtime/2.3.2//jaxb-runtime-2.3.2.jar
jcl-over-slf4j/1.7.30//jcl-over-slf4j-1.7.30.jar
jdo-api/3.0.1//jdo-api-3.0.1.jar
jersey-client/2.30//jersey-client-2.30.jar
jersey-common/2.30//jersey-common-2.30.jar
jersey-container-servlet-core/2.30//jersey-container-servlet-core-2.30.jar
jersey-container-servlet/2.30//jersey-container-servlet-2.30.jar
jersey-hk2/2.30//jersey-hk2-2.30.jar
jersey-media-jaxb/2.30//jersey-media-jaxb-2.30.jar
jersey-server/2.30//jersey-server-2.30.jar
jersey-client/2.34//jersey-client-2.34.jar
jersey-common/2.34//jersey-common-2.34.jar
jersey-container-servlet-core/2.34//jersey-container-servlet-core-2.34.jar
jersey-container-servlet/2.34//jersey-container-servlet-2.34.jar
jersey-hk2/2.34//jersey-hk2-2.34.jar
jersey-server/2.34//jersey-server-2.34.jar
jetty-sslengine/6.1.26//jetty-sslengine-6.1.26.jar
jetty-util/6.1.26//jetty-util-6.1.26.jar
jetty/6.1.26//jetty-6.1.26.jar
Expand All @@ -155,26 +154,26 @@ jsr305/3.0.0//jsr305-3.0.0.jar
jta/1.1//jta-1.1.jar
jul-to-slf4j/1.7.30//jul-to-slf4j-1.7.30.jar
kryo-shaded/4.0.2//kryo-shaded-4.0.2.jar
kubernetes-client/5.3.0//kubernetes-client-5.3.0.jar
kubernetes-model-admissionregistration/5.3.0//kubernetes-model-admissionregistration-5.3.0.jar
kubernetes-model-apiextensions/5.3.0//kubernetes-model-apiextensions-5.3.0.jar
kubernetes-model-apps/5.3.0//kubernetes-model-apps-5.3.0.jar
kubernetes-model-autoscaling/5.3.0//kubernetes-model-autoscaling-5.3.0.jar
kubernetes-model-batch/5.3.0//kubernetes-model-batch-5.3.0.jar
kubernetes-model-certificates/5.3.0//kubernetes-model-certificates-5.3.0.jar
kubernetes-model-common/5.3.0//kubernetes-model-common-5.3.0.jar
kubernetes-model-coordination/5.3.0//kubernetes-model-coordination-5.3.0.jar
kubernetes-model-core/5.3.0//kubernetes-model-core-5.3.0.jar
kubernetes-model-discovery/5.3.0//kubernetes-model-discovery-5.3.0.jar
kubernetes-model-events/5.3.0//kubernetes-model-events-5.3.0.jar
kubernetes-model-extensions/5.3.0//kubernetes-model-extensions-5.3.0.jar
kubernetes-model-metrics/5.3.0//kubernetes-model-metrics-5.3.0.jar
kubernetes-model-networking/5.3.0//kubernetes-model-networking-5.3.0.jar
kubernetes-model-node/5.3.0//kubernetes-model-node-5.3.0.jar
kubernetes-model-policy/5.3.0//kubernetes-model-policy-5.3.0.jar
kubernetes-model-rbac/5.3.0//kubernetes-model-rbac-5.3.0.jar
kubernetes-model-scheduling/5.3.0//kubernetes-model-scheduling-5.3.0.jar
kubernetes-model-storageclass/5.3.0//kubernetes-model-storageclass-5.3.0.jar
kubernetes-client/5.3.1//kubernetes-client-5.3.1.jar
kubernetes-model-admissionregistration/5.3.1//kubernetes-model-admissionregistration-5.3.1.jar
kubernetes-model-apiextensions/5.3.1//kubernetes-model-apiextensions-5.3.1.jar
kubernetes-model-apps/5.3.1//kubernetes-model-apps-5.3.1.jar
kubernetes-model-autoscaling/5.3.1//kubernetes-model-autoscaling-5.3.1.jar
kubernetes-model-batch/5.3.1//kubernetes-model-batch-5.3.1.jar
kubernetes-model-certificates/5.3.1//kubernetes-model-certificates-5.3.1.jar
kubernetes-model-common/5.3.1//kubernetes-model-common-5.3.1.jar
kubernetes-model-coordination/5.3.1//kubernetes-model-coordination-5.3.1.jar
kubernetes-model-core/5.3.1//kubernetes-model-core-5.3.1.jar
kubernetes-model-discovery/5.3.1//kubernetes-model-discovery-5.3.1.jar
kubernetes-model-events/5.3.1//kubernetes-model-events-5.3.1.jar
kubernetes-model-extensions/5.3.1//kubernetes-model-extensions-5.3.1.jar
kubernetes-model-metrics/5.3.1//kubernetes-model-metrics-5.3.1.jar
kubernetes-model-networking/5.3.1//kubernetes-model-networking-5.3.1.jar
kubernetes-model-node/5.3.1//kubernetes-model-node-5.3.1.jar
kubernetes-model-policy/5.3.1//kubernetes-model-policy-5.3.1.jar
kubernetes-model-rbac/5.3.1//kubernetes-model-rbac-5.3.1.jar
kubernetes-model-scheduling/5.3.1//kubernetes-model-scheduling-5.3.1.jar
kubernetes-model-storageclass/5.3.1//kubernetes-model-storageclass-5.3.1.jar
lapack/2.0.0//lapack-2.0.0.jar
leveldbjni-all/1.8//leveldbjni-all-1.8.jar
libfb303/0.9.3//libfb303-0.9.3.jar
Expand Down
53 changes: 26 additions & 27 deletions dev/deps/spark-deps-hadoop-3.2-hive-2.3
Original file line number Diff line number Diff line change
Expand Up @@ -106,13 +106,12 @@ jaxb-api/2.2.11//jaxb-api-2.2.11.jar
jaxb-runtime/2.3.2//jaxb-runtime-2.3.2.jar
jcl-over-slf4j/1.7.30//jcl-over-slf4j-1.7.30.jar
jdo-api/3.0.1//jdo-api-3.0.1.jar
jersey-client/2.30//jersey-client-2.30.jar
jersey-common/2.30//jersey-common-2.30.jar
jersey-container-servlet-core/2.30//jersey-container-servlet-core-2.30.jar
jersey-container-servlet/2.30//jersey-container-servlet-2.30.jar
jersey-hk2/2.30//jersey-hk2-2.30.jar
jersey-media-jaxb/2.30//jersey-media-jaxb-2.30.jar
jersey-server/2.30//jersey-server-2.30.jar
jersey-client/2.34//jersey-client-2.34.jar
jersey-common/2.34//jersey-common-2.34.jar
jersey-container-servlet-core/2.34//jersey-container-servlet-core-2.34.jar
jersey-container-servlet/2.34//jersey-container-servlet-2.34.jar
jersey-hk2/2.34//jersey-hk2-2.34.jar
jersey-server/2.34//jersey-server-2.34.jar
jline/2.14.6//jline-2.14.6.jar
joda-time/2.10.5//joda-time-2.10.5.jar
jodd-core/3.5.2//jodd-core-3.5.2.jar
Expand All @@ -126,26 +125,26 @@ jsr305/3.0.0//jsr305-3.0.0.jar
jta/1.1//jta-1.1.jar
jul-to-slf4j/1.7.30//jul-to-slf4j-1.7.30.jar
kryo-shaded/4.0.2//kryo-shaded-4.0.2.jar
kubernetes-client/5.3.0//kubernetes-client-5.3.0.jar
kubernetes-model-admissionregistration/5.3.0//kubernetes-model-admissionregistration-5.3.0.jar
kubernetes-model-apiextensions/5.3.0//kubernetes-model-apiextensions-5.3.0.jar
kubernetes-model-apps/5.3.0//kubernetes-model-apps-5.3.0.jar
kubernetes-model-autoscaling/5.3.0//kubernetes-model-autoscaling-5.3.0.jar
kubernetes-model-batch/5.3.0//kubernetes-model-batch-5.3.0.jar
kubernetes-model-certificates/5.3.0//kubernetes-model-certificates-5.3.0.jar
kubernetes-model-common/5.3.0//kubernetes-model-common-5.3.0.jar
kubernetes-model-coordination/5.3.0//kubernetes-model-coordination-5.3.0.jar
kubernetes-model-core/5.3.0//kubernetes-model-core-5.3.0.jar
kubernetes-model-discovery/5.3.0//kubernetes-model-discovery-5.3.0.jar
kubernetes-model-events/5.3.0//kubernetes-model-events-5.3.0.jar
kubernetes-model-extensions/5.3.0//kubernetes-model-extensions-5.3.0.jar
kubernetes-model-metrics/5.3.0//kubernetes-model-metrics-5.3.0.jar
kubernetes-model-networking/5.3.0//kubernetes-model-networking-5.3.0.jar
kubernetes-model-node/5.3.0//kubernetes-model-node-5.3.0.jar
kubernetes-model-policy/5.3.0//kubernetes-model-policy-5.3.0.jar
kubernetes-model-rbac/5.3.0//kubernetes-model-rbac-5.3.0.jar
kubernetes-model-scheduling/5.3.0//kubernetes-model-scheduling-5.3.0.jar
kubernetes-model-storageclass/5.3.0//kubernetes-model-storageclass-5.3.0.jar
kubernetes-client/5.3.1//kubernetes-client-5.3.1.jar
kubernetes-model-admissionregistration/5.3.1//kubernetes-model-admissionregistration-5.3.1.jar
kubernetes-model-apiextensions/5.3.1//kubernetes-model-apiextensions-5.3.1.jar
kubernetes-model-apps/5.3.1//kubernetes-model-apps-5.3.1.jar
kubernetes-model-autoscaling/5.3.1//kubernetes-model-autoscaling-5.3.1.jar
kubernetes-model-batch/5.3.1//kubernetes-model-batch-5.3.1.jar
kubernetes-model-certificates/5.3.1//kubernetes-model-certificates-5.3.1.jar
kubernetes-model-common/5.3.1//kubernetes-model-common-5.3.1.jar
kubernetes-model-coordination/5.3.1//kubernetes-model-coordination-5.3.1.jar
kubernetes-model-core/5.3.1//kubernetes-model-core-5.3.1.jar
kubernetes-model-discovery/5.3.1//kubernetes-model-discovery-5.3.1.jar
kubernetes-model-events/5.3.1//kubernetes-model-events-5.3.1.jar
kubernetes-model-extensions/5.3.1//kubernetes-model-extensions-5.3.1.jar
kubernetes-model-metrics/5.3.1//kubernetes-model-metrics-5.3.1.jar
kubernetes-model-networking/5.3.1//kubernetes-model-networking-5.3.1.jar
kubernetes-model-node/5.3.1//kubernetes-model-node-5.3.1.jar
kubernetes-model-policy/5.3.1//kubernetes-model-policy-5.3.1.jar
kubernetes-model-rbac/5.3.1//kubernetes-model-rbac-5.3.1.jar
kubernetes-model-scheduling/5.3.1//kubernetes-model-scheduling-5.3.1.jar
kubernetes-model-storageclass/5.3.1//kubernetes-model-storageclass-5.3.1.jar
lapack/2.0.0//lapack-2.0.0.jar
leveldbjni-all/1.8//leveldbjni-all-1.8.jar
libfb303/0.9.3//libfb303-0.9.3.jar
Expand Down
4 changes: 4 additions & 0 deletions docs/sql-ref-ansi-compliance.md
Original file line number Diff line number Diff line change
Expand Up @@ -254,6 +254,7 @@ Below is a list of all the keywords in Spark SQL.
|DATA|non-reserved|non-reserved|non-reserved|
|DATABASE|non-reserved|non-reserved|non-reserved|
|DATABASES|non-reserved|non-reserved|non-reserved|
|DAY|non-reserved|non-reserved|non-reserved|
|DBPROPERTIES|non-reserved|non-reserved|non-reserved|
|DEFINED|non-reserved|non-reserved|non-reserved|
|DELETE|non-reserved|non-reserved|reserved|
Expand Down Expand Up @@ -336,6 +337,7 @@ Below is a list of all the keywords in Spark SQL.
|MATCHED|non-reserved|non-reserved|non-reserved|
|MERGE|non-reserved|non-reserved|non-reserved|
|MINUS|non-reserved|strict-non-reserved|non-reserved|
|MONTH|non-reserved|non-reserved|non-reserved|
|MSCK|non-reserved|non-reserved|non-reserved|
|NAMESPACE|non-reserved|non-reserved|non-reserved|
|NAMESPACES|non-reserved|non-reserved|non-reserved|
Expand Down Expand Up @@ -396,6 +398,7 @@ Below is a list of all the keywords in Spark SQL.
|ROWS|non-reserved|non-reserved|reserved|
|SCHEMA|non-reserved|non-reserved|non-reserved|
|SCHEMAS|non-reserved|non-reserved|not a keyword|
|SECOND|non-reserved|non-reserved|non-reserved|
|SELECT|reserved|non-reserved|reserved|
|SEMI|non-reserved|strict-non-reserved|non-reserved|
|SEPARATED|non-reserved|non-reserved|non-reserved|
Expand Down Expand Up @@ -456,4 +459,5 @@ Below is a list of all the keywords in Spark SQL.
|WHERE|reserved|non-reserved|reserved|
|WINDOW|non-reserved|non-reserved|reserved|
|WITH|reserved|non-reserved|reserved|
|YEAR|non-reserved|non-reserved|non-reserved|
|ZONE|non-reserved|non-reserved|non-reserved|
Loading

0 comments on commit 9ee1d2d

Please sign in to comment.