Merge branch 'master' of github.com:apache/spark into event-log-tests

.gitignore

@@ -18,6 +18,7 @@ conf/java-opts
 conf/spark-env.sh
 conf/streaming-env.sh
 conf/log4j.properties
+conf/spark-defaults.conf
 docs/_site
 docs/api
 target/

.rat-excludes

@@ -11,6 +11,7 @@ RELEASE
 control
 docs
 fairscheduler.xml.template
+spark-defaults.conf.template
 log4j.properties
 log4j.properties.template
 metrics.properties.template
@@ -39,4 +40,6 @@ work
 .*\.q
 golden
 test.out/*
-.*iml
+.*iml
+service.properties
+db.lck

README.md

@@ -10,20 +10,33 @@ guide, on the project webpage at <http://spark.apache.org/documentation.html>.
 This README file only contains basic setup instructions.
 
 
-## Building
+## Building Spark
 
-Spark requires Scala 2.10. The project is built using Simple Build Tool (SBT),
-which can be obtained [here](http://www.scala-sbt.org). If SBT is installed we
-will use the system version of sbt otherwise we will attempt to download it
-automatically. To build Spark and its example programs, run:
+Spark is built on Scala 2.10. To build Spark and its example programs, run:
 
     ./sbt/sbt assembly
 
-Once you've built Spark, the easiest way to start using it is the shell:
+## Interactive Scala Shell
+
+The easiest way to start using Spark is through the Scala shell:
 
     ./bin/spark-shell
 
-Or, for the Python API, the Python shell (`./bin/pyspark`).
+Try the following command, which should return 1000:
+
+    scala> sc.parallelize(1 to 1000).count()
+
+## Interactive Python Shell
+
+Alternatively, if you prefer Python, you can use the Python shell:
+
+    ./bin/pyspark
+
+And run the following command, which should also return 1000:
+
+    >>> sc.parallelize(range(1000)).count()
+
+## Example Programs
 
 Spark also comes with several sample programs in the `examples` directory.
 To run one of them, use `./bin/run-example <class> <params>`. For example:
@@ -38,13 +51,13 @@ All of the Spark samples take a `<master>` parameter that is the cluster URL
 to connect to. This can be a mesos:// or spark:// URL, or "local" to run
 locally with one thread, or "local[N]" to run locally with N threads.
 
-## Running tests
+## Running Tests
 
-Testing first requires [Building](#building) Spark. Once Spark is built, tests
+Testing first requires [building Spark](#building-spark). Once Spark is built, tests
 can be run using:
 
-`./sbt/sbt test`
- 
+    ./sbt/sbt test
+
 ## A Note About Hadoop Versions
 
 Spark uses the Hadoop core library to talk to HDFS and other Hadoop-supported

assembly/pom.xml

@@ -33,7 +33,7 @@
 
   <properties>
     <spark.jar.dir>scala-${scala.binary.version}</spark.jar.dir>
-    <spark.jar.basename>${project.artifactId}-${project.version}-hadoop${hadoop.version}.jar</spark.jar.basename>
+    <spark.jar.basename>spark-assembly-${project.version}-hadoop${hadoop.version}.jar</spark.jar.basename>
     <spark.jar>${project.build.directory}/${spark.jar.dir}/${spark.jar.basename}</spark.jar>
     <deb.pkg.name>spark</deb.pkg.name>
     <deb.install.path>/usr/share/spark</deb.install.path>

bagel/src/test/scala/org/apache/spark/bagel/BagelSuite.scala

@@ -24,6 +24,8 @@ import org.scalatest.time.SpanSugar._
 import org.apache.spark._
 import org.apache.spark.storage.StorageLevel
 
+import scala.language.postfixOps
+
 class TestVertex(val active: Boolean, val age: Int) extends Vertex with Serializable
 class TestMessage(val targetId: String) extends Message[String] with Serializable
 

bin/compute-classpath.cmd

@@ -1,69 +1,88 @@
-@echo off
-
-rem
-rem Licensed to the Apache Software Foundation (ASF) under one or more
-rem contributor license agreements.  See the NOTICE file distributed with
-rem this work for additional information regarding copyright ownership.
-rem The ASF licenses this file to You under the Apache License, Version 2.0
-rem (the "License"); you may not use this file except in compliance with
-rem the License.  You may obtain a copy of the License at
-rem
-rem    http://www.apache.org/licenses/LICENSE-2.0
-rem
-rem Unless required by applicable law or agreed to in writing, software
-rem distributed under the License is distributed on an "AS IS" BASIS,
-rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-rem See the License for the specific language governing permissions and
-rem limitations under the License.
-rem
-
-rem This script computes Spark's classpath and prints it to stdout; it's used by both the "run"
-rem script and the ExecutorRunner in standalone cluster mode.
-
-set SCALA_VERSION=2.10
-
-rem Figure out where the Spark framework is installed
-set FWDIR=%~dp0..\
-
-rem Load environment variables from conf\spark-env.cmd, if it exists
-if exist "%FWDIR%conf\spark-env.cmd" call "%FWDIR%conf\spark-env.cmd"
-
-rem Build up classpath
-set CLASSPATH=%FWDIR%conf
-if exist "%FWDIR%RELEASE" (
-  for %%d in ("%FWDIR%jars\spark-assembly*.jar") do (
-    set ASSEMBLY_JAR=%%d
-  )
-) else (
-  for %%d in ("%FWDIR%assembly\target\scala-%SCALA_VERSION%\spark-assembly*hadoop*.jar") do (
-    set ASSEMBLY_JAR=%%d
-  )
-)
-set CLASSPATH=%CLASSPATH%;%ASSEMBLY_JAR%
-
-if "x%SPARK_TESTING%"=="x1" (
-  rem Add test clases to path
-  set CLASSPATH=%CLASSPATH%;%FWDIR%core\target\scala-%SCALA_VERSION%\test-classes
-  set CLASSPATH=%CLASSPATH%;%FWDIR%repl\target\scala-%SCALA_VERSION%\test-classes
-  set CLASSPATH=%CLASSPATH%;%FWDIR%mllib\target\scala-%SCALA_VERSION%\test-classes
-  set CLASSPATH=%CLASSPATH%;%FWDIR%bagel\target\scala-%SCALA_VERSION%\test-classes
-  set CLASSPATH=%CLASSPATH%;%FWDIR%streaming\target\scala-%SCALA_VERSION%\test-classes
-)
-
-rem Add hadoop conf dir - else FileSystem.*, etc fail
-rem Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
-rem the configurtion files.
-if "x%HADOOP_CONF_DIR%"=="x" goto no_hadoop_conf_dir
-  set CLASSPATH=%CLASSPATH%;%HADOOP_CONF_DIR%
-:no_hadoop_conf_dir
-
-if "x%YARN_CONF_DIR%"=="x" goto no_yarn_conf_dir
-  set CLASSPATH=%CLASSPATH%;%YARN_CONF_DIR%
-:no_yarn_conf_dir
-
-rem A bit of a hack to allow calling this script within run2.cmd without seeing output
-if "%DONT_PRINT_CLASSPATH%"=="1" goto exit
-
-echo %CLASSPATH%
-
-:exit
+@echo off
+
+rem
+rem Licensed to the Apache Software Foundation (ASF) under one or more
+rem contributor license agreements.  See the NOTICE file distributed with
+rem this work for additional information regarding copyright ownership.
+rem The ASF licenses this file to You under the Apache License, Version 2.0
+rem (the "License"); you may not use this file except in compliance with
+rem the License.  You may obtain a copy of the License at
+rem
+rem    http://www.apache.org/licenses/LICENSE-2.0
+rem
+rem Unless required by applicable law or agreed to in writing, software
+rem distributed under the License is distributed on an "AS IS" BASIS,
+rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+rem See the License for the specific language governing permissions and
+rem limitations under the License.
+rem
+
+rem This script computes Spark's classpath and prints it to stdout; it's used by both the "run"
+rem script and the ExecutorRunner in standalone cluster mode.
+
+set SCALA_VERSION=2.10
+
+rem Figure out where the Spark framework is installed
+set FWDIR=%~dp0..\
+
+rem Load environment variables from conf\spark-env.cmd, if it exists
+if exist "%FWDIR%conf\spark-env.cmd" call "%FWDIR%conf\spark-env.cmd"
+
+rem Build up classpath
+set CLASSPATH=%FWDIR%conf
+if exist "%FWDIR%RELEASE" (
+  for %%d in ("%FWDIR%jars\spark-assembly*.jar") do (
+    set ASSEMBLY_JAR=%%d
+  )
+) else (
+  for %%d in ("%FWDIR%assembly\target\scala-%SCALA_VERSION%\spark-assembly*hadoop*.jar") do (
+    set ASSEMBLY_JAR=%%d
+  )
+)
+
+set CLASSPATH=%CLASSPATH%;%ASSEMBLY_JAR%
+
+set SPARK_CLASSES=%FWDIR%core\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%repl\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%mllib\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%bagel\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%graphx\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%streaming\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%tools\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%sql\catalyst\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%sql\core\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%sql\hive\target\scala-%SCALA_VERSION%\classes
+
+set SPARK_TEST_CLASSES=%FWDIR%core\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%repl\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%mllib\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%bagel\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%graphx\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%streaming\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%sql\catalyst\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%sql\core\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%sql\hive\target\scala-%SCALA_VERSION%\test-classes
+
+if "x%SPARK_TESTING%"=="x1" (
+  rem Add test clases to path - note, add SPARK_CLASSES and SPARK_TEST_CLASSES before CLASSPATH
+  rem so that local compilation takes precedence over assembled jar
+  set CLASSPATH=%SPARK_CLASSES%;%SPARK_TEST_CLASSES%;%CLASSPATH%
+)
+
+rem Add hadoop conf dir - else FileSystem.*, etc fail
+rem Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
+rem the configurtion files.
+if "x%HADOOP_CONF_DIR%"=="x" goto no_hadoop_conf_dir
+  set CLASSPATH=%CLASSPATH%;%HADOOP_CONF_DIR%
+:no_hadoop_conf_dir
+
+if "x%YARN_CONF_DIR%"=="x" goto no_yarn_conf_dir
+  set CLASSPATH=%CLASSPATH%;%YARN_CONF_DIR%
+:no_yarn_conf_dir
+
+rem A bit of a hack to allow calling this script within run2.cmd without seeing output
+if "%DONT_PRINT_CLASSPATH%"=="1" goto exit
+
+echo %CLASSPATH%
+
+:exit

bin/compute-classpath.sh

@@ -50,9 +50,9 @@ if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then
 else
   # Else use spark-assembly jar from either RELEASE or assembly directory
   if [ -f "$FWDIR/RELEASE" ]; then
-    ASSEMBLY_JAR=`ls "$FWDIR"/jars/spark*-assembly*.jar`
+    ASSEMBLY_JAR=`ls "$FWDIR"/lib/spark-assembly*hadoop*.jar`
   else
-    ASSEMBLY_JAR=`ls "$ASSEMBLY_DIR"/spark*-assembly*hadoop*.jar`
+    ASSEMBLY_JAR=`ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*.jar`
   fi
   CLASSPATH="$CLASSPATH:$ASSEMBLY_JAR"
 fi

bin/run-example

@@ -40,12 +40,15 @@ fi
 # Figure out the JAR file that our examples were packaged into. This includes a bit of a hack
 # to avoid the -sources and -doc packages that are built by publish-local.
 EXAMPLES_DIR="$FWDIR"/examples
-SPARK_EXAMPLES_JAR=""
-if [ -e "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar ]; then
-  export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar`
+
+if [ -f "$FWDIR/RELEASE" ]; then
+  export SPARK_EXAMPLES_JAR=`ls "$FWDIR"/lib/spark-examples-*hadoop*.jar`
+elif [ -e "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/spark-examples-*hadoop*.jar ]; then
+  export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/spark-examples-*hadoop*.jar`
 fi
+
 if [[ -z $SPARK_EXAMPLES_JAR ]]; then
-  echo "Failed to find Spark examples assembly in $FWDIR/examples/target" >&2
+  echo "Failed to find Spark examples assembly in $FWDIR/lib or $FWDIR/examples/target" >&2
   echo "You need to build Spark with sbt/sbt assembly before running this program" >&2
   exit 1
 fi
@@ -75,7 +78,6 @@ fi
 
 # Set JAVA_OPTS to be able to load native libraries and to set heap size
 JAVA_OPTS="$SPARK_JAVA_OPTS"
-JAVA_OPTS="$JAVA_OPTS -Djava.library.path=$SPARK_LIBRARY_PATH"
 # Load extra JAVA_OPTS from conf/java-opts, if it exists
 if [ -e "$FWDIR/conf/java-opts" ] ; then
   JAVA_OPTS="$JAVA_OPTS `cat $FWDIR/conf/java-opts`"

bin/spark-class

@@ -98,7 +98,7 @@ fi
 
 # Set JAVA_OPTS to be able to load native libraries and to set heap size
 JAVA_OPTS="$OUR_JAVA_OPTS"
-JAVA_OPTS="$JAVA_OPTS -Djava.library.path=$SPARK_LIBRARY_PATH"
+JAVA_OPTS="$JAVA_OPTS -Djava.library.path=$_SPARK_LIBRARY_PATH"
 JAVA_OPTS="$JAVA_OPTS -Xms$OUR_JAVA_MEM -Xmx$OUR_JAVA_MEM"
 # Load extra JAVA_OPTS from conf/java-opts, if it exists
 if [ -e "$FWDIR/conf/java-opts" ] ; then