tdas · giwa · Aug 5, 2014 · Aug 5, 2014 · Aug 5, 2014 · Aug 5, 2014
diff --git a/.gitignore b/.gitignore
@@ -19,6 +19,7 @@ conf/spark-env.sh
 conf/streaming-env.sh
 conf/log4j.properties
 conf/spark-defaults.conf
+conf/hive-site.xml
 docs/_site
 docs/api
 target/
@@ -50,9 +51,11 @@ unit-tests.log
 rat-results.txt
 scalastyle.txt
 conf/*.conf
+scalastyle-output.xml
 
 # For Hive
 metastore_db/
 metastore/
 warehouse/
 TempStatsStore/
+sql/hive-thriftserver/test_warehouses
diff --git a/.rat-excludes b/.rat-excludes
@@ -25,6 +25,7 @@ log4j-defaults.properties
 bootstrap-tooltip.js
 jquery-1.11.1.min.js
 sorttable.js
+.*avsc
 .*txt
 .*json
 .*data
@@ -55,3 +56,4 @@ dist/*
 .*ipr
 .*iws
 logs
+.*scalastyle-output.xml
diff --git a/LICENSE b/LICENSE
@@ -272,7 +272,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 
 ========================================================================
-For Py4J (python/lib/py4j0.7.egg and files in assembly/lib/net/sf/py4j):
+For Py4J (python/lib/py4j-0.8.2.1-src.zip)
 ========================================================================
 
 Copyright (c) 2009-2011, Barthelemy Dagenais All rights reserved.
@@ -442,7 +442,7 @@ Written by Pavel Binko, Dino Ferrero Merlino, Wolfgang Hoschek, Tony Johnson, An
 
 
 ========================================================================
-Fo SnapTree:
+For SnapTree:
 ========================================================================
 
 SNAPTREE LICENSE
@@ -482,6 +482,24 @@ OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 SUCH DAMAGE.
 
 
+========================================================================
+For Timsort (core/src/main/java/org/apache/spark/util/collection/Sorter.java):
+========================================================================
+Copyright (C) 2008 The Android Open Source Project
+
+Licensed 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.
+
+
 ========================================================================
 BSD-style licenses
 ========================================================================
@@ -514,7 +532,7 @@ The following components are provided under a BSD-style license. See project lin
      (New BSD license) Protocol Buffer Java API (org.spark-project.protobuf:protobuf-java:2.4.1-shaded - http://code.google.com/p/protobuf)
      (The BSD License) Fortran to Java ARPACK (net.sourceforge.f2j:arpack_combined_all:0.1 - http://f2j.sourceforge.net)
      (The BSD License) xmlenc Library (xmlenc:xmlenc:0.52 - http://xmlenc.sourceforge.net)
-     (The New BSD License) Py4J (net.sf.py4j:py4j:0.8.1 - http://py4j.sourceforge.net/)
+     (The New BSD License) Py4J (net.sf.py4j:py4j:0.8.2.1 - http://py4j.sourceforge.net/)
      (Two-clause BSD-style license) JUnit-Interface (com.novocode:junit-interface:0.10 - http://github.com/szeiger/junit-interface/)
      (ISC/BSD License) jbcrypt (org.mindrot:jbcrypt:0.3m - http://www.mindrot.org/)
 
@@ -531,3 +549,4 @@ The following components are provided under the MIT License. See project link fo
      (MIT License) pyrolite (org.spark-project:pyrolite:2.0.1 - http://pythonhosted.org/Pyro4/)
      (MIT License) scopt (com.github.scopt:scopt_2.10:3.2.0 - https://github.com/scopt/scopt)
      (The MIT License) Mockito (org.mockito:mockito-all:1.8.5 - http://www.mockito.org)
+     (MIT License) jquery (https://jquery.org/license/)
diff --git a/README.md b/README.md
@@ -1,6 +1,13 @@
 # Apache Spark
 
-Lightning-Fast Cluster Computing - <http://spark.apache.org/>
+Spark is a fast and general cluster computing system for Big Data. It provides
+high-level APIs in Scala, Java, and Python, and an optimized engine that
+supports general computation graphs for data analysis. It also supports a
+rich set of higher-level tools including Spark SQL for SQL and structured
+data processing, MLLib for machine learning, GraphX for graph processing,
+and Spark Streaming.
+
+<http://spark.apache.org/>
 
 
 ## Online Documentation
@@ -69,29 +76,28 @@ can be run using:
 Spark uses the Hadoop core library to talk to HDFS and other Hadoop-supported
 storage systems. Because the protocols have changed in different versions of
 Hadoop, you must build Spark against the same version that your cluster runs.
-You can change the version by setting the `SPARK_HADOOP_VERSION` environment
-when building Spark.
+You can change the version by setting `-Dhadoop.version` when building Spark.
 
 For Apache Hadoop versions 1.x, Cloudera CDH MRv1, and other Hadoop
 versions without YARN, use:
 
     # Apache Hadoop 1.2.1
-    $ SPARK_HADOOP_VERSION=1.2.1 sbt/sbt assembly
+    $ sbt/sbt -Dhadoop.version=1.2.1 assembly
 
     # Cloudera CDH 4.2.0 with MapReduce v1
-    $ SPARK_HADOOP_VERSION=2.0.0-mr1-cdh4.2.0 sbt/sbt assembly
+    $ sbt/sbt -Dhadoop.version=2.0.0-mr1-cdh4.2.0 assembly
 
 For Apache Hadoop 2.2.X, 2.1.X, 2.0.X, 0.23.x, Cloudera CDH MRv2, and other Hadoop versions
-with YARN, also set `SPARK_YARN=true`:
+with YARN, also set `-Pyarn`:
 
     # Apache Hadoop 2.0.5-alpha
-    $ SPARK_HADOOP_VERSION=2.0.5-alpha SPARK_YARN=true sbt/sbt assembly
+    $ sbt/sbt -Dhadoop.version=2.0.5-alpha -Pyarn assembly
 
     # Cloudera CDH 4.2.0 with MapReduce v2
-    $ SPARK_HADOOP_VERSION=2.0.0-cdh4.2.0 SPARK_YARN=true sbt/sbt assembly
+    $ sbt/sbt -Dhadoop.version=2.0.0-cdh4.2.0 -Pyarn assembly
 
     # Apache Hadoop 2.2.X and newer
-    $ SPARK_HADOOP_VERSION=2.2.0 SPARK_YARN=true sbt/sbt assembly
+    $ sbt/sbt -Dhadoop.version=2.2.0 -Pyarn assembly
 
 When developing a Spark application, specify the Hadoop version by adding the
 "hadoop-client" artifact to your project's dependencies. For example, if you're
@@ -109,6 +115,15 @@ If your project is built with Maven, add this to your POM file's `<dependencies>
     </dependency>
 
 
+## A Note About Thrift JDBC server and CLI for Spark SQL
+
+Spark SQL supports Thrift JDBC server and CLI.
+See sql-programming-guide.md for more information about those features.
+You can use those features by setting `-Phive-thriftserver` when building Spark as follows.
+
+    $ sbt/sbt -Phive-thriftserver assembly
+
+
 ## Configuration
 
 Please refer to the [Configuration guide](http://spark.apache.org/docs/latest/configuration.html)

diff --git a/assembly/pom.xml b/assembly/pom.xml
@@ -32,12 +32,14 @@
   <packaging>pom</packaging>
 
   <properties>
+    <sbt.project.name>assembly</sbt.project.name>
     <spark.jar.dir>scala-${scala.binary.version}</spark.jar.dir>
     <spark.jar.basename>spark-assembly-${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>
     <deb.user>root</deb.user>
+    <deb.bin.filemode>744</deb.bin.filemode>
   </properties>
 
   <dependencies>
@@ -163,6 +165,16 @@
         </dependency>
       </dependencies>
     </profile>
+    <profile>
+      <id>hive-thriftserver</id>
+      <dependencies>
+        <dependency>
+          <groupId>org.apache.spark</groupId>
+          <artifactId>spark-hive-thriftserver_${scala.binary.version}</artifactId>
+          <version>${project.version}</version>
+        </dependency>
+      </dependencies>
+    </profile>
     <profile>
       <id>spark-ganglia-lgpl</id>
       <dependencies>
@@ -275,7 +287,7 @@
                         <user>${deb.user}</user>
                         <group>${deb.user}</group>
                         <prefix>${deb.install.path}/bin</prefix>
-                        <filemode>744</filemode>
+                        <filemode>${deb.bin.filemode}</filemode>
                       </mapper>
                     </data>
                     <data>

diff --git a/bagel/pom.xml b/bagel/pom.xml
@@ -27,6 +27,9 @@
 
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-bagel_2.10</artifactId>
+  <properties>
+    <sbt.project.name>bagel</sbt.project.name>
+  </properties>
   <packaging>jar</packaging>
   <name>Spark Project Bagel</name>
   <url>http://spark.apache.org/</url>

diff --git a/bagel/src/main/scala/org/apache/spark/bagel/Bagel.scala b/bagel/src/main/scala/org/apache/spark/bagel/Bagel.scala
@@ -72,6 +72,7 @@ object Bagel extends Logging {
     var verts = vertices
     var msgs = messages
     var noActivity = false
+    var lastRDD: RDD[(K, (V, Array[M]))] = null
     do {
       logInfo("Starting superstep " + superstep + ".")
       val startTime = System.currentTimeMillis
@@ -83,6 +84,10 @@ object Bagel extends Logging {
       val superstep_ = superstep  // Create a read-only copy of superstep for capture in closure
       val (processed, numMsgs, numActiveVerts) =
         comp[K, V, M, C](sc, grouped, compute(_, _, aggregated, superstep_), storageLevel)
+      if (lastRDD != null) {
+        lastRDD.unpersist(false)
+      }
+      lastRDD = processed
 
       val timeTaken = System.currentTimeMillis - startTime
       logInfo("Superstep %d took %d s".format(superstep, timeTaken / 1000))

diff --git a/bin/beeline b/bin/beeline
@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+
+#
+# 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.
+#
+
+#
+# Shell script for starting BeeLine
+
+# Enter posix mode for bash
+set -o posix
+
+# Figure out where Spark is installed
+FWDIR="$(cd `dirname $0`/..; pwd)"
+
+CLASS="org.apache.hive.beeline.BeeLine"
+exec "$FWDIR/bin/spark-class" $CLASS "$@"
diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh
@@ -52,6 +52,7 @@ if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SCALA_VERSION/classes"
 fi
 

diff --git a/bin/pyspark b/bin/pyspark
@@ -23,12 +23,18 @@ FWDIR="$(cd `dirname $0`/..; pwd)"
 # Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
 
+source $FWDIR/bin/utils.sh
+
 SCALA_VERSION=2.10
 
-if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
+function usage() {
   echo "Usage: ./bin/pyspark [options]" 1>&2
   $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
   exit 0
+}
+
+if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
+  usage
 fi
 
 # Exit if the user hasn't compiled Spark
@@ -52,7 +58,7 @@ export PYSPARK_PYTHON
 
 # Add the PySpark classes to the Python path:
 export PYTHONPATH=$SPARK_HOME/python/:$PYTHONPATH
-export PYTHONPATH=$SPARK_HOME/python/lib/py4j-0.8.1-src.zip:$PYTHONPATH
+export PYTHONPATH=$SPARK_HOME/python/lib/py4j-0.8.2.1-src.zip:$PYTHONPATH
 
 # Load the PySpark shell.py script when ./pyspark is used interactively:
 export OLD_PYTHONSTARTUP=$PYTHONSTARTUP
@@ -66,10 +72,11 @@ fi
 # Build up arguments list manually to preserve quotes and backslashes.
 # We export Spark submit arguments as an environment variable because shell.py must run as a
 # PYTHONSTARTUP script, which does not take in arguments. This is required for IPython notebooks.
-
+SUBMIT_USAGE_FUNCTION=usage
+gatherSparkSubmitOpts "$@"
 PYSPARK_SUBMIT_ARGS=""
 whitespace="[[:space:]]"
-for i in "$@"; do
+for i in "${SUBMISSION_OPTS[@]}"; do
   if [[ $i =~ \" ]]; then i=$(echo $i | sed 's/\"/\\\"/g'); fi
   if [[ $i =~ $whitespace ]]; then i=\"$i\"; fi
   PYSPARK_SUBMIT_ARGS="$PYSPARK_SUBMIT_ARGS $i"
@@ -90,7 +97,10 @@ fi
 if [[ "$1" =~ \.py$ ]]; then
   echo -e "\nWARNING: Running python applications through ./bin/pyspark is deprecated as of Spark 1.0." 1>&2
   echo -e "Use ./bin/spark-submit <python file>\n" 1>&2
-  exec $FWDIR/bin/spark-submit "$@"
+  primary=$1
+  shift
+  gatherSparkSubmitOpts "$@"
+  exec $FWDIR/bin/spark-submit "${SUBMISSION_OPTS[@]}" $primary "${APPLICATION_OPTS[@]}"
 else
   # Only use ipython if no command line arguments were provided [SPARK-1134]
   if [[ "$IPYTHON" = "1" ]]; then

diff --git a/bin/pyspark2.cmd b/bin/pyspark2.cmd
@@ -45,7 +45,7 @@ rem Figure out which Python to use.
 if [%PYSPARK_PYTHON%] == [] set PYSPARK_PYTHON=python
 
 set PYTHONPATH=%FWDIR%python;%PYTHONPATH%
-set PYTHONPATH=%FWDIR%python\lib\py4j-0.8.1-src.zip;%PYTHONPATH%
+set PYTHONPATH=%FWDIR%python\lib\py4j-0.8.2.1-src.zip;%PYTHONPATH%
 
 set OLD_PYTHONSTARTUP=%PYTHONSTARTUP%
 set PYTHONSTARTUP=%FWDIR%python\pyspark\shell.py

diff --git a/bin/run-example b/bin/run-example
@@ -29,7 +29,8 @@ if [ -n "$1" ]; then
 else
   echo "Usage: ./bin/run-example <example-class> [example-args]" 1>&2
   echo "  - set MASTER=XX to use a specific master" 1>&2
-  echo "  - can use abbreviated example class name (e.g. SparkPi, mllib.LinearRegression)" 1>&2
+  echo "  - can use abbreviated example class name relative to com.apache.spark.examples" 1>&2
+  echo "     (e.g. SparkPi, mllib.LinearRegression, streaming.KinesisWordCountASL)" 1>&2
   exit 1
 fi
 

diff --git a/bin/run-example2.cmd b/bin/run-example2.cmd
@@ -32,7 +32,8 @@ rem Test that an argument was given
 if not "x%1"=="x" goto arg_given
   echo Usage: run-example ^<example-class^> [example-args]
   echo   - set MASTER=XX to use a specific master
-  echo   - can use abbreviated example class name (e.g. SparkPi, mllib.LinearRegression)
+  echo   - can use abbreviated example class name relative to com.apache.spark.examples
+  echo      (e.g. SparkPi, mllib.LinearRegression, streaming.KinesisWordCountASL)
   goto exit
 :arg_given
 

diff --git a/bin/spark-class b/bin/spark-class
@@ -110,9 +110,9 @@ export JAVA_OPTS
 
 TOOLS_DIR="$FWDIR"/tools
 SPARK_TOOLS_JAR=""
-if [ -e "$TOOLS_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar ]; then
+if [ -e "$TOOLS_DIR"/target/scala-$SCALA_VERSION/spark-tools*[0-9Tg].jar ]; then
   # Use the JAR from the SBT build
-  export SPARK_TOOLS_JAR=`ls "$TOOLS_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar`
+  export SPARK_TOOLS_JAR=`ls "$TOOLS_DIR"/target/scala-$SCALA_VERSION/spark-tools*[0-9Tg].jar`
 fi
 if [ -e "$TOOLS_DIR"/target/spark-tools*[0-9Tg].jar ]; then
   # Use the JAR from the Maven build