synced with apache spark and resolved merge conflict

Author: leahmcguire

.rat-excludes

@@ -1,4 +1,5 @@
 target
+cache
 .gitignore
 .gitattributes
 .project
@@ -18,6 +19,7 @@ fairscheduler.xml.template
 spark-defaults.conf.template
 log4j.properties
 log4j.properties.template
+metrics.properties
 metrics.properties.template
 slaves
 slaves.template

README.md

@@ -26,7 +26,7 @@ To build Spark and its example programs, run:
 
 (You do not need to do this if you downloaded a pre-built package.)
 More detailed documentation is available from the project site, at
-["Building Spark with Maven"](http://spark.apache.org/docs/latest/building-spark.html).
+["Building Spark"](http://spark.apache.org/docs/latest/building-spark.html).
 
 ## Interactive Scala Shell
 

assembly/pom.xml

@@ -36,19 +36,9 @@
     <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>
-    <!-- Promote Guava to compile scope in this module so it's included while shading. -->
-    <dependency>
-      <groupId>com.google.guava</groupId>
-      <artifactId>guava</artifactId>
-      <scope>compile</scope>
-    </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-core_${scala.binary.version}</artifactId>
@@ -124,6 +114,16 @@
                 <exclude>META-INF/*.RSA</exclude>
               </excludes>
             </filter>
+            <filter>
+              <!-- Exclude libgfortran, libgcc for license issues -->
+              <artifact>org.jblas:jblas</artifact>
+              <excludes>
+                <!-- Linux amd64 is OK; not statically linked -->
+                <exclude>lib/static/Linux/i386/**</exclude>
+                <exclude>lib/static/Mac OS X/**</exclude>
+                <exclude>lib/static/Windows/**</exclude>
+              </excludes>
+            </filter>
           </filters>
         </configuration>
         <executions>
@@ -133,20 +133,6 @@
               <goal>shade</goal>
             </goals>
             <configuration>
-              <relocations>
-                <relocation>
-                  <pattern>com.google</pattern>
-                  <shadedPattern>org.spark-project.guava</shadedPattern>
-                  <includes>
-                    <include>com.google.common.**</include>
-                  </includes>
-                  <excludes>
-                    <exclude>com/google/common/base/Absent*</exclude>
-                    <exclude>com/google/common/base/Optional*</exclude>
-                    <exclude>com/google/common/base/Present*</exclude>
-                  </excludes>
-                </relocation>
-              </relocations>
               <transformers>
                 <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
                 <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
@@ -237,113 +223,6 @@
         </plugins>
       </build>
     </profile>
-    <profile>
-      <id>deb</id>
-      <build>
-        <plugins>
-          <plugin>
-            <groupId>org.codehaus.mojo</groupId>
-            <artifactId>buildnumber-maven-plugin</artifactId>
-            <version>1.2</version>
-            <executions>
-              <execution>
-                <phase>validate</phase>
-                <goals>
-                  <goal>create</goal>
-                </goals>
-                <configuration>
-                  <shortRevisionLength>8</shortRevisionLength>
-                </configuration>
-              </execution>
-            </executions>
-          </plugin>
-          <plugin>
-            <groupId>org.vafer</groupId>
-            <artifactId>jdeb</artifactId>
-            <version>0.11</version>
-            <executions>
-              <execution>
-                <phase>package</phase>
-                <goals>
-                  <goal>jdeb</goal>
-                </goals>
-                <configuration>
-                  <deb>${project.build.directory}/${deb.pkg.name}_${project.version}-${buildNumber}_all.deb</deb>
-                  <attach>false</attach>
-                  <compression>gzip</compression>
-                  <dataSet>
-                    <data>
-                      <src>${spark.jar}</src>
-                      <type>file</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}/jars</prefix>
-                      </mapper>
-                    </data>
-                    <data>
-                      <src>${basedir}/src/deb/RELEASE</src>
-                      <type>file</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}</prefix>
-                      </mapper>
-                    </data>
-                    <data>
-                      <src>${basedir}/../conf</src>
-                      <type>directory</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}/conf</prefix>
-                        <filemode>744</filemode>
-                      </mapper>
-                    </data>
-                    <data>
-                      <src>${basedir}/../bin</src>
-                      <type>directory</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}/bin</prefix>
-                        <filemode>${deb.bin.filemode}</filemode>
-                      </mapper>
-                    </data>
-                    <data>
-                      <src>${basedir}/../sbin</src>
-                      <type>directory</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}/sbin</prefix>
-                        <filemode>744</filemode>
-                      </mapper>
-                    </data>
-                    <data>
-                      <src>${basedir}/../python</src>
-                      <type>directory</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}/python</prefix>
-                        <filemode>744</filemode>
-                      </mapper>
-                    </data>
-                  </dataSet>
-                </configuration>
-              </execution>
-            </executions>
-          </plugin>
-        </plugins>
-      </build>
-    </profile>
     <profile>
       <id>kinesis-asl</id>
       <dependencies>

assembly/src/deb/RELEASE

@@ -50,8 +50,8 @@ fi
 if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   echo "NOTE: SPARK_PREPEND_CLASSES is set, placing locally compiled Spark"\
     "classes ahead of assembly." >&2
+  # Spark classes
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SPARK_SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
   CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SPARK_SCALA_VERSION/classes"
@@ -63,6 +63,8 @@ if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SPARK_SCALA_VERSION/classes"
+  # Jars for shaded deps in their original form (copied here during build)
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
 fi
 
 # Use spark-assembly jar from either RELEASE or assembly directory
@@ -72,22 +74,25 @@ else
   assembly_folder="$ASSEMBLY_DIR"
 fi
 
-num_jars="$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*\.jar$" | wc -l)"
-if [ "$num_jars" -eq "0" ]; then
-  echo "Failed to find Spark assembly in $assembly_folder"
-  echo "You need to build Spark before running this program."
-  exit 1
-fi
+num_jars=0
+
+for f in "${assembly_folder}"/spark-assembly*hadoop*.jar; do
+  if [[ ! -e "$f" ]]; then
+    echo "Failed to find Spark assembly in $assembly_folder" 1>&2
+    echo "You need to build Spark before running this program." 1>&2
+    exit 1
+  fi
+  ASSEMBLY_JAR="$f"
+  num_jars=$((num_jars+1))
+done
+
 if [ "$num_jars" -gt "1" ]; then
-  jars_list=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*.jar$")
-  echo "Found multiple Spark assembly jars in $assembly_folder:"
-  echo "$jars_list"
-  echo "Please remove all but one jar."
+  echo "Found multiple Spark assembly jars in $assembly_folder:" 1>&2
+  ls "${assembly_folder}"/spark-assembly*hadoop*.jar 1>&2
+  echo "Please remove all but one jar." 1>&2
   exit 1
 fi
 
-ASSEMBLY_JAR="$(ls "$assembly_folder"/spark-assembly*hadoop*.jar 2>/dev/null)"
-
 # Verify that versions of java used to build the jars and run Spark are compatible
 jar_error_check=$("$JAR_CMD" -tf "$ASSEMBLY_JAR" nonexistent/class/path 2>&1)
 if [[ "$jar_error_check" =~ "invalid CEN header" ]]; then

assembly/src/deb/control/control

@@ -35,17 +35,32 @@ else
 fi
 
 if [ -f "$FWDIR/RELEASE" ]; then
-  export SPARK_EXAMPLES_JAR="`ls "$FWDIR"/lib/spark-examples-*hadoop*.jar`"
-elif [ -e "$EXAMPLES_DIR"/target/scala-$SPARK_SCALA_VERSION/spark-examples-*hadoop*.jar ]; then
-  export SPARK_EXAMPLES_JAR="`ls "$EXAMPLES_DIR"/target/scala-$SPARK_SCALA_VERSION/spark-examples-*hadoop*.jar`"
+  JAR_PATH="${FWDIR}/lib"
+else
+  JAR_PATH="${EXAMPLES_DIR}/target/scala-${SPARK_SCALA_VERSION}"
 fi
 
-if [[ -z "$SPARK_EXAMPLES_JAR" ]]; then
-  echo "Failed to find Spark examples assembly in $FWDIR/lib or $FWDIR/examples/target" 1>&2
-  echo "You need to build Spark before running this program" 1>&2
+JAR_COUNT=0
+
+for f in "${JAR_PATH}"/spark-examples-*hadoop*.jar; do
+  if [[ ! -e "$f" ]]; then
+    echo "Failed to find Spark examples assembly in $FWDIR/lib or $FWDIR/examples/target" 1>&2
+    echo "You need to build Spark before running this program" 1>&2
+    exit 1
+  fi
+  SPARK_EXAMPLES_JAR="$f"
+  JAR_COUNT=$((JAR_COUNT+1))
+done
+
+if [ "$JAR_COUNT" -gt "1" ]; then
+  echo "Found multiple Spark examples assembly jars in ${JAR_PATH}" 1>&2
+  ls "${JAR_PATH}"/spark-examples-*hadoop*.jar 1>&2
+  echo "Please remove all but one jar." 1>&2
   exit 1
 fi
 
+export SPARK_EXAMPLES_JAR
+
 EXAMPLE_MASTER=${MASTER:-"local[*]"}
 
 if [[ ! $EXAMPLE_CLASS == org.apache.spark.examples* ]]; then

bin/compute-classpath.sh

@@ -29,6 +29,7 @@ FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 # Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
+export SPARK_CONF_DIR="${SPARK_CONF_DIR:-"$SPARK_HOME/conf"}"
 
 . "$FWDIR"/bin/load-spark-env.sh
 
@@ -71,6 +72,8 @@ case "$1" in
   'org.apache.spark.executor.MesosExecutorBackend')
     OUR_JAVA_OPTS="$SPARK_JAVA_OPTS $SPARK_EXECUTOR_OPTS"
     OUR_JAVA_MEM=${SPARK_EXECUTOR_MEMORY:-$DEFAULT_MEM}
+    export PYTHONPATH="$FWDIR/python:$PYTHONPATH"
+    export PYTHONPATH="$FWDIR/python/lib/py4j-0.8.2.1-src.zip:$PYTHONPATH"
     ;;
 
   # Spark submit uses SPARK_JAVA_OPTS + SPARK_SUBMIT_OPTS +
@@ -118,8 +121,8 @@ fi
 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 "$FWDIR/conf/java-opts" ] ; then
-  JAVA_OPTS="$JAVA_OPTS `cat "$FWDIR"/conf/java-opts`"
+if [ -e "$SPARK_CONF_DIR/java-opts" ] ; then
+  JAVA_OPTS="$JAVA_OPTS `cat "$SPARK_CONF_DIR"/java-opts`"
 fi
 
 # Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in CommandUtils.scala!
@@ -148,7 +151,7 @@ fi
 if [[ "$1" =~ org.apache.spark.tools.* ]]; then
   if test -z "$SPARK_TOOLS_JAR"; then
     echo "Failed to find Spark Tools Jar in $FWDIR/tools/target/scala-$SPARK_SCALA_VERSION/" 1>&2
-    echo "You need to build Spark before running $1." 1>&2
+    echo "You need to run \"build/sbt tools/package\" before running $1." 1>&2
     exit 1
   fi
   CLASSPATH="$CLASSPATH:$SPARK_TOOLS_JAR"

bin/run-example

@@ -25,7 +25,7 @@ set ORIG_ARGS=%*
 rem Reset the values of all variables used
 set SPARK_SUBMIT_DEPLOY_MODE=client
 
-if not defined %SPARK_CONF_DIR% (
+if [%SPARK_CONF_DIR%] == [] (
   set SPARK_CONF_DIR=%SPARK_HOME%\conf
 )
 set SPARK_SUBMIT_PROPERTIES_FILE=%SPARK_CONF_DIR%\spark-defaults.conf