#!/bin/bash SCALA_VERSION=2.9.2 # Figure out where the Scala framework is installed FWDIR="$(cd `dirname $0`; pwd)" # Export this as SPARK_HOME export SPARK_HOME="$FWDIR" # Load environment variables from conf/spark-env.sh, if it exists if [ -e $FWDIR/conf/spark-env.sh ] ; then . $FWDIR/conf/spark-env.sh fi # Check that SCALA_HOME has been specified if [ -z "$SCALA_HOME" ]; then echo "SCALA_HOME is not set" >&2 exit 1 fi # If the user specifies a Mesos JAR, put it before our included one on the classpath MESOS_CLASSPATH="" if [ -z "$MESOS_JAR" ] ; then MESOS_CLASSPATH="$MESOS_JAR" fi # Figure out how much memory to use per executor and set it as an environment # variable so that our process sees it and can report it to Mesos if [ -z "$SPARK_MEM" ] ; then SPARK_MEM="512m" fi export SPARK_MEM # Set JAVA_OPTS to be able to load native libraries and to set heap size JAVA_OPTS="$SPARK_JAVA_OPTS" JAVA_OPTS+=" -Djava.library.path=$SPARK_LIBRARY_PATH" JAVA_OPTS+=" -Xms$SPARK_MEM -Xmx$SPARK_MEM" # Load extra JAVA_OPTS from conf/java-opts, if it exists if [ -e $FWDIR/conf/java-opts ] ; then JAVA_OPTS+=" `cat $FWDIR/conf/java-opts`" fi export JAVA_OPTS CORE_DIR="$FWDIR/core" REPL_DIR="$FWDIR/repl" EXAMPLES_DIR="$FWDIR/examples" BAGEL_DIR="$FWDIR/bagel" # Build up classpath CLASSPATH="$SPARK_CLASSPATH" CLASSPATH+=":$MESOS_CLASSPATH" CLASSPATH+=":$FWDIR/conf" CLASSPATH+=":$CORE_DIR/target/scala-$SCALA_VERSION/classes" CLASSPATH+=":$CORE_DIR/target/scala-$SCALA_VERSION/test-classes" CLASSPATH+=":$CORE_DIR/src/main/resources" CLASSPATH+=":$REPL_DIR/target/scala-$SCALA_VERSION/classes" CLASSPATH+=":$EXAMPLES_DIR/target/scala-$SCALA_VERSION/classes" for jar in `find $CORE_DIR/lib -name '*jar'`; do CLASSPATH+=":$jar" done for jar in `find $FWDIR/lib_managed/jars -name '*jar'`; do CLASSPATH+=":$jar" done for jar in `find $FWDIR/lib_managed/bundles -name '*jar'`; do CLASSPATH+=":$jar" done for jar in `find $REPL_DIR/lib -name '*jar'`; do CLASSPATH+=":$jar" done CLASSPATH+=":$BAGEL_DIR/target/scala-$SCALA_VERSION/classes" export CLASSPATH # Needed for spark-shell # Figure out whether to run our class with java or with the scala launcher. # In most cases, we'd prefer to execute our process with java because scala # creates a shell script as the parent of its Java process, which makes it # hard to kill the child with stuff like Process.destroy(). However, for # the Spark shell, the wrapper is necessary to properly reset the terminal # when we exit, so we allow it to set a variable to launch with scala. if [ "$SPARK_LAUNCH_WITH_SCALA" == "1" ]; then RUNNER="${SCALA_HOME}/bin/scala" EXTRA_ARGS="" # Java options will be passed to scala as JAVA_OPTS else CLASSPATH+=":$SCALA_HOME/lib/scala-library.jar" CLASSPATH+=":$SCALA_HOME/lib/scala-compiler.jar" CLASSPATH+=":$SCALA_HOME/lib/jline.jar" if [ -n "$JAVA_HOME" ]; then RUNNER="${JAVA_HOME}/bin/java" else RUNNER=java fi # The JVM doesn't read JAVA_OPTS by default so we need to pass it in EXTRA_ARGS="$JAVA_OPTS" fi exec "$RUNNER" -cp "$CLASSPATH" $EXTRA_ARGS "$@"