| #!/bin/bash |
| |
| SCALA_VERSION=2.9.3 |
| |
| # Enable extended globbing |
| shopt -s extglob |
| |
| # 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 |
| |
| if [ -z "$1" ]; then |
| echo "Usage: run <spark-class> [<args>]" >&2 |
| exit 1 |
| fi |
| |
| # If this is a standalone cluster daemon, reset SPARK_JAVA_OPTS and SPARK_MEM to reasonable |
| # values for that; it doesn't need a lot |
| if [ "$1" = "spark.deploy.master.Master" -o "$1" = "spark.deploy.worker.Worker" ]; then |
| SPARK_MEM=${SPARK_DAEMON_MEMORY:-512m} |
| SPARK_DAEMON_JAVA_OPTS+=" -Dspark.akka.logLifecycleEvents=true" |
| SPARK_JAVA_OPTS=$SPARK_DAEMON_JAVA_OPTS # Empty by default |
| fi |
| |
| |
| # Add java opts for master, worker, executor. The opts maybe null |
| case "$1" in |
| 'spark.deploy.master.Master') |
| SPARK_JAVA_OPTS+=" $SPARK_MASTER_OPTS" |
| ;; |
| 'spark.deploy.worker.Worker') |
| SPARK_JAVA_OPTS+=" $SPARK_WORKER_OPTS" |
| ;; |
| 'spark.executor.StandaloneExecutorBackend') |
| SPARK_JAVA_OPTS+=" $SPARK_EXECUTOR_OPTS" |
| ;; |
| 'spark.executor.MesosExecutorBackend') |
| SPARK_JAVA_OPTS+=" $SPARK_EXECUTOR_OPTS" |
| ;; |
| 'spark.repl.Main') |
| SPARK_JAVA_OPTS+=" $SPARK_REPL_OPTS" |
| ;; |
| esac |
| |
| if [ "$SPARK_LAUNCH_WITH_SCALA" == "1" ]; then |
| if [ "$SCALA_HOME" ]; then |
| RUNNER="${SCALA_HOME}/bin/scala" |
| else |
| if [ `command -v scala` ]; then |
| RUNNER="scala" |
| else |
| echo "SCALA_HOME is not set and scala is not in PATH" >&2 |
| exit 1 |
| fi |
| fi |
| else |
| if [ `command -v java` ]; then |
| RUNNER="java" |
| else |
| if [ -z "$JAVA_HOME" ]; then |
| echo "JAVA_HOME is not set" >&2 |
| exit 1 |
| fi |
| RUNNER="${JAVA_HOME}/bin/java" |
| fi |
| if [ -z "$SCALA_LIBRARY_PATH" ]; then |
| if [ -z "$SCALA_HOME" ]; then |
| echo "SCALA_HOME is not set" >&2 |
| exit 1 |
| fi |
| SCALA_LIBRARY_PATH="$SCALA_HOME/lib" |
| fi |
| fi |
| |
| # Figure out how much memory to use per executor and set it as an environment |
| # variable so that our process sees it and can report it to Mesos |
| if [ -z "$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="$FWDIR/bagel" |
| STREAMING_DIR="$FWDIR/streaming" |
| PYSPARK_DIR="$FWDIR/python" |
| |
| # Exit if the user hasn't compiled Spark |
| if [ ! -e "$REPL_DIR/target" ]; then |
| echo "Failed to find Spark classes in $REPL_DIR/target" >&2 |
| echo "You need to compile Spark before running this program" >&2 |
| exit 1 |
| fi |
| |
| # Build up classpath |
| CLASSPATH="$SPARK_CLASSPATH" |
| CLASSPATH+=":$FWDIR/conf" |
| CLASSPATH+=":$CORE_DIR/target/scala-$SCALA_VERSION/classes" |
| if [ -n "$SPARK_TESTING" ] ; then |
| CLASSPATH+=":$CORE_DIR/target/scala-$SCALA_VERSION/test-classes" |
| CLASSPATH+=":$STREAMING_DIR/target/scala-$SCALA_VERSION/test-classes" |
| fi |
| CLASSPATH+=":$CORE_DIR/src/main/resources" |
| CLASSPATH+=":$REPL_DIR/target/scala-$SCALA_VERSION/classes" |
| CLASSPATH+=":$EXAMPLES_DIR/target/scala-$SCALA_VERSION/classes" |
| CLASSPATH+=":$STREAMING_DIR/target/scala-$SCALA_VERSION/classes" |
| CLASSPATH+=":$STREAMING_DIR/lib/org/apache/kafka/kafka/0.7.2-spark/*" # <-- our in-project Kafka Jar |
| if [ -e "$FWDIR/lib_managed" ]; then |
| CLASSPATH+=":$FWDIR/lib_managed/jars/*" |
| CLASSPATH+=":$FWDIR/lib_managed/bundles/*" |
| fi |
| CLASSPATH+=":$REPL_DIR/lib/*" |
| if [ -e repl-bin/target ]; then |
| for jar in `find "repl-bin/target" -name 'spark-repl-*-shaded.jar'`; do |
| CLASSPATH+=":$jar" |
| done |
| fi |
| CLASSPATH+=":$BAGEL_DIR/target/scala-$SCALA_VERSION/classes" |
| for jar in `find $PYSPARK_DIR/lib -name '*jar'`; do |
| CLASSPATH+=":$jar" |
| done |
| export CLASSPATH # Needed for spark-shell |
| |
| # 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. |
| if [ -e "$EXAMPLES_DIR/target/scala-$SCALA_VERSION/spark-examples-"!(*sources|*javadoc) ]; then |
| # Use the JAR from the SBT build |
| export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/scala-$SCALA_VERSION/spark-examples-"!(*sources|*javadoc).jar` |
| fi |
| if [ -e "$EXAMPLES_DIR/target/spark-examples-"!(*sources|*javadoc).jar ]; then |
| # Use the JAR from the Maven build |
| export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples-"!(*sources|*javadoc).jar` |
| fi |
| |
| # 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 [ "$SPARK_LAUNCH_WITH_SCALA" == "1" ]; then |
| EXTRA_ARGS="" # Java options will be passed to scala as JAVA_OPTS |
| else |
| CLASSPATH+=":$SCALA_LIBRARY_PATH/scala-library.jar" |
| CLASSPATH+=":$SCALA_LIBRARY_PATH/scala-compiler.jar" |
| CLASSPATH+=":$SCALA_LIBRARY_PATH/jline.jar" |
| # 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" $EXTRA_ARGS "$@" |