diff options
Diffstat (limited to 'run')
| -rwxr-xr-x | run | 121 |
1 files changed, 89 insertions, 32 deletions
@@ -1,6 +1,6 @@ #!/bin/bash -SCALA_VERSION=2.9.2 +SCALA_VERSION=2.9.3 # Figure out where the Scala framework is installed FWDIR="$(cd `dirname $0`; pwd)" @@ -22,21 +22,43 @@ fi # 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="$SPARK_DAEMON_JAVA_OPTS -Dspark.akka.logLifecycleEvents=true" # Do not overwrite SPARK_JAVA_OPTS environment variable in this script - OUR_JAVA_OPTS=$SPARK_DAEMON_JAVA_OPTS # Empty by default + OUR_JAVA_OPTS="$SPARK_DAEMON_JAVA_OPTS" # Empty by default else - OUR_JAVA_OPTS=$SPARK_JAVA_OPTS + OUR_JAVA_OPTS="$SPARK_JAVA_OPTS" fi + +# Add java opts for master, worker, executor. The opts maybe null +case "$1" in + 'spark.deploy.master.Master') + OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_MASTER_OPTS" + ;; + 'spark.deploy.worker.Worker') + OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_WORKER_OPTS" + ;; + 'spark.executor.StandaloneExecutorBackend') + OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_EXECUTOR_OPTS" + ;; + 'spark.executor.MesosExecutorBackend') + OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_EXECUTOR_OPTS" + ;; + 'spark.repl.Main') + OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_REPL_OPTS" + ;; +esac + if [ "$SPARK_LAUNCH_WITH_SCALA" == "1" ]; then - if [ `command -v scala` ]; then - RUNNER="scala" + if [ "$SCALA_HOME" ]; then + RUNNER="${SCALA_HOME}/bin/scala" else - if [ -z "$SCALA_HOME" ]; then - echo "SCALA_HOME is not set" >&2 + if [ `command -v scala` ]; then + RUNNER="scala" + else + echo "SCALA_HOME is not set and scala is not in PATH" >&2 exit 1 fi - RUNNER="${SCALA_HOME}/bin/scala" fi else if [ `command -v java` ]; then @@ -66,55 +88,89 @@ export SPARK_MEM # Set JAVA_OPTS to be able to load native libraries and to set heap size JAVA_OPTS="$OUR_JAVA_OPTS" -JAVA_OPTS+=" -Djava.library.path=$SPARK_LIBRARY_PATH" -JAVA_OPTS+=" -Xms$SPARK_MEM -Xmx$SPARK_MEM" +JAVA_OPTS="$JAVA_OPTS -Djava.library.path=$SPARK_LIBRARY_PATH" +JAVA_OPTS="$JAVA_OPTS -Xms$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 $FWDIR/conf/java-opts`" + JAVA_OPTS="$JAVA_OPTS `cat $FWDIR/conf/java-opts`" fi export JAVA_OPTS # Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in ExecutorRunner.scala! CORE_DIR="$FWDIR/core" REPL_DIR="$FWDIR/repl" +REPL_BIN_DIR="$FWDIR/repl-bin" 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 $REPL_DIR/target" >&2 +if [ ! -e "$CORE_DIR/target" ]; then + echo "Failed to find Spark classes in $CORE_DIR/target" >&2 echo "You need to compile Spark before running this program" >&2 exit 1 fi +if [[ "$@" = *repl* && ! -e "$REPL_DIR/target" ]]; then + echo "Failed to find Spark classes in $REPL_DIR/target" >&2 + echo "You need to compile Spark repl module before running this program" >&2 + exit 1 +fi + # Build up classpath CLASSPATH="$SPARK_CLASSPATH" -CLASSPATH+=":$FWDIR/conf" -CLASSPATH+=":$CORE_DIR/target/scala-$SCALA_VERSION/classes" +CLASSPATH="$CLASSPATH:$FWDIR/conf" +CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/classes" if [ -n "$SPARK_TESTING" ] ; then - CLASSPATH+=":$CORE_DIR/target/scala-$SCALA_VERSION/test-classes" + CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/test-classes" + CLASSPATH="$CLASSPATH:$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="$CLASSPATH:$CORE_DIR/src/main/resources" +CLASSPATH="$CLASSPATH:$REPL_DIR/target/scala-$SCALA_VERSION/classes" +CLASSPATH="$CLASSPATH:$EXAMPLES_DIR/target/scala-$SCALA_VERSION/classes" +CLASSPATH="$CLASSPATH:$STREAMING_DIR/target/scala-$SCALA_VERSION/classes" +CLASSPATH="$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/*" + CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/jars/*" + CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/bundles/*" fi -CLASSPATH+=":$REPL_DIR/lib/*" -if [ -e repl-bin/target ]; then - for jar in `find "repl-bin/target" -name 'spark-repl-*-shaded-hadoop*.jar'`; do - CLASSPATH+=":$jar" +CLASSPATH="$CLASSPATH:$REPL_DIR/lib/*" +# Add the shaded JAR for Maven builds +if [ -e $REPL_BIN_DIR/target ]; then + for jar in `find "$REPL_BIN_DIR/target" -name 'spark-repl-*-shaded-hadoop*.jar'`; do + CLASSPATH="$CLASSPATH:$jar" done + # The shaded JAR doesn't contain examples, so include those separately + EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar` + CLASSPATH+=":$EXAMPLES_JAR" fi -CLASSPATH+=":$BAGEL_DIR/target/scala-$SCALA_VERSION/classes" +CLASSPATH="$CLASSPATH:$BAGEL_DIR/target/scala-$SCALA_VERSION/classes" for jar in `find $PYSPARK_DIR/lib -name '*jar'`; do - CLASSPATH+=":$jar" + CLASSPATH="$CLASSPATH:$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"*[0-9T].jar ]; then + # Use the JAR from the SBT build + export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/scala-$SCALA_VERSION/spark-examples"*[0-9T].jar` +fi +if [ -e "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar ]; then + # Use the JAR from the Maven build + export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar` +fi + +# Add hadoop conf dir - else FileSystem.*, etc fail ! +# Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts +# the configurtion files. +if [ "x" != "x$HADOOP_CONF_DIR" ]; then + CLASSPATH="$CLASSPATH:$HADOOP_CONF_DIR" +fi +if [ "x" != "x$YARN_CONF_DIR" ]; then + CLASSPATH="$CLASSPATH:$YARN_CONF_DIR" +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 @@ -125,11 +181,12 @@ export CLASSPATH # Needed for spark-shell 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" + CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/scala-library.jar" + CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/scala-compiler.jar" + CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/jline.jar" # The JVM doesn't read JAVA_OPTS by default so we need to pass it in EXTRA_ARGS="$JAVA_OPTS" fi +export CLASSPATH # Needed for spark-shell exec "$RUNNER" -cp "$CLASSPATH" $EXTRA_ARGS "$@" |