spark-instrumented-optimizer/bin/spark-class
Marcelo Vanzin 9717389365 [SPARK-6890] [core] Fix launcher lib work with SPARK_PREPEND_CLASSES.
The fix for SPARK-6406 broke the case where sub-processes are launched
when SPARK_PREPEND_CLASSES is set, because the code now would only add
the launcher's build directory to the sub-process's classpath instead
of the complete assembly.

This patch fixes the problem by having the launch scripts stash the
assembly's location in an environment variable. This is not the prettiest
solution, but it avoids having to plumb that location all the way through
the Worker code that launches executors. The env variable is always
set by the launch scripts, so users cannot override it.

Author: Marcelo Vanzin <vanzin@cloudera.com>

Closes #5504 from vanzin/SPARK-6890 and squashes the following commits:

7aec921 [Marcelo Vanzin] Fix tests.
ff87a60 [Marcelo Vanzin] Merge branch 'master' into SPARK-6890
31d3ce8 [Marcelo Vanzin] [SPARK-6890] [core] Fix launcher lib work with SPARK_PREPEND_CLASSES.
2015-04-14 18:51:39 -07:00

107 lines
3.4 KiB
Bash
Executable file

#!/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.
#
set -e
# Figure out where Spark is installed
export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
. "$SPARK_HOME"/bin/load-spark-env.sh
if [ -z "$1" ]; then
echo "Usage: spark-class <class> [<args>]" 1>&2
exit 1
fi
# Find the java binary
if [ -n "${JAVA_HOME}" ]; then
RUNNER="${JAVA_HOME}/bin/java"
else
if [ `command -v java` ]; then
RUNNER="java"
else
echo "JAVA_HOME is not set" >&2
exit 1
fi
fi
# Find assembly jar
SPARK_ASSEMBLY_JAR=
if [ -f "$SPARK_HOME/RELEASE" ]; then
ASSEMBLY_DIR="$SPARK_HOME/lib"
else
ASSEMBLY_DIR="$SPARK_HOME/assembly/target/scala-$SPARK_SCALA_VERSION"
fi
num_jars="$(ls -1 "$ASSEMBLY_DIR" | grep "^spark-assembly.*hadoop.*\.jar$" | wc -l)"
if [ "$num_jars" -eq "0" -a -z "$SPARK_ASSEMBLY_JAR" ]; then
echo "Failed to find Spark assembly in $ASSEMBLY_DIR." 1>&2
echo "You need to build Spark before running this program." 1>&2
exit 1
fi
ASSEMBLY_JARS="$(ls -1 "$ASSEMBLY_DIR" | grep "^spark-assembly.*hadoop.*\.jar$" || true)"
if [ "$num_jars" -gt "1" ]; then
echo "Found multiple Spark assembly jars in $ASSEMBLY_DIR:" 1>&2
echo "$ASSEMBLY_JARS" 1>&2
echo "Please remove all but one jar." 1>&2
exit 1
fi
SPARK_ASSEMBLY_JAR="${ASSEMBLY_DIR}/${ASSEMBLY_JARS}"
# Verify that versions of java used to build the jars and run Spark are compatible
if [ -n "$JAVA_HOME" ]; then
JAR_CMD="$JAVA_HOME/bin/jar"
else
JAR_CMD="jar"
fi
if [ $(command -v "$JAR_CMD") ] ; then
jar_error_check=$("$JAR_CMD" -tf "$SPARK_ASSEMBLY_JAR" nonexistent/class/path 2>&1)
if [[ "$jar_error_check" =~ "invalid CEN header" ]]; then
echo "Loading Spark jar with '$JAR_CMD' failed. " 1>&2
echo "This is likely because Spark was compiled with Java 7 and run " 1>&2
echo "with Java 6. (see SPARK-1703). Please use Java 7 to run Spark " 1>&2
echo "or build Spark with Java 6." 1>&2
exit 1
fi
fi
LAUNCH_CLASSPATH="$SPARK_ASSEMBLY_JAR"
# Add the launcher build dir to the classpath if requested.
if [ -n "$SPARK_PREPEND_CLASSES" ]; then
LAUNCH_CLASSPATH="$SPARK_HOME/launcher/target/scala-$SPARK_SCALA_VERSION/classes:$LAUNCH_CLASSPATH"
fi
export _SPARK_ASSEMBLY="$SPARK_ASSEMBLY_JAR"
# The launcher library will print arguments separated by a NULL character, to allow arguments with
# characters that would be otherwise interpreted by the shell. Read that in a while loop, populating
# an array that will be used to exec the final command.
CMD=()
while IFS= read -d '' -r ARG; do
CMD+=("$ARG")
done < <("$RUNNER" -cp "$LAUNCH_CLASSPATH" org.apache.spark.launcher.Main "$@")
if [ "${CMD[0]}" = "usage" ]; then
"${CMD[@]}"
else
exec "${CMD[@]}"
fi