Change build and run instructions to use assemblies

This commit makes Spark invocation saner by using an assembly JAR to
find all of Spark's dependencies instead of adding all the JARs in
lib_managed. It also packages the examples into an assembly and uses
that as SPARK_EXAMPLES_JAR. Finally, it replaces the old "run" script
with two better-named scripts: "run-examples" for examples, and
"spark-class" for Spark internal classes (e.g. REPL, master, etc). This
is also designed to minimize the confusion people have in trying to use
"run" to run their own classes; it's not meant to do that, but now at
least if they look at it, they can modify run-examples to do a decent
job for them.

As part of this, Bagel's examples are also now properly moved to the
examples package instead of bagel.

1 files changed, 124 insertions, 0 deletions

diff --git a/spark-class b/spark-class
new file mode 100755
index 0000000000..5ef3de9773
--- /dev/null
+++ b/spark-class
@@ -0,0 +1,124 @@
+#!/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.
+#
+
+SCALA_VERSION=2.9.3
+
+# 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="$SPARK_DAEMON_JAVA_OPTS -Dspark.akka.logLifecycleEvents=true"
+  # Do not overwrite SPARK_JAVA_OPTS environment variable in this script
+  OUR_JAVA_OPTS="$SPARK_DAEMON_JAVA_OPTS"   # Empty by default
+else
+  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 $SPARK_REPL_OPTS"
+    ;;
+esac
+
+# Find the java binary
+if [ -n "${JAVA_HOME}" ]; then
+  RUNNER="${JAVA_HOME}/bin/java"
+else
+  if [ `command -v java` ]; then
+    RUNNER="java"
+  else
+    echo "JAVA_HOME is not set" >&2
+    exit 1
+  fi
+fi
+if [[ ! -f "$FWDIR/RELEASE" && -z "$SCALA_LIBRARY_PATH" ]]; then
+  if [ -z "$SCALA_HOME" ]; then
+    echo "SCALA_HOME is not set" >&2
+    exit 1
+  fi
+  SCALA_LIBRARY_PATH="$SCALA_HOME/lib"
+fi
+
+# Set SPARK_MEM if it isn't already set since we also use it for this process
+SPARK_MEM=${SPARK_MEM:-512m}
+export SPARK_MEM
+
+# Set JAVA_OPTS to be able to load native libraries and to set heap size
+JAVA_OPTS="$OUR_JAVA_OPTS"
+JAVA_OPTS="$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 $FWDIR/conf/java-opts ] ; then
+  JAVA_OPTS="$JAVA_OPTS `cat $FWDIR/conf/java-opts`"
+fi
+export JAVA_OPTS
+# Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in ExecutorRunner.scala!
+
+if [ ! -f "$FWDIR/RELEASE" ]; then
+  # Exit if the user hasn't compiled Spark
+  ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*.jar >& /dev/null
+  if [[ $? != 0 ]]; then
+    echo "Failed to find Spark assembly in $FWDIR/assembly/target" >&2
+    echo "You need to compile Spark before running this program" >&2
+    exit 1
+  fi
+fi
+
+# Compute classpath using external script
+CLASSPATH=`$FWDIR/bin/compute-classpath.sh`
+export CLASSPATH
+
+if [ "$SPARK_PRINT_LAUNCH_COMMAND" == "1" ]; then
+  echo -n "Spark Command: "
+  echo "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@"
+  echo "========================================"
+  echo
+fi
+
+exec "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@"