blob: 16fb0efc6e887220dac532d3a25eccb5e5a9bf1a (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
|
#!/bin/bash
SCALA_VERSION=2.10
# 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
. $FWDIR/conf/spark-env.sh
fi
if [ "$SPARK_LAUNCH_WITH_SCALA" == "1" ]; then
if [ `command -v scala` ]; then
RUNNER="scala"
else
if [ -z "$SCALA_HOME" ]; then
echo "SCALA_HOME is not set" >&2
exit 1
fi
RUNNER="${SCALA_HOME}/bin/scala"
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="$FWDIR/bagel"
PYSPARK_DIR="$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"
fi
CLASSPATH+=":$CORE_DIR/src/main/resources"
CLASSPATH+=":$REPL_DIR/target/scala-$SCALA_VERSION/classes"
CLASSPATH+=":$EXAMPLES_DIR/target/scala-$SCALA_VERSION/classes"
if [ -e "$FWDIR/lib_managed" ]; then
CLASSPATH+=":$FWDIR/lib_managed/jars/*"
CLASSPATH+=":$FWDIR/lib_managed/bundles/*"
fi
CLASSPATH+=":$REPL_DIR/lib/*"
for jar in `find "$REPL_DIR/target" -name 'spark-repl-*-shaded-hadoop*.jar'`; do
CLASSPATH+=":$jar"
done
CLASSPATH+=":$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 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" $EXTRA_ARGS "$@"
|