run


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

#!/bin/bash

# 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="$SPARK_DAEMON_JAVA_OPTS -Dspark.akka.logLifecycleEvents=true"
  SPARK_JAVA_OPTS=$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_JAVA_OPTS $SPARK_MASTER_OPTS"
    ;;
  'spark.deploy.worker.Worker')
    SPARK_JAVA_OPTS="$SPARK_JAVA_OPTS $SPARK_WORKER_OPTS"
    ;;
  'spark.executor.StandaloneExecutorBackend')
    SPARK_JAVA_OPTS="$SPARK_JAVA_OPTS $SPARK_EXECUTOR_OPTS"
    ;;
  'spark.executor.MesosExecutorBackend')
    SPARK_JAVA_OPTS="$SPARK_JAVA_OPTS $SPARK_EXECUTOR_OPTS"
    ;;
  'spark.repl.Main')
    SPARK_JAVA_OPTS="$SPARK_JAVA_OPTS $SPARK_REPL_OPTS"
    ;;
esac

# 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="$SPARK_JAVA_OPTS"
JAVA_OPTS="$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

# Check if this is a binary distribution or source distribution
# and build up the classpath appropriately
if [ -f "$FWDIR/RELEASE" ]; then
  if [ `command -v java` ]; then
    RUNNER="java"
  else
    if [ -z "$JAVA_HOME" ]; then
      echo "JAVA_HOME is not set" >&2
      exit 1
    fi
    RUNNER="${JAVA_HOME}/bin/java"
  fi

  CLASSPATH="$SPARK_CLASSPATH:$FWDIR/jars/*"

  # The JVM doesn't read JAVA_OPTS by default so we need to pass it in
  EXTRA_ARGS="$JAVA_OPTS"
else
  . "$FWDIR/set-dev-classpath.sh"
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

export CLASSPATH # Needed for spark-shell
exec "$RUNNER" -cp "$CLASSPATH" $EXTRA_ARGS "$@"