aboutsummaryrefslogtreecommitdiff
path: root/spark-class
blob: 802e4aa1045e483fc96f061b44640d53f781df9b (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
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
#!/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.
#

cygwin=false
case "`uname`" in
    CYGWIN*) cygwin=true;;
esac

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 [ -z "$1" ]; then
  echo "Usage: spark-class <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" = "org.apache.spark.deploy.master.Master" -o "$1" = "org.apache.spark.deploy.worker.Worker" ]; then
  SPARK_MEM=${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 "$1" in
  'org.apache.spark.deploy.master.Master')
    OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_MASTER_OPTS"
    ;;
  'org.apache.spark.deploy.worker.Worker')
    OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_WORKER_OPTS"
    ;;
  'org.apache.spark.executor.CoarseGrainedExecutorBackend')
    OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_EXECUTOR_OPTS"
    ;;
  'org.apache.spark.executor.MesosExecutorBackend')
    OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_EXECUTOR_OPTS"
    ;;
  'org.apache.spark.repl.Main')
    OUR_JAVA_OPTS="$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

# 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 "$FWDIR/RELEASE" ]; then
  # Exit if the user hasn't compiled Spark
  num_jars=$(ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/ | grep "spark-assembly.*hadoop.*.jar" | wc -l)
  jars_list=$(ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/ | grep "spark-assembly.*hadoop.*.jar")
  if [ "$num_jars" -eq "0" ]; then
    echo "Failed to find Spark assembly in $FWDIR/assembly/target/scala-$SCALA_VERSION/" >&2
    echo "You need to build Spark with 'sbt/sbt assembly' before running this program." >&2
    exit 1
  fi
  if [ "$num_jars" -gt "1" ]; then
    echo "Found multiple Spark assembly jars in $FWDIR/assembly/target/scala-$SCALA_VERSION:" >&2
    echo "$jars_list"
    echo "Please remove all but one jar."
    exit 1
  fi
fi

TOOLS_DIR="$FWDIR"/tools
SPARK_TOOLS_JAR=""
if [ -e "$TOOLS_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar ]; then
  # Use the JAR from the SBT build
  export SPARK_TOOLS_JAR=`ls "$TOOLS_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar`
fi
if [ -e "$TOOLS_DIR"/target/spark-tools*[0-9Tg].jar ]; then
  # Use the JAR from the Maven build
  # TODO: this also needs to become an assembly!
  export SPARK_TOOLS_JAR=`ls "$TOOLS_DIR"/target/spark-tools*[0-9Tg].jar`
fi

# Compute classpath using external script
CLASSPATH=`$FWDIR/bin/compute-classpath.sh`
CLASSPATH="$CLASSPATH:$SPARK_TOOLS_JAR"

if $cygwin; then
  CLASSPATH=`cygpath -wp $CLASSPATH`
  export SPARK_TOOLS_JAR=`cygpath -w $SPARK_TOOLS_JAR`
fi
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" $JAVA_OPTS "$@"