2010-08-13 21:54:32 -04:00
|
|
|
|
#!/usr/bin/env bash
|
|
|
|
|
|
2014-04-21 13:26:33 -04:00
|
|
|
|
# This file is sourced when running various Spark programs.
|
|
|
|
|
# Copy it as spark-env.sh and edit that to configure Spark for your site.
|
|
|
|
|
|
2015-04-28 15:08:18 -04:00
|
|
|
|
# Options read when launching programs locally with
|
2014-04-21 13:26:33 -04:00
|
|
|
|
# ./bin/run-example or ./bin/spark-submit
|
2014-04-22 22:22:06 -04:00
|
|
|
|
# - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files
|
2014-04-21 13:26:33 -04:00
|
|
|
|
# - SPARK_LOCAL_IP, to set the IP address Spark binds to on this node
|
|
|
|
|
# - SPARK_PUBLIC_DNS, to set the public dns name of the driver program
|
|
|
|
|
# - SPARK_CLASSPATH, default classpath entries to append
|
|
|
|
|
|
|
|
|
|
# Options read by executors and drivers running inside the cluster
|
2013-08-31 20:40:33 -04:00
|
|
|
|
# - SPARK_LOCAL_IP, to set the IP address Spark binds to on this node
|
2014-04-21 13:26:33 -04:00
|
|
|
|
# - SPARK_PUBLIC_DNS, to set the public DNS name of the driver program
|
|
|
|
|
# - SPARK_CLASSPATH, default classpath entries to append
|
|
|
|
|
# - SPARK_LOCAL_DIRS, storage directories to use on this node for shuffle and RDD data
|
2015-03-15 11:46:55 -04:00
|
|
|
|
# - MESOS_NATIVE_JAVA_LIBRARY, to point to your libmesos.so if you use Mesos
|
2014-04-21 13:26:33 -04:00
|
|
|
|
|
|
|
|
|
# Options read in YARN client mode
|
2014-04-22 22:22:06 -04:00
|
|
|
|
# - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files
|
2014-04-21 13:26:33 -04:00
|
|
|
|
# - SPARK_EXECUTOR_INSTANCES, Number of workers to start (Default: 2)
|
|
|
|
|
# - SPARK_EXECUTOR_CORES, Number of cores for the workers (Default: 1).
|
|
|
|
|
# - SPARK_EXECUTOR_MEMORY, Memory per Worker (e.g. 1000M, 2G) (Default: 1G)
|
|
|
|
|
# - SPARK_DRIVER_MEMORY, Memory for Master (e.g. 1000M, 2G) (Default: 512 Mb)
|
|
|
|
|
# - SPARK_YARN_APP_NAME, The name of your application (Default: Spark)
|
|
|
|
|
# - SPARK_YARN_QUEUE, The hadoop queue to use for allocation requests (Default: ‘default’)
|
|
|
|
|
# - SPARK_YARN_DIST_FILES, Comma separated list of files to be distributed with the job.
|
|
|
|
|
# - SPARK_YARN_DIST_ARCHIVES, Comma separated list of archives to be distributed with the job.
|
|
|
|
|
|
2014-11-14 16:33:35 -05:00
|
|
|
|
# Options for the daemons used in the standalone deploy mode
|
2013-08-31 20:41:47 -04:00
|
|
|
|
# - SPARK_MASTER_IP, to bind the master to a different IP address or hostname
|
2014-05-12 22:44:14 -04:00
|
|
|
|
# - SPARK_MASTER_PORT / SPARK_MASTER_WEBUI_PORT, to use non-default ports for the master
|
2014-04-21 13:26:33 -04:00
|
|
|
|
# - SPARK_MASTER_OPTS, to set config properties only for the master (e.g. "-Dx=y")
|
2012-10-13 19:20:25 -04:00
|
|
|
|
# - SPARK_WORKER_CORES, to set the number of cores to use on this machine
|
2014-04-21 13:26:33 -04:00
|
|
|
|
# - SPARK_WORKER_MEMORY, to set how much total memory workers have to give executors (e.g. 1000m, 2g)
|
2014-05-12 22:44:14 -04:00
|
|
|
|
# - SPARK_WORKER_PORT / SPARK_WORKER_WEBUI_PORT, to use non-default ports for the worker
|
2013-08-31 17:21:10 -04:00
|
|
|
|
# - SPARK_WORKER_INSTANCES, to set the number of worker processes per node
|
2014-01-07 12:53:04 -05:00
|
|
|
|
# - SPARK_WORKER_DIR, to set the working directory of worker processes
|
2014-04-21 13:26:33 -04:00
|
|
|
|
# - SPARK_WORKER_OPTS, to set config properties only for the worker (e.g. "-Dx=y")
|
|
|
|
|
# - SPARK_HISTORY_OPTS, to set config properties only for the history server (e.g. "-Dx=y")
|
2015-04-28 15:08:18 -04:00
|
|
|
|
# - SPARK_SHUFFLE_OPTS, to set config properties only for the external shuffle service (e.g. "-Dx=y")
|
2014-05-12 22:42:35 -04:00
|
|
|
|
# - SPARK_DAEMON_JAVA_OPTS, to set config properties for all daemons (e.g. "-Dx=y")
|
2014-04-21 13:26:33 -04:00
|
|
|
|
# - SPARK_PUBLIC_DNS, to set the public dns name of the master or workers
|
2014-11-14 16:33:35 -05:00
|
|
|
|
|
|
|
|
|
# Generic options for the daemons used in the standalone deploy mode
|
|
|
|
|
# - SPARK_CONF_DIR Alternate conf dir. (Default: ${SPARK_HOME}/conf)
|
|
|
|
|
# - SPARK_LOG_DIR Where log files are stored. (Default: ${SPARK_HOME}/logs)
|
|
|
|
|
# - SPARK_PID_DIR Where the pid file is stored. (Default: /tmp)
|
|
|
|
|
# - SPARK_IDENT_STRING A string representing this instance of spark. (Default: $USER)
|
|
|
|
|
# - SPARK_NICENESS The scheduling priority for daemons. (Default: 0)
|