templates.spark.conf.spark-env.sh.mustache Maven / Gradle / Ivy

Go to download
#!/usr/bin/env bash

# This file is sourced when running various Spark programs.
# Copy it as spark-env.sh and edit that to configure Spark for your site.
{{#JAVA_HOME}}JAVA_HOME={{JAVA_HOME}}{{/JAVA_HOME}}{{^JAVA_HOME}}# - JAVA_HOME, to set the path to your Java installation{{/JAVA_HOME}}

{{#SPARK_PID_DIR}}SPARK_PID_DIR={{SPARK_PID_DIR}}{{/SPARK_PID_DIR}}{{^SPARK_PID_DIR}}# - SPARK_PID_DIR, directory where pid files are stored{{/SPARK_PID_DIR}}

# Options read when launching programs locally with
# ./bin/run-example or ./bin/spark-submit
{{#HADOOP_CONF_DIR}}HADOOP_CONF_DIR={{HADOOP_CONF_DIR}}{{/HADOOP_CONF_DIR}}{{^HADOOP_CONF_DIR}}# - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files{{/HADOOP_CONF_DIR}}
{{#SPARK_LOCAL_IP}}SPARK_LOCAL_IP={{SPARK_LOCAL_IP}}{{/SPARK_LOCAL_IP}}{{^SPARK_LOCAL_IP}}# - SPARK_LOCAL_IP, to set the IP address Spark binds to on this node{{/SPARK_LOCAL_IP}}
{{#SPARK_PUBLIC_DNS}}SPARK_PUBLIC_DNS={{SPARK_PUBLIC_DNS}}{{/SPARK_PUBLIC_DNS}}{{^SPARK_PUBLIC_DNS}}# - SPARK_PUBLIC_DNS, to set the public dns name of the driver program{{/SPARK_PUBLIC_DNS}}
{{#SPARK_CLASSPATH}}SPARK_CLASSPATH={{SPARK_CLASSPATH}}{{/SPARK_CLASSPATH}}{{^SPARK_CLASSPATH}}# - SPARK_CLASSPATH, default classpath entries to append{{/SPARK_CLASSPATH}}

# Options read by executors and drivers running inside the cluster
{{#SPARK_LOCAL_IP}}SPARK_LOCAL_IP={{SPARK_LOCAL_IP}}{{/SPARK_LOCAL_IP}}{{^SPARK_LOCAL_IP}}# - SPARK_LOCAL_IP, to set the IP address Spark binds to on this node{{/SPARK_LOCAL_IP}}
{{#SPARK_PUBLIC_DNS}}SPARK_PUBLIC_DNS={{SPARK_PUBLIC_DNS}}{{/SPARK_PUBLIC_DNS}}{{^SPARK_PUBLIC_DNS}}# - SPARK_PUBLIC_DNS, to set the public DNS name of the driver program{{/SPARK_PUBLIC_DNS}}
{{#SPARK_CLASSPATH}}SPARK_CLASSPATH={{SPARK_CLASSPATH}}{{/SPARK_CLASSPATH}}{{^SPARK_CLASSPATH}}# - SPARK_CLASSPATH, default classpath entries to append{{/SPARK_CLASSPATH}}
{{#SPARK_LOCAL_DIRS}}SPARK_LOCAL_DIRS={{SPARK_LOCAL_DIRS}}{{/SPARK_LOCAL_DIRS}}{{^SPARK_LOCAL_DIRS}}# - SPARK_LOCAL_DIRS, storage directories to use on this node for shuffle and RDD data{{/SPARK_LOCAL_DIRS}}
{{#MESOS_NATIVE_LIBRARY}}MESOS_NATIVE_LIBRARY={{MESOS_NATIVE_LIBRARY}}{{/MESOS_NATIVE_LIBRARY}}{{^MESOS_NATIVE_LIBRARY}}# - MESOS_NATIVE_LIBRARY, to point to your libmesos.so if you use Mesos{{/MESOS_NATIVE_LIBRARY}}

# Options read in YARN client mode
{{#HADOOP_CONF_DIR}}HADOOP_CONF_DIR={{HADOOP_CONF_DIR}}{{/HADOOP_CONF_DIR}}{{^HADOOP_CONF_DIR}}# - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files{{/HADOOP_CONF_DIR}}
{{#SPARK_EXECUTOR_INSTANCES}}SPARK_EXECUTOR_INSTANCES={{SPARK_EXECUTOR_INSTANCES}}{{/SPARK_EXECUTOR_INSTANCES}}{{^SPARK_EXECUTOR_INSTANCES}}# - SPARK_EXECUTOR_INSTANCES, Number of workers to start (Default: 2){{/SPARK_EXECUTOR_INSTANCES}}
{{#SPARK_EXECUTOR_CORES}}SPARK_EXECUTOR_CORES={{SPARK_EXECUTOR_CORES}}{{/SPARK_EXECUTOR_CORES}}{{^SPARK_EXECUTOR_CORES}}# - SPARK_EXECUTOR_CORES, Number of cores for the workers (Default: 1).{{/SPARK_EXECUTOR_CORES}}
{{#SPARK_EXECUTOR_MEMORY}}SPARK_EXECUTOR_MEMORY={{SPARK_EXECUTOR_MEMORY}}{{/SPARK_EXECUTOR_MEMORY}}{{^SPARK_EXECUTOR_MEMORY}}# - SPARK_EXECUTOR_MEMORY, Memory per Worker (e.g. 1000M, 2G) (Default: 1G){{/SPARK_EXECUTOR_MEMORY}}
{{#SPARK_DRIVER_MEMORY}}SPARK_DRIVER_MEMORY={{SPARK_DRIVER_MEMORY}}{{/SPARK_DRIVER_MEMORY}}{{^SPARK_DRIVER_MEMORY}}# - SPARK_DRIVER_MEMORY, Memory for Master (e.g. 1000M, 2G) (Default: 512 Mb){{/SPARK_DRIVER_MEMORY}}
{{#SPARK_YARN_APP_NAME}}SPARK_YARN_APP_NAME={{SPARK_YARN_APP_NAME}}{{/SPARK_YARN_APP_NAME}}{{^SPARK_YARN_APP_NAME}}# - SPARK_YARN_APP_NAME, The name of your application (Default: Spark){{/SPARK_YARN_APP_NAME}}
{{#SPARK_YARN_QUEUE}}SPARK_YARN_QUEUE={{SPARK_YARN_QUEUE}}{{/SPARK_YARN_QUEUE}}{{^SPARK_YARN_QUEUE}}# - SPARK_YARN_QUEUE, The hadoop queue to use for allocation requests (Default: ‘default’){{/SPARK_YARN_QUEUE}}
{{#SPARK_YARN_DIST_FILES}}SPARK_YARN_DIST_FILES={{SPARK_YARN_DIST_FILES}}{{/SPARK_YARN_DIST_FILES}}{{^SPARK_YARN_DIST_FILES}}# - SPARK_YARN_DIST_FILES, Comma separated list of files to be distributed with the job.{{/SPARK_YARN_DIST_FILES}}
{{#SPARK_YARN_DIST_ARCHIVES}}SPARK_YARN_DIST_ARCHIVES={{SPARK_YARN_DIST_ARCHIVES}}{{/SPARK_YARN_DIST_ARCHIVES}}{{^SPARK_YARN_DIST_ARCHIVES}}# - SPARK_YARN_DIST_ARCHIVES, Comma separated list of archives to be distributed with the job.{{/SPARK_YARN_DIST_ARCHIVES}}

# Options for the daemons used in the standalone deploy mode:
{{#SPARK_MASTER_IP}}SPARK_MASTER_IP={{SPARK_MASTER_IP}}{{/SPARK_MASTER_IP}}{{^SPARK_MASTER_IP}}# - SPARK_MASTER_IP, to bind the master to a different IP address or hostname{{/SPARK_MASTER_IP}}
{{#SPARK_MASTER_PORT}}SPARK_MASTER_PORT={{SPARK_MASTER_PORT}}{{/SPARK_MASTER_PORT}}{{^SPARK_MASTER_PORT}}# - SPARK_MASTER_PORT, to use non-default ports for the master{{/SPARK_MASTER_PORT}}
{{#SPARK_MASTER_WEBUI_PORT}}SPARK_MASTER_WEBUI_PORT={{SPARK_MASTER_WEBUI_PORT}}{{/SPARK_MASTER_WEBUI_PORT}}{{^SPARK_MASTER_WEBUI_PORT}}# - SPARK_MASTER_WEBUI_PORT, to use non-default ports for the master{{/SPARK_MASTER_WEBUI_PORT}}
{{#SPARK_MASTER_OPTS}}SPARK_MASTER_OPTS={{SPARK_MASTER_OPTS}}{{/SPARK_MASTER_OPTS}}{{^SPARK_MASTER_OPTS}}# - SPARK_MASTER_OPTS, to set config properties only for the master (e.g. "-Dx=y"){{/SPARK_MASTER_OPTS}}
{{#SPARK_WORKER_CORES}}SPARK_WORKER_CORES={{SPARK_WORKER_CORES}}{{/SPARK_WORKER_CORES}}{{^SPARK_WORKER_CORES}}# - SPARK_WORKER_CORES, to set the number of cores to use on this machine{{/SPARK_WORKER_CORES}}
{{#SPARK_WORKER_MEMORY}}SPARK_WORKER_MEMORY={{SPARK_WORKER_MEMORY}}{{/SPARK_WORKER_MEMORY}}{{^SPARK_WORKER_MEMORY}}# - SPARK_WORKER_MEMORY, to set how much total memory workers have to give executors (e.g. 1000m, 2g){{/SPARK_WORKER_MEMORY}}
{{#SPARK_DAEMON_MEMORY}}SPARK_DAEMON_MEMORY={{SPARK_DAEMON_MEMORY}}{{/SPARK_DAEMON_MEMORY}}{{^SPARK_DAEMON_MEMORY}}# - SPARK_DAEMON_MEMORY, to set how much total memory the master has (e.g. 1000m, 2g){{/SPARK_DAEMON_MEMORY}}
{{#SPARK_WORKER_PORT}}SPARK_WORKER_PORT={{SPARK_WORKER_PORT}}{{/SPARK_WORKER_PORT}}{{^SPARK_WORKER_PORT}}# - SPARK_WORKER_PORT, to use non-default ports for the worker{{/SPARK_WORKER_PORT}}
{{#SPARK_WORKER_WEBUI_PORT}}SPARK_WORKER_WEBUI_PORT={{SPARK_WORKER_WEBUI_PORT}}{{/SPARK_WORKER_WEBUI_PORT}}{{^SPARK_WORKER_WEBUI_PORT}}# - SPARK_WORKER_WEBUI_PORT, to use non-default ports for the worker{{/SPARK_WORKER_WEBUI_PORT}}
{{#SPARK_WORKER_INSTANCES}}SPARK_WORKER_INSTANCES={{SPARK_WORKER_INSTANCES}}{{/SPARK_WORKER_INSTANCES}}{{^SPARK_WORKER_INSTANCES}}# - SPARK_WORKER_INSTANCES, to set the number of worker processes per node{{/SPARK_WORKER_INSTANCES}}
{{#SPARK_WORKER_DIR}}SPARK_WORKER_DIR={{SPARK_WORKER_DIR}}{{/SPARK_WORKER_DIR}}{{^SPARK_WORKER_DIR}}# - SPARK_WORKER_DIR, to set the working directory of worker processes{{/SPARK_WORKER_DIR}}
{{#SPARK_WORKER_OPTS}}SPARK_WORKER_OPTS={{{SPARK_WORKER_OPTS}}}{{/SPARK_WORKER_OPTS}}{{^SPARK_WORKER_OPTS}}# - SPARK_WORKER_OPTS, to set config properties only for the worker (e.g. "-Dx=y"){{/SPARK_WORKER_OPTS}}
{{#SPARK_HISTORY_OPTS}}SPARK_HISTORY_OPTS={{SPARK_HISTORY_OPTS}}{{/SPARK_HISTORY_OPTS}}{{^SPARK_HISTORY_OPTS}}# - SPARK_HISTORY_OPTS, to set config properties only for the history server (e.g. "-Dx=y"){{/SPARK_HISTORY_OPTS}}
{{#SPARK_DAEMON_JAVA_OPTS}}SPARK_DAEMON_JAVA_OPTS={{SPARK_DAEMON_JAVA_OPTS}}{{/SPARK_DAEMON_JAVA_OPTS}}{{^SPARK_DAEMON_JAVA_OPTS}}# - SPARK_DAEMON_JAVA_OPTS, to set config properties for all daemons (e.g. "-Dx=y"){{/SPARK_DAEMON_JAVA_OPTS}}
{{#SPARK_PUBLIC_DNS}}SPARK_PUBLIC_DNS={{SPARK_PUBLIC_DNS}}{{/SPARK_PUBLIC_DNS}}{{^SPARK_PUBLIC_DNS}}# - SPARK_PUBLIC_DNS, to set the public dns name of the master or workers{{/SPARK_PUBLIC_DNS}}