#!/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. # # This file is sourced when running various Spark programs. # Copy it as spark-env.sh and edit that to configure Spark for your site. # Options read when launching programs locally with # ./bin/run-example or ./bin/spark-submit # - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files # - 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 # Options read by executors and drivers running inside the cluster # - 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_LOCAL_DIRS, storage directories to use on this node for shuffle and RDD data # - MESOS_NATIVE_JAVA_LIBRARY, to point to your libmesos.so if you use Mesos # Options read in YARN client mode # - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files # - SPARK_EXECUTOR_CORES, Number of cores for the executors (Default: 1). # - SPARK_EXECUTOR_MEMORY, Memory per Executor (e.g. 1000M, 2G) (Default: 1G) # - SPARK_DRIVER_MEMORY, Memory for Driver (e.g. 1000M, 2G) (Default: 1G) HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop # Options for the daemons used in the standalone deploy mode # - SPARK_MASTER_HOST, to bind the master to a different IP address or hostname # - SPARK_MASTER_PORT / SPARK_MASTER_WEBUI_PORT, to use non-default ports for the master # - SPARK_MASTER_OPTS, to set config properties only for the master (e.g. "-Dx=y") # - SPARK_WORKER_CORES, to set the number of cores to use on this machine # - SPARK_WORKER_MEMORY, to set how much total memory workers have to give executors (e.g. 1000m, 2g) # - SPARK_WORKER_PORT / SPARK_WORKER_WEBUI_PORT, to use non-default ports for the worker # - SPARK_WORKER_DIR, to set the working directory of worker processes # - SPARK_WORKER_OPTS, to set config properties only for the worker (e.g. "-Dx=y") # - SPARK_DAEMON_MEMORY, to allocate to the master, worker and history server themselves (default: 1g). # - SPARK_HISTORY_OPTS, to set config properties only for the history server (e.g. "-Dx=y") # - SPARK_SHUFFLE_OPTS, to set config properties only for the external shuffle service (e.g. "-Dx=y") # - SPARK_DAEMON_JAVA_OPTS, to set config properties for all daemons (e.g. "-Dx=y") # - SPARK_DAEMON_CLASSPATH, to set the classpath for all daemons # - SPARK_PUBLIC_DNS, to set the public dns name of the master or workers # 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: $USER) # - SPARK_NICENESS The scheduling priority for daemons. (Default: 0) # - SPARK_NO_DAEMONIZE Run the proposed command in the foreground. It will not output a PID file. export JAVA_HOME=/usr/lib/jvm/java-1.8.0-openjdk export SCALA_HOME=/usr/share/scala export HADOOP_HOME=/usr/local/hadoop/hadoop-2.7.3 export SPARK_MASTER_IP=192.168.1.116 export SPARK_MASTER_PORT=7077 export SPARK_MASTER_WEBUI_PORT=7070 export SPARK_WORKER_CORES=2 export SPARK_WORKER_MEMORY=1024m export SPARK_WORKER_INSTANCES=2 export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop export SPARK_YARN_USER_ENV="CLASSPATH=/usr/local/hadoop/hadoop-2.7.3/etc/hadoop" export SPARK_CLASSPATH=$HBASE_HOME/lib/hbase-protocol-1.2.4.jar:$HBASE_HOME/lib/hbase-common-1.2.4.jar:$HBASE_HOME/lib/htrace-core-3.1.0-incubating.jar:$HBASE_HOME/lib/hbase-server-1.2.4.jar:$HBASE_HOME/lib/hbase-client-1.2.4.jar:$HBASE_HOME/lib/metrics-core-2.2.0.jar:$SPARK_CLASSPATH export SPARK_LOCAL_DIR="/mnt/spark/tmp" export YARN_CONF_DIR=$HADOOP_HOME/etc/hadoop export SPARK_JAVA_OPTS="-Dspark.storage.blockManagerHeartBeatMs=60000-Dspark.local.dir=$SPARK_LOCAL_DIR -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -Xloggc:$SPARK_HOME/logs/gc.log -XX:+UseConcMarkSweepGC -XX:+UseCMSCompactAtFullCollection -XX:CMSInitiatingOccupancyFraction=60" export SPARK_DAEMON_JAVA_OPTS="-Dspark.deploy.recoveryMode=ZOOKEEPER -Dspark.deploy.zookeeper.url=hadoop-2:2181,hadoop-3:2181,hadoop-5:2181 -Dspark.deploy.zookeeper.dir=/spark"