BIGTOP-1974. Revise SPARK_HOME/conf/spark-env.sh

1 files changed, 54 insertions, 26 deletions

diff --git a/bigtop-deploy/puppet/modules/spark/templates/spark-env.sh b/bigtop-deploy/puppet/modules/spark/templates/spark-env.sh
index bbd70815..e3550345 100644
--- a/bigtop-deploy/puppet/modules/spark/templates/spark-env.sh
+++ b/bigtop-deploy/puppet/modules/spark/templates/spark-env.sh
@@ -14,39 +14,67 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# This file contains environment variables required to run Spark. Copy it as
-# spark-env.sh and edit that to configure Spark for your site.
-#
-# The following variables can be set in this file:
+# 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
-# - MESOS_NATIVE_LIBRARY, to point to your libmesos.so if you use Mesos
-# - SPARK_JAVA_OPTS, to set node-specific JVM options for Spark. Note that
-#   we recommend setting app-wide options in the application's driver program.
-#     Examples of node-specific options : -Dspark.local.dir, GC options
-#     Examples of app-wide options : -Dspark.serializer
-#
-# If using the standalone deploy mode, you can also set variables for it here:
+# - 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
+# - 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
+# - 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_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.
+
+# Options for the daemons used in the standalone deploy mode
 # - SPARK_MASTER_IP, to bind the master to a different IP address or hostname
-# - SPARK_MASTER_PORT / SPARK_MASTER_WEBUI_PORT, to use non-default ports
+# - 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 memory to use (e.g. 1000m, 2g)
-# - SPARK_WORKER_PORT / SPARK_WORKER_WEBUI_PORT
+# - 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_INSTANCES, to set the number of worker processes per node
+# - 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_HISTORY_OPTS, to set config properties only for the history server (e.g. "-Dx=y")
+# - SPARK_DAEMON_JAVA_OPTS, to set config properties for all daemons (e.g. "-Dx=y")
+# - 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)
 
-### Let's run everything with JVM runtime, instead of Scala
-export SPARK_LAUNCH_WITH_SCALA=0
-export SPARK_LIBRARY_PATH=${SPARK_HOME}/lib
-export SCALA_LIBRARY_PATH=${SPARK_HOME}/lib
-export SPARK_MASTER_WEBUI_PORT=<%= @master_ui_port %>
-export SPARK_MASTER_PORT=<%= @master_port %>
+export HADOOP_HOME=${HADOOP_HOME:-/usr/lib/hadoop}
+export HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-/etc/hadoop/conf}
 
-### Comment above 2 lines and uncomment the following if
-### you want to run with scala version, that is included with the package
-#export SCALA_HOME=${SCALA_HOME:-/usr/lib/spark/scala}
-#export PATH=$PATH:$SCALA_HOME/bin
+export SPARK_MASTER_IP=<%= @master_port %>
+export SPARK_MASTER_WEBUI_PORT=<%= @master_ui_port %>
+export SPARK_MASTER_PORT=7077
+export SPARK_WORKER_PORT=7078
+export SPARK_WORKER_WEBUI_PORT=18081
+export SPARK_WORKER_DIR=/var/run/spark/work
+export SPARK_HISTORY_OPTS="$SPARK_HISTORY_OPTS -Dspark.history.fs.logDirectory=hdfs:///var/log/spark/apps -Dspark.history.ui.port=18082"
 
-### change the following to specify a real cluster's Master host
-export STANDALONE_SPARK_MASTER_HOST=<%= @master_host %>
+export SPARK_LOG_DIR=/var/log/spark
 
+export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:${HADOOP_HOME}/lib/native