aboutsummaryrefslogtreecommitdiff
path: root/bin/spark-class
diff options
context:
space:
mode:
authorAaron Davidson <aaron@databricks.com>2014-03-09 11:08:39 -0700
committerAaron Davidson <aaron@databricks.com>2014-03-09 11:08:39 -0700
commit52834d761b059264214dfc6a1f9c70b8bc7ec089 (patch)
treedeadb9fd8330b40da0b455478c9319dd75421f58 /bin/spark-class
parente59a3b6c415b95e8137f5a154716b12653a8aed0 (diff)
downloadspark-52834d761b059264214dfc6a1f9c70b8bc7ec089.tar.gz
spark-52834d761b059264214dfc6a1f9c70b8bc7ec089.tar.bz2
spark-52834d761b059264214dfc6a1f9c70b8bc7ec089.zip
SPARK-929: Fully deprecate usage of SPARK_MEM
(Continued from old repo, prior discussion at https://github.com/apache/incubator-spark/pull/615) This patch cements our deprecation of the SPARK_MEM environment variable by replacing it with three more specialized variables: SPARK_DAEMON_MEMORY, SPARK_EXECUTOR_MEMORY, and SPARK_DRIVER_MEMORY The creation of the latter two variables means that we can safely set driver/job memory without accidentally setting the executor memory. Neither is public. SPARK_EXECUTOR_MEMORY is only used by the Mesos scheduler (and set within SparkContext). The proper way of configuring executor memory is through the "spark.executor.memory" property. SPARK_DRIVER_MEMORY is the new way of specifying the amount of memory run by jobs launched by spark-class, without possibly affecting executor memory. Other memory considerations: - The repl's memory can be set through the "--drivermem" command-line option, which really just sets SPARK_DRIVER_MEMORY. - run-example doesn't use spark-class, so the only way to modify examples' memory is actually an unusual use of SPARK_JAVA_OPTS (which is normally overriden in all cases by spark-class). This patch also fixes a lurking bug where spark-shell misused spark-class (the first argument is supposed to be the main class name, not java options), as well as a bug in the Windows spark-class2.cmd. I have not yet tested this patch on either Windows or Mesos, however. Author: Aaron Davidson <aaron@databricks.com> Closes #99 from aarondav/sparkmem and squashes the following commits: 9df4c68 [Aaron Davidson] SPARK-929: Fully deprecate usage of SPARK_MEM
Diffstat (limited to 'bin/spark-class')
-rwxr-xr-xbin/spark-class48
1 files changed, 28 insertions, 20 deletions
diff --git a/bin/spark-class b/bin/spark-class
index c4225a392d..229ae2cebb 100755
--- a/bin/spark-class
+++ b/bin/spark-class
@@ -40,34 +40,46 @@ if [ -z "$1" ]; then
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="$SPARK_JAVA_OPTS"
+if [ -n "$SPARK_MEM" ]; then
+ echo "Warning: SPARK_MEM is deprecated, please use a more specific config option"
+ echo "(e.g., spark.executor.memory or SPARK_DRIVER_MEMORY)."
fi
+# Use SPARK_MEM or 512m as the default memory, to be overridden by specific options
+DEFAULT_MEM=${SPARK_MEM:-512m}
+
+SPARK_DAEMON_JAVA_OPTS="$SPARK_DAEMON_JAVA_OPTS -Dspark.akka.logLifecycleEvents=true"
-# Add java opts for master, worker, executor. The opts maybe null
+# Add java opts and memory settings for master, worker, executors, and repl.
case "$1" in
+ # Master and Worker use SPARK_DAEMON_JAVA_OPTS (and specific opts) + SPARK_DAEMON_MEMORY.
'org.apache.spark.deploy.master.Master')
- OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_MASTER_OPTS"
+ OUR_JAVA_OPTS="$SPARK_DAEMON_JAVA_OPTS $SPARK_MASTER_OPTS"
+ OUR_JAVA_MEM=${SPARK_DAEMON_MEMORY:-$DEFAULT_MEM}
;;
'org.apache.spark.deploy.worker.Worker')
- OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_WORKER_OPTS"
+ OUR_JAVA_OPTS="$SPARK_DAEMON_JAVA_OPTS $SPARK_WORKER_OPTS"
+ OUR_JAVA_MEM=${SPARK_DAEMON_MEMORY:-$DEFAULT_MEM}
;;
+
+ # Executors use SPARK_JAVA_OPTS + SPARK_EXECUTOR_MEMORY.
'org.apache.spark.executor.CoarseGrainedExecutorBackend')
- OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_EXECUTOR_OPTS"
+ OUR_JAVA_OPTS="$SPARK_JAVA_OPTS $SPARK_EXECUTOR_OPTS"
+ OUR_JAVA_MEM=${SPARK_EXECUTOR_MEMORY:-$DEFAULT_MEM}
;;
'org.apache.spark.executor.MesosExecutorBackend')
- OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_EXECUTOR_OPTS"
+ OUR_JAVA_OPTS="$SPARK_JAVA_OPTS $SPARK_EXECUTOR_OPTS"
+ OUR_JAVA_MEM=${SPARK_EXECUTOR_MEMORY:-$DEFAULT_MEM}
;;
+
+ # All drivers use SPARK_JAVA_OPTS + SPARK_DRIVER_MEMORY. The repl also uses SPARK_REPL_OPTS.
'org.apache.spark.repl.Main')
- OUR_JAVA_OPTS="$OUR_JAVA_OPTS $SPARK_REPL_OPTS"
+ OUR_JAVA_OPTS="$SPARK_JAVA_OPTS $SPARK_REPL_OPTS"
+ OUR_JAVA_MEM=${SPARK_DRIVER_MEMORY:-$DEFAULT_MEM}
+ ;;
+ *)
+ OUR_JAVA_OPTS="$SPARK_JAVA_OPTS"
+ OUR_JAVA_MEM=${SPARK_DRIVER_MEMORY:-$DEFAULT_MEM}
;;
esac
@@ -83,14 +95,10 @@ else
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$SPARK_MEM"
+JAVA_OPTS="$JAVA_OPTS -Xms$OUR_JAVA_MEM -Xmx$OUR_JAVA_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`"