[SPARK-10916] [YARN] Set perm gen size when launching containers on YARN.

This makes YARN containers behave like all other processes launched by
Spark, which launch with a default perm gen size of 256m unless
overridden by the user (or not needed by the vm).

Author: Marcelo Vanzin <vanzin@cloudera.com>

Closes #8970 from vanzin/SPARK-10916.

3 files changed, 24 insertions, 3 deletions

diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala
index 8c53c24a79..f8748ef658 100644
--- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala
+++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala
@@ -54,8 +54,9 @@ import org.apache.hadoop.yarn.conf.YarnConfiguration
 import org.apache.hadoop.yarn.exceptions.ApplicationNotFoundException
 import org.apache.hadoop.yarn.util.Records
 
-import org.apache.spark.deploy.SparkHadoopUtil
 import org.apache.spark.{Logging, SecurityManager, SparkConf, SparkContext, SparkException}
+import org.apache.spark.deploy.SparkHadoopUtil
+import org.apache.spark.launcher.YarnCommandBuilderUtils
 import org.apache.spark.util.Utils
 
 private[spark] class Client(
@@ -730,6 +731,7 @@ private[spark] class Client(
 
     // For log4j configuration to reference
     javaOpts += ("-Dspark.yarn.app.container.log.dir=" + ApplicationConstants.LOG_DIR_EXPANSION_VAR)
+    YarnCommandBuilderUtils.addPermGenSizeOpt(javaOpts)
 
     val userClass =
       if (isClusterMode) {
diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala
index 9abd09b3cc..2232ffba47 100644
--- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala
+++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala
@@ -38,6 +38,7 @@ import org.apache.hadoop.yarn.ipc.YarnRPC
 import org.apache.hadoop.yarn.util.{ConverterUtils, Records}
 
 import org.apache.spark.{Logging, SecurityManager, SparkConf, SparkException}
+import org.apache.spark.launcher.YarnCommandBuilderUtils
 import org.apache.spark.network.util.JavaUtils
 import org.apache.spark.util.Utils
 
@@ -199,6 +200,7 @@ class ExecutorRunnable(
 
     // For log4j configuration to reference
     javaOpts += ("-Dspark.yarn.app.container.log.dir=" + ApplicationConstants.LOG_DIR_EXPANSION_VAR)
+    YarnCommandBuilderUtils.addPermGenSizeOpt(javaOpts)
 
     val userClassPath = Client.getUserClasspath(sparkConf).flatMap { uri =>
       val absPath =
diff --git a/yarn/src/main/scala/org/apache/spark/launcher/YarnCommandBuilderUtils.scala b/yarn/src/main/scala/org/apache/spark/launcher/YarnCommandBuilderUtils.scala
index 3ac36ef0a1..7d246bf407 100644
--- a/yarn/src/main/scala/org/apache/spark/launcher/YarnCommandBuilderUtils.scala
+++ b/yarn/src/main/scala/org/apache/spark/launcher/YarnCommandBuilderUtils.scala
@@ -17,11 +17,28 @@
 
 package org.apache.spark.launcher
 
+import scala.collection.JavaConverters._
+import scala.collection.mutable.ListBuffer
+
 /**
- * Exposes needed methods
+ * Exposes methods from the launcher library that are used by the YARN backend.
  */
 private[spark] object YarnCommandBuilderUtils {
-  def quoteForBatchScript(arg: String) : String = {
+
+  def quoteForBatchScript(arg: String): String = {
     CommandBuilderUtils.quoteForBatchScript(arg)
   }
+
+  /**
+   * Adds the perm gen configuration to the list of java options if needed and not yet added.
+   *
+   * Note that this method adds the option based on the local JVM version; if the node where
+   * the container is running has a different Java version, there's a risk that the option will
+   * not be added (e.g. if the AM is running Java 8 but the container's node is set up to use
+   * Java 7).
+   */
+  def addPermGenSizeOpt(args: ListBuffer[String]): Unit = {
+    CommandBuilderUtils.addPermGenSizeOpt(args.asJava)
+  }
+
 }