From d3cbd38c33e6a2addcf8caa18eeb10036fbfd01b Mon Sep 17 00:00:00 2001
From: Nishkam Ravi <nravi@cloudera.com>
Date: Sat, 21 Feb 2015 09:59:28 -0800
Subject: [PATCH] SPARK-5841 [CORE] [HOTFIX 2] Memory leak in DiskBlockManager
Continue to see IllegalStateException in YARN cluster mode. Adding a simple workaround for now.
Author: Nishkam Ravi <nravi@cloudera.com>
Author: nishkamravi2 <nishkamravi@gmail.com>
Author: nravi <nravi@c1704.halxg.cloudera.com>
Closes #4690 from nishkamravi2/master_nravi and squashes the following commits:
d453197 [nishkamravi2] Update NewHadoopRDD.scala
6f41a1d [nishkamravi2] Update NewHadoopRDD.scala
0ce2c32 [nishkamravi2] Update HadoopRDD.scala
f7e33c2 [Nishkam Ravi] Merge branch 'master_nravi' of https://github.com/nishkamravi2/spark into master_nravi
ba1eb8b [Nishkam Ravi] Try-catch block around the two occurrences of removeShutDownHook. Deletion of semi-redundant occurrences of expensive operation inShutDown.
71d0e17 [Nishkam Ravi] Merge branch 'master' of https://github.com/apache/spark into master_nravi
494d8c0 [nishkamravi2] Update DiskBlockManager.scala
3c5ddba [nishkamravi2] Update DiskBlockManager.scala
f0d12de [Nishkam Ravi] Workaround for IllegalStateException caused by recent changes to BlockManager.stop
79ea8b4 [Nishkam Ravi] Merge branch 'master' of https://github.com/apache/spark into master_nravi
b446edc [Nishkam Ravi] Merge branch 'master' of https://github.com/apache/spark into master_nravi
5c9a4cb [nishkamravi2] Update TaskSetManagerSuite.scala
535295a [nishkamravi2] Update TaskSetManager.scala
3e1b616 [Nishkam Ravi] Modify test for maxResultSize
9f6583e [Nishkam Ravi] Changes to maxResultSize code (improve error message and add condition to check if maxResultSize > 0)
5f8f9ed [Nishkam Ravi] Merge branch 'master' of https://github.com/apache/spark into master_nravi
636a9ff [nishkamravi2] Update YarnAllocator.scala
8f76c8b [Nishkam Ravi] Doc change for yarn memory overhead
35daa64 [Nishkam Ravi] Slight change in the doc for yarn memory overhead
5ac2ec1 [Nishkam Ravi] Remove out
dac1047 [Nishkam Ravi] Additional documentation for yarn memory overhead issue
42c2c3d [Nishkam Ravi] Additional changes for yarn memory overhead issue
362da5e [Nishkam Ravi] Additional changes for yarn memory overhead
c726bd9 [Nishkam Ravi] Merge branch 'master' of https://github.com/apache/spark into master_nravi
f00fa31 [Nishkam Ravi] Improving logging for AM memoryOverhead
1cf2d1e [nishkamravi2] Update YarnAllocator.scala
ebcde10 [Nishkam Ravi] Modify default YARN memory_overhead-- from an additive constant to a multiplier (redone to resolve merge conflicts)
2e69f11 [Nishkam Ravi] Merge branch 'master' of https://github.com/apache/spark into master_nravi
efd688a [Nishkam Ravi] Merge branch 'master' of https://github.com/apache/spark
2b630f9 [nravi] Accept memory input as "30g", "512M" instead of an int value, to be consistent with rest of Spark
3bf8fad [nravi] Merge branch 'master' of https://github.com/apache/spark
5423a03 [nravi] Merge branch 'master' of https://github.com/apache/spark
eb663ca [nravi] Merge branch 'master' of https://github.com/apache/spark
df2aeb1 [nravi] Improved fix for ConcurrentModificationIssue (Spark-1097, Hadoop-10456)
6b840f0 [nravi] Undo the fix for SPARK-1758 (the problem is fixed)
5108700 [nravi] Fix in Spark for the Concurrent thread modification issue (SPARK-1097, HADOOP-10456)
681b36f [nravi] Fix for SPARK-1758: failing test org.apache.spark.JavaAPISuite.wholeTextFiles
---
.../org/apache/spark/deploy/worker/ExecutorRunner.scala | 6 +++++-
.../scala/org/apache/spark/storage/DiskBlockManager.scala | 6 +++++-
2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala b/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala
index 0add3064da..bea04cd542 100644
--- a/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala
+++ b/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala
@@ -105,7 +105,11 @@ private[spark] class ExecutorRunner(
workerThread.interrupt()
workerThread = null
state = ExecutorState.KILLED
- Runtime.getRuntime.removeShutdownHook(shutdownHook)
+ try {
+ Runtime.getRuntime.removeShutdownHook(shutdownHook)
+ } catch {
+ case e: IllegalStateException => None
+ }
}
}
diff --git a/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala b/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala
index b297f3fd9d..12cd8ea3bd 100644
--- a/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala
+++ b/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala
@@ -148,7 +148,11 @@ private[spark] class DiskBlockManager(blockManager: BlockManager, conf: SparkCon
/** Cleanup local dirs and stop shuffle sender. */
private[spark] def stop() {
// Remove the shutdown hook. It causes memory leaks if we leave it around.
- Runtime.getRuntime.removeShutdownHook(shutdownHook)
+ try {
+ Runtime.getRuntime.removeShutdownHook(shutdownHook)
+ } catch {
+ case e: IllegalStateException => None
+ }
doStop()
}
--
GitLab