From 25889d8d97094325f10fbf52f3b36412f212eeb2 Mon Sep 17 00:00:00 2001 From: Evan Jones Date: Fri, 8 May 2015 22:00:39 +0100 Subject: [SPARK-7490] [CORE] [Minor] MapOutputTracker.deserializeMapStatuses: close input streams GZIPInputStream allocates native memory that is not freed until close() or when the finalizer runs. It is best to close() these streams explicitly. stephenh made the same change for serializeMapStatuses in commit b0d884f0. This is the same change for deserialize. (I ran the unit test suite! it seems to have passed. I did not make a JIRA since this seems "trivial", and the guidelines suggest it is not required for trivial changes) Author: Evan Jones Closes #5982 from evanj/master and squashes the following commits: 0d76e85 [Evan Jones] [CORE] MapOutputTracker.deserializeMapStatuses: close input streams --- core/src/main/scala/org/apache/spark/MapOutputTracker.scala | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/core/src/main/scala/org/apache/spark/MapOutputTracker.scala b/core/src/main/scala/org/apache/spark/MapOutputTracker.scala index 16072283ed..018422827e 100644 --- a/core/src/main/scala/org/apache/spark/MapOutputTracker.scala +++ b/core/src/main/scala/org/apache/spark/MapOutputTracker.scala @@ -367,7 +367,11 @@ private[spark] object MapOutputTracker extends Logging { // Opposite of serializeMapStatuses. def deserializeMapStatuses(bytes: Array[Byte]): Array[MapStatus] = { val objIn = new ObjectInputStream(new GZIPInputStream(new ByteArrayInputStream(bytes))) - objIn.readObject().asInstanceOf[Array[MapStatus]] + Utils.tryWithSafeFinally { + objIn.readObject().asInstanceOf[Array[MapStatus]] + } { + objIn.close() + } } // Convert an array of MapStatuses to locations and sizes for a given reduce ID. If -- cgit v1.2.3