[
https://issues.apache.org/jira/browse/SPARK-17113?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Davies Liu resolved SPARK-17113.
--------------------------------
Resolution: Fixed
Fix Version/s: 2.1.0
2.0.1
> Job failure due to Executor OOM in offheap mode
> -----------------------------------------------
>
> Key: SPARK-17113
> URL: https://issues.apache.org/jira/browse/SPARK-17113
> Project: Spark
> Issue Type: Bug
> Affects Versions: 1.6.2, 2.0.0
> Reporter: Sital Kedia
> Assignee: Sital Kedia
> Fix For: 2.0.1, 2.1.0
>
>
> We have been seeing many job failure due to executor OOM with following stack
> trace -
> {code}
> java.lang.OutOfMemoryError: Unable to acquire 1220 bytes of memory, got 0
> at
> org.apache.spark.memory.MemoryConsumer.allocatePage(MemoryConsumer.java:120)
> at
> org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.acquireNewPageIfNecessary(UnsafeExternalSorter.java:341)
> at
> org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.insertRecord(UnsafeExternalSorter.java:362)
> at
> org.apache.spark.sql.execution.UnsafeExternalRowSorter.insertRow(UnsafeExternalRowSorter.java:93)
> at
> org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(UnsafeExternalRowSorter.java:170)
> at org.apache.spark.sql.execution.Sort$$anonfun$1.apply(Sort.scala:90)
> at org.apache.spark.sql.execution.Sort$$anonfun$1.apply(Sort.scala:64)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$21.apply(RDD.scala:736)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$21.apply(RDD.scala:736)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:307)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:271)
> at
> org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:88)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:307)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:271)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:307)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:271)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:307)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:271)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:89)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> {code}
> Digging into the code, we found out that this is an issue with cooperative
> memory management for off heap memory allocation.
> In the code
> https://github.com/sitalkedia/spark/blob/master/core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeExternalSorter.java#L463,
> when the UnsafeExternalSorter is checking if memory page is being used by
> upstream, the base object in case of off heap memory is always null so the
> UnsafeExternalSorter does not spill the memory pages.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
