You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "John Zhuge (JIRA)" <ji...@apache.org> on 2018/10/08 17:23:00 UTC
[jira] [Commented] (SPARK-16707)
TransportClientFactory.createClient may throw NPE
[ https://issues.apache.org/jira/browse/SPARK-16707?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16642191#comment-16642191 ]
John Zhuge commented on SPARK-16707:
------------------------------------
Saw the same NPE with 2.1.1:
{noformat}
org.apache.spark.shuffle.FetchFailedException
at org.apache.spark.storage.ShuffleBlockFetcherIterator.throwFetchFailedException(ShuffleBlockFetcherIterator.scala:361)
at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:336)
at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:54)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.util.collection.ExternalAppendOnlyMap.insertAll(ExternalAppendOnlyMap.scala:154)
at org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$4.apply(CoGroupedRDD.scala:154)
at org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$4.apply(CoGroupedRDD.scala:153)
at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:733)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:732)
at org.apache.spark.rdd.CoGroupedRDD.compute(CoGroupedRDD.scala:153)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:328)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:292)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:328)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:292)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:328)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:292)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:328)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:292)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:328)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:292)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:328)
at org.apache.spark.rdd.RDD$$anonfun$8.apply(RDD.scala:341)
at org.apache.spark.rdd.RDD$$anonfun$8.apply(RDD.scala:339)
at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1032)
at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1007)
at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:947)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1007)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:711)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:339)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:290)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:328)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:292)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:328)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:292)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:328)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:292)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:100)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:353)
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)
Caused by: java.lang.NullPointerException
at org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:149)
at org.apache.spark.network.shuffle.ExternalShuffleClient$1.createAndStart(ExternalShuffleClient.java:105)
at org.apache.spark.network.shuffle.RetryingBlockFetcher.fetchAllOutstanding(RetryingBlockFetcher.java:141)
at org.apache.spark.network.shuffle.RetryingBlockFetcher.start(RetryingBlockFetcher.java:121)
at org.apache.spark.network.shuffle.ExternalShuffleClient.fetchBlocks(ExternalShuffleClient.java:114)
at org.apache.spark.storage.ShuffleBlockFetcherIterator.sendRequest(ShuffleBlockFetcherIterator.scala:169)
at org.apache.spark.storage.ShuffleBlockFetcherIterator.fetchUpToMaxBytes(ShuffleBlockFetcherIterator.scala:354)
at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:332)
... 57 more
{noformat}
> TransportClientFactory.createClient may throw NPE
> -------------------------------------------------
>
> Key: SPARK-16707
> URL: https://issues.apache.org/jira/browse/SPARK-16707
> Project: Spark
> Issue Type: Bug
> Affects Versions: 1.6.0
> Reporter: Hong Shen
> Priority: Major
>
> I have encounter some NullPointerException when TransportClientFactory.createClient in my cluster, here is the following stack trace.
> {code}
> org.apache.spark.shuffle.FetchFailedException
> at org.apache.spark.storage.ShuffleBlockFetcherIterator.throwFetchFailedException(ShuffleBlockFetcherIterator.scala:326)
> at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:303)
> at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:53)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32)
> at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:511)
> at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.<init>(TungstenAggregationIterator.scala:686)
> at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:95)
> at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86)
> at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:741)
> at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:741)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:337)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:301)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:337)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:301)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:337)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:301)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:337)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:301)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:89)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:215)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> Caused by: java.lang.NullPointerException
> at org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:144)
> at org.apache.spark.network.shuffle.ExternalShuffleClient$1.createAndStart(ExternalShuffleClient.java:107)
> at org.apache.spark.network.shuffle.RetryingBlockFetcher.fetchAllOutstanding(RetryingBlockFetcher.java:146)
> at org.apache.spark.network.shuffle.RetryingBlockFetcher.start(RetryingBlockFetcher.java:126)
> at org.apache.spark.network.shuffle.ExternalShuffleClient.fetchBlocks(ExternalShuffleClient.java:116)
> at org.apache.spark.storage.ShuffleBlockFetcherIterator.sendRequest(ShuffleBlockFetcherIterator.scala:155)
> at org.apache.spark.storage.ShuffleBlockFetcherIterator.fetchUpToMaxBytes(ShuffleBlockFetcherIterator.scala:319)
> at org.apache.spark.storage.ShuffleBlockFetcherIterator.next(ShuffleBlockFetcherIterator.scala:299)
> ... 32 more
> {code}
> The code is at https://github.com/apache/spark/blob/branch-1.6/network/common/src/main/java/org/apache/spark/network/client/TransportClientFactory.java#L144
> {code}
> TransportChannelHandler handler = cachedClient.getChannel().pipeline()
> .get(TransportChannelHandler.class);
> synchronized (handler) {
> {code}
> synchronized (handler) throw NullPointerException, handler is null.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org