You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Hyukjin Kwon (Jira)" <ji...@apache.org> on 2019/10/08 05:43:18 UTC
[jira] [Resolved] (SPARK-22907) MetadataFetchFailedException
broadcast is already present
[ https://issues.apache.org/jira/browse/SPARK-22907?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Hyukjin Kwon resolved SPARK-22907.
----------------------------------
Resolution: Incomplete
> MetadataFetchFailedException broadcast is already present
> ---------------------------------------------------------
>
> Key: SPARK-22907
> URL: https://issues.apache.org/jira/browse/SPARK-22907
> Project: Spark
> Issue Type: Bug
> Components: Spark Core
> Affects Versions: 2.1.0, 2.3.0
> Environment: Spark2.1.0 + yarn
> Reporter: liupengcheng
> Priority: Major
> Labels: bulk-closed
>
> Currently, some IOException(may caused by physical environment) may cause MetadataFetchFailedException, and the stage will be retried. however, when in the retrying of the stage, if the task is scheduled at the same executors where the first MetadataFetchFailedException happens, a 'MetadataFetchFailedException: broadcast is already present' will be thrown.
> {noformat}
> org.apache.spark.shuffle.MetadataFetchFailedException: java.io.IOException: java.lang.IllegalArgumentException: requirement failed: Block broadcast_22 is already present in the MemoryStore
> at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1224)
> at org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(TorrentBroadcast.scala:167)
> at org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(TorrentBroadcast.scala:64)
> at org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast.scala:64)
> at org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.scala:88)
> at org.apache.spark.broadcast.Broadcast.value(Broadcast.scala:70)
> at org.apache.spark.MapOutputTracker$$anonfun$deserializeMapStatuses$1.apply(MapOutputTracker.scala:675)
> at org.apache.spark.MapOutputTracker$$anonfun$deserializeMapStatuses$1.apply(MapOutputTracker.scala:675)
> at org.apache.spark.Logging$class.logInfo(Logging.scala:58)
> at org.apache.spark.MapOutputTracker$.logInfo(MapOutputTracker.scala:612)
> at org.apache.spark.MapOutputTracker$.deserializeMapStatuses(MapOutputTracker.scala:674)
> at org.apache.spark.MapOutputTracker.getStatuses(MapOutputTracker.scala:202)
> at org.apache.spark.MapOutputTracker.getMapSizesByExecutorId(MapOutputTracker.scala:141)
> at org.apache.spark.shuffle.BlockStoreShuffleReader.read(BlockStoreShuffleReader.scala:55)
> at org.apache.spark.rdd.ShuffledRDD.compute(ShuffledRDD.scala:98)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$2.apply(CoGroupedRDD.scala:140)
> at org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$2.apply(CoGroupedRDD.scala:136)
> at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771)
> at org.apache.spark.rdd.CoGroupedRDD.compute(CoGroupedRDD.scala:136)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.CoalescedRDD$$anonfun$compute$1.apply(CoalescedRDD.scala:96)
> at org.apache.spark.rdd.CoalescedRDD$$anonfun$compute$1.apply(CoalescedRDD.scala:95)
> at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12$$anonfun$apply$4.apply$mcV$sp(PairRDDFunctions.scala:1112)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12$$anonfun$apply$4.apply(PairRDDFunctions.scala:1112)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12$$anonfun$apply$4.apply(PairRDDFunctions.scala:1112)
> at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1252)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1120)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1091)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:90)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:241)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.IllegalArgumentException: requirement failed: Block broadcast_22 is already present in the MemoryStore
> at scala.Predef$.require(Predef.scala:233)
> at org.apache.spark.storage.MemoryStore.putIterator(MemoryStore.scala:161)
> at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:894)
> at org.apache.spark.storage.BlockManager.putIterator(BlockManager.scala:728)
> at org.apache.spark.storage.BlockManager.putSingle(BlockManager.scala:1113)
> at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$1.apply(TorrentBroadcast.scala:183)
> at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1221)
> ... 49 more
> at org.apache.spark.MapOutputTracker.getStatuses(MapOutputTracker.scala:207)
> at org.apache.spark.MapOutputTracker.getMapSizesByExecutorId(MapOutputTracker.scala:141)
> at org.apache.spark.shuffle.BlockStoreShuffleReader.read(BlockStoreShuffleReader.scala:55)
> at org.apache.spark.rdd.ShuffledRDD.compute(ShuffledRDD.scala:98)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$2.apply(CoGroupedRDD.scala:140)
> at org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$2.apply(CoGroupedRDD.scala:136)
> at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771)
> at org.apache.spark.rdd.CoGroupedRDD.compute(CoGroupedRDD.scala:136)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.CoalescedRDD$$anonfun$compute$1.apply(CoalescedRDD.scala:96)
> at org.apache.spark.rdd.CoalescedRDD$$anonfun$compute$1.apply(CoalescedRDD.scala:95)
> at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12$$anonfun$apply$4.apply$mcV$sp(PairRDDFunctions.scala:1112)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12$$anonfun$apply$4.apply(PairRDDFunctions.scala:1112)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12$$anonfun$apply$4.apply(PairRDDFunctions.scala:1112)
> at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1252)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1120)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1091)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:90)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:241)
> 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:745)
> {noformat}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org