[
https://issues.apache.org/jira/browse/SPARK-17453?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Chris Bannister updated SPARK-17453:
------------------------------------
Description:
Whilst doing a broadcast join we reliably hit this exception, the code worked
earlier on in 2.0.0 branch before release, and in 1.6. The data for the join is
coming from another RDD which is collected to a Set and then broadcast. This is
run in a Mesos cluster.
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1450)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1438)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1437)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1437)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at scala.Option.foreach(Option.scala:257)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1659)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1618)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1607)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1871)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1884)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1897)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1911)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:893)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
at org.apache.spark.rdd.RDD.collect(RDD.scala:892)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:729)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.io.IOException: java.lang.IllegalArgumentException: requirement
failed: Block broadcast_17_piece0 is already present in the MemoryStore
at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1260)
at
org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(TorrentBroadcast.scala:174)
at
org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(TorrentBroadcast.scala:65)
at
org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast.scala:65)
at
org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.scala:89)
at org.apache.spark.broadcast.Broadcast.value(Broadcast.scala:70)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:72)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:47)
at org.apache.spark.scheduler.Task.run(Task.scala:85)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.IllegalArgumentException: requirement failed: Block
broadcast_17_piece0 is already present in the MemoryStore
at scala.Predef$.require(Predef.scala:224)
at
org.apache.spark.storage.memory.MemoryStore.putBytes(MemoryStore.scala:144)
at
org.apache.spark.storage.BlockManager$$anonfun$doPutBytes$1.apply(BlockManager.scala:792)
at
org.apache.spark.storage.BlockManager$$anonfun$doPutBytes$1.apply(BlockManager.scala:761)
at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:866)
at
org.apache.spark.storage.BlockManager.doPutBytes(BlockManager.scala:761)
at
org.apache.spark.storage.BlockManager.putBytes(BlockManager.scala:740)
at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply$mcVI$sp(TorrentBroadcast.scala:140)
at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala:125)
at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala:125)
at scala.collection.immutable.List.foreach(List.scala:381)
at
org.apache.spark.broadcast.TorrentBroadcast.org$apache$spark$broadcast$TorrentBroadcast$$readBlocks(TorrentBroadcast.scala:125)
at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$1.apply(TorrentBroadcast.scala:186)
at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1253)
... 12 more
was:
Whilst doing a broadcast join we reliably hit this exception, the code worked
earlier on in 2.0.0 branch before release, and in 1.6. The data for the join is
coming from another RDD which is collected to a Set and then broadcast. This is
run in a Mesos cluster.
Stacktrace is attached
> Broadcast block already exists in MemoryStore
> ---------------------------------------------
>
> Key: SPARK-17453
> URL: https://issues.apache.org/jira/browse/SPARK-17453
> Project: Spark
> Issue Type: Bug
> Components: Block Manager
> Affects Versions: 2.0.0
> Reporter: Chris Bannister
>
> Whilst doing a broadcast join we reliably hit this exception, the code worked
> earlier on in 2.0.0 branch before release, and in 1.6. The data for the join
> is coming from another RDD which is collected to a Set and then broadcast.
> This is run in a Mesos cluster.
> Driver stacktrace:
> at
> org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1450)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1438)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1437)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
> at
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1437)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
> at scala.Option.foreach(Option.scala:257)
> at
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1659)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1618)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1607)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> at
> org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1871)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1884)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1897)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1911)
> at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:893)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
> at org.apache.spark.rdd.RDD.collect(RDD.scala:892)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at
> org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:729)
> at
> org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
> at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> Caused by: java.io.IOException: java.lang.IllegalArgumentException:
> requirement failed: Block broadcast_17_piece0 is already present in the
> MemoryStore
> at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1260)
> at
> org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(TorrentBroadcast.scala:174)
> at
> org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(TorrentBroadcast.scala:65)
> at
> org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast.scala:65)
> at
> org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.scala:89)
> at org.apache.spark.broadcast.Broadcast.value(Broadcast.scala:70)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:72)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:47)
> at org.apache.spark.scheduler.Task.run(Task.scala:85)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.IllegalArgumentException: requirement failed: Block
> broadcast_17_piece0 is already present in the MemoryStore
> at scala.Predef$.require(Predef.scala:224)
> at
> org.apache.spark.storage.memory.MemoryStore.putBytes(MemoryStore.scala:144)
> at
> org.apache.spark.storage.BlockManager$$anonfun$doPutBytes$1.apply(BlockManager.scala:792)
> at
> org.apache.spark.storage.BlockManager$$anonfun$doPutBytes$1.apply(BlockManager.scala:761)
> at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:866)
> at
> org.apache.spark.storage.BlockManager.doPutBytes(BlockManager.scala:761)
> at
> org.apache.spark.storage.BlockManager.putBytes(BlockManager.scala:740)
> at
> org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply$mcVI$sp(TorrentBroadcast.scala:140)
> at
> org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala:125)
> at
> org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala:125)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at
> org.apache.spark.broadcast.TorrentBroadcast.org$apache$spark$broadcast$TorrentBroadcast$$readBlocks(TorrentBroadcast.scala:125)
> at
> org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$1.apply(TorrentBroadcast.scala:186)
> at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1253)
> ... 12 more
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
