[
https://issues.apache.org/jira/browse/MAHOUT-1607?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14349793#comment-14349793
]
Andrew Palumbo commented on MAHOUT-1607:
----------------------------------------
this looks like it was probably due to a the user's spark version: 1.0.2 while
we were still on 0.9.1.
> spark-shell:scheduler.DAGScheduler: Failed to run fold at
> CheckpointedDrmSpark.scala:192
> ----------------------------------------------------------------------------------------
>
> Key: MAHOUT-1607
> URL: https://issues.apache.org/jira/browse/MAHOUT-1607
> Project: Mahout
> Issue Type: Bug
> Components: CLI
> Affects Versions: 1.0
> Environment: ubuntu 13.x x64
> jdk1.7.0_65
> scala 2.10.4
> spark 1.0.2
> Reporter: hhlin
> Labels: DSL, scala, spark, test
> Fix For: 1.0
>
>
> follow the step by
> http://mahout.apache.org/users/sparkbindings/play-with-shell.html, mahou
> spark-shell startup normally,but when exec "val drmX = drmData(::, 0 until
> 4);" ,it throw exception as bellow:
> 14/08/17 20:13:20 INFO scheduler.DAGScheduler: Failed to run fold at
> CheckpointedDrmSpark.scala:192
> 14/08/17 20:13:20 INFO scheduler.TaskSetManager: Loss was due to
> java.lang.ArrayStoreException: scala.Tuple3 [duplicate 6]
> 14/08/17 20:13:20 INFO scheduler.TaskSchedulerImpl: Removed TaskSet 0.0,
> whose tasks have all completed, from pool
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 0.0:1
> failed 4 times, most recent failure: Exception failure in TID 6 on host
> iZ23qefud7nZ: java.lang.ArrayStoreException: scala.Tuple3
>
> com.esotericsoftware.kryo.serializers.DefaultArraySerializers$ObjectArraySerializer.read(DefaultArraySerializers.java:338)
>
> com.esotericsoftware.kryo.serializers.DefaultArraySerializers$ObjectArraySerializer.read(DefaultArraySerializers.java:293)
> com.esotericsoftware.kryo.Kryo.readClassAndObject(Kryo.java:729)
>
> com.twitter.chill.WrappedArraySerializer.read(WrappedArraySerializer.scala:34)
>
> com.twitter.chill.WrappedArraySerializer.read(WrappedArraySerializer.scala:21)
> com.esotericsoftware.kryo.Kryo.readClassAndObject(Kryo.java:729)
>
> org.apache.spark.serializer.KryoDeserializationStream.readObject(KryoSerializer.scala:118)
>
> org.apache.spark.rdd.ParallelCollectionPartition$$anonfun$readObject$1.apply(ParallelCollectionRDD.scala:80)
>
> org.apache.spark.rdd.ParallelCollectionPartition$$anonfun$readObject$1.apply(ParallelCollectionRDD.scala:80)
>
> org.apache.spark.util.Utils$.deserializeViaNestedStream(Utils.scala:120)
>
> org.apache.spark.rdd.ParallelCollectionPartition.readObject(ParallelCollectionRDD.scala:80)
> sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
>
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
>
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> java.lang.reflect.Method.invoke(Method.java:606)
>
> java.io.ObjectStreamClass.invokeReadObject(ObjectStreamClass.java:1017)
> java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1893)
>
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
> java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
> java.io.ObjectInputStream.skipCustomData(ObjectInputStream.java:1956)
>
> java.io.ObjectInputStream.readExternalData(ObjectInputStream.java:1850)
>
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1796)
> java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
> java.io.ObjectInputStream.readObject(ObjectInputStream.java:370)
>
> org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:63)
>
> org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:85)
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:165)
>
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
>
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> java.lang.Thread.run(Thread.java:745)
> Driver stacktrace:
> at
> org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1049)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1033)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1031)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1031)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:635)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:635)
> at scala.Option.foreach(Option.scala:236)
> at
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:635)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1234)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
> at akka.actor.ActorCell.invoke(ActorCell.scala:456)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
> at akka.dispatch.Mailbox.run(Mailbox.scala:219)
> at
> akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
> at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> at
> scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> at
> scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> at
> scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
