You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Lu Lu (JIRA)" <ji...@apache.org> on 2014/08/04 09:12:11 UTC
[jira] [Updated] (SPARK-2823) GraphX jobs throw
IllegalArgumentException
[ https://issues.apache.org/jira/browse/SPARK-2823?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Lu Lu updated SPARK-2823:
-------------------------
Description:
If the users set “spark.default.parallelism” and the value is different with the EdgeRDD partition number, GraphX jobs will throw IllegalArgumentException:
14/07/26 21:06:51 WARN DAGScheduler: Creating new stage failed due to exception - job: 1
java.lang.IllegalArgumentException: Can't zip RDDs with unequal numbers of partitions
at org.apache.spark.rdd.ZippedPartitionsBaseRDD.getPartitions(ZippedPartitionsRDD.scala:60)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
at org.apache.spark.rdd.ZippedPartitionsBaseRDD.getPartitions(ZippedPartitionsRDD.scala:54)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$getShuffleMapStage(DAGScheduler.scala:1
97)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:272)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:269)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$visit$1(DAGScheduler.scala:269)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:274)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:269)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$visit$1(DAGScheduler.scala:269)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:274)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:269)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$visit$1(DAGScheduler.scala:269)
at org.apache.spark.scheduler.DAGScheduler.getParentStages(DAGScheduler.scala:279)
at org.apache.spark.scheduler.DAGScheduler.newStage(DAGScheduler.scala:219)
at org.apache.spark.scheduler.DAGScheduler.handleJobSubmitted(DAGScheduler.scala:672)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1184)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
was:
If the users set “spark.default.parallelism” and the value is different with the EdgeRDD partition number, GraphX jobs will throw IllegalArgumentException:
14/07/26 21:06:51 WARN DAGScheduler: Creating new stage failed due to exception - job: 1
.lang.IllegalArgumentException: Can't zip RDDs with unequal numbers of partitions
at org.apache.spark.rdd.ZippedPartitionsBaseRDD.getPartitions(ZippedPartitionsRDD.scala:60)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
at org.apache.spark.rdd.ZippedPartitionsBaseRDD.getPartitions(ZippedPartitionsRDD.scala:54)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$getShuffleMapStage(DAGScheduler.scala:1
97)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:272)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:269)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$visit$1(DAGScheduler.scala:269)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:274)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:269)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$visit$1(DAGScheduler.scala:269)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:274)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
cala:269)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$visit$1(DAGScheduler.scala:269)
at org.apache.spark.scheduler.DAGScheduler.getParentStages(DAGScheduler.scala:279)
at org.apache.spark.scheduler.DAGScheduler.newStage(DAGScheduler.scala:219)
at org.apache.spark.scheduler.DAGScheduler.handleJobSubmitted(DAGScheduler.scala:672)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1184)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at akka.dispatch.ForkJoinExecutorConfigurator$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)
> GraphX jobs throw IllegalArgumentException
> ------------------------------------------
>
> Key: SPARK-2823
> URL: https://issues.apache.org/jira/browse/SPARK-2823
> Project: Spark
> Issue Type: Bug
> Components: GraphX
> Reporter: Lu Lu
>
> If the users set “spark.default.parallelism” and the value is different with the EdgeRDD partition number, GraphX jobs will throw IllegalArgumentException:
> 14/07/26 21:06:51 WARN DAGScheduler: Creating new stage failed due to exception - job: 1
> java.lang.IllegalArgumentException: Can't zip RDDs with unequal numbers of partitions
> at org.apache.spark.rdd.ZippedPartitionsBaseRDD.getPartitions(ZippedPartitionsRDD.scala:60)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
> at scala.Option.getOrElse(Option.scala:120)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
> at org.apache.spark.rdd.ZippedPartitionsBaseRDD.getPartitions(ZippedPartitionsRDD.scala:54)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
> at scala.Option.getOrElse(Option.scala:120)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
> at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
> at scala.Option.getOrElse(Option.scala:120)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$getShuffleMapStage(DAGScheduler.scala:1
> 97)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
> cala:272)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
> cala:269)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$visit$1(DAGScheduler.scala:269)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
> cala:274)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
> cala:269)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$visit$1(DAGScheduler.scala:269)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
> cala:274)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$visit$1$1.apply(DAGScheduler.s
> cala:269)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$visit$1(DAGScheduler.scala:269)
> at org.apache.spark.scheduler.DAGScheduler.getParentStages(DAGScheduler.scala:279)
> at org.apache.spark.scheduler.DAGScheduler.newStage(DAGScheduler.scala:219)
> at org.apache.spark.scheduler.DAGScheduler.handleJobSubmitted(DAGScheduler.scala:672)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1184)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
> at akka.actor.ActorCell.invoke(ActorCell.scala:456)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
> at akka.dispatch.Mailbox.run(Mailbox.scala:219)
> at akka.dispatch.ForkJoinExecutorConfigurator$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
(v6.2#6252)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org