[
https://issues.apache.org/jira/browse/SPARK-5480?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14551366#comment-14551366
]
Niklas Wilcke edited comment on SPARK-5480 at 5/19/15 11:36 PM:
----------------------------------------------------------------
I'm running Spark 1.3.1 and I'm facing the same exception on small graphs. In
my case the exception always occures.
There are 160049 edges in the graph. I don't know the number of vertices at the
moment.
I can't provide a few lines of code to reproduce the exception because my
application is complex and the exception only occures in some rare cases.
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to
stage failure: Task 25 in stage 40.0 failed 4 times, most recent failure: Lost
task 25.3 in stage 40.0 (TID 3250, blub.bla):
java.lang.ArrayIndexOutOfBoundsException: -1
at
org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap$mcJI$sp.apply$mcJI$sp(GraphXPrimitiveKeyOpenHashMap.scala:64)
at
org.apache.spark.graphx.impl.EdgePartition.updateVertices(EdgePartition.scala:91)
at
org.apache.spark.graphx.impl.ReplicatedVertexView$$anonfun$2$$anonfun$apply$1.apply(ReplicatedVertexView.scala:75)
at
org.apache.spark.graphx.impl.ReplicatedVertexView$$anonfun$2$$anonfun$apply$1.apply(ReplicatedVertexView.scala:73)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at
org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:210)
at
org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:63)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:64)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:203)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
was (Author: numbnut):
I'm running Spark 1.3.1 and I'm facing the same exception on small graphs. In
my case the exception always occures.
There are 160049 edges in the graph. I don't know the number of vertices at the
moment.
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to
stage failure: Task 25 in stage 40.0 failed 4 times, most recent failure: Lost
task 25.3 in stage 40.0 (TID 3250, blub.bla):
java.lang.ArrayIndexOutOfBoundsException: -1
at
org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap$mcJI$sp.apply$mcJI$sp(GraphXPrimitiveKeyOpenHashMap.scala:64)
at
org.apache.spark.graphx.impl.EdgePartition.updateVertices(EdgePartition.scala:91)
at
org.apache.spark.graphx.impl.ReplicatedVertexView$$anonfun$2$$anonfun$apply$1.apply(ReplicatedVertexView.scala:75)
at
org.apache.spark.graphx.impl.ReplicatedVertexView$$anonfun$2$$anonfun$apply$1.apply(ReplicatedVertexView.scala:73)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at
org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:210)
at
org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:63)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:64)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:203)
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)
> GraphX pageRank: java.lang.ArrayIndexOutOfBoundsException:
> -----------------------------------------------------------
>
> Key: SPARK-5480
> URL: https://issues.apache.org/jira/browse/SPARK-5480
> Project: Spark
> Issue Type: Bug
> Components: GraphX
> Affects Versions: 1.2.0
> Environment: Yarn client
> Reporter: Stephane Maarek
>
> Running the following code:
> val subgraph = graph.subgraph (
> vpred = (id,article) => //working predicate)
> ).cache()
> println( s"Subgraph contains ${subgraph.vertices.count} nodes and
> ${subgraph.edges.count} edges")
> val prGraph = subgraph.staticPageRank(5).cache
> val titleAndPrGraph = subgraph.outerJoinVertices(prGraph.vertices) {
> (v, title, rank) => (rank.getOrElse(0.0), title)
> }
> titleAndPrGraph.vertices.top(13) {
> Ordering.by((entry: (VertexId, (Double, _))) => entry._2._1)
> }.foreach(t => println(t._2._2._1 + ": " + t._2._1 + ", id:" + t._1))
> Returns a graph with 5000 nodes and 4000 edges.
> Then it crashes during the PageRank with the following:
> 15/01/29 05:51:07 INFO scheduler.TaskSetManager: Starting task 125.0 in stage
> 39.0 (TID 1808, *HIDDEN, PROCESS_LOCAL, 2059 bytes)
> 15/01/29 05:51:07 WARN scheduler.TaskSetManager: Lost task 107.0 in stage
> 39.0 (TID 1794, *HIDDEN): java.lang.ArrayIndexOutOfBoundsException: -1
> at
> org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap$mcJI$sp.apply$mcJI$sp(GraphXPrimitiveKeyOpenHashMap.scala:64)
> at
> org.apache.spark.graphx.impl.EdgePartition.updateVertices(EdgePartition.scala:91)
> at
> org.apache.spark.graphx.impl.ReplicatedVertexView$$anonfun$2$$anonfun$apply$1.apply(ReplicatedVertexView.scala:75)
> at
> org.apache.spark.graphx.impl.ReplicatedVertexView$$anonfun$2$$anonfun$apply$1.apply(ReplicatedVertexView.scala:73)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at
> org.apache.spark.graphx.impl.EdgeRDDImpl$$anonfun$mapEdgePartitions$1.apply(EdgeRDDImpl.scala:110)
> at
> org.apache.spark.graphx.impl.EdgeRDDImpl$$anonfun$mapEdgePartitions$1.apply(EdgeRDDImpl.scala:108)
> at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601)
> at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
> at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:61)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:228)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
> at
> org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:88)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
> at
> org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:88)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
> at
> org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:88)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
> at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:61)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:228)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
> 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)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
