[SPARK-30327] Caused by: java.lang.ArrayIndexOutOfBoundsException: -1

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Incomplete
• Affects Version/s: 2.3.2
• Component/s: GraphX
• Labels: bulk-closed
• Assignee: Unassigned
• Reporter: lujun
• Created: 23/Dec/19 05:36
• Updated: 12/Dec/22 18:11
• Resolved: 25/May/21 01:42

Description

val edgeRdd: RDD[Edge[Int]] = rdd.map(rec =>

{ Edge(rec._2._1.getOldcid, rec._2._1.getNewcid, 0) }

)
val vertexRdd: RDD[(Long, String)] = rdd.map(rec =>

{ (rec._2._1.getOldcid, rec._2._1.getCustomer_id)}

)
val returnRdd = Graph(vertexRdd, edgeRdd).connectedComponents().vertices.
join(vertexRdd)
.map { case (cid, (groupid, cus)) => (cus, groupid)}

 

For the same batch of data, sometimes it succeeds, and the following errors are reported！

 

Exception in thread "main" java.lang.reflect.InvocationTargetException
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.worker.DriverWrapper$.main(DriverWrapper.scala:65)
at org.apache.spark.deploy.worker.DriverWrapper.main(DriverWrapper.scala)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 24374.0 failed 4 times, most recent failure: Lost task 2.3 in stage 24374.0 (TID 133352, lx-es-04, executor 0): java.lang.ArrayIndexOutOfBoundsException: -1
at org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap$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:73)
at org.apache.spark.graphx.impl.ReplicatedVertexView$$anonfun$2$$anonfun$apply$1.apply(ReplicatedVertexView.scala:71)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
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)

Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1651)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1639)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1638)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1638)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1872)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1821)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1810)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:642)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2034)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2131)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:1035)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.reduce(RDD.scala:1017)
at org.apache.spark.graphx.impl.VertexRDDImpl.count(VertexRDDImpl.scala:90)
at org.apache.spark.graphx.Pregel$.apply(Pregel.scala:140)
at org.apache.spark.graphx.lib.ConnectedComponents$.run(ConnectedComponents.scala:54)
at org.apache.spark.graphx.lib.ConnectedComponents$.run(ConnectedComponents.scala:73)
at org.apache.spark.graphx.GraphOps.connectedComponents(GraphOps.scala:434)
at com.hailian.spark.streaming.mainClass.StreamingCustomerAndAccountCombinMain$.sourceIDGroupByReleation(StreamingCustomerAndAccountCombinMain.scala:409)
at com.hailian.spark.streaming.mainClass.StreamingCustomerAndAccountCombinMain$$anonfun$main$2.apply(StreamingCustomerAndAccountCombinMain.scala:310)
at com.hailian.spark.streaming.mainClass.StreamingCustomerAndAccountCombinMain$$anonfun$main$2.apply(StreamingCustomerAndAccountCombinMain.scala:207)
at org.apache.spark.streaming.dstream.DStream$$anonfun$foreachRDD$1$$anonfun$apply$mcV$sp$3.apply(DStream.scala:628)
at org.apache.spark.streaming.dstream.DStream$$anonfun$foreachRDD$1$$anonfun$apply$mcV$sp$3.apply(DStream.scala:628)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(ForEachDStream.scala:51)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply(ForEachDStream.scala:51)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply(ForEachDStream.scala:51)
at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:416)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply$mcV$sp(ForEachDStream.scala:50)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply(ForEachDStream.scala:50)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply(ForEachDStream.scala:50)
at scala.util.Try$.apply(Try.scala:192)
at org.apache.spark.streaming.scheduler.Job.run(Job.scala:39)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply$mcV$sp(JobScheduler.scala:257)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:257)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:257)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:256)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.ArrayIndexOutOfBoundsException: -1
at org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap$mcJI$sp.apply$mcJI$sp(GraphXPrimitiveKeyOpenHashMap.scala:64)
at org.apache.spark.graphx.impl.EdgePartition.updateVertices(EdgePartition.scala:91)
at org.apache.spark.graphx.impl.ReplicatedVertexView$$anonfun$2$$anonfun$apply$1.apply(ReplicatedVertexView.scala:73)
at org.apache.spark.graphx.impl.ReplicatedVertexView$$anonfun$2$$anonfun$apply$1.apply(ReplicatedVertexView.scala:71)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)