Apache Spark GraphX:java.lang.ArrayIndexOutOfBoundsException:-1

时间:2017-10-13 15:17:32

标签: scala hadoop apache-spark spark-graphx

我们在调用connectedComponents函数时遇到了GraphX的错误,其中出现以下错误错误 java.lang.ArrayIndexOutOfBoundsException:-1

我发现了这个错误报告: https://issues.apache.org/jira/browse/SPARK-5480

有没有其他人遇到过这个问题,如果有的话,你是如何解决它或解决它的?这是在scala 2.10中的Spark 1.6.2上运行

来自Shell的堆栈跟踪:

17/10/13 17:05:58 ERROR TaskSetManager: Task 12 in stage 2036.0 failed 4 times; aborting job
org.apache.spark.SparkException: Job aborted due to stage failure: Task 12 in stage 2036.0 failed 4 times, most recent failure: Lost task 12.3 in stage 2036.0 (TID 106840, cl-bigdata5.hosting.dbg.internal): 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:120)
    at org.apache.spark.graphx.impl.EdgeRDDImpl$$anonfun$mapEdgePartitions$1.apply(EdgeRDDImpl.scala:118)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$22.apply(RDD.scala:717)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$22.apply(RDD.scala:717)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.graphx.EdgeRDD.compute(EdgeRDD.scala:51)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:275)
    at org.apache.spark.graphx.EdgeRDD.compute(EdgeRDD.scala:51)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227)
    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:745)

Driver stacktrace:
    at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1433)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1421)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1420)
    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1420)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:801)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:801)
    at scala.Option.foreach(Option.scala:236)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:801)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1642)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1601)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1590)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:622)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1856)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1869)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1882)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1953)
    at org.apache.spark.rdd.RDD.count(RDD.scala:1164)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:95)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:100)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:102)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:104)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:106)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:108)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:110)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:112)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:114)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:116)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:118)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:120)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:122)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:124)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:126)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:128)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:130)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:132)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:134)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:136)
    at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:138)
    at $iwC$$iwC$$iwC$$iwC.<init>(<console>:140)
    at $iwC$$iwC$$iwC.<init>(<console>:142)
    at $iwC$$iwC.<init>(<console>:144)
    at $iwC.<init>(<console>:146)
    at <init>(<console>:148)
    at .<init>(<console>:152)
    at .<clinit>(<console>)
    at .<init>(<console>:7)
    at .<clinit>(<console>)
    at $print(<console>)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:606)
    at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
    at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346)
    at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
    at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
    at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
    at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
    at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
    at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
    at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
    at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
    at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
    at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
    at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
    at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
    at org.apache.spark.repl.Main$.main(Main.scala:31)
    at org.apache.spark.repl.Main.main(Main.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:606)
    at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:738)
    at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
    at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
    at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
    at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.ArrayIndexOutOfBoundsException: -1
    at org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap$mcJI$sp.apply$mcJI$sp(GraphXPrimitiveKeyOpenHashMap.scala:64)
    at org.apache.spark.graphx.impl.EdgePartition.updateVertices(EdgePartition.scala:91)
    at org.apache.spark.graphx.impl.ReplicatedVertexView$$anonfun$2$$anonfun$apply$1.apply(ReplicatedVertexView.scala:75)
    at org.apache.spark.graphx.impl.ReplicatedVertexView$$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$$anonfun$mapEdgePartitions$1.apply(EdgeRDDImpl.scala:120)
    at org.apache.spark.graphx.impl.EdgeRDDImpl$$anonfun$mapEdgePartitions$1.apply(EdgeRDDImpl.scala:118)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$22.apply(RDD.scala:717)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$22.apply(RDD.scala:717)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.graphx.EdgeRDD.compute(EdgeRDD.scala:51)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:275)
    at org.apache.spark.graphx.EdgeRDD.compute(EdgeRDD.scala:51)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:277)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227)
    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:745)

0 个答案:

没有答案