Hi, I'm running a spark standalone cluster to calculate single source
shortest path.
Here is the code, VertexRDD[(String, Long)], String for the path and Long
for the distance
codes before these lines related to reading graph data from file and
building the graph.
71 val sssp = initialGraph.pregel(("", Long.MaxValue)) (
72 (id, mine, rece) => {
73 if(mine._2 > rece._2)
74 rece
75 else
76 mine},
77 triplet => {
78 if(triplet.srcAttr._2 + triplet.attr.toLong <
triplet.dstAttr._2) {
79 Iterator((triplet.dstId, (triplet.srcAttr._1 + "
" + triplet.srcId.toString, triplet.srcAttr._2 + triplet.attr)))
80 } else {
81 Iterator.empty
82 }
83 },
84 (a, b) => {
85 if(a._2 < b._2)
86 a
87 else
88 b}
89 )
it will throw an exception and terminate:
[error] (run-main-0) org.apache.spark.SparkException: Job aborted due to
stage failure: Task 6.0:4 failed 4 times, most recent failure: Exception
failure in TID 598 on host worker6.local: java.lang.NullPointerException
[error] scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
[error] scala.collection.Iterator$class.foreach(Iterator.scala:727)
[error]
scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
[error]
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
[error]
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
[error]
org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:107)
[error] org.apache.spark.rdd.RDD.iterator(RDD.scala:227)
[error]
org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:87)
[error]
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
[error] org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
[error]
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
[error]
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
[error] org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
[error]
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:158)
[error]
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
[error] org.apache.spark.scheduler.Task.run(Task.scala:51)
[error]
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:183)
[error]
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
[error]
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
[error] java.lang.Thread.run(Thread.java:744)
[error] Driver stacktrace:
14/07/29 15:46:12 WARN scheduler.TaskSetManager: Task 574 was killed.
org.apache.spark.SparkException: Job aborted due to stage failure: Task
6.0:4 failed 4 times, most recent failure: Exception failure in TID 598 on
host worker6.local: java.lang.NullPointerException
scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
scala.collection.Iterator$class.foreach(Iterator.scala:727)
scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:107)
org.apache.spark.rdd.RDD.iterator(RDD.scala:227)
org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:87)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:158)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
org.apache.spark.scheduler.Task.run(Task.scala:51)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:183)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:744)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1044)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1028)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1026)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at
scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1026)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:634)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:634)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:634)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1229)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at
akka.dispatch.ForkJoinExecutorConfigurator$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)
[trace] Stack trace suppressed: run last compile:run for the full output.
14/07/29 15:46:12 WARN scheduler.TaskSetManager: Task 578 was killed.
14/07/29 15:46:13 INFO network.ConnectionManager: Selector thread was
interrupted!
14/07/29 15:46:13 ERROR spark.ContextCleaner: Error in cleaning thread
java.lang.InterruptedException
at java.lang.Object.wait(Native Method)
at java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:135)
at
org.apache.spark.ContextCleaner$$anonfun$org$apache$spark$ContextCleaner$$keepCleaning$1.apply$mcV$sp(ContextCleaner.scala:117)
at
org.apache.spark.ContextCleaner$$anonfun$org$apache$spark$ContextCleaner$$keepCleaning$1.apply(ContextCleaner.scala:115)
at
org.apache.spark.ContextCleaner$$anonfun$org$apache$spark$ContextCleaner$$keepCleaning$1.apply(ContextCleaner.scala:115)
at
org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1160)
at
org.apache.spark.ContextCleaner.org$apache$spark$ContextCleaner$$keepCleaning(ContextCleaner.scala:114)
at
org.apache.spark.ContextCleaner$$anon$3.run(ContextCleaner.scala:65)
14/07/29 15:46:13 ERROR util.Utils: Uncaught exception in thread
SparkListenerBus
java.lang.InterruptedException
at
java.util.concurrent.locks.AbstractQueuedSynchronizer.doAcquireSharedInterruptibly(AbstractQueuedSynchronizer.java:996)
at
java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1303)
at java.util.concurrent.Semaphore.acquire(Semaphore.java:317)
at
org.apache.spark.scheduler.LiveListenerBus$$anon$1$$anonfun$run$1.apply$mcV$sp(LiveListenerBus.scala:48)
at
org.apache.spark.scheduler.LiveListenerBus$$anon$1$$anonfun$run$1.apply(LiveListenerBus.scala:47)
at
org.apache.spark.scheduler.LiveListenerBus$$anon$1$$anonfun$run$1.apply(LiveListenerBus.scala:47)
at
org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1160)
at
org.apache.spark.scheduler.LiveListenerBus$$anon$1.run(LiveListenerBus.scala:46)
Before these errors, there are some INFO about lost TID.
I've worked on this program for long without a success. What caused this
problem, bugs in my codes or some other issues? Thanks.
--
View this message in context:
http://apache-spark-user-list.1001560.n3.nabble.com/the-pregel-operator-of-graphx-throws-NullPointerException-tp10865.html
Sent from the Apache Spark User List mailing list archive at Nabble.com.
