Hi all
This is a bug of spark?
val Array(host, IntParam(port)) = args
val batchInterval = Milliseconds(120000)
// Create the context and set the batch size
val sparkConf = new SparkConf().setAppName("FlumeEventCount")
val ssc = new StreamingContext(sparkConf, batchInterval)
// Create a flume stream
val stream = FlumeUtils.createStream(ssc, host, port,
StorageLevel.MEMORY_ONLY_SER_2)
stream.map(event=>"Event: header:"+ event.event.get(0).toString+"
body:"+ new String(event.event.getBody.array) ).print
java.lang.ArrayIndexOutOfBoundsException: 1
FlumeEventSaveHdfs$$anonfun$1$$anonfun$3.apply(FlumeEventCount.scala:62)
FlumeEventSaveHdfs$$anonfun$1$$anonfun$3.apply(FlumeEventCount.scala:62)
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
scala.collection.immutable.List.foreach(List.scala:318)
scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
scala.collection.AbstractTraversable.map(Traversable.scala:105)
FlumeEventSaveHdfs$$anonfun$1.apply(FlumeEventCount.scala:62)
FlumeEventSaveHdfs$$anonfun$1.apply(FlumeEventCount.scala:58)
scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:984)
org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:974)
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
ERROR scheduler.JobScheduler: Error running job streaming job
1411388760000 ms.0
org.apache.spark.SparkException: Job aborted due to stage failure:
Task 0 in stage 3.0 failed 4 times, most recent failure: Lost task 0.3
in stage 3.0 (TID 107, idc02-sp-sr-05.dns.abc.com):
java.lang.ArrayIndexOutOfBoundsException:
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1185)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1174)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1173)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1173)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:688)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1391)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at
akka.dispatch.ForkJoinExecutorConfigurator$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)
--
cente...@gmail.com|齐忠
---------------------------------------------------------------------
To unsubscribe, e-mail: user-unsubscr...@spark.apache.org
For additional commands, e-mail: user-h...@spark.apache.org
