---------- Forwarded message ---------- From: rapelly kartheek <kartheek.m...@gmail.com> Date: Thu, Jan 1, 2015 at 12:05 PM Subject: Re: NullPointerException To: Josh Rosen <rosenvi...@gmail.com>, user@spark.apache.org
spark-1.0.0 On Thu, Jan 1, 2015 at 12:04 PM, Josh Rosen <rosenvi...@gmail.com> wrote: > Which version of Spark are you using? > > On Wed, Dec 31, 2014 at 10:24 PM, rapelly kartheek < > kartheek.m...@gmail.com> wrote: > >> Hi, >> I get this following Exception when I submit spark application that >> calculates the frequency of characters in a file. Especially, when I >> increase the size of data, I face this problem. >> >> Exception in thread "Thread-47" org.apache.spark.SparkException: Job >> aborted due to stage failure: Task 11.0:10 failed 4 times, most recent >> failure: Exception failure in TID 295 on host s1: >> java.lang.NullPointerException >> org.apache.spark.storage.BlockManager.org >> $apache$spark$storage$BlockManager$$replicate(BlockManager.scala:786) >> >> org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:752) >> org.apache.spark.storage.BlockManager.put(BlockManager.scala:574) >> org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:108) >> org.apache.spark.rdd.RDD.iterator(RDD.scala:227) >> org.apache.spark.rdd.FilteredRDD.compute(FilteredRDD.scala:34) >> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) >> org.apache.spark.rdd.RDD.iterator(RDD.scala:229) >> org.apache.spark.rdd.MappedRDD.compute(MappedRDD.scala:31) >> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) >> org.apache.spark.rdd.RDD.iterator(RDD.scala:229) >> >> org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) >> org.apache.spark.scheduler.Task.run(Task.scala:51) >> >> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187) >> >> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) >> >> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) >> java.lang.Thread.run(Thread.java:745) >> Driver stacktrace: >> at org.apache.spark.scheduler.DAGScheduler.org >> $apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1033) >> at >> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1017) >> at >> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1015) >> at >> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) >> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) >> at >> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1015) >> at >> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633) >> at >> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633) >> at scala.Option.foreach(Option.scala:236) >> at >> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:633) >> at >> org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1207) >> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498) >> at akka.actor.ActorCell.invoke(ActorCell.scala:456) >> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237) >> at akka.dispatch.Mailbox.run(Mailbox.scala:219) >> at >> akka.dispatch.ForkJoinExecutorConfigurator$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) >> >> >> Any help? >> >> Thank you! >> > >
