It's not allowed to use RDD in map function. RDD can only operated at driver of spark program. At your case, group RDD can't be found at every executor.
I guess you want to implement subquery like operation, try to use RDD.intersection() or join() 2014-08-29 12:43 GMT+08:00 Gary Zhao <garyz...@gmail.com>: > Hello > > I'm new to Spark and playing around, but saw the following error. Could > anyone to help on it? > > Thanks > Gary > > > > scala> c > res15: org.apache.spark.rdd.RDD[String] = FlatMappedRDD[7] at flatMap at > <console>:23 > > scala> group > res16: org.apache.spark.rdd.RDD[(String, Iterable[String])] = > MappedValuesRDD[5] at groupByKey at <console>:19 > > val d = c.map(i=>group.filter(_._1 ==i )) > > d.first > > 14/08/29 04:39:33 INFO TaskSchedulerImpl: Cancelling stage 28 > 14/08/29 04:39:33 INFO DAGScheduler: Failed to run first at <console>:28 > org.apache.spark.SparkException: Job aborted due to stage failure: Task > 28.0:180 failed 4 times, most recent failure: Exception failure in TID 3605 > on host mcs-spark-slave1-staging.snc1: java.lang.NullPointerException > org.apache.spark.rdd.RDD.filter(RDD.scala:282) > $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:25) > $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:25) > scala.collection.Iterator$$anon$11.next(Iterator.scala:328) > scala.collection.Iterator$$anon$10.next(Iterator.scala:312) > scala.collection.Iterator$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$eq(ArrayBuffer.scala:103) > > scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) > scala.collection.TraversableOnce$class.to > (TraversableOnce.scala:273) > scala.collection.AbstractIterator.to(Iterator.scala:1157) > > scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) > scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) > > scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) > scala.collection.AbstractIterator.toArray(Iterator.scala:1157) > org.apache.spark.rdd.RDD$$anonfun$28.apply(RDD.scala:1003) > org.apache.spark.rdd.RDD$$anonfun$28.apply(RDD.scala:1003) > > org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1083) > > org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1083) > org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) > org.apache.spark.scheduler.Task.run(Task.scala:51) > > org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala: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$$failJobAndIndependentStages(DAGScheduler.scala:1049) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1033) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1031) > at > scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) > at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) > at > org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1031) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:635) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:635) > at scala.Option.foreach(Option.scala:236) > at > org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:635) > at > org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1234) > at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498) > at akka.actor.ActorCell.invoke(ActorCell.scala:456) > at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237) > at akka.dispatch.Mailbox.run(Mailbox.scala:219) > at > akka.dispatch.ForkJoinExecutorConfigurator$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) >
