RDDPersistProblem

gistfile1.txt

Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 7 in stage 2.0 failed 4 times, most recent failure: Lost task 7.3 in stage 2.0 (TID 253, ec2-??-???-??-???.compute-1.amazonaws.com): java.lang.IllegalArgumentException: Size exceeds Integer.MAX_VALUE
        at sun.nio.ch.FileChannelImpl.map(FileChannelImpl.java:829)
        at org.apache.spark.storage.DiskStore.getBytes(DiskStore.scala:123)
        at org.apache.spark.storage.DiskStore.getBytes(DiskStore.scala:132)
        at org.apache.spark.storage.BlockManager.doGetLocal(BlockManager.scala:517)
        at org.apache.spark.storage.BlockManager.getLocal(BlockManager.scala:432)
        at org.apache.spark.storage.BlockManager.get(BlockManager.scala:618)
        at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:44)
        at org.apache.spark.rdd.RDD.iterator(RDD.scala:228)
        at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
        at org.apache.spark.scheduler.Task.run(Task.scala:56)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
        at java.util.concurrent.ThreadPoolExecutor$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$$failJobAndIndependentStages(DAGScheduler.scala:1214)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202)
        at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
        at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
        at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
        at scala.Option.foreach(Option.scala:236)
        at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420)
        at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
        at akka.actor.ActorCell.invoke(ActorCell.scala:456)
        at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
        at akka.dispatch.Mailbox.run(Mailbox.scala:219)
        at akka.dispatch.ForkJoinExecutorConfigurator$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)

I have the same problem