我使用Mllib在Spark上运行了一个python代码。它适用于小型数据集,但在大型数据集的两次迭代后,我收到以下错误:
ERROR TaskSchedulerImpl: Exception in statusUpdate
java.util.concurrent.RejectedExecutionException: Task org.apache.spark.scheduler.TaskResultGetter$$anon$2@15b59543 rejected from java.util.concurrent.ThreadPoolExecutor@22427929[Terminated, pool size = 0, active threads = 0, queued tasks = 0, completed tasks = 2701]
at java.util.concurrent.ThreadPoolExecutor$AbortPolicy.rejectedExecution(ThreadPoolExecutor.java:2050)
at java.util.concurrent.ThreadPoolExecutor.reject(ThreadPoolExecutor.java:821)
at java.util.concurrent.ThreadPoolExecutor.execute(ThreadPoolExecutor.java:1372)
at org.apache.spark.scheduler.TaskResultGetter.enqueueSuccessfulTask(TaskResultGetter.scala:49)
at org.apache.spark.scheduler.TaskSchedulerImpl$$anonfun$liftedTree2$1$1.apply(TaskSchedulerImpl.scala:327)
at org.apache.spark.scheduler.TaskSchedulerImpl$$anonfun$liftedTree2$1$1.apply(TaskSchedulerImpl.scala:324)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.TaskSchedulerImpl.liftedTree2$1(TaskSchedulerImpl.scala:324)
at org.apache.spark.scheduler.TaskSchedulerImpl.statusUpdate(TaskSchedulerImpl.scala:309)
at org.apache.spark.scheduler.local.LocalEndpoint$$anonfun$receive$1.applyOrElse(LocalBackend.scala:61)
at org.apache.spark.rpc.akka.AkkaRpcEnv.org$apache$spark$rpc$akka$AkkaRpcEnv$$processMessage(AkkaRpcEnv.scala:178)
at org.apache.spark.rpc.akka.AkkaRpcEnv$$anonfun$actorRef$lzycompute$1$1$$anon$1$$anonfun$receiveWithLogging$1$$anonfun$applyOrElse$4.apply$mcV$sp(AkkaRpcEnv.scala:127)
at org.apache.spark.rpc.akka.AkkaRpcEnv.org$apache$spark$rpc$akka$AkkaRpcEnv$$safelyCall(AkkaRpcEnv.scala:198)
at org.apache.spark.rpc.akka.AkkaRpcEnv$$anonfun$actorRef$lzycompute$1$1$$anon$1$$anonfun$receiveWithLogging$1.applyOrElse(AkkaRpcEnv.scala:126)
at scala.runtime.AbstractPartialFunction$mcVL$sp.apply$mcVL$sp(AbstractPartialFunction.scala:33)
at scala.runtime.AbstractPartialFunction$mcVL$sp.apply(AbstractPartialFunction.scala:33)
at scala.runtime.AbstractPartialFunction$mcVL$sp.apply(AbstractPartialFunction.scala:25)
at org.apache.spark.util.ActorLogReceive$$anon$1.apply(ActorLogReceive.scala:59)
at org.apache.spark.util.ActorLogReceive$$anon$1.apply(ActorLogReceive.scala:42)
at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:118)
at org.apache.spark.util.ActorLogReceive$$anon$1.applyOrElse(ActorLogReceive.scala:42)
at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
at org.apache.spark.rpc.akka.AkkaRpcEnv$$anonfun$actorRef$lzycompute$1$1$$anon$1.aroundReceive(AkkaRpcEnv.scala:93)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
at akka.actor.ActorCell.invoke(ActorCell.scala:487)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
at akka.dispatch.Mailbox.run(Mailbox.scala:220)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:393)
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)
你对此有任何想法吗?