Hi, While running spark application, I get the following Exception leading to several failed stages.
Exception in thread "Thread-46" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 11.0 failed 4 times, most recent failure: Lost task 0.3 in stage 11.0 (TID 262, s4): java.io.IOException: Connection from s5/10.0.1.93:53496 closed at org.apache.spark.network.client.TransportResponseHandler.channelUnregistered(TransportResponseHandler.java:98) at org.apache.spark.network.server.TransportChannelHandler.channelUnregistered(TransportChannelHandler.java:81) at io.netty.channel.AbstractChannelHandlerContext.invokeChannelUnregistered(AbstractChannelHandlerContext.java:183) at io.netty.channel.AbstractChannelHandlerContext.fireChannelUnregistered(AbstractChannelHandlerContext.java:169) at io.netty.channel.ChannelInboundHandlerAdapter.channelUnregistered(ChannelInboundHandlerAdapter.java:53) at io.netty.channel.AbstractChannelHandlerContext.invokeChannelUnregistered(AbstractChannelHandlerContext.java:183) at io.netty.channel.AbstractChannelHandlerContext.fireChannelUnregistered(AbstractChannelHandlerContext.java:169) at io.netty.channel.ChannelInboundHandlerAdapter.channelUnregistered(ChannelInboundHandlerAdapter.java:53) at io.netty.channel.AbstractChannelHandlerContext.invokeChannelUnregistered(AbstractChannelHandlerContext.java:183) at io.netty.channel.AbstractChannelHandlerContext.fireChannelUnregistered(AbstractChannelHandlerContext.java:169) at io.netty.channel.DefaultChannelPipeline.fireChannelUnregistered(DefaultChannelPipeline.java:738) at io.netty.channel.AbstractChannel$AbstractUnsafe$6.run(AbstractChannel.java:606) at io.netty.util.concurrent.SingleThreadEventExecutor.runAllTasks(SingleThreadEventExecutor.java:380) at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:357) at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:116) 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$2.applyOrElse(DAGScheduler.scala:1420) at akka.actor.Actor$class.aroundReceive(Actor.scala:465) at org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375) 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) Can someone please tell me how to resolve this issue? Thanks -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/java-io-IOException-connection-closed-tp21348.html Sent from the Apache Spark User List mailing list archive at Nabble.com.
