14/04/23 17:17:40 INFO DAGScheduler: Failed to run collect at
SparkListDocByTopic.scala:407
Exception in thread "main" java.lang.reflect.InvocationTargetException
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.worker.DriverWrapper$.main(DriverWrapper.scala:40)
at
org.apache.spark.deploy.worker.DriverWrapper.main(DriverWrapper.scala)
Caused by: org.apache.spark.SparkException: Job aborted due to stage
failure: Task not serializable: java.io.NotSerializableExceptio
n: SparkListDocByTopic$EnvParameter
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler
.scala:1013)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$abortStage$1.apply(DAGScheduler
.scala:1002)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$abortStage$1.apply(DAGScheduler
.scala:1000)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at
scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$abortStage(DAGScheduler.scala:1000)
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$submitMissingTasks(DAGScheduler.scala:77
2)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$16$$anonfun$apply$1.apply$mcVI$sp(DAGScheduler.scal
a:892)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$16$$anonfun$apply$1.apply(DAGScheduler.scala:889)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$16$$anonfun$apply$1.apply(DAGScheduler.scala:889)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$16.apply(DAGScheduler.scala:889)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$16.apply(DAGScheduler.scala:888)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at
scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskCompletion(DAGScheduler.scala:888)
at
org.apache.spark.scheduler.DAGScheduler.processEvent(DAGScheduler.scala:592)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$start$1$$anon$2$$anonfun$receive$1.applyOrElse(DAGScheduler.scala:143)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
at
scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at
scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
--
View this message in context:
http://apache-spark-user-list.1001560.n3.nabble.com/about-rdd-filter-tp4657p4717.html
Sent from the Apache Spark User List mailing list archive at Nabble.com.
