Hello, I am porting a data process running in Spark from Scala to Java (8) using Lambdas to see how practical Java 8 is.
The first few steps are working (parsing data, creating JavaRDDs) but then it fails while doing a cogroup between two JavaPairRDD<String, String>. I am getting a bunch of java.io.StreamCorruptedException: invalid type code: 00 and ultimately the stack trace below. It is running on Mac OS X local mode with Java SE 8. java version "1.8.0_11" Java(TM) SE Runtime Environment (build 1.8.0_11-b12) Java HotSpot(TM) 64-Bit Server VM (build 25.11-b03, mixed mode) Any ideas on possible root cause ?? Thanks, Alexis — Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 3.0:0 failed 1 times, most recent failure: Exception failure in TID 0 on host localhost: java.io.StreamCorruptedException: invalid type code: 00 java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1379) java.io.ObjectInputStream.skipCustomData(ObjectInputStream.java:1959) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1921) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1993) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1918) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1993) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1918) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1993) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1918) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1993) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1918) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.readArray(ObjectInputStream.java:1707) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1345) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1993) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1918) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1993) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1918) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1993) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1918) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1993) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1918) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.readObject(ObjectInputStream.java:371) scala.collection.immutable.$colon$colon.readObject(List.scala:362) sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.lang.reflect.Method.invoke(Method.java:483) java.io.ObjectStreamClass.invokeReadObject(ObjectStreamClass.java:1017) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1896) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1993) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1918) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1993) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1918) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.readObject(ObjectInputStream.java:371) scala.collection.immutable.$colon$colon.readObject(List.scala:362) sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.lang.reflect.Method.invoke(Method.java:483) java.io.ObjectStreamClass.invokeReadObject(ObjectStreamClass.java:1017) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1896) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1993) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1918) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.readObject(ObjectInputStream.java:371) org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:63) org.apache.spark.scheduler.ShuffleMapTask$.deserializeInfo(ShuffleMapTask.scala:63) org.apache.spark.scheduler.ShuffleMapTask.readExternal(ShuffleMapTask.scala:135) java.io.ObjectInputStream.readExternalData(ObjectInputStream.java:1840) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1799) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351) java.io.ObjectInputStream.readObject(ObjectInputStream.java:371) org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:63) org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:85) org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:165) java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1044) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1028) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1026) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1026) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:634) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:634) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:634) at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1229) at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498) at akka.actor.ActorCell.invoke(ActorCell.scala:456) at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237) at akka.dispatch.Mailbox.run(Mailbox.scala:219) at akka.dispatch.ForkJoinExecutorConfigurator$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)