Hi I'm using Spark 0.9.0.
When calling saveAsTextFile on a custom hadoop inputformat (loaded with newAPIHadoopRDD), I get the following error below. If I call count, I get the correct count of number of records, so the inputformat is being read correctly... the issue only appears when trying to use saveAsTextFile. If I call first() I get the correct output, also. So it doesn't appear to be anything with the data or inputformat. Any idea what the actual problem is, since this stack trace is not obvious (though it seems to be in ResultTask which ultimately causes this). Is this a known issue at all? ====== 14/04/08 16:00:46 ERROR OneForOneStrategy: java.lang.NullPointerException at com.typesafe.config.impl.SerializedConfigValue.writeOrigin(SerializedConfigValue.java:202) at com.typesafe.config.impl.ConfigImplUtil.writeOrigin(ConfigImplUtil.java:228) at com.typesafe.config.ConfigException.writeObject(ConfigException.java:58) 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:601) at java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:975) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1480) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1416) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1528) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1493) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1416) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1528) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1493) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1416) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1528) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1493) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1416) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1528) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1493) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1416) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1528) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1493) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1416) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1528) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1493) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1416) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174) at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:346) at scala.collection.immutable.$colon$colon.writeObject(List.scala:379) 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:601) at java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:975) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1480) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1416) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1528) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1493) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1416) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174) at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:346) at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:28) at org.apache.spark.scheduler.ResultTask$.serializeInfo(ResultTask.scala:48) at org.apache.spark.scheduler.ResultTask.writeExternal(ResultTask.scala:123) at java.io.ObjectOutputStream.writeExternalData(ObjectOutputStream.java:1443) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1414) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174) at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:346) at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:28) at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:48) at org.apache.spark.scheduler.DAGScheduler.org $apache$spark$scheduler$DAGScheduler$$submitMissingTasks(DAGScheduler.scala:778) at org.apache.spark.scheduler.DAGScheduler.org $apache$spark$scheduler$DAGScheduler$$submitStage(DAGScheduler.scala:724) at org.apache.spark.scheduler.DAGScheduler.processEvent(DAGScheduler.scala:554) at org.apache.spark.scheduler.DAGScheduler$$anonfun$start$1$$anon$2$$anonfun$receive$1.applyOrElse(DAGScheduler.scala:190) at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498) at akka.actor.ActorCell.invoke(ActorCell.scala:456) at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237) at akka.dispatch.Mailbox.run(Mailbox.scala:219) at akka.dispatch.ForkJoinExecutorConfigurator$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)