Hi All,
I am just trying to save the kafka dstream to hadoop as followed
val dStream = KafkaUtils.createStream(ssc, zkQuorum, group, topicpMap)
dStream.saveAsHadoopFiles(hdfsDataUrl, "data")
It throws the following exception. What am I doing wrong?
14/08/15 14:30:09 ERROR OneForOneStrategy: org.apache.hadoop.mapred.JobConf
java.io.NotSerializableException: org.apache.hadoop.mapred.JobConf
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1183)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at
java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1377)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1173)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at
java.io.ObjectOutputStream.defaultWriteObject(ObjectOutputStream.java:440)
at
org.apache.spark.streaming.DStreamGraph.writeObject(DStreamGraph.scala:168)
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
java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:988)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1495)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at
java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:347)
at
org.apache.spark.streaming.CheckpointWriter.write(Checkpoint.scala:185)
at
org.apache.spark.streaming.scheduler.JobGenerator.doCheckpoint(JobGenerator.scala:259)
at
org.apache.spark.streaming.scheduler.JobGenerator.org$apache$spark$streaming$scheduler$JobGenerator$$processEvent(JobGenerator.scala:167)
at
org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$start$1$$anon$1$$anonfun$receive$1.applyOrElse(JobGenerator.scala:76)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at
akka.dispatch.ForkJoinExecutorConfigurator$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)
^C14/08/15 14:30:10 ERROR OneForOneStrategy:
org.apache.hadoop.mapred.JobConf
java.io.NotSerializableException: org.apache.hadoop.mapred.JobConf
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1183)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at
java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1377)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1173)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at
java.io.ObjectOutputStream.defaultWriteObject(ObjectOutputStream.java:440)
at
org.apache.spark.streaming.DStreamGraph.writeObject(DStreamGraph.scala:168)
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
java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:988)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1495)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at
java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:347)
at
org.apache.spark.streaming.CheckpointWriter.write(Checkpoint.scala:185)
at
org.apache.spark.streaming.scheduler.JobGenerator.doCheckpoint(JobGenerator.scala:259)
at
org.apache.spark.streaming.scheduler.JobGenerator.org$apache$spark$streaming$scheduler$JobGenerator$$processEvent(JobGenerator.scala:167)
at
org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$start$1$$anon$1$$anonfun$receive$1.applyOrElse(JobGenerator.scala:76)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at
akka.dispatch.ForkJoinExecutorConfigurator$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)
--
View this message in context:
http://apache-spark-user-list.1001560.n3.nabble.com/spark-streaming-saving-kafka-DStream-into-hadoop-throws-exception-tp12202.html
Sent from the Apache Spark User List mailing list archive at Nabble.com.
---------------------------------------------------------------------
To unsubscribe, e-mail: user-unsubscr...@spark.apache.org
For additional commands, e-mail: user-h...@spark.apache.org
