[
https://issues.apache.org/jira/browse/SPARK-5826?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14321862#comment-14321862
]
Littlestar commented on SPARK-5826:
-----------------------------------
I put some txt files into /testspark/watchdir, It throws NullPointerException
15/02/15 16:18:20 WARN dstream.FileInputDStream: Error finding new files
java.lang.NullPointerException
at
org.apache.spark.streaming.api.java.JavaStreamingContext$$anonfun$fn$3$1.apply(JavaStreamingContext.scala:329)
at
org.apache.spark.streaming.api.java.JavaStreamingContext$$anonfun$fn$3$1.apply(JavaStreamingContext.scala:329)
at
org.apache.spark.streaming.dstream.FileInputDStream.org$apache$spark$streaming$dstream$FileInputDStream$$isNewFile(FileInputDStream.scala:215)
at
org.apache.spark.streaming.dstream.FileInputDStream$$anon$3.accept(FileInputDStream.scala:172)
at org.apache.hadoop.fs.FileSystem.listStatus(FileSystem.java:1489)
at org.apache.hadoop.fs.FileSystem.listStatus(FileSystem.java:1523)
at
org.apache.spark.streaming.dstream.FileInputDStream.findNewFiles(FileInputDStream.scala:174)
at
org.apache.spark.streaming.dstream.FileInputDStream.compute(FileInputDStream.scala:132)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:301)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:301)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:300)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:288)
at scala.Option.orElse(Option.scala:257)
at
org.apache.spark.streaming.dstream.DStream.getOrCompute(DStream.scala:285)
at
org.apache.spark.streaming.dstream.MappedDStream.compute(MappedDStream.scala:35)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:301)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:301)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:300)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:288)
at scala.Option.orElse(Option.scala:257)
at
org.apache.spark.streaming.dstream.DStream.getOrCompute(DStream.scala:285)
at
org.apache.spark.streaming.dstream.ShuffledDStream.compute(ShuffledDStream.scala:41)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:301)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:301)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:300)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:288)
at scala.Option.orElse(Option.scala:257)
at
org.apache.spark.streaming.dstream.DStream.getOrCompute(DStream.scala:285)
at
org.apache.spark.streaming.dstream.ForEachDStream.generateJob(ForEachDStream.scala:38)
at
org.apache.spark.streaming.DStreamGraph$$anonfun$1.apply(DStreamGraph.scala:116)
at
org.apache.spark.streaming.DStreamGraph$$anonfun$1.apply(DStreamGraph.scala:116)
at
scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
at
scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:251)
at scala.collection.AbstractTraversable.flatMap(Traversable.scala:105)
at
org.apache.spark.streaming.DStreamGraph.generateJobs(DStreamGraph.scala:116)
at
org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$2.apply(JobGenerator.scala:232)
at
org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$2.apply(JobGenerator.scala:230)
at scala.util.Try$.apply(Try.scala:161)
at
org.apache.spark.streaming.scheduler.JobGenerator.generateJobs(JobGenerator.scala:230)
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$1.applyOrElse(JobGenerator.scala:78)
at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
at
org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$start$1$$anon$1.aroundReceive(JobGenerator.scala:76)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
at akka.actor.ActorCell.invoke(ActorCell.scala:487)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
at akka.dispatch.Mailbox.run(Mailbox.scala:220)
at
akka.dispatch.ForkJoinExecutorConfigurator$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)
> JavaStreamingContext.fileStream cause Configuration NotSerializableException
> ----------------------------------------------------------------------------
>
> Key: SPARK-5826
> URL: https://issues.apache.org/jira/browse/SPARK-5826
> Project: Spark
> Issue Type: Bug
> Components: Streaming
> Affects Versions: 1.2.1
> Reporter: Littlestar
> Priority: Minor
> Attachments: TestStream.java
>
>
> org.apache.spark.streaming.api.java.JavaStreamingContext.fileStream(String
> directory, Class<LongWritable> kClass, Class<Text> vClass,
> Class<TextInputFormat> fClass, Function<Path, Boolean> filter, boolean
> newFilesOnly, Configuration conf)
> I use JavaStreamingContext.fileStream with 1.3.0/master with Configuration.
> but it throw strange exception.
> java.io.NotSerializableException: org.apache.hadoop.conf.Configuration
> 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$$anonfun$writeObject$1.apply$mcV$sp(DStreamGraph.scala:177)
> at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1075)
> at
> org.apache.spark.streaming.DStreamGraph.writeObject(DStreamGraph.scala:172)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at
> java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:988)
> at
> java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1495)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
> at
> java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
> at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:347)
> at
> org.apache.spark.streaming.CheckpointWriter.write(Checkpoint.scala:184)
> at
> org.apache.spark.streaming.scheduler.JobGenerator.doCheckpoint(JobGenerator.scala:278)
> at
> org.apache.spark.streaming.scheduler.JobGenerator.org$apache$spark$streaming$scheduler$JobGenerator$$processEvent(JobGenerator.scala:169)
> at
> org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$start$1$$anon$1$$anonfun$receive$1.applyOrElse(JobGenerator.scala:78)
> at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
> at
> org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$start$1$$anon$1.aroundReceive(JobGenerator.scala:76)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
> at akka.actor.ActorCell.invoke(ActorCell.scala:487)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
> at akka.dispatch.Mailbox.run(Mailbox.scala:220)
> at
> akka.dispatch.ForkJoinExecutorConfigurator$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)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
