我想從使用Spark的HBase流式傳輸數據。當我運行的Scala腳本,這是錯誤我得到:使用Spark不能序列化從HBase流式傳輸
ERROR Executor: Exception in task 0.0 in stage 10.0 (TID 10)
java.io.NotSerializableException: org.apache.hadoop.hbase.io.ImmutableBytesWritable
我起初以爲我的數據格式不正確,所以我想只有一個行創建一個非常基本的表:
row1 column=fam1:c1, timestamp=1422306700801, value=abc
即使這一行,我仍然會得到相同的錯誤。任何明顯的我失蹤?這裏的腳本:
def convertScanToString(scan: Scan): String = {
val out: ByteArrayOutputStream = new ByteArrayOutputStream
val dos: DataOutputStream = new DataOutputStream(out)
scan.write(dos)
Base64.encodeBytes(out.toByteArray)
}
val conf = HBaseConfiguration.create()
val scan = new Scan()
scan.setCaching(500)
scan.setCacheBlocks(false)
conf.set(TableInputFormat.INPUT_TABLE, "test_table")
conf.set(TableInputFormat.SCAN, convertScanToString(scan))
val rdd = sc.newAPIHadoopRDD(conf, classOf[TableInputFormat], classOf[ImmutableBytesWritable], classOf[Result])
rdd.first
編輯:按照要求,這裏是完整的堆棧跟蹤
15/01/26 21:50:50 ERROR Executor: Exception in task 0.0 in stage 14.0 (TID 14)
java.io.NotSerializableException: org.apache.hadoop.hbase.io.ImmutableBytesWritable
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.writeArray(ObjectOutputStream.java:1377)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1173)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:347)
at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:42)
at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:73)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:206)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
15/01/26 21:50:50 ERROR TaskSetManager: Task 0.0 in stage 14.0 (TID 14) had a not serializable result: org.apache.hadoop.hbase.io.ImmutableBytesWritable; not retrying
15/01/26 21:50:50 INFO TaskSchedulerImpl: Removed TaskSet 14.0, whose tasks have all completed, from pool
15/01/26 21:50:50 INFO TaskSchedulerImpl: Cancelling stage 14
15/01/26 21:50:50 INFO DAGScheduler: Job 14 failed: first at <console>:207, took 0.021506 s
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0.0 in stage 14.0 (TID 14) had a not serializable result: org.apache.hadoop.hbase.io.ImmutableBytesWritable
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420)
at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375)
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)
您可以更新您的問題,包括完整的堆棧跟蹤,而不僅僅是最後的例外呢? – 2015-01-26 22:24:09