[
https://issues.apache.org/jira/browse/SPARK-3245?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
刘勇 closed SPARK-3245.
---------------------
> spark insert into hbase class not serialize
> --------------------------------------------
>
> Key: SPARK-3245
> URL: https://issues.apache.org/jira/browse/SPARK-3245
> Project: Spark
> Issue Type: Bug
> Environment: spark-1.0.1 + hbase-0.96.2 + hadoop-2.2.0
> Reporter: 刘勇
>
> val result: org.apache.spark.rdd.RDD[(String, Int)]
> result.foreach(res =>{
> var put = new
> Put(java.util.UUID.randomUUID().toString.reverse.getBytes())
> .add("lv6".getBytes(), res._1.toString.getBytes(),
> res._2.toString.getBytes)
> table.put(put)
> }
> )
> Exception in thread "Thread-3" java.lang.reflect.InvocationTargetException
> 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
> org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:186)
> Caused by: org.apache.spark.SparkException: Job aborted due to stage failure:
> Task not serializable: java.io.NotSerializableException:
> org.apache.hadoop.hbase.client.HTablePool$PooledHTable
> at
> org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$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.org$apache$spark$scheduler$DAGScheduler$$submitMissingTasks(DAGScheduler.scala:771)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$16$$anonfun$apply$1.apply$mcVI$sp(DAGScheduler.scala:901)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$16$$anonfun$apply$1.apply(DAGScheduler.scala:898)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$16$$anonfun$apply$1.apply(DAGScheduler.scala:898)
> at scala.Option.foreach(Option.scala:236)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$16.apply(DAGScheduler.scala:898)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$16.apply(DAGScheduler.scala:897)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at
> org.apache.spark.scheduler.DAGScheduler.handleTaskCompletion(DAGScheduler.scala:897)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1226)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
> at akka.actor.ActorCell.invoke(ActorCell.scala:456)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
> at akka.dispatch.Mailbox.run(Mailbox.scala:219)
> at
> akka.dispatch.ForkJoinExecutorConfigurator$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)
--
This message was sent by Atlassian JIRA
(v6.2#6252)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
