由于spark算子用到的class没有实现序列化,报错如下所示
15/11/23 14:43:47 ERROR Executor: Exception in task 0.0 in stage 4.0 (TID 4) java.io.NotSerializableException: EntityMention Serialization stack: - object not serializable (class: EntityMention, value: EntityMention@5cdadff6) at org.apache.spark.serializer.SerializationDebugger$.improveException(SerializationDebugger.scala:40) at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:47) at org.apache.spark.serializer.SerializationStream.writeValue(Serializer.scala:147) at org.apache.spark.storage.DiskBlockObjectWriter.write(DiskBlockObjectWriter.scala:181) at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.insertAll(BypassMergeSortShuffleWriter.java:121) at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:73) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:744) 15/11/23 14:43:47 ERROR TaskSetManager: Task 0.0 in stage 4.0 (TID 4) had a not serializable result: EntityMention Serialization stack: - object not serializable (class: EntityMention, value: EntityMention@5cdadff6); not retrying 15/11/23 14:43:47 INFO TaskSchedulerImpl: Removed TaskSet 4.0, whose tasks have all completed, from pool 15/11/23 14:43:47 INFO TaskSchedulerImpl: Cancelling stage 4 15/11/23 14:43:47 INFO DAGScheduler: ShuffleMapStage 4 (groupBy at Relation_Detector.scala:78) failed in 0.081 s 15/11/23 14:43:47 INFO DAGScheduler: Job 4 failed: collect at Relation_Detector.scala:79, took 0.097801 s Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0.0 in stage 4.0 (TID 4) had a not serializable result: EntityMention Serialization stack: - object not serializable (class: EntityMention, value: EntityMention@5cdadff6) at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1283) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1271) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1270) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1270) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1496) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1447) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1822) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1835) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1848) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1919) at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:905) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108) at org.apache.spark.rdd.RDD.withScope(RDD.scala:306) at org.apache.spark.rdd.RDD.collect(RDD.scala:904) at Relation_Detector$.main(Relation_Detector.scala:79) at Relation_Detector.main(Relation_Detector.scala) 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 com.intellij.rt.execution.application.AppMain.main(AppMain.java:140) 15/11/23 14:43:47 INFO SparkContext: Invoking stop() from shutdown hook
解决方法:对类实现序列化Serializable
class EntityMention(val pentitymention_id:String,var pname:String,var pentitymention_type:String, var pHbaseID:String,var ptopicID:String,var ppost_type:String, var psenIndex:String,var psenOffset:String, var ppostTime:String, var pinsertTime:String,var pentityID:String) extends Serializable { var entitymention_id = pentitymention_id var name = pname var entitymention_type = pentitymention_type var HbaseID = pHbaseID var topicID= ptopicID var post_type = ppost_type var senIndex = psenOffset var senOffset = psenOffset var postTime = ppostTime var insertTime = pinsertTime var entityID = pentityID }