Hi,
We run Spark Streaming on YARN,the Streaming Driver restart very often. I don't known what's the matter. The exception is below: 16/02/01 18:55:14 ERROR scheduler.JobScheduler: Error running job streaming job 1454324113000 ms.0 org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 11032.0 failed 4 times, most recent failure: Lost task 2.3 in stage 11032.0 (TID 16137, hadoop225.localdomain): java.lang.Exception: Could not compute split, block input-0-1454324106400 not found at org.apache.spark.rdd.BlockRDD.compute(BlockRDD.scala:51) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1294) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1282) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1281) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1281) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1507) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1469) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1824) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1837) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1850) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1921) at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:898) at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:896) at org.apache.spark.rdd.RDDOperationScope$.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.foreachPartition(RDD.scala:896) at com.in.sevenseas.onedegree.OneDegreeCompute_Repair$$anonfun$addCompute$1.apply(OneDegreeCompute_Repair.scala:98) at com.in.sevenseas.onedegree.OneDegreeCompute_Repair$$anonfun$addCompute$1.apply(OneDegreeCompute_Repair.scala:95) at org.apache.spark.streaming.dstream.DStream$$anonfun$foreachRDD$1$$anonfun$apply$mcV$sp$3.apply(DStream.scala:631) at org.apache.spark.streaming.dstream.DStream$$anonfun$foreachRDD$1$$anonfun$apply$mcV$sp$3.apply(DStream.scala:631) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(ForEachDStream.scala:42) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply(ForEachDStream.scala:40) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply(ForEachDStream.scala:40) at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:399) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply$mcV$sp(ForEachDStream.scala:40) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply(ForEachDStream.scala:40) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply(ForEachDStream.scala:40) at scala.util.Try$.apply(Try.scala:161) at org.apache.spark.streaming.scheduler.Job.run(Job.scala:34) at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply$mcV$sp(JobScheduler.scala:207) at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:207) at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:207) at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57) at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:206) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Caused by: java.lang.Exception: Could not compute split, block input-0-1454324106400 not found at org.apache.spark.rdd.BlockRDD.compute(BlockRDD.scala:51) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) ... 3 more 16/02/01 18:55:14 ERROR yarn.ApplicationMaster: User class threw exception: org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 11032.0 failed 4 times, most recent failure: Lost task 2.3 in stage 11032.0 (TID 16137, hadoop225.localdomain): java.lang.Exception: Could not compute split, block input-0-1454324106400 not found at org.apache.spark.rdd.BlockRDD.compute(BlockRDD.scala:51) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Driver stacktrace: org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 11032.0 failed 4 times, most recent failure: Lost task 2.3 in stage 11032.0 (TID 16137, hadoop225.localdomain): java.lang.Exception: Could not compute split, block input-0-1454324106400 not found at org.apache.spark.rdd.BlockRDD.compute(BlockRDD.scala:51) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1294) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1282) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1281) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1281) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1507) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1469) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1824) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1837) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1850) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1921) at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:898) at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:896) at org.apache.spark.rdd.RDDOperationScope$.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.foreachPartition(RDD.scala:896) at com.in.sevenseas.onedegree.OneDegreeCompute_Repair$$anonfun$addCompute$1.apply(OneDegreeCompute_Repair.scala:98) at com.in.sevenseas.onedegree.OneDegreeCompute_Repair$$anonfun$addCompute$1.apply(OneDegreeCompute_Repair.scala:95) at org.apache.spark.streaming.dstream.DStream$$anonfun$foreachRDD$1$$anonfun$apply$mcV$sp$3.apply(DStream.scala:631) at org.apache.spark.streaming.dstream.DStream$$anonfun$foreachRDD$1$$anonfun$apply$mcV$sp$3.apply(DStream.scala:631) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(ForEachDStream.scala:42) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply(ForEachDStream.scala:40) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply(ForEachDStream.scala:40) at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:399) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply$mcV$sp(ForEachDStream.scala:40) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply(ForEachDStream.scala:40) at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply(ForEachDStream.scala:40) at scala.util.Try$.apply(Try.scala:161) at org.apache.spark.streaming.scheduler.Job.run(Job.scala:34) at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply$mcV$sp(JobScheduler.scala:207) at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:207) at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:207) at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57) at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:206) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Caused by: java.lang.Exception: Could not compute split, block input-0-1454324106400 not found at org.apache.spark.rdd.BlockRDD.compute(BlockRDD.scala:51) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) ... 3 more 16/02/01 18:55:14 INFO yarn.ApplicationMaster: Final app status: FAILED, exitCode: 15, (reason: User class threw exception: org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 11032.0 failed 4 times, most recent failure: Lost task 2.3 in stage 11032.0 (TID 16137, hadoop225.localdomain): java.lang.Exception: Could not compute split, block input-0-1454324106400 not found at org.apache.spark.rdd.BlockRDD.compute(BlockRDD.scala:51) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69) at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745)