- nebula 版本：2.6.1
- 部署方式：分布式
- 安装方式：源码编译
- 是否为线上版本：Y
- 硬件信息
- 磁盘1.5T
- CPU8、内存信息 128G
- 问题的具体描述
执行spark任务时部分task执行报错导致失败，之前看有人说调低batch数量，可是我已经将之前推荐的256降低到128了
22/03/27 20:06:10 INFO ApplicationMaster: Final app status: FAILED, exitCode: 15, (reason: User class threw exception: org.apache.spark.SparkException: Job aborted due to stage failure: Task 685 in stage 2.0 failed 4 times, most recent failure: Lost task 685.3 in stage 2.0 (TID 122, ap-bp********-core-014.spark.rds.aliyuncs.com, executor 2): java.io.EOFException: Cannot seek after EOF
at org.apache.hadoop.hdfs.DFSInputStream.seek(DFSInputStream.java:1591)
at org.apache.hadoop.fs.FSDataInputStream.seek(FSDataInputStream.java:62)
at org.apache.hadoop.mapreduce.lib.input.LineRecordReader.initialize(LineRecordReader.java:107)
at org.apache.spark.sql.execution.datasources.HadoopFileLinesReader.<init>(HadoopFileLinesReader.scala:65)
at org.apache.spark.sql.execution.datasources.text.TextFileFormat$$anonfun$readToUnsafeMem$1.apply(TextFileFormat.scala:119)
at org.apache.spark.sql.execution.datasources.text.TextFileFormat$$anonfun$readToUnsafeMem$1.apply(TextFileFormat.scala:116)
at org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(FileFormat.scala:148)
at org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(FileFormat.scala:132)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.org$apache$spark$sql$execution$datasources$FileScanRDD$$anon$$readCurrentFile(FileScanRDD.scala:124)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:177)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:101)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:181)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:101)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:181)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:101)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$class.foreach(Iterator.scala:891)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
at com.vesoft.nebula.exchange.processor.ReloadProcessor.com$vesoft$nebula$exchange$processor$ReloadProcessor$$processEachPartition(ReloadProcessor.scala:47)
at com.vesoft.nebula.exchange.processor.ReloadProcessor$$anonfun$process$1.apply(ReloadProcessor.scala:27)
at com.vesoft.nebula.exchange.processor.ReloadProcessor$$anonfun$process$1.apply(ReloadProcessor.scala:27)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$28.apply(RDD.scala:935)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$28.apply(RDD.scala:935)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2101)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2101)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:121)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1147)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:622)
at java.lang.Thread.run(Thread.java:834)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1889)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1877)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1876)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1876)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2110)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2059)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2048)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:737)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2082)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2101)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2126)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:935)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:933)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.foreachPartition(RDD.scala:933)
at org.apache.spark.sql.Dataset$$anonfun$foreachPartition$1.apply$mcV$sp(Dataset.scala:2735)
at org.apache.spark.sql.Dataset$$anonfun$foreachPartition$1.apply(Dataset.scala:2735)
at org.apache.spark.sql.Dataset$$anonfun$foreachPartition$1.apply(Dataset.scala:2735)
at org.apache.spark.sql.Dataset$$anonfun$withNewRDDExecutionId$1.apply(Dataset.scala:3349)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.Dataset.withNewRDDExecutionId(Dataset.scala:3345)
at org.apache.spark.sql.Dataset.foreachPartition(Dataset.scala:2734)
at com.vesoft.nebula.exchange.processor.ReloadProcessor.process(ReloadProcessor.scala:27)
at com.vesoft.nebula.exchange.Exchange$.main(Exchange.scala:199)
at com.vesoft.nebula.exchange.Exchange.main(Exchange.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:684)
Caused by: java.io.EOFException: Cannot seek after EOF
at org.apache.hadoop.hdfs.DFSInputStream.seek(DFSInputStream.java:1591)
at org.apache.hadoop.fs.FSDataInputStream.seek(FSDataInputStream.java:62)
at org.apache.hadoop.mapreduce.lib.input.LineRecordReader.initialize(LineRecordReader.java:107)
at org.apache.spark.sql.execution.datasources.HadoopFileLinesReader.<init>(HadoopFileLinesReader.scala:65)
at org.apache.spark.sql.execution.datasources.text.TextFileFormat$$anonfun$readToUnsafeMem$1.apply(TextFileFormat.scala:119)
at org.apache.spark.sql.execution.datasources.text.TextFileFormat$$anonfun$readToUnsafeMem$1.apply(TextFileFormat.scala:116)
at org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(FileFormat.scala:148)
at org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(FileFormat.scala:132)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.org$apache$spark$sql$execution$datasources$FileScanRDD$$anon$$readCurrentFile(FileScanRDD.scala:124)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:177)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:101)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:181)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:101)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:181)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:101)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$class.foreach(Iterator.scala:891)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
at com.vesoft.nebula.exchange.processor.ReloadProcessor.com$vesoft$nebula$exchange$processor$ReloadProcessor$$processEachPartition(ReloadProcessor.scala:47)
at com.vesoft.nebula.exchange.processor.ReloadProcessor$$anonfun$process$1.apply(ReloadProcessor.scala:27)
at com.vesoft.nebula.exchange.processor.ReloadProcessor$$anonfun$process$1.apply(ReloadProcessor.scala:27)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$28.apply(RDD.scala:935)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$28.apply(RDD.scala:935)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2101)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2101)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:121)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1147)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:622)
at java.lang.Thread.run(Thread.java:834)
最后烦请删掉本模版和问题无关的信息之后，再提交提问，Thx