[ https://issues.apache.org/jira/browse/SPARK-19268?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Shixiong Zhu updated SPARK-19268: --------------------------------- Priority: Critical (was: Major) > File does not exist: > /tmp/temporary-157b89c1-27bb-49f3-a70c-ca1b75022b4d/state/0/2/1.delta > ------------------------------------------------------------------------------------------ > > Key: SPARK-19268 > URL: https://issues.apache.org/jira/browse/SPARK-19268 > Project: Spark > Issue Type: Bug > Components: Structured Streaming > Affects Versions: 2.1.0 > Environment: - hadoop2.7 > - Java 7 > Reporter: liyan > Priority: Critical > > bq. ./run-example sql.streaming.JavaStructuredKafkaWordCount > 192.168.3.110:9092 subscribe topic03 > when i run the spark example raises the following error: > {quote} > Exception in thread "main" 17/01/17 14:13:41 DEBUG ContextCleaner: Got > cleaning task CleanBroadcast(4) > org.apache.spark.sql.streaming.StreamingQueryException: Job aborted due to > stage failure: Task 2 in stage 9.0 failed 1 times, most recent failure: Lost > task 2.0 in stage 9.0 (TID 46, localhost, executor driver): > java.lang.IllegalStateException: Error reading delta file > /tmp/temporary-157b89c1-27bb-49f3-a70c-ca1b75022b4d/state/0/2/1.delta of > HDFSStateStoreProvider[id = (op=0, part=2), dir = > /tmp/temporary-157b89c1-27bb-49f3-a70c-ca1b75022b4d/state/0/2]: > /tmp/temporary-157b89c1-27bb-49f3-a70c-ca1b75022b4d/state/0/2/1.delta does > not exist > at > org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$updateFromDeltaFile(HDFSBackedStateStoreProvider.scala:354) > at > org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider$$anonfun$org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$loadMap$1$$anonfun$6.apply(HDFSBackedStateStoreProvider.scala:306) > at > org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider$$anonfun$org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$loadMap$1$$anonfun$6.apply(HDFSBackedStateStoreProvider.scala:303) > at scala.Option.getOrElse(Option.scala:121) > at > org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider$$anonfun$org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$loadMap$1.apply(HDFSBackedStateStoreProvider.scala:303) > at > org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider$$anonfun$org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$loadMap$1.apply(HDFSBackedStateStoreProvider.scala:302) > at scala.Option.getOrElse(Option.scala:121) > at > org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$loadMap(HDFSBackedStateStoreProvider.scala:302) > at > org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.getStore(HDFSBackedStateStoreProvider.scala:220) > at > org.apache.spark.sql.execution.streaming.state.StateStore$.get(StateStore.scala:151) > at > org.apache.spark.sql.execution.streaming.state.StateStoreRDD.compute(StateStoreRDD.scala:61) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) > at org.apache.spark.scheduler.Task.run(Task.scala:99) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > Caused by: java.io.FileNotFoundException: File does not exist: > /tmp/temporary-157b89c1-27bb-49f3-a70c-ca1b75022b4d/state/0/2/1.delta > at > org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:71) > at > org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:61) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1828) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1799) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1712) > at > org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:587) > at > org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getBlockLocations(ClientNamenodeProtocolServerSideTranslatorPB.java:365) > at > org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java) > at > org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:616) > at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:969) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2049) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2045) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:415) > at > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657) > at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2043) > at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) > at > sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:57) > at > sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) > at java.lang.reflect.Constructor.newInstance(Constructor.java:526) > at > org.apache.hadoop.ipc.RemoteException.instantiateException(RemoteException.java:106) > at > org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:73) > at > org.apache.hadoop.hdfs.DFSClient.callGetBlockLocations(DFSClient.java:1228) > at > org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1213) > at > org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1201) > at > org.apache.hadoop.hdfs.DFSInputStream.fetchLocatedBlocksAndGetLastBlockLength(DFSInputStream.java:306) > at > org.apache.hadoop.hdfs.DFSInputStream.openInfo(DFSInputStream.java:272) > at org.apache.hadoop.hdfs.DFSInputStream.<init>(DFSInputStream.java:264) > at org.apache.hadoop.hdfs.DFSClient.open(DFSClient.java:1526) > at > org.apache.hadoop.hdfs.DistributedFileSystem$3.doCall(DistributedFileSystem.java:304) > at > org.apache.hadoop.hdfs.DistributedFileSystem$3.doCall(DistributedFileSystem.java:299) > at > org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81) > at > org.apache.hadoop.hdfs.DistributedFileSystem.open(DistributedFileSystem.java:312) > at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:769) > at > org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$updateFromDeltaFile(HDFSBackedStateStoreProvider.scala:351) > ... 24 more > {quote} > I checked my spark configuration file, found the value of > {{spark.sql.adaptive.enabled}} is {{true}}, to modify it into {{false}}, the > example program can work. > Is this a bug? > thanks! -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org