hdfs directory item limit - (dfs.namenode.fs-limits.max-directory-items)
阿新 • • 發佈：2018-11-06
18/11/05 22:21:44 WARN scheduler.TaskSetManager: Lost task 186792.0 in stage 0.0 (TID 1046119, emr-worker-343.cluster-40699, executor 324): org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.hdfs.protocol.FSLimitException$MaxDirectoryItemsExceededException): The directory item limit of /public/sample/big_scale_fm/test_data_50_billion_sorted/_temporary/0/ is exceeded: limit=1048576 items=1048576 at org.apache.hadoop.hdfs.server.namenode.FSDirectory.verifyMaxDirItems(FSDirectory.java:932) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.verifyFsLimitsForRename(FSDirRenameOp.java:117) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.unprotectedRenameTo(FSDirRenameOp.java:189) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.renameTo(FSDirRenameOp.java:474) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.renameToInt(FSDirRenameOp.java:73) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.renameTo(FSNamesystem.java:3650) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.rename(NameNodeRpcServer.java:867) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.rename(ClientNamenodeProtocolServerSideTranslatorPB.java:575) at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$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$1.run(Server.java:2045) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2045) at org.apache.hadoop.ipc.Client.call(Client.java:1475) at org.apache.hadoop.ipc.Client.call(Client.java:1412) at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229) at com.sun.proxy.$Proxy15.rename(Unknown Source) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.rename(ClientNamenodeProtocolTranslatorPB.java:487) at sun.reflect.GeneratedMethodAccessor43.invoke(Unknown Source) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:191) at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102) at com.sun.proxy.$Proxy16.rename(Unknown Source) at org.apache.hadoop.hdfs.DFSClient.rename(DFSClient.java:1951) at org.apache.hadoop.hdfs.DistributedFileSystem.rename(DistributedFileSystem.java:626) at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.commitTask(FileOutputCommitter.java:531) at org.apache.hadoop.mapred.FileOutputCommitter.commitTask(FileOutputCommitter.java:172) at org.apache.hadoop.mapred.OutputCommitter.commitTask(OutputCommitter.java:343) at org.apache.spark.mapred.SparkHadoopMapRedUtil$.performCommit$1(SparkHadoopMapRedUtil.scala:50) at org.apache.spark.mapred.SparkHadoopMapRedUtil$.commitTask(SparkHadoopMapRedUtil.scala:76) at org.apache.spark.SparkHadoopWriter.commit(SparkHadoopWriter.scala:106) at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13.apply(PairRDDFunctions.scala:1219) at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13.apply(PairRDDFunctions.scala:1197) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:99) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) 18/11/05 22:21:44 INFO scheduler.TaskSetManager: Starting task 186792.1 in stage 0.0 (TID 1050576, emr-worker-801.cluster-40699, executor 158, partition 186792, RACK_LOCAL, 6062 bytes) 18/11/05 22:21:44 INFO scheduler.TaskSetManager: Lost task 197623.0 in stage 0.0 (TID 1048044) on emr-worker-801.cluster-40699, executor 158: org.apache.hadoop.ipc.RemoteException (The directory item limit of /public/sample/big_scale_fm/test_data_50_billion_sorted/_temporary/0/ is exceeded: limit=1048576 items=1048576 at org.apache.hadoop.hdfs.server.namenode.FSDirectory.verifyMaxDirItems(FSDirectory.java:932) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.verifyFsLimitsForRename(FSDirRenameOp.java:117) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.unprotectedRenameTo(FSDirRenameOp.java:189) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.renameTo(FSDirRenameOp.java:474) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.renameToInt(FSDirRenameOp.java:73) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.renameTo(FSNamesystem.java:3650) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.rename(NameNodeRpcServer.java:867) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.rename(ClientNamenodeProtocolServerSideTranslatorPB.java:575) at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$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$1.run(Server.java:2045) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2045) ) [duplicate 1] 18/11/05 22:21:44 INFO scheduler.TaskSetManager: Starting task 197623.1 in stage 0.0 (TID 1050577, emr-worker-176.cluster-40699, executor 201, partition 197623, RACK_LOCAL, 6063 bytes) 18/11/05 22:21:44 INFO scheduler.TaskSetManager: Lost task 198559.0 in stage 0.0 (TID 1048304) on emr-worker-176.cluster-40699, executor 201: org.apache.hadoop.ipc.RemoteException (The directory item limit of /public/sample/big_scale_fm/test_data_50_billion_sorted/_temporary/0/ is exceeded: limit=1048576 items=1048576 at org.apache.hadoop.hdfs.server.namenode.FSDirectory.verifyMaxDirItems(FSDirectory.java:932) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.verifyFsLimitsForRename(FSDirRenameOp.java:117) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.unprotectedRenameTo(FSDirRenameOp.java:189) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.renameTo(FSDirRenameOp.java:474) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.renameToInt(FSDirRenameOp.java:73) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.renameTo(FSNamesystem.java:3650) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.rename(NameNodeRpcServer.java:867) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.rename(ClientNamenodeProtocolServerSideTranslatorPB.java:575) 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$1.run(Server.java:2045) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2045) ) [duplicate 2]
18/11/05 22:22:15 INFO scheduler.TaskSetManager: Lost task 203616.0 in stage 0.0 (TID 1049710) on emr-worker-412.cluster-40699, executor 228: org.apache.hadoop.ipc.RemoteException (The directory item limit of /public/sample/big_scale_fm/test_data_50_billion_sorted/_temporary/0/ is exceeded: limit=1048576 items=1048576 at org.apache.hadoop.hdfs.server.namenode.FSDirectory.verifyMaxDirItems(FSDirectory.java:932) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.verifyFsLimitsForRename(FSDirRenameOp.java:117) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.unprotectedRenameTo(FSDirRenameOp.java:189) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.renameTo(FSDirRenameOp.java:474) at org.apache.hadoop.hdfs.server.namenode.FSDirRenameOp.renameToInt(FSDirRenameOp.java:73) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.renameTo(FSNamesystem.java:3650) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.rename(NameNodeRpcServer.java:867) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.rename(ClientNamenodeProtocolServerSideTranslatorPB.java:575) 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$1.run(Server.java:2045) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2045) ) [duplicate 23]
錯誤原因： 一個目錄下的子目錄數量達到限制，預設的上限是 1048576。 每次執行hive語句時，都會在 hive.exec.scratchdir 配置的目錄下生成一個臨時目錄，執行結束後會自動刪除，如果異常中斷則有可能會保留目錄。
提供兩種解決辦法：
提高目錄的限制上限，通過 dfs.namenode.fs-limits.max-directory-items 引數限制，最高不能超過 6400000
<property> <name>dfs.namenode.fs-limits.max-directory-items</name> <value>1048576</value> <description>Defines the maximum number of items that a directory may contain. Cannot set the property to a value less than 1 or more than 6400000.</description> </property>
比較靠譜的方法還是在作業中，適當做一下控制。