将 parquet 文件从 Zeppelin executor 保存到 HDFS 时出现问题
Problems when save the parquet file from Zeppelin executor to HDFS
我们在将 parquet 文件从 Zeppelin 执行器保存到 HDFS 时遇到问题
resultIndexed
.repartition(1)
.write
.parquet(s"hdfs://hdfs-hadoop-hdfs-nn.svc.cluster.local:9000/home/zeppelin/sensor_parquet")
并得到异常：
org.apache.hadoop.security.AccessControlException: Permission denied: user=zeppelin, access=WRITE, inode="/home/zeppelin":sparkjob:hdfs:drwxr-xr-x
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.check(FSPermissionChecker.java:399)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:255)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:193)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1879)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1863)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkAncestorAccess(FSDirectory.java:1822)
at org.apache.hadoop.hdfs.server.namenode.FSDirMkdirOp.mkdirs(FSDirMkdirOp.java:59)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.mkdirs(FSNamesystem.java:3233)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.mkdirs(NameNodeRpcServer.java:1145)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.mkdirs(ClientNamenodeProtocolServerSideTranslatorPB.java:720)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:528)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1070)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:999)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:927)
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:1730)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2915)
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at org.apache.hadoop.ipc.RemoteException.instantiateException(RemoteException.java:121)
at org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:88)
at org.apache.hadoop.hdfs.DFSClient.primitiveMkdir(DFSClient.java:2426)
at org.apache.hadoop.hdfs.DFSClient.mkdirs(DFSClient.java:2400)
at org.apache.hadoop.hdfs.DistributedFileSystem.doCall(DistributedFileSystem.java:1324)
at org.apache.hadoop.hdfs.DistributedFileSystem.doCall(DistributedFileSystem.java:1321)
at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at org.apache.hadoop.hdfs.DistributedFileSystem.mkdirsInternal(DistributedFileSystem.java:1338)
at org.apache.hadoop.hdfs.DistributedFileSystem.mkdirs(DistributedFileSystem.java:1313)
at org.apache.hadoop.fs.FileSystem.mkdirs(FileSystem.java:2275)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.setupJob(FileOutputCommitter.java:354)
at org.apache.spark.internal.io.HadoopMapReduceCommitProtocol.setupJob(HadoopMapReduceCommitProtocol.scala:163)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:168)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:178)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:108)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:106)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:131)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute(SparkPlan.scala:175)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery(SparkPlan.scala:213)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:210)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:171)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:122)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:121)
at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand(DataFrameWriter.scala:963)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId(SQLExecution.scala:100)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:160)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId(SQLExecution.scala:87)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:764)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:963)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:415)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:399)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:288)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:848)
... 50 elided
Caused by: org.apache.hadoop.ipc.RemoteException: Permission denied: user=zeppelin, access=WRITE, inode="/home/zeppelin":sparkjob:hdfs:drwxr-xr-x
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.check(FSPermissionChecker.java:399)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:255)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:193)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1879)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1863)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkAncestorAccess(FSDirectory.java:1822)
at org.apache.hadoop.hdfs.server.namenode.FSDirMkdirOp.mkdirs(FSDirMkdirOp.java:59)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.mkdirs(FSNamesystem.java:3233)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.mkdirs(NameNodeRpcServer.java:1145)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.mkdirs(ClientNamenodeProtocolServerSideTranslatorPB.java:720)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:528)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1070)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:999)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:927)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1730)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2915)
at org.apache.hadoop.ipc.Client.getRpcResponse(Client.java:1511)
at org.apache.hadoop.ipc.Client.call(Client.java:1457)
at org.apache.hadoop.ipc.Client.call(Client.java:1367)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:228)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:116)
at com.sun.proxy.$Proxy25.mkdirs(Unknown Source)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.mkdirs(ClientNamenodeProtocolTranslatorPB.java:656)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:422)
at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invokeMethod(RetryInvocationHandler.java:165)
at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invoke(RetryInvocationHandler.java:157)
at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invokeOnce(RetryInvocationHandler.java:95)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:359)
at com.sun.proxy.$Proxy26.mkdirs(Unknown Source)
at org.apache.hadoop.hdfs.DFSClient.primitiveMkdir(DFSClient.java:2424)
... 82 more
问题的原因可能是什么？
原因是缺少 hdfs zeppelin 用户的访问权限：
hdfs dfs -chown -R zeppelin:hdfs /home/zeppelin
我们在将 parquet 文件从 Zeppelin 执行器保存到 HDFS 时遇到问题
resultIndexed
.repartition(1)
.write
.parquet(s"hdfs://hdfs-hadoop-hdfs-nn.svc.cluster.local:9000/home/zeppelin/sensor_parquet")
并得到异常：
org.apache.hadoop.security.AccessControlException: Permission denied: user=zeppelin, access=WRITE, inode="/home/zeppelin":sparkjob:hdfs:drwxr-xr-x
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.check(FSPermissionChecker.java:399)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:255)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:193)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1879)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1863)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkAncestorAccess(FSDirectory.java:1822)
at org.apache.hadoop.hdfs.server.namenode.FSDirMkdirOp.mkdirs(FSDirMkdirOp.java:59)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.mkdirs(FSNamesystem.java:3233)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.mkdirs(NameNodeRpcServer.java:1145)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.mkdirs(ClientNamenodeProtocolServerSideTranslatorPB.java:720)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:528)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1070)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:999)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:927)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1730)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2915)
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at org.apache.hadoop.ipc.RemoteException.instantiateException(RemoteException.java:121)
at org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:88)
at org.apache.hadoop.hdfs.DFSClient.primitiveMkdir(DFSClient.java:2426)
at org.apache.hadoop.hdfs.DFSClient.mkdirs(DFSClient.java:2400)
at org.apache.hadoop.hdfs.DistributedFileSystem.doCall(DistributedFileSystem.java:1324)
at org.apache.hadoop.hdfs.DistributedFileSystem.doCall(DistributedFileSystem.java:1321)
at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at org.apache.hadoop.hdfs.DistributedFileSystem.mkdirsInternal(DistributedFileSystem.java:1338)
at org.apache.hadoop.hdfs.DistributedFileSystem.mkdirs(DistributedFileSystem.java:1313)
at org.apache.hadoop.fs.FileSystem.mkdirs(FileSystem.java:2275)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.setupJob(FileOutputCommitter.java:354)
at org.apache.spark.internal.io.HadoopMapReduceCommitProtocol.setupJob(HadoopMapReduceCommitProtocol.scala:163)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:168)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:178)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:108)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:106)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:131)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute(SparkPlan.scala:175)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery(SparkPlan.scala:213)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:210)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:171)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:122)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:121)
at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand(DataFrameWriter.scala:963)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId(SQLExecution.scala:100)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:160)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId(SQLExecution.scala:87)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:764)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:963)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:415)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:399)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:288)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:848)
... 50 elided
Caused by: org.apache.hadoop.ipc.RemoteException: Permission denied: user=zeppelin, access=WRITE, inode="/home/zeppelin":sparkjob:hdfs:drwxr-xr-x
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.check(FSPermissionChecker.java:399)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:255)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:193)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1879)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1863)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkAncestorAccess(FSDirectory.java:1822)
at org.apache.hadoop.hdfs.server.namenode.FSDirMkdirOp.mkdirs(FSDirMkdirOp.java:59)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.mkdirs(FSNamesystem.java:3233)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.mkdirs(NameNodeRpcServer.java:1145)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.mkdirs(ClientNamenodeProtocolServerSideTranslatorPB.java:720)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:528)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1070)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:999)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:927)
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:1730)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2915)
at org.apache.hadoop.ipc.Client.getRpcResponse(Client.java:1511)
at org.apache.hadoop.ipc.Client.call(Client.java:1457)
at org.apache.hadoop.ipc.Client.call(Client.java:1367)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:228)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:116)
at com.sun.proxy.$Proxy25.mkdirs(Unknown Source)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.mkdirs(ClientNamenodeProtocolTranslatorPB.java:656)
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.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:422)
at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invokeMethod(RetryInvocationHandler.java:165)
at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invoke(RetryInvocationHandler.java:157)
at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invokeOnce(RetryInvocationHandler.java:95)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:359)
at com.sun.proxy.$Proxy26.mkdirs(Unknown Source)
at org.apache.hadoop.hdfs.DFSClient.primitiveMkdir(DFSClient.java:2424)
... 82 more
问题的原因可能是什么？
原因是缺少 hdfs zeppelin 用户的访问权限：
hdfs dfs -chown -R zeppelin:hdfs /home/zeppelin