在命令行启动spark-shell时,发生报错
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
21/06/10 15:17:28 ERROR spark.SparkContext: Error initializing SparkContext.
org.apache.hadoop.security.AccessControlException: Permission denied: user=root, access=WRITE, inode="/user":hdfs:supergroup:drwxr-xr-x
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.check(FSPermissionChecker.java:400)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:256)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:194)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1855)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1839)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkAncestorAccess(FSDirectory.java:1798)
at org.apache.hadoop.hdfs.server.namenode.FSDirMkdirOp.mkdirs(FSDirMkdirOp.java:61)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.mkdirs(FSNamesystem.java:3101)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.mkdirs(NameNodeRpcServer.java:1123)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.mkdirs(ClientNamenodeProtocolServerSideTranslatorPB.java:696)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:523)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:991)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:869)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:815)
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:1875)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2675)
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:2341)
at org.apache.hadoop.hdfs.DFSClient.mkdirs(DFSClient.java:2315)
at org.apache.hadoop.hdfs.DistributedFileSystem$27.doCall(DistributedFileSystem.java:1248)
at org.apache.hadoop.hdfs.DistributedFileSystem$27.doCall(DistributedFileSystem.java:1245)
at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at org.apache.hadoop.hdfs.DistributedFileSystem.mkdirsInternal(DistributedFileSystem.java:1262)
at org.apache.hadoop.hdfs.DistributedFileSystem.mkdirs(DistributedFileSystem.java:1237)
at org.apache.hadoop.fs.FileSystem.mkdirs(FileSystem.java:2209)
at org.apache.hadoop.fs.FileSystem.mkdirs(FileSystem.java:673)
at org.apache.spark.deploy.yarn.Client.prepareLocalResources(Client.scala:428)
at org.apache.spark.deploy.yarn.Client.createContainerLaunchContext(Client.scala:868)
at org.apache.spark.deploy.yarn.Client.submitApplication(Client.scala:183)
at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend.start(YarnClientSchedulerBackend.scala:60)
at org.apache.spark.scheduler.TaskSchedulerImpl.start(TaskSchedulerImpl.scala:186)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:511)
at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2549)
at org.apache.spark.sql.SparkSession$Builder$$anonfun$7.apply(SparkSession.scala:944)
at org.apache.spark.sql.SparkSession$Builder$$anonfun$7.apply(SparkSession.scala:935)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:935)
at org.apache.spark.repl.Main$.createSparkSession(Main.scala:106)
at $line3.$read$$iw$$iw.<init>(<console>:15)
at $line3.$read$$iw.<init>(<console>:43)
at $line3.$read.<init>(<console>:45)
at $line3.$read$.<init>(<console>:49)
at $line3.$read$.<clinit>(<console>)
at $line3.$eval$.$print$lzycompute(<console>:7)
at $line3.$eval$.$print(<console>:6)
at $line3.$eval.$print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:793)
at scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:1054)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:645)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:644)
at scala.reflect.internal.util.ScalaClassLoader$class.asContext(ScalaClassLoader.scala:31)
at scala.reflect.internal.util.AbstractFileClassLoader.asContext(AbstractFileClassLoader.scala:19)
at scala.tools.nsc.interpreter.IMain$WrappedRequest.loadAndRunReq(IMain.scala:644)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:576)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:572)
at scala.tools.nsc.interpreter.IMain$$anonfun$quietRun$1.apply(IMain.scala:231)
at scala.tools.nsc.interpreter.IMain$$anonfun$quietRun$1.apply(IMain.scala:231)
at scala.tools.nsc.interpreter.IMain.beQuietDuring(IMain.scala:221)
at scala.tools.nsc.interpreter.IMain.quietRun(IMain.scala:231)
at org.apache.spark.repl.SparkILoop$$anonfun$initializeSpark$1$$anonfun$apply$mcV$sp$1.apply(SparkILoop.scala:109)
at org.apache.spark.repl.SparkILoop$$anonfun$initializeSpark$1$$anonfun$apply$mcV$sp$1.apply(SparkILoop.scala:109)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.apache.spark.repl.SparkILoop$$anonfun$initializeSpark$1.apply$mcV$sp(SparkILoop.scala:109)
at org.apache.spark.repl.SparkILoop$$anonfun$initializeSpark$1.apply(SparkILoop.scala:109)
at org.apache.spark.repl.SparkILoop$$anonfun$initializeSpark$1.apply(SparkILoop.scala:109)
at scala.tools.nsc.interpreter.ILoop.savingReplayStack(ILoop.scala:91)
at org.apache.spark.repl.SparkILoop.initializeSpark(SparkILoop.scala:108)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1$$anonfun$org$apache$spark$repl$SparkILoop$$anonfun$$loopPostInit$1$1.apply$mcV$sp(SparkILoop.scala:211)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1$$anonfun$org$apache$spark$repl$SparkILoop$$anonfun$$loopPostInit$1$1.apply(SparkILoop.scala:199)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1$$anonfun$org$apache$spark$repl$SparkILoop$$anonfun$$loopPostInit$1$1.apply(SparkILoop.scala:199)
at scala.tools.nsc.interpreter.ILoop$$anonfun$mumly$1.apply(ILoop.scala:189)
at scala.tools.nsc.interpreter.IMain.beQuietDuring(IMain.scala:221)
at scala.tools.nsc.interpreter.ILoop.mumly(ILoop.scala:186)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1.org$apache$spark$repl$SparkILoop$$anonfun$$loopPostInit$1(SparkILoop.scala:199)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1$$anonfun$startup$1$1.apply(SparkILoop.scala:267)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1$$anonfun$startup$1$1.apply(SparkILoop.scala:247)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1.withSuppressedSettings$1(SparkILoop.scala:235)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1.startup$1(SparkILoop.scala:247)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply$mcZ$sp(SparkILoop.scala:282)
at org.apache.spark.repl.SparkILoop.runClosure(SparkILoop.scala:159)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:182)
at org.apache.spark.repl.Main$.doMain(Main.scala:78)
at org.apache.spark.repl.Main$.main(Main.scala:58)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:851)
at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:167)
at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:195)
at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86)
at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:926)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:935)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.security.AccessControlException): Permission denied: user=root, access=WRITE, inode="/user":hdfs:supergroup:drwxr-xr-x
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.check(FSPermissionChecker.java:400)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:256)
at org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:194)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1855)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkPermission(FSDirectory.java:1839)
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.checkAncestorAccess(FSDirectory.java:1798)
at org.apache.hadoop.hdfs.server.namenode.FSDirMkdirOp.mkdirs(FSDirMkdirOp.java:61)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.mkdirs(FSNamesystem.java:3101)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.mkdirs(NameNodeRpcServer.java:1123)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.mkdirs(ClientNamenodeProtocolServerSideTranslatorPB.java:696)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:523)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:991)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:869)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:815)
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:1875)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2675)
at org.apache.hadoop.ipc.Client.getRpcResponse(Client.java:1499)
at org.apache.hadoop.ipc.Client.call(Client.java:1445)
at org.apache.hadoop.ipc.Client.call(Client.java:1355)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:228)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:116)
at com.sun.proxy.$Proxy13.mkdirs(Unknown Source)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.mkdirs(ClientNamenodeProtocolTranslatorPB.java:640)
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$Call.invokeOnce(RetryInvocationHandler.java:95)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:359)
at com.sun.proxy.$Proxy14.mkdirs(Unknown Source)
at org.apache.hadoop.hdfs.DFSClient.primitiveMkdir(DFSClient.java:2339)
... 82 more
查看日志可以发现是因为org.apache.hadoop.security.AccessControlException: Permission denied: user=root, access=WRITE, inode="/user":hdfs:supergroup:drwxr-xr-x
因为当前执行Spark Application的用户没有Hdfs“/user”目录的写入权限
造成这个问题可以有以下几个解决办法:
1、将当前用户添加到supergroup用户组种
由于我是root用户,以root用户为例
groupadd supergroup
usermod -a -G supergroup root
2、关闭HDFS的安全检查
在Cloudera Manager主页中,进入HDFS页面,选择配置,在配置中搜索dfs.permissions
将HDFS前面的勾选掉
保存更改
重启HDFS
此种办法会导致HDFS中所有的安全特性都被禁用,让HDFS的安全性降低
3、修改报错中路径权限
hadoop fs -chmod 777 /user
将HDFS上的/user路径改为全权限,这样spark就可以在/user中写入了。