HBase 全部RS节点宕机,请帮助分析

weixin_35511318 2018-01-29 11:22:34
2018-01-20T03:26:18 Region server slave6.bigdata.test.cn,16020,1507703889028 reported a fatal error:
ABORTING region server slave6.bigdata.test.cn,16020,1507703889028: IOE in log roller
Cause:
java.io.IOException: cannot get log writer
at org.apache.hadoop.hbase.wal.DefaultWALProvider.createWriter(DefaultWALProvider.java:374)
at org.apache.hadoop.hbase.regionserver.wal.FSHLog.createWriterInstance(FSHLog.java:781)
at org.apache.hadoop.hbase.regionserver.wal.FSHLog.rollWriter(FSHLog.java:746)
at org.apache.hadoop.hbase.regionserver.LogRoller.run(LogRoller.java:148)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.FileNotFoundException: Parent directory doesn't exist: /hbase/WALs/slave6.bigdata.test.cn,16020,1507703889028
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.verifyParentDir(FSDirectory.java:1979)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInternal(FSNamesystem.java:2739)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInt(FSNamesystem.java:2671)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:2555)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.create(NameNodeRpcServer.java:735)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.create(ClientNamenodeProtocolServerSideTranslatorPB.java:408)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:640)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:982)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2351)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2347)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1866)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2345)
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:106)
at org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:73)
at org.apache.hadoop.hdfs.DFSOutputStream.newStreamForCreate(DFSOutputStream.java:1804)
at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1701)
at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1670)
at org.apache.hadoop.hdfs.DistributedFileSystem$9.doCall(DistributedFileSystem.java:527)
at org.apache.hadoop.hdfs.DistributedFileSystem$9.doCall(DistributedFileSystem.java:523)
at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at org.apache.hadoop.hdfs.DistributedFileSystem.createNonRecursive(DistributedFileSystem.java:523)
at org.apache.hadoop.fs.FileSystem.createNonRecursive(FileSystem.java:1134)
at org.apache.hadoop.fs.FileSystem.createNonRecursive(FileSystem.java:1110)
at org.apache.hadoop.hbase.regionserver.wal.ProtobufLogWriter.init(ProtobufLogWriter.java:90)
at org.apache.hadoop.hbase.wal.DefaultWALProvider.createWriter(DefaultWALProvider.java:363)
... 4 more
Caused by: org.apache.hadoop.ipc.RemoteException(java.io.FileNotFoundException): Parent directory doesn't exist: /hbase/WALs/slave6.bigdata.test.cn,16020,1507703889028
at org.apache.hadoop.hdfs.server.namenode.FSDirectory.verifyParentDir(FSDirectory.java:1979)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInternal(FSNamesystem.java:2739)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInt(FSNamesystem.java:2671)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:2555)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.create(NameNodeRpcServer.java:735)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.create(ClientNamenodeProtocolServerSideTranslatorPB.java:408)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:640)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:982)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2351)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2347)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1866)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2345)
at org.apache.hadoop.ipc.Client.getRpcResponse(Client.java:1554)
at org.apache.hadoop.ipc.Client.call(Client.java:1498)
at org.apache.hadoop.ipc.Client.call(Client.java:1398)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:233)
at com.sun.proxy.$Proxy16.create(Unknown Source)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.create(ClientNamenodeProtocolTranslatorPB.java:313)
at sun.reflect.GeneratedMethodAccessor4.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:291)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:203)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:185)
at com.sun.proxy.$Proxy17.create(Unknown Source)
at sun.reflect.GeneratedMethodAccessor4.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.hadoop.hbase.fs.HFileSystem$1.invoke(HFileSystem.java:283)
at com.sun.proxy.$Proxy18.create(Unknown Source)
at org.apache.hadoop.hdfs.DFSOutputStream.newStreamForCreate(DFSOutputStream.java:1799)
... 14 more
2018-01-20T03:26:19 Region server slave6.bigdata.test.cn,16020,1507703889028 reported a fatal error:
ABORTING region server slave6.bigdata.test.cn,16020,1507703889028: Get list of registered region servers
Cause:
org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired for /hbase-unsecure/rs
at org.apache.zookeeper.KeeperException.create(KeeperException.java:127)
at org.apache.zookeeper.KeeperException.create(KeeperException.java:51)
at org.apache.zookeeper.ZooKeeper.getChildren(ZooKeeper.java:1472)
at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.getChildren(RecoverableZooKeeper.java:292)
at org.apache.hadoop.hbase.zookeeper.ZKUtil.listChildrenAndWatchForNewChildren(ZKUtil.java:455)
at org.apache.hadoop.hbase.zookeeper.ZKUtil.listChildrenAndWatchThem(ZKUtil.java:483)
at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.getRegisteredRegionServers(ReplicationTrackerZKImpl.java:245)
at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.refreshOtherRegionServersList(ReplicationTrackerZKImpl.java:226)
at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.access$400(ReplicationTrackerZKImpl.java:42)
at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl$OtherRegionServerWatcher.refreshListIfRightPath(ReplicationTrackerZKImpl.java:142)
at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl$OtherRegionServerWatcher.nodeDeleted(ReplicationTrackerZKImpl.java:117)
at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:539)
at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534)
at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510)
2018-01-20T03:26:19 Region server slave6.bigdata.test.cn,16020,1507703889028 reported a fatal error:
ABORTING region server slave6.bigdata.test.cn,16020,1507703889028: regionserver:16020-0x35ec011d31a0174, quorum=master1.bigdata.test.cn:2181,master3.bigdata.test.cn:2181,master2.bigdata.test.cn:2181, baseZNode=/hbase-unsecure regionserver:16020-0x35ec011d31a0174 received expired from ZooKeeper, aborting
Cause:
org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired
at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.connectionEvent(ZooKeeperWatcher.java:592)
at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:524)
at org.apache.hadoop.hbase.zookeeper.PendingWatcher.process(PendingWatcher.java:40)
at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534)
at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510)
2018-01-20T03:26:19 Region server slave6.bigdata.test.cn,16020,1507703889028 reported a fatal error:
ABORTING region server slave6.bigdata.test.cn,16020,1507703889028: regionserver:16020-0x35ec011d31a0174, quorum=master1.bigdata.test.cn:2181,master3.bigdata.test.cn:2181,master2.bigdata.test.cn:2181, baseZNode=/hbase-unsecure regionserver:16020-0x35ec011d31a0174 received expired from ZooKeeper, aborting
Cause:
org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired
at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.connectionEvent(ZooKeeperWatcher.java:592)
at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:524)
at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534)
at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510)
...全文
813 4 打赏 收藏 转发到动态 举报
写回复
用AI写文章
4 条回复
切换为时间正序
请发表友善的回复…
发表回复
双林子木 2018-01-30
  • 打赏
  • 举报
回复
IOE in log roller: Session Expired->Server REPORT rejected: you are dead->Parent directory doesn't exist: /hbase/WALs/slave5.bigdata.test.cn,16020,1507703887266>cannot get log writer Session expired->Failed to replace a bad datanode on the existing pipeline due to no more good datanodes->Failed appending 232848742, requesting roll of WAL 产生了两条异常线,一条写log时发现/hbase/WALs/slave5.bigdata.test.cn目录不存在导致写log异常,从而触发Session失效错误导致节点dead 另一条异常线为zookeeper尝试对出问题的节点进行处理,但没有找到可用的节点 个人理解,仅供参考!
weixin_35511318 2018-01-29
  • 打赏
  • 举报
回复
2018-01-20T03:33:54 Region server slave4.bigdata.test.cn,16020,1507703887311 reported a fatal error: ABORTING region server slave4.bigdata.test.cn,16020,1507703887311: Get list of registered region servers Cause: org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired for /hbase-unsecure/rs at org.apache.zookeeper.KeeperException.create(KeeperException.java:127) at org.apache.zookeeper.KeeperException.create(KeeperException.java:51) at org.apache.zookeeper.ZooKeeper.getChildren(ZooKeeper.java:1472) at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.getChildren(RecoverableZooKeeper.java:292) at org.apache.hadoop.hbase.zookeeper.ZKUtil.listChildrenAndWatchForNewChildren(ZKUtil.java:455) at org.apache.hadoop.hbase.zookeeper.ZKUtil.listChildrenAndWatchThem(ZKUtil.java:483) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.getRegisteredRegionServers(ReplicationTrackerZKImpl.java:245) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.refreshOtherRegionServersList(ReplicationTrackerZKImpl.java:226) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.access$400(ReplicationTrackerZKImpl.java:42) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl$OtherRegionServerWatcher.refreshListIfRightPath(ReplicationTrackerZKImpl.java:142) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl$OtherRegionServerWatcher.nodeDeleted(ReplicationTrackerZKImpl.java:117) at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:539) at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534) at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510) 2018-01-20T03:33:54 Region server slave4.bigdata.test.cn,16020,1507703887311 reported a fatal error: ABORTING region server slave4.bigdata.test.cn,16020,1507703887311: regionserver:16020-0x15ec011d2c60192, quorum=master1.bigdata.test.cn:2181,master3.bigdata.test.cn:2181,master2.bigdata.test.cn:2181, baseZNode=/hbase-unsecure regionserver:16020-0x15ec011d2c60192 received expired from ZooKeeper, aborting Cause: org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.connectionEvent(ZooKeeperWatcher.java:592) at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:524) at org.apache.hadoop.hbase.zookeeper.PendingWatcher.process(PendingWatcher.java:40) at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534) at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510) 2018-01-20T03:33:54 Region server slave4.bigdata.test.cn,16020,1507703887311 reported a fatal error: ABORTING region server slave4.bigdata.test.cn,16020,1507703887311: regionserver:16020-0x15ec011d2c60192, quorum=master1.bigdata.test.cn:2181,master3.bigdata.test.cn:2181,master2.bigdata.test.cn:2181, baseZNode=/hbase-unsecure regionserver:16020-0x15ec011d2c60192 received expired from ZooKeeper, aborting Cause: org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.connectionEvent(ZooKeeperWatcher.java:592) at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:524) at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534) at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510) 2018-01-20T03:34:32 Region server slave1.bigdata.test.cn,16020,1507703886465 reported a fatal error: ABORTING region server slave1.bigdata.test.cn,16020,1507703886465: Failed log close in log roller Cause: org.apache.hadoop.hbase.regionserver.wal.FailedLogCloseException: hdfs://zebra/hbase/WALs/slave1.bigdata.test.cn,16020,1507703886465/slave1.bigdata.test.cn%2C16020%2C1507703886465.default.1516389615103, unflushedEntries=5 at org.apache.hadoop.hbase.regionserver.wal.FSHLog.replaceWriter(FSHLog.java:1056) at org.apache.hadoop.hbase.regionserver.wal.FSHLog.rollWriter(FSHLog.java:756) at org.apache.hadoop.hbase.regionserver.LogRoller.run(LogRoller.java:148) at java.lang.Thread.run(Thread.java:748) Caused by: org.apache.hadoop.hbase.regionserver.wal.FailedSyncBeforeLogCloseException: org.apache.hadoop.hbase.regionserver.wal.DamagedWALException: On sync at org.apache.hadoop.hbase.regionserver.wal.FSHLog$SafePointZigZagLatch.waitSafePoint(FSHLog.java:1968) at org.apache.hadoop.hbase.regionserver.wal.FSHLog.replaceWriter(FSHLog.java:1004) ... 3 more Caused by: org.apache.hadoop.hbase.regionserver.wal.DamagedWALException: On sync at org.apache.hadoop.hbase.regionserver.wal.FSHLog$RingBufferEventHandler.onEvent(FSHLog.java:2165) at org.apache.hadoop.hbase.regionserver.wal.FSHLog$RingBufferEventHandler.onEvent(FSHLog.java:2025) at com.lmax.disruptor.BatchEventProcessor.run(BatchEventProcessor.java:128) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) ... 1 more Caused by: org.apache.hadoop.hbase.regionserver.wal.DamagedWALException: Failed appending 232848742, requesting roll of WAL at org.apache.hadoop.hbase.regionserver.wal.FSHLog$RingBufferEventHandler.append(FSHLog.java:2281) at org.apache.hadoop.hbase.regionserver.wal.FSHLog$RingBufferEventHandler.onEvent(FSHLog.java:2114) ... 5 more Caused by: java.io.IOException: Failed to replace a bad datanode on the existing pipeline due to no more good datanodes being available to try. (Nodes: current=[DatanodeInfoWithStorage[192.168.10.31:50010,DS-01934787-2450-4117-88dd-f6d8eeb10b76,DISK], DatanodeInfoWithStorage[192.168.10.32:50010,DS-7104e3f4-79d7-42ed-b194-2a6574e4d97c,DISK]], original=[DatanodeInfoWithStorage[192.168.10.31:50010,DS-01934787-2450-4117-88dd-f6d8eeb10b76,DISK], DatanodeInfoWithStorage[192.168.10.32:50010,DS-7104e3f4-79d7-42ed-b194-2a6574e4d97c,DISK]]). The current failed datanode replacement policy is DEFAULT, and a client may configure this via 'dfs.client.block.write.replace-datanode-on-failure.policy' in its configuration. at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.findNewDatanode(DFSOutputStream.java:1036) at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.addDatanode2ExistingPipeline(DFSOutputStream.java:1110) at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.setupPipelineForAppendOrRecovery(DFSOutputStream.java:1268) at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.processDatanodeError(DFSOutputStream.java:993) at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.run(DFSOutputStream.java:500)
weixin_35511318 2018-01-29
  • 打赏
  • 举报
回复
2018-01-20T03:56:50 Region server slave2.bigdata.test.cn,16020,1507703886422 reported a fatal error: ABORTING region server slave2.bigdata.test.cn,16020,1507703886422: org.apache.hadoop.hbase.YouAreDeadException: Server REPORT rejected; currently processing slave2.bigdata.test.cn,16020,1507703886422 as dead server at org.apache.hadoop.hbase.master.ServerManager.checkIsDead(ServerManager.java:419) at org.apache.hadoop.hbase.master.ServerManager.regionServerReport(ServerManager.java:324) at org.apache.hadoop.hbase.master.MasterRpcServices.regionServerReport(MasterRpcServices.java:352) at org.apache.hadoop.hbase.protobuf.generated.RegionServerStatusProtos$RegionServerStatusService$2.callBlockingMethod(RegionServerStatusProtos.java:10446) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:2141) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:112) at org.apache.hadoop.hbase.ipc.RpcExecutor$Handler.run(RpcExecutor.java:187) at org.apache.hadoop.hbase.ipc.RpcExecutor$Handler.run(RpcExecutor.java:167) Cause: org.apache.hadoop.hbase.YouAreDeadException: org.apache.hadoop.hbase.YouAreDeadException: Server REPORT rejected; currently processing slave2.bigdata.test.cn,16020,1507703886422 as dead server at org.apache.hadoop.hbase.master.ServerManager.checkIsDead(ServerManager.java:419) at org.apache.hadoop.hbase.master.ServerManager.regionServerReport(ServerManager.java:324) at org.apache.hadoop.hbase.master.MasterRpcServices.regionServerReport(MasterRpcServices.java:352) at org.apache.hadoop.hbase.protobuf.generated.RegionServerStatusProtos$RegionServerStatusService$2.callBlockingMethod(RegionServerStatusProtos.java:10446) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:2141) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:112) at org.apache.hadoop.hbase.ipc.RpcExecutor$Handler.run(RpcExecutor.java:187) at org.apache.hadoop.hbase.ipc.RpcExecutor$Handler.run(RpcExecutor.java:167) at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62) at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) at java.lang.reflect.Constructor.newInstance(Constructor.java:423) at org.apache.hadoop.ipc.RemoteException.instantiateException(RemoteException.java:106) at org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:95) at org.apache.hadoop.hbase.protobuf.ProtobufUtil.getRemoteException(ProtobufUtil.java:334) at org.apache.hadoop.hbase.regionserver.HRegionServer.tryRegionServerReport(HRegionServer.java:1188) at org.apache.hadoop.hbase.regionserver.HRegionServer.run(HRegionServer.java:992) at java.lang.Thread.run(Thread.java:748) Caused by: org.apache.hadoop.hbase.ipc.RemoteWithExtrasException(org.apache.hadoop.hbase.YouAreDeadException): org.apache.hadoop.hbase.YouAreDeadException: Server REPORT rejected; currently processing slave2.bigdata.test.cn,16020,1507703886422 as dead server at org.apache.hadoop.hbase.master.ServerManager.checkIsDead(ServerManager.java:419) at org.apache.hadoop.hbase.master.ServerManager.regionServerReport(ServerManager.java:324) at org.apache.hadoop.hbase.master.MasterRpcServices.regionServerReport(MasterRpcServices.java:352) at org.apache.hadoop.hbase.protobuf.generated.RegionServerStatusProtos$RegionServerStatusService$2.callBlockingMethod(RegionServerStatusProtos.java:10446) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:2141) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:112) at org.apache.hadoop.hbase.ipc.RpcExecutor$Handler.run(RpcExecutor.java:187) at org.apache.hadoop.hbase.ipc.RpcExecutor$Handler.run(RpcExecutor.java:167) at org.apache.hadoop.hbase.ipc.RpcClientImpl.call(RpcClientImpl.java:1225) at org.apache.hadoop.hbase.ipc.AbstractRpcClient.callBlockingMethod(AbstractRpcClient.java:213) at org.apache.hadoop.hbase.ipc.AbstractRpcClient$BlockingRpcChannelImplementation.callBlockingMethod(AbstractRpcClient.java:287) at org.apache.hadoop.hbase.protobuf.generated.RegionServerStatusProtos$RegionServerStatusService$BlockingStub.regionServerReport(RegionServerStatusProtos.java:10871) at org.apache.hadoop.hbase.regionserver.HRegionServer.tryRegionServerReport(HRegionServer.java:1186) ... 2 more 2018-01-20T03:56:51 Region server slave2.bigdata.test.cn,16020,1507703886422 reported a fatal error: ABORTING region server slave2.bigdata.test.cn,16020,1507703886422: Get list of registered region servers Cause: org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired for /hbase-unsecure/rs at org.apache.zookeeper.KeeperException.create(KeeperException.java:127) at org.apache.zookeeper.KeeperException.create(KeeperException.java:51) at org.apache.zookeeper.ZooKeeper.getChildren(ZooKeeper.java:1472) at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.getChildren(RecoverableZooKeeper.java:292) at org.apache.hadoop.hbase.zookeeper.ZKUtil.listChildrenAndWatchForNewChildren(ZKUtil.java:455) at org.apache.hadoop.hbase.zookeeper.ZKUtil.listChildrenAndWatchThem(ZKUtil.java:483) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.getRegisteredRegionServers(ReplicationTrackerZKImpl.java:245) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.refreshOtherRegionServersList(ReplicationTrackerZKImpl.java:226) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.access$400(ReplicationTrackerZKImpl.java:42) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl$OtherRegionServerWatcher.refreshListIfRightPath(ReplicationTrackerZKImpl.java:142) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl$OtherRegionServerWatcher.nodeDeleted(ReplicationTrackerZKImpl.java:117) at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:539) at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534) at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510) 2018-01-20T03:56:51 Region server slave2.bigdata.test.cn,16020,1507703886422 reported a fatal error: ABORTING region server slave2.bigdata.test.cn,16020,1507703886422: regionserver:16020-0x25ec011d2cc0182, quorum=master1.bigdata.test.cn:2181,master3.bigdata.test.cn:2181,master2.bigdata.test.cn:2181, baseZNode=/hbase-unsecure regionserver:16020-0x25ec011d2cc0182 received expired from ZooKeeper, aborting Cause: org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.connectionEvent(ZooKeeperWatcher.java:592) at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:524) at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534) at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510) 2018-01-20T03:56:51 Region server slave2.bigdata.test.cn,16020,1507703886422 reported a fatal error: ABORTING region server slave2.bigdata.test.cn,16020,1507703886422: regionserver:16020-0x25ec011d2cc0182, quorum=master1.bigdata.test.cn:2181,master3.bigdata.test.cn:2181,master2.bigdata.test.cn:2181, baseZNode=/hbase-unsecure regionserver:16020-0x25ec011d2cc0182 received expired from ZooKeeper, aborting Cause: org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.connectionEvent(ZooKeeperWatcher.java:592) at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:524) at org.apache.hadoop.hbase.zookeeper.PendingWatcher.process(PendingWatcher.java:40) at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534) at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510)
weixin_35511318 2018-01-29
  • 打赏
  • 举报
回复
2018-01-20T03:34:33 Region server slave3.bigdata.test.cn,16020,1507703886150 reported a fatal error: ABORTING region server slave3.bigdata.test.cn,16020,1507703886150: Get list of registered region servers Cause: org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired for /hbase-unsecure/rs at org.apache.zookeeper.KeeperException.create(KeeperException.java:127) at org.apache.zookeeper.KeeperException.create(KeeperException.java:51) at org.apache.zookeeper.ZooKeeper.getChildren(ZooKeeper.java:1472) at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.getChildren(RecoverableZooKeeper.java:292) at org.apache.hadoop.hbase.zookeeper.ZKUtil.listChildrenAndWatchForNewChildren(ZKUtil.java:455) at org.apache.hadoop.hbase.zookeeper.ZKUtil.listChildrenAndWatchThem(ZKUtil.java:483) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.getRegisteredRegionServers(ReplicationTrackerZKImpl.java:245) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.refreshOtherRegionServersList(ReplicationTrackerZKImpl.java:226) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl.access$400(ReplicationTrackerZKImpl.java:42) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl$OtherRegionServerWatcher.refreshListIfRightPath(ReplicationTrackerZKImpl.java:142) at org.apache.hadoop.hbase.replication.ReplicationTrackerZKImpl$OtherRegionServerWatcher.nodeDeleted(ReplicationTrackerZKImpl.java:117) at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:539) at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534) at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510) 2018-01-20T03:34:33 Region server slave3.bigdata.test.cn,16020,1507703886150 reported a fatal error: ABORTING region server slave3.bigdata.test.cn,16020,1507703886150: regionserver:16020-0x25ec011d2cc0181, quorum=master1.bigdata.test.cn:2181,master3.bigdata.test.cn:2181,master2.bigdata.test.cn:2181, baseZNode=/hbase-unsecure regionserver:16020-0x25ec011d2cc0181 received expired from ZooKeeper, aborting Cause: org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.connectionEvent(ZooKeeperWatcher.java:592) at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:524) at org.apache.hadoop.hbase.zookeeper.PendingWatcher.process(PendingWatcher.java:40) at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534) at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510) 2018-01-20T03:34:33 Region server slave3.bigdata.test.cn,16020,1507703886150 reported a fatal error: ABORTING region server slave3.bigdata.test.cn,16020,1507703886150: regionserver:16020-0x25ec011d2cc0181, quorum=master1.bigdata.test.cn:2181,master3.bigdata.test.cn:2181,master2.bigdata.test.cn:2181, baseZNode=/hbase-unsecure regionserver:16020-0x25ec011d2cc0181 received expired from ZooKeeper, aborting Cause: org.apache.zookeeper.KeeperException$SessionExpiredException: KeeperErrorCode = Session expired at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.connectionEvent(ZooKeeperWatcher.java:592) at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.process(ZooKeeperWatcher.java:524) at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:534) at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:510) 2018-01-20T03:34:36 Region server slave5.bigdata.test.cn,16020,1507703887266 reported a fatal error: ABORTING region server slave5.bigdata.test.cn,16020,1507703887266: IOE in log roller Cause: java.io.IOException: cannot get log writer at org.apache.hadoop.hbase.wal.DefaultWALProvider.createWriter(DefaultWALProvider.java:374) at org.apache.hadoop.hbase.regionserver.wal.FSHLog.createWriterInstance(FSHLog.java:781) at org.apache.hadoop.hbase.regionserver.wal.FSHLog.rollWriter(FSHLog.java:746) at org.apache.hadoop.hbase.regionserver.LogRoller.run(LogRoller.java:148) at java.lang.Thread.run(Thread.java:748) Caused by: java.io.FileNotFoundException: Parent directory doesn't exist: /hbase/WALs/slave5.bigdata.test.cn,16020,1507703887266 at org.apache.hadoop.hdfs.server.namenode.FSDirectory.verifyParentDir(FSDirectory.java:1979) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInternal(FSNamesystem.java:2739) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInt(FSNamesystem.java:2671) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:2555) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.create(NameNodeRpcServer.java:735) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.create(ClientNamenodeProtocolServerSideTranslatorPB.java:408) at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java) at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:640) at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:982) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2351) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2347) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1866) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2345) 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:106) at org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:73) at org.apache.hadoop.hdfs.DFSOutputStream.newStreamForCreate(DFSOutputStream.java:1804) at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1701) at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1670) at org.apache.hadoop.hdfs.DistributedFileSystem$9.doCall(DistributedFileSystem.java:527) at org.apache.hadoop.hdfs.DistributedFileSystem$9.doCall(DistributedFileSystem.java:523) at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81) at org.apache.hadoop.hdfs.DistributedFileSystem.createNonRecursive(DistributedFileSystem.java:523) at org.apache.hadoop.fs.FileSystem.createNonRecursive(FileSystem.java:1134) at org.apache.hadoop.fs.FileSystem.createNonRecursive(FileSystem.java:1110) at org.apache.hadoop.hbase.regionserver.wal.ProtobufLogWriter.init(ProtobufLogWriter.java:90) at org.apache.hadoop.hbase.wal.DefaultWALProvider.createWriter(DefaultWALProvider.java:363) ... 4 more Caused by: org.apache.hadoop.ipc.RemoteException(java.io.FileNotFoundException): Parent directory doesn't exist: /hbase/WALs/slave5.bigdata.test.cn,16020,1507703887266 at org.apache.hadoop.hdfs.server.namenode.FSDirectory.verifyParentDir(FSDirectory.java:1979) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInternal(FSNamesystem.java:2739) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInt(FSNamesystem.java:2671) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:2555) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.create(NameNodeRpcServer.java:735) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.create(ClientNamenodeProtocolServerSideTranslatorPB.java:408) at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java) at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:640) at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:982) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2351) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2347) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1866) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2345) at org.apache.hadoop.ipc.Client.getRpcResponse(Client.java:1554) at org.apache.hadoop.ipc.Client.call(Client.java:1498) at org.apache.hadoop.ipc.Client.call(Client.java:1398) at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:233) at com.sun.proxy.$Proxy16.create(Unknown Source) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.create(ClientNamenodeProtocolTranslatorPB.java:313) at sun.reflect.GeneratedMethodAccessor4.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:291) at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:203) at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:185) at com.sun.proxy.$Proxy17.create(Unknown Source) at sun.reflect.GeneratedMethodAccessor4.invoke(Unknown Source) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at org.apache.hadoop.hbase.fs.HFileSystem$1.invoke(HFileSystem.java:283) at com.sun.proxy.$Proxy18.create(Unknown Source) at org.apache.hadoop.hdfs.DFSOutputStream.newStreamForCreate(DFSOutputStream.java:1799) ... 14 more

20,807

社区成员

发帖
与我相关
我的任务
社区描述
Hadoop生态大数据交流社区,致力于有Hadoop,hive,Spark,Hbase,Flink,ClickHouse,Kafka,数据仓库,大数据集群运维技术分享和交流等。致力于收集优质的博客
社区管理员
  • 分布式计算/Hadoop社区
  • 涤生大数据
加入社区
  • 近7日
  • 近30日
  • 至今
社区公告
暂无公告

试试用AI创作助手写篇文章吧