因磁盘空间不足，内存不足，系统掉电，删除节点等等原因导致block损坏，dataNode丢失。系统自动进入安全模式。并出现如下异常信息：
2018-12-07 10:10:52 WARN Client:87 - Failed to cleanup staging dir hdfs://master:9000/user/root/.sparkStaging/application_1544148219961_0001 org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.hdfs.server.namenode.SafeModeException): Cannot delete /user/root/.sparkStaging/application_1544148219961_0001. Name node is in safe mode. The reported blocks 38 needs additional 26 blocks to reach the threshold 0.9990 of total blocks 64. The number of live datanodes 4 has reached the minimum number 0. Safe mode will be turned off automatically once the thresholds have been reached. at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkNameNodeSafeMode(FSNamesystem.java:1335) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.delete(FSNamesystem.java:3689) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.delete(NameNodeRpcServer.java:953) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.delete(ClientNamenodeProtocolServerSideTranslatorPB.java:623) 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:982) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2217) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2213) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1762) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2211) 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$Invoker.invoke(ProtobufRpcEngine.java:229) at com.sun.proxy.$Proxy10.delete(Unknown Source) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.delete(ClientNamenodeProtocolTranslatorPB.java:540) 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:191) at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102) at com.sun.proxy.$Proxy11.delete(Unknown Source) at org.apache.hadoop.hdfs.DFSClient.delete(DFSClient.java:2044) at org.apache.hadoop.hdfs.DistributedFileSystem$14.doCall(DistributedFileSystem.java:707) at org.apache.hadoop.hdfs.DistributedFileSystem$14.doCall(DistributedFileSystem.java:703) at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81) at org.apache.hadoop.hdfs.DistributedFileSystem.delete(DistributedFileSystem.java:714) at org.apache.spark.deploy.yarn.Client.org$apache$spark$deploy$yarn$Client$$cleanupStagingDirInternal$1(Client.scala:200) at org.apache.spark.deploy.yarn.Client.cleanupStagingDir(Client.scala:217) at org.apache.spark.deploy.yarn.Client.submitApplication(Client.scala:182) at org.apache.spark.deploy.yarn.Client.run(Client.scala:1146) at org.apache.spark.deploy.yarn.YarnClusterApplication.start(Client.scala:1518) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:879) at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:197) at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:227) at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:136) at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala) Exception in thread "main" org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.hdfs.server.namenode.SafeModeException): Cannot create directory /user/root/.sparkStaging/application_1544148219961_0001. Name node is in safe mode. The reported blocks 38 needs additional 26 blocks to reach the threshold 0.9990 of total blocks 64. The number of live datanodes 4 has reached the minimum number 0. Safe mode will be turned off automatically once the thresholds have been reached. at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkNameNodeSafeMode(FSNamesystem.java:1335) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.mkdirs(FSNamesystem.java:3874) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.mkdirs(NameNodeRpcServer.java:984) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.mkdirs(ClientNamenodeProtocolServerSideTranslatorPB.java:634) at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$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:982) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2217) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2213) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1762) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2211) 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$Invoker.invoke(ProtobufRpcEngine.java:229) at com.sun.proxy.$Proxy10.mkdirs(Unknown Source) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.mkdirs(ClientNamenodeProtocolTranslatorPB.java:558) 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:191) at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102) at com.sun.proxy.$Proxy11.mkdirs(Unknown Source) at org.apache.hadoop.hdfs.DFSClient.primitiveMkdir(DFSClient.java:3000) at org.apache.hadoop.hdfs.DFSClient.mkdirs(DFSClient.java:2970) at org.apache.hadoop.hdfs.DistributedFileSystem$21.doCall(DistributedFileSystem.java:1047) at org.apache.hadoop.hdfs.DistributedFileSystem$21.doCall(DistributedFileSystem.java:1043) at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81) at org.apache.hadoop.hdfs.DistributedFileSystem.mkdirsInternal(DistributedFileSystem.java:1061) at org.apache.hadoop.hdfs.DistributedFileSystem.mkdirs(DistributedFileSystem.java:1036) at org.apache.hadoop.fs.FileSystem.mkdirs(FileSystem.java:1881) at org.apache.hadoop.fs.FileSystem.mkdirs(FileSystem.java:600) at org.apache.spark.deploy.yarn.Client.prepareLocalResources(Client.scala:429) at org.apache.spark.deploy.yarn.Client.createContainerLaunchContext(Client.scala:863) at org.apache.spark.deploy.yarn.Client.submitApplication(Client.scala:169) at org.apache.spark.deploy.yarn.Client.run(Client.scala:1146) at org.apache.spark.deploy.yarn.YarnClusterApplication.start(Client.scala:1518) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:879) at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:197) at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:227) at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:136) at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
解决方法：
1.执行命令退出安全模式：
hadoop dfsadmin -safemode leave
2.执行健康检查，删除损坏掉的block。
hdfs fsck / -delete
注意: 这种方式会出现数据丢失，损坏的block会被删掉
