1.datanode起不来
2016-11-25 09:46:43,685 WARN org.apache.hadoop.hdfs.server.datanode.DataNode: Invalid dfs.datanode.data.dir /home/hadoop3/hadoop_data/data :
org.apache.hadoop.util.DiskChecker$DiskErrorException: Directory is not writable: /home/hadoop3/hadoop_data/data
at org.apache.hadoop.util.DiskChecker.checkAccessByFileMethods(DiskChecker.java:193)
at org.apache.hadoop.util.DiskChecker.checkDirAccess(DiskChecker.java:174)
at org.apache.hadoop.util.DiskChecker.checkDir(DiskChecker.java:157)
at org.apache.hadoop.hdfs.server.datanode.DataNode$DataNodeDiskChecker.checkDir(DataNode.java:2272)
at org.apache.hadoop.hdfs.server.datanode.DataNode.checkStorageLocations(DataNode.java:2314)
at org.apache.hadoop.hdfs.server.datanode.DataNode.makeInstance(DataNode.java:2296)
at org.apache.hadoop.hdfs.server.datanode.DataNode.instantiateDataNode(DataNode.java:2188)
at org.apache.hadoop.hdfs.server.datanode.DataNode.createDataNode(DataNode.java:2235)
at org.apache.hadoop.hdfs.server.datanode.DataNode.secureMain(DataNode.java:2411)
at org.apache.hadoop.hdfs.server.datanode.DataNode.main(DataNode.java:2435)
java.io.IOException: BlockPoolSliceStorage.recoverTransitionRead: attempt to load an used block storage: /home/hdmaster/hadoop_data/data/current/BP-994368505-192.168.30.223-1441944900262
at org.apache.hadoop.hdfs.server.datanode.BlockPoolSliceStorage.loadBpStorageDirectories(BlockPoolSliceStorage.java:210)
at org.apache.hadoop.hdfs.server.datanode.BlockPoolSliceStorage.recoverTransitionRead(BlockPoolSliceStorage.java:242)
at org.apache.hadoop.hdfs.server.datanode.DataStorage.addStorageLocations(DataStorage.java:391)
at org.apache.hadoop.hdfs.server.datanode.DataStorage.recoverTransitionRead(DataStorage.java:472)
at org.apache.hadoop.hdfs.server.datanode.DataNode.initStorage(DataNode.java:1322)
at org.apache.hadoop.hdfs.server.datanode.DataNode.initBlockPool(DataNode.java:1292)
at org.apache.hadoop.hdfs.server.datanode.BPOfferService.verifyAndSetNamespaceInfo(BPOfferService.java:321)
at org.apache.hadoop.hdfs.server.datanode.BPServiceActor.connectToNNAndHandshake(BPServiceActor.java:225)
at org.apache.hadoop.hdfs.server.datanode.BPServiceActor.run(BPServiceActor.java:862)
at java.lang.Thread.run(Thread.java:745)
2016-11-25 09:27:18,795 WARN org.apache.hadoop.hdfs.server.common.Storage: Failed to add storage for block pool: BP-994368505-192.168.30.223-1441944900262 : BlockPoolSliceStorage.recoverTransitionRead: attempt to load an used block storage: /home/hdmaster/hadoop_data/data/current/BP-994368505-192.168.30.223-1441944900262
2016-11-25 09:27:18,795 INFO org.apache.hadoop.hdfs.server.common.Storage: Storage directory [DISK]file:/home/hadoop1/hadoop_data/data/ has already been used.
2016-11-25 09:27:18,818 INFO org.apache.hadoop.hdfs.server.common.Storage: Analyzing storage directories for bpid BP-994368505-192.168.30.223-1441944900262
2016-11-25 09:27:18,818 WARN org.apache.hadoop.hdfs.server.common.Storage: Failed to analyze storage directories for block pool BP-994368505-192.168.30.223-1441944900262
java.io.IOException: BlockPoolSliceStorage.recoverTransitionRead: attempt to load an used block storage: /home/hadoop1/hadoop_data/data/current/BP-994368505-192.168.30.223-1441944900262
at org.apache.hadoop.hdfs.server.datanode.BlockPoolSliceStorage.loadBpStorageDirectories(BlockPoolSliceStorage.java:210)
at org.apache.hadoop.hdfs.server.datanode.BlockPoolSliceStorage.recoverTransitionRead(BlockPoolSliceStorage.java:242)
at org.apache.hadoop.hdfs.server.datanode.DataStorage.addStorageLocations(DataStorage.java:391)
at org.apache.hadoop.hdfs.server.datanode.DataStorage.recoverTransitionRead(DataStorage.java:472)
at org.apache.hadoop.hdfs.server.datanode.DataNode.initStorage(DataNode.java:1322)
at org.apache.hadoop.hdfs.server.datanode.DataNode.initBlockPool(DataNode.java:1292)
at org.apache.hadoop.hdfs.server.datanode.BPOfferService.verifyAndSetNamespaceInfo(BPOfferService.java:321)
at org.apache.hadoop.hdfs.server.datanode.BPServiceActor.connectToNNAndHandshake(BPServiceActor.java:225)
at org.apache.hadoop.hdfs.server.datanode.BPServiceActor.run(BPServiceActor.java:862)
at java.lang.Thread.run(Thread.java:745)
2016-11-25 09:27:18,818 WARN org.apache.hadoop.hdfs.server.common.Storage: Failed to add storage for block pool: BP-994368505-192.168.30.223-1441944900262 : BlockPoolSliceStorage.recoverTransitionRead: attempt to load an used block storage: /home/hadoop1/hadoop_data/data/current/BP-994368505-192.168.30.223-1441944900262
2016-11-25 09:27:18,818 INFO org.apache.hadoop.hdfs.server.common.Storage: Storage directory [DISK]file:/home/hadoop2/hadoop_data/data/ has already been used.
2016-11-25 09:27:18,839 INFO org.apache.hadoop.hdfs.server.common.Storage: Analyzing storage directories for bpid BP-994368505-192.168.30.223-1441944900262
2016-11-25 09:27:18,839 WARN org.apache.hadoop.hdfs.server.common.Storage: Failed to analyze storage directories for block pool BP-994368505-192.168.30.223-1441944900262
java.io.IOException: BlockPoolSliceStorage.recoverTransitionRead: attempt to load an used block storage: /home/hadoop2/hadoop_data/data/current/BP-994368505-192.168.30.223-1441944900262
at org.apache.hadoop.hdfs.server.datanode.BlockPoolSliceStorage.loadBpStorageDirectories(BlockPoolSliceStorage.java:210)
at org.apache.hadoop.hdfs.server.datanode.BlockPoolSliceStorage.recoverTransitionRead(BlockPoolSliceStorage.java:242)
at org.apache.hadoop.hdfs.server.datanode.DataStorage.addStorageLocations(DataStorage.java:391)
at org.apache.hadoop.hdfs.server.datanode.DataStorage.recoverTransitionRead(DataStorage.java:472)
at org.apache.hadoop.hdfs.server.datanode.DataNode.initStorage(DataNode.java:1322)
at org.apache.hadoop.hdfs.server.datanode.DataNode.initBlockPool(DataNode.java:1292)
at org.apache.hadoop.hdfs.server.datanode.BPOfferService.verifyAndSetNamespaceInfo(BPOfferService.java:321)
at org.apache.hadoop.hdfs.server.datanode.BPServiceActor.connectToNNAndHandshake(BPServiceActor.java:225)
at org.apache.hadoop.hdfs.server.datanode.BPServiceActor.run(BPServiceActor.java:862)
at java.lang.Thread.run(Thread.java:745)
2016-11-25 09:27:18,840 WARN org.apache.hadoop.hdfs.server.common.Storage: Failed to add storage for block pool: BP-994368505-192.168.30.223-1441944900262 : BlockPoolSliceStorage.recoverTransitionRead: attempt to load an used block storage: /home/hadoop2/hadoop_data/data/current/BP-994368505-192.168.30.223-1441944900262
2016-11-25 09:27:18,840 FATAL org.apache.hadoop.hdfs.server.datanode.DataNode: Initialization failed for Block pool <registering> (Datanode Uuid unassigned) service to namenode01/192.168.30.223:9000. Exiting.
java.io.IOException: All specified directories are failed to load.
at org.apache.hadoop.hdfs.server.datanode.DataStorage.recoverTransitionRead(DataStorage.java:473)
at org.apache.hadoop.hdfs.server.datanode.DataNode.initStorage(DataNode.java:1322)
at org.apache.hadoop.hdfs.server.datanode.DataNode.initBlockPool(DataNode.java:1292)
at org.apache.hadoop.hdfs.server.datanode.BPOfferService.verifyAndSetNamespaceInfo(BPOfferService.java:321)
at org.apache.hadoop.hdfs.server.datanode.BPServiceActor.connectToNNAndHandshake(BPServiceActor.java:225)
at org.apache.hadoop.hdfs.server.datanode.BPServiceActor.run(BPServiceActor.java:862)
at java.lang.Thread.run(Thread.java:745)
2016-11-25 09:27:18,840 FATAL org.apache.hadoop.hdfs.server.datanode.DataNode: Initialization failed for Block pool <registering> (Datanode Uuid unassigned) service to namenode02/192.168.32.124:9000. Exiting.
org.apache.hadoop.util.DiskChecker$DiskErrorException: Too many failed volumes - current valid volumes: 3, volumes configured: 4, volumes failed: 1, volume failures tolerated: 0
at org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetImpl.<init>(FsDatasetImpl.java:247)
at org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetFactory.newInstance(FsDatasetFactory.java:34)
at org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetFactory.newInstance(FsDatasetFactory.java:30)
at org.apache.hadoop.hdfs.server.datanode.DataNode.initStorage(DataNode.java:1335)
at org.apache.hadoop.hdfs.server.datanode.DataNode.initBlockPool(DataNode.java:1292)
at org.apache.hadoop.hdfs.server.datanode.BPOfferService.verifyAndSetNamespaceInfo(BPOfferService.java:321)
at org.apache.hadoop.hdfs.server.datanode.BPServiceActor.connectToNNAndHandshake(BPServiceActor.java:225)
at org.apache.hadoop.hdfs.server.datanode.BPServiceActor.run(BPServiceActor.java:862)
at java.lang.Thread.run(Thread.java:745)
---原因第三块盘坏了
解决步骤1：修复磁盘
[root@hdslave04 ~]# df -h
Filesystem Size Used Avail Use% Mounted on
/dev/mapper/vg_server03-lv_root
50G 27G 20G 58% /
tmpfs 16G 68K 16G 1% /dev/shm
/dev/sda1 477M 59M 393M 13% /boot
/dev/mapper/vg_server03-lv_home
1.8T 1.5T 207G 88% /home
/dev/sdb1 1.8T 1.5T 303G 83% /home/hadoop1
/dev/sdc1 1.8T 1.5T 286G 84% /home/hadoop2
/dev/sdd1 1.8T 1.5T 250G 86% /home/hadoop3
umount /dev/sdd1
如果出现umount: /dev/sdd1: device is busy,
fuser -m /home/hadoop3
kill pid
umount /dev/sdd1
[root@hdslave04 ~]# fsck -y /dev/sdd1
fsck from util-linux-ng 2.17.2
e2fsck 1.41.12 (17-May-2010)
fsck.ext4: 没有那个设备或地址 当尝试打开 /dev/sdd1 时
Possibly non-existent or swap device?
--以上说明磁盘已经损坏
解决步骤2：更换磁盘 Parted工具来实现对GPT磁盘进行分区
参考：http://soft.chinabyte.com/os/447/12439447.shtml
parted /dev/sdd
(parted) mklabel ----创建创建磁盘标签
New disk labeltype? gpt
(parted) p ----查看分区状态
Model: VMware,VMware Virtual S (scsi)
Disk /dev/sde:2000GB
Sector size(logical/physical)： 512B/512B
Partition Table:gpt
Number Start End Size File system Name Flags
(parted) mkpart
Partition name? []? sdd1 ---指定分区名称
File system type? [ext2]ext4 ----指定分区类型
Start? 1 ---指定开始位置
End? 2000GB ---指定结束位置
(parted) P ----显示分区信息
Model: VMware, VMware Virtual S (scsi)
Disk /dev/sde: 2000GB
Sector size (logical/physical)： 512B/512B
Partition Table: gpt
Number Start End Size File system Name Flags
1 17.4kB 2000GB 2000GB sdd1
(parted) Q ---退出
步骤三:格式化最新磁盘
mkfs.ext4 /dev/sdd1
修改fstab挂载最新磁盘
/dev/sdd1 1.8T 1.5T 250G 86% /home/hadoop3
重启
shutdown -r now
步骤四:重启datanode ,nodeManager
sh hadoop-daemon.sh start datanode
sh yarn-daemon.sh start nodemanager
--步骤1附加 死马当活马医看看重启是否
重启服务器看看 shutdown -r now
发现机器卡住了
1.进入Linux单用户模式
执行 root# mount -o remount,rw /
vim /etc/fstab
#/dev/sdd1 1.8T 1.5T 250G 86% /home/hadoop3
2.重启服务器进入系统正常
shutdown -r now