HDFS常用命令整理

简介：

• HDFS 文件系统提供了相当多的shell 操作命令，大大方便了程序员和系统管理人员查看、修改HDFS 上的文件。进一步，HDFS 的操作命令和Unix/Linux 的命令名称和格式相当一致，因而学习HDFS 命令的成本也大为缩小。

1.命令帮助

[hadoop@hadoop000 ~]$ hdfs dfsUsage: hadoop fs [generic options]        [-appendToFile  ... ]        [-cat [-ignoreCrc]  ...]        [-checksum  ...]        [-chgrp [-R] GROUP PATH...]        [-chmod [-R]  PATH...]        [-chown [-R] [OWNER][:[GROUP]] PATH...]        [-copyFromLocal [-f] [-p] [-l] [-d]  ... ]        [-copyToLocal [-f] [-p] [-ignoreCrc] [-crc]  ... ]        [-count [-q] [-h] [-v] [-t []] [-u] [-x]  ...]        [-cp [-f] [-p | -p[topax]] [-d]  ... ]        [-createSnapshot  []]        [-deleteSnapshot  ]        [-df [-h] [ ...]]        [-du [-s] [-h] [-x]  ...]        [-expunge]        [-find  ...  ...]        [-get [-f] [-p] [-ignoreCrc] [-crc]  ... ]        [-getfacl [-R] ]        [-getfattr [-R] {-n name | -d} [-e en] ]        [-getmerge [-nl] [-skip-empty-file]  ]        [-help [cmd ...]]        [-ls [-C] [-d] [-h] [-q] [-R] [-t] [-S] [-r] [-u] [ ...]]        [-mkdir [-p]  ...]        [-moveFromLocal  ... ]        [-moveToLocal  ]        [-mv  ... ]        [-put [-f] [-p] [-l] [-d]  ... ]        [-renameSnapshot   ]        [-rm [-f] [-r|-R] [-skipTrash] [-safely]  ...]        [-rmdir [--ignore-fail-on-non-empty]  ...]        [-setfacl [-R] [{-b|-k} {-m|-x } ]|[--set  ]]        [-setfattr {-n name [-v value] | -x name} ]        [-setrep [-R] [-w]   ...]        [-stat [format]  ...]        [-tail [-f] ]        [-test -[defsz] ]        [-text [-ignoreCrc]  ...]        [-touchz  ...]        [-truncate [-w]   ...]        [-usage [cmd ...]]# 注：hdfs dfs等同于hadoop fs

2.文件操作命令案例

hdfs dfs -copyFromLocal /local/data /hdfs/data：将本地文件上传到 hdfs 上（原路径只能是一个文件）
hdfs dfs -put /tmp/ /hdfs/ ：和 copyFromLocal 区别是，put 原路径可以是文件夹等
hadoop fs -ls / ：查看根目录文件
hadoop fs -ls /tmp/data：查看/tmp/data目录
hadoop fs -cat /tmp/a.txt ：查看 a.txt，与 -text 一样
hadoop fs -mkdir dir：创建目录dir
hadoop fs -get /aaa/jdk.tar.gz :等同于copyToLocal，就是从hdfs下载文件到本地
hadoop fs -df -h / :统计文件系统的可用空间信息
hadoop fs -cp /aaa/jdk.tar.gz /bbb/jdk.tar.gz.2 :从hdfs的一个路径拷贝hdfs的另一个路径
hadoop fs -mv /aaa/jdk.tar.gz / :在hdfs目录中移动文件
hadoop fs -du -s -h /aaa/* :统计文件夹的大小信息
hadoop fs -rm -r /aaa/bbb/ :删除文件或文件夹
hadoop fs -rmdir /aaa/bbb/ccc :删除目录
hadoop fs -tail /weblog/access_log.1 :显示一个文件的末尾

3.管理命令

# 命令帮助[hadoop@hadoop000 ~]$ hdfs dfsadminUsage: hdfs dfsadminNote: Administrative commands can only be run as the HDFS superuser.        [-report [-live] [-dead] [-decommissioning]]        [-safemode ]        [-saveNamespace]        [-rollEdits]        [-restoreFailedStorage true|false|check]        [-refreshNodes]        [-setQuota  ...]        [-clrQuota ...]        [-setSpaceQuota  [-storageType ] ...]        [-clrSpaceQuota [-storageType ] ...]        [-finalizeUpgrade]        [-rollingUpgrade []]        [-refreshServiceAcl]        [-refreshUserToGroupsMappings]        [-refreshSuperUserGroupsConfiguration]        [-refreshCallQueue]        [-refresh   [arg1..argn]        [-reconfig   ]        [-printTopology]        [-refreshNamenodes datanode_host:ipc_port]        [-deleteBlockPool datanode_host:ipc_port blockpoolId [force]]        [-setBalancerBandwidth ]        [-getBalancerBandwidth ]        [-fetchImage ]        [-allowSnapshot ]        [-disallowSnapshot ]        [-shutdownDatanode  [upgrade]]        [-evictWriters ]        [-getDatanodeInfo ]        [-metasave filename]        [-triggerBlockReport [-incremental] ]        [-help [cmd]]

hdfs dfsadmin -report :显示所有dataNode
hdfs dfsadmin -safemode leave :离开安全模式