操作hdfs系统

#基本格式
hdfs dfs -[linux命令]
#如hdfs dfs -mkdir  -p /user/root
#上传文件到dfs目录
hdfs dfs -put hadoop-2.6.5.tar.gz /user/root
#指点块大小上传文件，hdfs中不同文件可以按不同块大小存储
hdfs dfs -D dfs.blocksize=1048576 -put test.txt

hdfs存储位置和样式

文件上传后是分块的，基础块大小128M

#文件被存在/var/sxt/hadoop/local/dfs/data/current/BP-984896948-192.168.112.11-1557190945798/current/finalized/subdir0/subdir0
#每个文件块都有一个数据块和一个元数据信息
[root@node01 subdir0]# ll
total 198160
-rw-r--r-- 1 root root 134217728 May  7 09:45 blk_1073741825
-rw-r--r-- 1 root root   1048583 May  7 09:45 blk_1073741825_1001.meta
-rw-r--r-- 1 root root  65417541 May  7 09:45 blk_1073741826
-rw-r--r-- 1 root root    511083 May  7 09:45 blk_1073741826_1002.meta
-rw-r--r-- 1 root root   1048576 May  7 10:00 blk_1073741827
-rw-r--r-- 1 root root      8199 May  7 10:00 blk_1073741827_1003.meta
-rw-r--r-- 1 root root    640405 May  7 10:00 blk_1073741828
-rw-r--r-- 1 root root      5011 May  7 10:00 blk_1073741828_1004.meta

[root@node01 ~]# hdfs dfs
Usage: hadoop fs [generic options]
	[-appendToFile <localsrc> ... <dst>]
	[-cat [-ignoreCrc] <src> ...]
	[-checksum <src> ...]
	[-chgrp [-R] GROUP PATH...]
	[-chmod [-R] <MODE[,MODE]... | OCTALMODE> PATH...]
	[-chown [-R] [OWNER][:[GROUP]] PATH...]
	[-copyFromLocal [-f] [-p] [-l] <localsrc> ... <dst>]
	[-copyToLocal [-p] [-ignoreCrc] [-crc] <src> ... <localdst>]
	[-count [-q] [-h] <path> ...]
	[-cp [-f] [-p | -p[topax]] <src> ... <dst>]
	[-createSnapshot <snapshotDir> [<snapshotName>]]
	[-deleteSnapshot <snapshotDir> <snapshotName>]
	[-df [-h] [<path> ...]]
	[-du [-s] [-h] <path> ...]
	[-expunge]
	[-get [-p] [-ignoreCrc] [-crc] <src> ... <localdst>]
	[-getfacl [-R] <path>]
	[-getfattr [-R] {-n name | -d} [-e en] <path>]
	[-getmerge [-nl] <src> <localdst>]
	[-help [cmd ...]]
	[-ls [-d] [-h] [-R] [<path> ...]]
	[-mkdir [-p] <path> ...]
	[-moveFromLocal <localsrc> ... <dst>]
	[-moveToLocal <src> <localdst>]
	[-mv <src> ... <dst>]
	[-put [-f] [-p] [-l] <localsrc> ... <dst>]
	[-renameSnapshot <snapshotDir> <oldName> <newName>]
	[-rm [-f] [-r|-R] [-skipTrash] <src> ...]
	[-rmdir [--ignore-fail-on-non-empty] <dir> ...]
	[-setfacl [-R] [{-b|-k} {-m|-x <acl_spec>} <path>]|[--set <acl_spec> <path>]]
	[-setfattr {-n name [-v value] | -x name} <path>]
	[-setrep [-R] [-w] <rep> <path> ...]
	[-stat [format] <path> ...]
	[-tail [-f] <file>]
	[-test -[defsz] <path>]
	[-text [-ignoreCrc] <src> ...]
	[-touchz <path> ...]
	[-usage [cmd ...]]

Generic options supported are
-conf <configuration file>     specify an application configuration file
-D <property=value>            use value for given property
-fs <local|namenode:port>      specify a namenode
-jt <local|resourcemanager:port>    specify a ResourceManager
-files <comma separated list of files>    specify comma separated files to be copied to the map reduce cluster
-libjars <comma separated list of jars>    specify comma separated jar files to include in the classpath.
-archives <comma separated list of archives>    specify comma separated archives to be unarchived on the compute machines.

The general command line syntax is
bin/hadoop command [genericOptions] [commandOptions]