Docker 安装Hadoop HDFS命令行操作

网上拉取Docker模板，使用singlarities/hadoop镜像

[root@localhost /]# docker pull singularities/hadoop

查看：

[root@localhost /]# docker image ls
REPOSITORY                       TAG                 IMAGE ID            CREATED             SIZE
docker.io/singularities/hadoop   latest              e213c9ae1b36         months ago        1.19 GB

创建docker-compose.yml文件，内容：

version: ""

services:
  namenode:
    image: singularities/hadoop
    command: start-hadoop namenode
    hostname: namenode
    environment:
      HDFS_USER: hdfsuser
    ports:
      - "8020:8020"
      - "14000:14000"
      - "50070:50070"
      - "50075:50075"
      - "10020:10020"
      - "13562:13562"
      - "19888:19888"
  datanode:
    image: singularities/hadoop
    command: start-hadoop datanode namenode
    environment:
      HDFS_USER: hdfsuser
    links:
      - namenode

执行：

[root@localhost hadoop]# docker-compose up -d
Creating network "hadoop_default" with the default driver
Creating hadoop_namenode_1 ... done
Creating hadoop_datanode_1 ... done

4个datanode:

[root@localhost hadoop]# docker-compose scale datanode=
WARNING: The scale command is deprecated. Use the up command with the --scale flag instead.
Starting hadoop_datanode_1 ... done
Creating hadoop_datanode_2 ... done
Creating hadoop_datanode_3 ... done
[root@localhost hadoop]# docker ps
CONTAINER ID        IMAGE                  COMMAND                  CREATED             STATUS              PORTS                                                                                                                                                                                                                                                 NAMES
19f9685e286f        singularities/hadoop   "start-hadoop data..."    seconds ago      Up  seconds       /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp                                                                                                           hadoop_datanode_3
e96b395f56e3        singularities/hadoop   "start-hadoop data..."    seconds ago      Up  seconds       /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp                                                                                                           hadoop_datanode_2
5a26b1069dbb        singularities/hadoop   "start-hadoop data..."    minutes ago       Up  minutes        /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp, /tcp                                                                                                           hadoop_datanode_1
a8656de09ecc        singularities/hadoop   "start-hadoop name..."    minutes ago       Up  minutes        0.0.0.0:->/tcp, 0.0.0.0:->/tcp, 0.0.0.0:->/tcp, 0.0.0.0:->/tcp, /tcp, /tcp, 0.0.0.0:->/tcp, 0.0.0.0:->/tcp, /tcp, /tcp, /tcp, 0.0.0.0:->/tcp, /tcp   hadoop_namenode_1
[root@localhost hadoop]# 

效果图；

hdfs基础命令：

1、创建目录

hadoop fs -mkdir /hdfs #在根目录下创建hdfs文件夹

2、查看目录

>hadoop fs -ls / #列出跟目录下的文件列表
drwxr-xr-x   - root supergroup           -- : /hdfs

3、级联创建目录

>hadoop fs -mkdir -p /hdfs/d1/d2

4、级联列出目录

>hadoop fs -ls -R /
drwxr-xr-x   - root supergroup           -- : /hdfs
drwxr-xr-x   - root supergroup           -- : /hdfs/d1
drwxr-xr-x   - root supergroup           -- : /hdfs/d1/d2

5、上传本地文件到HDFS

>echo "hello hdfs" >>local.txt
>hadoop fs -put local.txt /hdfs/d1/d2

6、查看HDFS中文件的内容

>hadoop fs -cat /hdfs/d1/d2/local.txt
hello hdfs

7、下载hdfs上文件的内容

>hadoop fs -get /hdfs/d1/d2/local.txt

8、删除hdfs文件

>hadoop fs -rm /hdfs/d1/d2/local.txt
Deleted /hdfs/d1/d2/local.txt

9、删除hdfs中目录

>hadoop fs -rmdir /hdfs/d1/d2

10、修改文件的权限

>hadoop fs -ls /hdfs
drwxr-xr-x   - root supergroup           -- : /hdfs/d1 #注意文件的权限
>hadoop fs -chmod  /hdfs/d1
drwxrwxrwx   - root supergroup           -- : /hdfs/d1 #修改后

11、修改文件所属的用户

>hadoop fs -chown admin /hdfs/d1 #修改文件所属用户为admin
>hadoop fs -ls /hdfs
drwxrwxrwx   - admin supergroup           -- : /hdfs/d1

12、修改文件的用户组

>hadoop fs -chgrp admin /hdfs/d1
>hadoop fs -ls /hdfs
drwxrwxrwx   - admin admin           -- : /hdfs/d1

查看所有命令方式：


root@master:/# hadoop fs
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] [-d] <localsrc> ... <dst>]
    [-copyToLocal [-f] [-p] [-ignoreCrc] [-crc] <src> ... <localdst>]
    [-count [-q] [-h] [-v] [-t [<storage type>]] [-u] [-x] <path> ...]
    [-cp [-f] [-p | -p[topax]] [-d] <src> ... <dst>]
    [-createSnapshot <snapshotDir> [<snapshotName>]]
    [-deleteSnapshot <snapshotDir> <snapshotName>]
    [-df [-h] [<path> ...]]
    [-du [-s] [-h] [-x] <path> ...]
    [-expunge]
    [-find <path> ... <expression> ...]
    [-get [-f] [-p] [-ignoreCrc] [-crc] <src> ... <localdst>]
    [-getfacl [-R] <path>]
    [-getfattr [-R] {-n name | -d} [-e en] <path>]
    [-getmerge [-nl] [-skip-empty-file] <src> <localdst>]
    [-help [cmd ...]]
    [-ls [-C] [-d] [-h] [-q] [-R] [-t] [-S] [-r] [-u] [<path> ...]]
    [-mkdir [-p] <path> ...]
    [-moveFromLocal <localsrc> ... <dst>]
    [-moveToLocal <src> <localdst>]
    [-mv <src> ... <dst>]
    [-put [-f] [-p] [-l] [-d] <localsrc> ... <dst>]
    [-renameSnapshot <snapshotDir> <oldName> <newName>]
    [-rm [-f] [-r|-R] [-skipTrash] [-safely] <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> ...]
    [-truncate [-w] <length> <path> ...]
    [-usage [cmd ...]]

Generic options supported are
-conf <configuration file>     specify an application configuration file
-D <property=value>            use value for given property
-fs <file:///|hdfs://namenode:port> specify default filesystem URL to use, overrides 'fs.defaultFS' property from configurations.
-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
command [genericOptions] [commandOptions]

进入一个容器内部进行上述操作，再进入其他的容器，可以发现数据同步了，另外一个节点的操作其他节点也可以看见。

参考：

https://github.com/SingularitiesCR/hadoop-docker

http://www.tianshouzhi.com/api/tutorials/hadoop/129