搭建分布式HDFS分布式文件系统

最新推荐文章于 2022-09-15 15:28:34 发布

熊国强

最新推荐文章于 2022-09-15 15:28:34 发布

阅读量356

点赞数

本文链接：https://blog.csdn.net/weixin_43181843/article/details/83550070

版权

一、安装Hadoop
**:hadoop集群：不同主机不同角色配置一样
禁用selinux,关闭firewall

单机模式安装Hadoop
安装JAVA环境设置环境变量
启动运行
在这里插入图片描述
1.安装java环境
四台机器配置主机名为nn01、node1、node2、node3，配置ip地址（ip如上图所示），yum源（系统源）

[root@nn01 ~]# yum -y install java-1.8.0-openjdk-devel
[root@nn01 ~]# java -version
openjdk version "1.8.0_131"
OpenJDK Runtime Environment (build 1.8.0_131-b12)
OpenJDK 64-Bit Server VM (build 25.131-b12, mixed mode)
[root@nn01 ~]# jps   //查看进程id 
1235 Jps

3）安装hadoop

[root@nn01 ~]# tar -xf hadoop-2.7.6.tar.gz
[root@nn01 ~]# mv hadoop-2.7.6 /usr/local/hadoop
[root@nn01 ~]# cd /usr/local/hadoop/
[root@nn01 hadoop]# ls
bin include libexec     NOTICE.txt sbin
etc lib LICENSE.txt README.txt share
[root@nn01 hadoop]# ./bin/hadoop       //报错，JAVA_HOME没有找到,hadoop必须安装openjdk
Error: JAVA_HOME is not set and could not be found

4）解决报错问题

]# rpm -ql java-1.8.0-openjdk   //找到openjdk安装路径
[root@nn01 hadoop]# cd ./etc/hadoop/
[root@nn01 hadoop]# vim hadoop-env.sh   //hadoop运行的环境变量
25行 export \ 
JAVA_HOME="/usr/lib/jvm/java-1.8.0-openjdk-1.8.0.131-11.b12.el7.x86_64/jre"    //指明openjdk安装路径

33行 export HADOOP_CONF_DIR="/usr/local/hadoop/etc/hadoop"  //配置文件的路径
[root@nn01 ~]# cd /usr/local/hadoop/
[root@nn01 hadoop]# ./bin/hadoop
Usage: hadoop [--config confdir] [COMMAND | CLASSNAME]
CLASSNAME run the class named CLASSNAME
or
where COMMAND is one of:
fs run a generic filesystem user client
version print the version
jar <jar> run a jar file
note: please use "yarn jar" to launch
YARN applications, not this command.
checknative [-a|-h] check native hadoop and compression libraries availability
distcp <srcurl> <desturl> copy file or directories recursively
archive -archiveName NAME -p <parent path> <src>* <dest> create a hadoop archive
classpath prints the class path needed to get the
credential interact with credential providers
Hadoop jar and the required libraries
daemonlog get/set the log level for each daemon
trace view and modify Hadoop tracing settings
Most commands print help when invoked w/o parameters.

[root@nn01 hadoop]# mkdir /usr/local/hadoop/aa
[root@nn01 hadoop]# ls
bin etc include lib libexec LICENSE.txt NOTICE.txt aa README.txt sbin share
[root@nn01 hadoop]# cp *.txt /usr/local/hadoop/aa
[root@nn01 hadoop]# ./bin/hadoop jar \
share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.6.jar wordcount aa bb     //wordcount为参数 统计aa这个文件夹，存到bb这个文件里面（这个文件不能存在，要是存在会报错，是为了防止数据覆盖）
[root@nn01 hadoop]# cat bb/part-r-00000 //查看

二、配置Hadoop
5)编辑/etc/hosts（四台主机同样操作，以nn01为例）

[root@nn01 ~]# vim /etc/hosts
192.168.1.21 nn01
192.168.1.22 node1
192.168.1.23 node2
192.168.1.24 node3

6）安装java环境，在node1，node2，node3上面操作（以node1为例）
[root@node1 ~]# yum -y install java-1.8.0-openjdk-devel
7）布置SSH信任关系

[root@nn01 ~]# vim /etc/ssh/ssh_config    //第一次登陆不需要输入yes
Host *
        GSSAPIAuthentication yes
        StrictHostKeyChecking no
[root@nn01 .ssh]# ssh-keygen
Generating public/private rsa key pair.
Enter file in which to save the key (/root/.ssh/id_rsa): 
Enter passphrase (empty for no passphrase): 
Enter same passphrase again: 
Your identification has been saved in /root/.ssh/id_rsa.
Your public key has been saved in /root/.ssh/id_rsa.pub.
The key fingerprint is:
SHA256:Ucl8OCezw92aArY5+zPtOrJ9ol1ojRE3EAZ1mgndYQM root@nn01
The key's randomart image is:
+---[RSA 2048]----+
|        o*E*=.   |
|         +XB+.   |
|        ..=Oo.   |
|        o.+o...  |
|       .S+.. o   |
|        + .=o    |
|         o+oo    |
|        o+=.o    |
|        o==O.    |
+----[SHA256]-----+
[root@nn01 .ssh]# for i in 21 22 23 24 ; do  ssh-copy-id  192.168.1.$i; done   
//部署公钥给nn01，node1，node2，node3

8）测试信任关系

[root@nn01 .ssh]# ssh node1
Last login: Fri Sep 7 16:52:00 2018 from 192.168.1.21
[root@node1 ~]# exit
logout
Connection to node1 closed.
[root@nn01 .ssh]# ssh node2
Last login: Fri Sep 7 16:52:05 2018 from 192.168.1.21
[root@node2 ~]# exit
logout
Connection to node2 closed.
[root@nn01 .ssh]# ssh node3

9）修改slaves文件

[root@nn01 ~]# cd  /usr/local/hadoop/etc/hadoop
[root@nn01 hadoop]# vim slaves
node1
node2
node3

10）hadoop的核心配置文件core-site

[root@nn01 hadoop]# vim core-site.xml
<configuration>
<property>
        <name>fs.defaultFS</name>
        <value>hdfs://nn01:9000</value>   //使用hdfs文件系统
    </property>
    <property>
        <name>hadoop.tmp.dir</name>   
        <value>/var/hadoop</value>        //分布式文件系统的数据根目录
    </property>
</configuration>

[root@nn01 hadoop]# mkdir /var/hadoop        //hadoop的数据根目录
[root@nn01 hadoop]# ssh node1 mkdir /var/hadoop
[root@nn01 hadoop]# ssh node2 mkdir /var/hadoop
[root@nn01 hadoop]# ssh node3 mkdir /var/hadoop

11）配置hdfs-site文件

[root@nn01 hadoop]# vim hdfs-site.xml    
<configuration>
 <property>
        <name>dfs.namenode.http-address</name>
        <value>nn01:50070</value>  //声明namenode的位置
    </property>
    <property>
        <name>dfs.namenode.secondary.http-address</name>
        <value>nn01:50090</value>    //声明secondary namenode的位置
    </property>
    <property>
        <name>dfs.replication</name>   
        <value>2</value>               //数字表示数据存几份
    </property>
</configuration>

12）同步配置到node1，node2，node3

[root@nn01 hadoop]# yum –y install rsync //同步的主机都要安装rsync

[root@nn01 hadoop]# yum –y install rsync  //同步的主机都要安装rsync
[root@nn01 hadoop]# for i in 22 23 24 ; do rsync -aSH --delete /usr/local/hadoop/ 
\   192.168.1.$i:/usr/local/hadoop/  -e 'ssh' & done
[1] 23260
[2] 23261
[3] 23262

三、格式化，并查看集群是否成功
13）查看是否同步成功

[root@nn01 hadoop]# ssh node1 ls /usr/local/hadoop/
bin
etc
include
lib
libexec
LICENSE.txt
NOTICE.txt
bb
README.txt
sbin
share
aa
[root@nn01 hadoop]# ssh node2 ls /usr/local/hadoop/
bin
etc
include
lib
libexec
LICENSE.txt
NOTICE.txt
bb
README.txt
sbin
share
aa
[root@nn01 hadoop]# ssh node3 ls /usr/local/hadoop/
bin
etc
include
lib
libexec
LICENSE.txt
NOTICE.txt
bb
README.txt
sbin
share
aa

14)格式化

[root@nn01 hadoop]# cd /usr/local/hadoop/
[root@nn01 hadoop]# ./bin/hdfs namenode -format         //格式化 namenode
[root@nn01 hadoop]# ./sbin/start-dfs.sh        //启动
[root@nn01 hadoop]# jps        //验证角色
23408 NameNode
23700 Jps
23591 SecondaryNameNode
[root@nn01 hadoop]# ./bin/hdfs dfsadmin -report        //查看集群是否组建成功
Live datanodes (3):        //有三个角色成功

15）排错：
如查看集群不成功，启动datanode启动之后在/usr/local/hadoop/的目录之下有一log目录，可查看相关日志进行排错