CDH5.7Hadoop集群搭建（离线版）

一、安装介质的准备

二、操作系统的准备

三.控制节点的准备步骤

1）安装jdk（首先卸载原有的openJDK）

[root@cdh1~]$ java -version
[root@cdh1~]$ rpm -qa | grep jdk
java-1.7.0-openjdk-1.7.0.75-2.5.4.2.el7_0.x86_64
java-1.7.0-openjdk-headless-1.7.0.75-2.5.4.2.el7_0.x86_64
[root@cdh1~]# yum -y remove java-1.7.0-openjdk-1.7.0.75-2.5.4.2.el7_0.x86_64
[root@cdh1~]# yum -y remove java-1.7.0-openjdk-headless-1.7.0.75-2.5.4.2.el7_0.x86_64
[root@cdh1~]# java -version
bash: /usr/bin/java: No such file or directory
[root@cdh1~]# rpm -ivh jdk-8u101-linux-x64.rpm 
[root@cdh1~]# java -version
java version "1.8.0_101"
Java(TM) SE Runtime Environment (build 1.8.0_101-b13)
Java HotSpot(TM) 64-Bit Server VM (build 25.101-b13, mixed mode)

2）修改NETWORKING，HOSTNAME，hosts（编辑的时候直接把内容添加到对应的

[root@cdh1~]# vi /etc/sysconfig/network
NETWORKING=yes
HOSTNAME=cdh1

[root@cdh1~]# vi /etc/hosts
127.0.0.1 localhost.cdh1
192.168.42.128  cdh1
192.168.42.129  cdh2
192.168.42.130  cdh3

3）selinux关闭，然后机器重启

[root@cdh1~]# vi /etc/sysconfig/selinux
SELINUX=disabled

//重启
[root@cdh1~]#reboot

//重启之后检查是否已经关闭
[root@cdh1~]#sestatus -v
SELinux status: disabled
表示已经关闭了

4）关闭防火墙

[root@cdh1~]# systemctl stop firewalld
[root@cdh1~]# systemctl disable firewalld
rm '/etc/systemd/system/dbus-org.fedoraproject.FirewallD1.service'
rm '/etc/systemd/system/basic.target.wants/firewalld.service'
[root@cdh1~]# systemctl status firewalld
firewalld.service - firewalld - dynamic firewall daemon
   Loaded: loaded (/usr/lib/systemd/system/firewalld.service; disabled)
   Active: inactive (dead)

5）ssh无密码登录配置，在控制节点中去设置各个节点免登录密码

下面以192.168.42.128到192.168.42.129的免密登录设置举例

[root@cdh1 /]# ssh-keygen -t rsa
Generating public/private rsa key pair.
Enter file in which to save the key (/root/.ssh/id_rsa):
/root/.ssh/id_rsa already exists.
Overwrite (y/n)? y
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:
1d:e9:b4:ed:1d:e5:c6:a7:f3:23:ac:02:2b:8c:fc:ca root@cdh1
The key's randomart image is:
+--[ RSA 2048]----+
|                 |
|           .     |
|          +     .|
|         + +   + |
|        S + . . =|
|       .   . . +.|
|  . o   o   o +  |
|  .o o . .   o + |
|   Eo..   ... . o|
+-----------------+
[root@cdh1 /]# ssh-copy-id 192.168.42.129
/usr/bin/ssh-copy-id: INFO: attempting to log in with the new key(s), to filter out any that are already installed
/usr/bin/ssh-copy-id: INFO: 1 key(s) remain to be installed -- if you are prompted now it is to install the new keys
root@192.168.42.129's password:

Number of key(s) added: 1

Now try logging into the machine, with:   "ssh '192.168.42.129'"
and check to make sure that only the key(s) you wanted were added.

6）安装mysql

[root@cdh1 /]# rpm -qa | grep mariadb
mariadb-libs-5.5.41-2.el7_0.x86_64
[root@cdh1 /]# rpm -e --nodeps mariadb-libs-5.5.41-2.el7_0.x86_64
[root@cdh1 /]# tar -xvf  MySQL-5.6.26-1.linux_glibc2.5.x86_64.rpm-bundle.tar   //mysql rpm包拷贝到服务器上然后解压

//在解压出来的rpm按照一下顺序安装，安装语句为 rpm -ivh
/*
mysql-shared
mysql-server
mysql-client
mysql-devel
mysql-shared
*/

[root@cdh1 /]# cp /usr/share/mysql/my-default.cnf /etc/my.cnf 
[root@cdh1 /]# vi /etc/my.cnf    //在配置文件中增加以下配置并保存
[mysqld]
default-storage-engine = innodb
innodb_file_per_table
collation-server = utf8_general_ci
init-connect = 'SET NAMES utf8'
character-set-server = utf8

[root@cdh1 /]# /usr/bin/mysql_install_db   //初始化mysql 
[root@cdh1 /]# service mysql restart       //启动mysql
 ERROR! MySQL server PID file could not be found!
Starting MySQL... SUCCESS! 
[root@cdh1 /]#  cat /root/.mysql_secret    //查看mysql root初始化密码
# The random password set for the root user at Fri Sep 22 11:13:25 2017 (local time): 9mp7uYFmgt6drdq3
[root@cdh1 /]#  mysql -u root -p9mp7uYFmgt6drdq3         //登录进行去更改密码
mysql> SET PASSWORD=PASSWORD('123456');
mysql>use mysql
mysql> update user set host='%' where user='root' and host='localhost';   //允许mysql远程访问
Query OK, 1 row affected (0.05 sec)
Rows matched: 1  Changed: 1  Warnings: 0
mysql> flush privileges;
Query OK, 0 rows affected (0.00 sec)

[root@cdh1 /]#  chkconfig mysql on   //配置开机启动

[root@cdh1 /]# tar -zcvf mysql-connector-java-5.1.44.tar.gz // 解压mysql-connector-java-5.1.44.tar.gz得到mysql-connector-java-5.1.44-bin.jar
[root@cdh1 /]#  mkdir /usr/share/java                          // 在各节点创建java文件夹
[root@cdh1 /]#  cp mysql-connector-java-5.1.44-bin.jar /usr/share/java/mysql-connector-java.jar       //将mysql-connector-java-5.1.44-bin.jar拷贝到/usr/share/java路径下并重命名为mysql-connector-java.jar

创建数据库

create database hive DEFAULT CHARSET utf8 COLLATE utf8_general_ci;
Query OK, 1 row affected (0.00 sec)
create database amon DEFAULT CHARSET utf8 COLLATE utf8_general_ci;
Query OK, 1 row affected (0.00 sec)
create database hue DEFAULT CHARSET utf8 COLLATE utf8_general_ci;
Query OK, 1 row affected (0.00 sec)
 create database monitor DEFAULT CHARSET utf8 COLLATE utf8_general_ci;
Query OK, 1 row affected (0.00 sec)
create database oozie DEFAULT CHARSET utf8 COLLATE utf8_general_ci;
Query OK, 1 row affected (0.00 sec)
grant all on *.* to root@"%" Identified by "123456";

//这些数据库用了cdh集成的选取数据库步骤中使用

7）安装Cloudera-Manager

//解压cm tar包到指定目录所有服务器都要(或者在主节点解压好，然后通过scp到各个节点同一目录下)

[root@cdh1 ~]#mkdir /opt/cloudera-manager
[root@cdh1 ~]# tar -axvf cloudera-manager-centos7-cm5.7.0_x86_64.tar.gz -C /opt/cloudera-manager  

//创建cloudera-scm用户（所有节点）
[root@cdh1 ~]# useradd --system --home=/opt/cloudera-manager/cm-5.7.0/run/cloudera-scm-server --no-create-home --shell=/bin/false --comment "Cloudera SCM User" cloudera-scm  

//在主节点创建cloudera-manager-server的本地元数据保存目录
[root@cdh1 ~]# mkdir /var/cloudera-scm-server
[root@cdh1 ~]# chown cloudera-scm:cloudera-scm /var/cloudera-scm-server
[root@cdh1 ~]# chown cloudera-scm:cloudera-scm /opt/cloudera-manager

//配置从节点cloudera-manger-agent指向主节点服务器
[root@cdh1 ~]# vi /opt/cloudera-manager/cm-5.7.0/etc/cloudera-scm-agent/config.ini
将server_host改为CMS所在的主机名即cdh1

//主节点中创建parcel-repo仓库目录
[root@cdh1 ~]# mkdir -p /opt/cloudera/parcel-repo
[root@cdh1 ~]# chown cloudera-scm:cloudera-scm /opt/cloudera/parcel-repo
[root@cdh1 ~]# cp CDH-5.7.0-1.cdh5.7.0.p0.18-el7.parcel CDH-5.7.0-1.cdh5.7.0.p0.18-el7.parcel.sha manifest.json /opt/cloudera/parcel-repo
注意：其中CDH-5.7.0-1.cdh5.7.0.p0.18-el5.parcel.sha1 后缀要把1去掉

//所有节点创建parcels目录
[root@cdh1 ~]# mkdir -p /opt/cloudera/parcels
[root@cdh1 ~]# chown cloudera-scm:cloudera-scm /opt/cloudera/parcels
解释：Clouder-Manager将CDHs从主节点的/opt/cloudera/parcel-repo目录中抽取出来，分发解压激活到各个节点的/opt/cloudera/parcels目录中


//初始脚本配置数据库scm_prepare_database.sh(在主节点上)
[root@cdh1 ~]# /opt/cloudera-manager/cm-5.7.0/share/cmf/schema/scm_prepare_database.sh mysql -hcdh1 -uroot -p123456 --scm-host cdh1 scmdbn scmdbu scmdbp
说明：这个脚本就是用来创建和配置CMS需要的数据库的脚本。各参数是指：
mysql：数据库用的是mysql，如果安装过程中用的oracle，那么该参数就应该改为oracle。
-cdh1：数据库建立在cdh1主机上面,也就是主节点上面。
-uroot：root身份运行mysql。-123456：mysql的root密码是***。
--scm-host cdh1：CMS的主机，一般是和mysql安装的主机是在同一个主机上,最后三个参数是：数据库名，数据库用户名，数据库密码。

如果报错：
ERROR com.cloudera.enterprise.dbutil.DbProvisioner  - Exception when creating/dropping database with user 'root' and jdbc url 'jdbc:mysql://localhost/?useUnicode=true&characterEncoding=UTF-8'
java.sql.SQLException: Access denied for user 'root'@'cdh1' (using password: YES)

则参考 http://forum.spring.io/forum/spring-projects/web/57254-java-sql-sqlexception-access-denied-for-user-root-localhost-using-password-yes

运行如下命令：

update user set PASSWORD=PASSWORD('123456') where user='root';

GRANT ALL PRIVILEGES ON *.* TO 'root'@'cdh1' IDENTIFIED BY '123456' WITH GRANT OPTION;

FLUSH PRIVILEGES;

//启动主节点
[root@cdh1 ~]# cp /opt/cloudera-manager/cm-5.7.0/etc/init.d/cloudera-scm-server /etc/init.d/cloudera-scm-server
[root@cdh1 ~]# chkconfig cloudera-scm-server on
[root@cdh1 ~]# vi /etc/init.d/cloudera-scm-server
CMF_DEFAULTS=${CMF_DEFAULTS:-/etc/default}改为=/opt/cloudera-manager/cm-5.7.0/etc/default
[root@cdh1 ~]# service cloudera-scm-server start
//同时为了保证在每次服务器重启的时候都能启动cloudera-scm-server，应该在开机启动脚本/etc/rc.local中加入命令：service cloudera-scm-server restart


//启动cloudera-scm-agent所有节点
[root@cdhX ~]# mkdir /opt/cloudera-manager/cm-5.7.0/run/cloudera-scm-agent
[root@cdhX ~]# cp /opt/cloudera-manager/cm-5.7.0/etc/init.d/cloudera-scm-agent /etc/init.d/cloudera-scm-agent
[root@cdhX ~]# chkconfig cloudera-scm-agent on
[root@cdhX ~]# vi /etc/init.d/cloudera-scm-agent
CMF_DEFAULTS=${CMF_DEFAULTS:-/etc/default}改为=/opt/cloudera-manager/cm-5.7.0/etc/default
[root@cdhX ~]# service cloudera-scm-agent start
//同时为了保证在每次服务器重启的时候都能启动cloudera-scm-agent，应该在开机启动脚本/etc/rc.local中加入命令：service cloudera-scm-agent restart

四.数据节点的准备步骤

1）安装jdk，首先卸载原有的openJDK

[root@cdh2~]$ java -version
[root@cdh2~]$ rpm -qa | grep jdk
java-1.7.0-openjdk-1.7.0.75-2.5.4.2.el7_0.x86_64
java-1.7.0-openjdk-headless-1.7.0.75-2.5.4.2.el7_0.x86_64
[root@cdh2~]# yum -y remove java-1.7.0-openjdk-1.7.0.75-2.5.4.2.el7_0.x86_64
[root@cdh2~]# yum -y remove java-1.7.0-openjdk-headless-1.7.0.75-2.5.4.2.el7_0.x86_64
[root@cdh2~]# java -version
bash: /usr/bin/java: No such file or directory
[root@cdh2~]# rpm -ivh jdk-8u101-linux-x64.rpm 
[root@cdh2~]# java -version
java version "1.8.0_101"
Java(TM) SE Runtime Environment (build 1.8.0_101-b13)
Java HotSpot(TM) 64-Bit Server VM (build 25.101-b13, mixed mode)

2）修改NETWORKING，HOSTNAME，hosts（编辑的时候直接把内容添加到对应的）

[root@cdh2~]# vi /etc/sysconfig/network
NETWORKING=yes
HOSTNAME=cdh2

[root@cdh2~]# vi /etc/hosts
127.0.0.1 localhost.cdh2
192.168.42.128  cdh1
192.168.42.129  cdh2
192.168.42.130  cdh3

3）关闭selinux

[root@cdh2~]# vi /etc/sysconfig/selinux
SELINUX=disabled
[root@cdh2~]#sestatus -v
SELinux status: disabled
表示已经关闭了

4）关闭防火墙

[root@cdh1~]# systemctl stop firewalld
[root@cdh1~]# systemctl disable firewalld
rm '/etc/systemd/system/dbus-org.fedoraproject.FirewallD1.service'
rm '/etc/systemd/system/basic.target.wants/firewalld.service'
[root@cdh1~]# systemctl status firewalld
firewalld.service - firewalld - dynamic firewall daemon
   Loaded: loaded (/usr/lib/systemd/system/firewalld.service; disabled)
   Active: inactive (dead)

5）安装Cloudera-Manager

//解压cm tar包到指定目录所有服务器都要(或者在主节点解压好，然后通过scp到各个节点同一目录下)

[root@cdh2 ~]#mkdir /opt/cloudera-manager
[root@cdh2 ~]# tar -axvf cloudera-manager-centos7-cm5.7.2_x86_64.tar.gz -C /opt/cloudera-manager  

//创建cloudera-scm用户（所有节点）
[root@cdh2 ~]# useradd --system --home=/opt/cloudera-manager/cm-5.7.2/run/cloudera-scm-server --no-create-home --shell=/bin/false --comment "Cloudera SCM User" cloudera-scm  

//配置从节点cloudera-manger-agent指向主节点服务器
[root@cdh2 ~]# vi /opt/cloudera-manager/cm-5.7.2/etc/cloudera-scm-agent/config.ini
将server_host改为CMS所在的主机名即cdh1

//所有节点创建parcels目录
[root@cdh2 ~]# mkdir -p /opt/cloudera/parcels
[root@cdh2 ~]# chown cloudera-scm:cloudera-scm /opt/cloudera/parcels
解释：Clouder-Manager将CDHs从主节点的/opt/cloudera/parcel-repo目录中抽取出来，分发解压激活到各个节点的/opt/cloudera/parcels目录中

//启动cloudera-scm-agent所有节点
[root@cdh2 ~]# mkdir /opt/cloudera-manager/cm-5.7.2/run/cloudera-scm-agent
[root@cdh2 ~]# cp /opt/cloudera-manager/cm-5.7.2/etc/init.d/cloudera-scm-agent /etc/init.d/cloudera-scm-agent
[root@cdh2 ~]# chkconfig cloudera-scm-agent on
[root@cdh2 ~]# vi /etc/init.d/cloudera-scm-agent
CMF_DEFAULTS=${CMF_DEFAULTS:-/etc/default}改为=/opt/cloudera-manager/cm-5.7.2/etc/default
[root@cdhX ~]# service cloudera-scm-agent start
//同时为了保证在每次服务器重启的时候都能启动cloudera-scm-agent，应该在开机启动脚本/etc/rc.local中加入命令：service cloudera-scm-agent restart

五.在线浏览器安装CDH

1）在浏览器输入192.168.42.128:7180，账号和密码都为admin，完成登录

2）进行以下图示安装

六、测试

在集群的一台机器上执行以下模拟Pi的示例程序：

sudo -u hdfs hadoop jar /opt/cloudera/parcels/CDH/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar pi 10 100

通过YARN的Web管理界面也可以看到MapReduce的执行状态：

MapReduce执行过程中终端的输出如下：

Number of Maps  = 10
Samples per Map = 100
Wrote input for Map #0
Wrote input for Map #1
Wrote input for Map #2
Wrote input for Map #3
Wrote input for Map #4
Wrote input for Map #5
Wrote input for Map #6
Wrote input for Map #7
Wrote input for Map #8
Wrote input for Map #9
Starting Job
17/09/22 17:17:50 INFO client.RMProxy: Connecting to ResourceManager at cdh1/192.168.42.128:8032
17/09/22 17:17:52 INFO input.FileInputFormat: Total input paths to process : 10
17/09/22 17:17:52 INFO mapreduce.JobSubmitter: number of splits:10
17/09/22 17:17:53 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1505892176617_0002
17/09/22 17:17:53 INFO impl.YarnClientImpl: Submitted application application_1505892176617_0002
17/09/22 17:17:54 INFO mapreduce.Job: The url to track the job: http://cdh1:8088/proxy/application_1505892176617_0002/
17/09/22 17:17:54 INFO mapreduce.Job: Running job: job_1505892176617_0002
17/09/22 17:18:07 INFO mapreduce.Job: Job job_1505892176617_0002 running in uber mode : false
17/09/22 17:18:07 INFO mapreduce.Job:  map 0% reduce 0%
17/09/22 17:18:22 INFO mapreduce.Job:  map 10% reduce 0%
17/09/22 17:18:29 INFO mapreduce.Job:  map 20% reduce 0%
17/09/22 17:18:37 INFO mapreduce.Job:  map 30% reduce 0%
17/09/22 17:18:43 INFO mapreduce.Job:  map 40% reduce 0%
17/09/22 17:18:49 INFO mapreduce.Job:  map 50% reduce 0%
17/09/22 17:18:56 INFO mapreduce.Job:  map 60% reduce 0%
17/09/22 17:19:02 INFO mapreduce.Job:  map 70% reduce 0%
17/09/22 17:19:10 INFO mapreduce.Job:  map 80% reduce 0%
17/09/22 17:19:16 INFO mapreduce.Job:  map 90% reduce 0%
17/09/22 17:19:24 INFO mapreduce.Job:  map 100% reduce 0%
17/09/22 17:19:30 INFO mapreduce.Job:  map 100% reduce 100%
17/09/22 17:19:32 INFO mapreduce.Job: Job job_1505892176617_0002 completed successfully
17/09/22 17:19:32 INFO mapreduce.Job: Counters: 49
        File System Counters
                FILE: Number of bytes read=91
                FILE: Number of bytes written=1308980
                FILE: Number of read operations=0
                FILE: Number of large read operations=0
                FILE: Number of write operations=0
                HDFS: Number of bytes read=2590
                HDFS: Number of bytes written=215
                HDFS: Number of read operations=43
                HDFS: Number of large read operations=0
                HDFS: Number of write operations=3
        Job Counters
                Launched map tasks=10
                Launched reduce tasks=1
                Data-local map tasks=10
                Total time spent by all maps in occupied slots (ms)=58972
                Total time spent by all reduces in occupied slots (ms)=5766
                Total time spent by all map tasks (ms)=58972
                Total time spent by all reduce tasks (ms)=5766
                Total vcore-seconds taken by all map tasks=58972
                Total vcore-seconds taken by all reduce tasks=5766
                Total megabyte-seconds taken by all map tasks=60387328
                Total megabyte-seconds taken by all reduce tasks=5904384
        Map-Reduce Framework
                Map input records=10
                Map output records=20
                Map output bytes=180
                Map output materialized bytes=340
                Input split bytes=1410
                Combine input records=0
                Combine output records=0
                Reduce input groups=2
                Reduce shuffle bytes=340
                Reduce input records=20
                Reduce output records=0
                Spilled Records=40
                Shuffled Maps =10
                Failed Shuffles=0
                Merged Map outputs=10
                GC time elapsed (ms)=1509
                CPU time spent (ms)=10760
                Physical memory (bytes) snapshot=4541886464
                Virtual memory (bytes) snapshot=30556168192
                Total committed heap usage (bytes)=3937402880
        Shuffle Errors
                BAD_ID=0
                CONNECTION=0
                IO_ERROR=0
                WRONG_LENGTH=0
                WRONG_MAP=0
                WRONG_REDUCE=0
        File Input Format Counters
                Bytes Read=1180
        File Output Format Counters
                Bytes Written=97
Job Finished in 102.286 seconds
Estimated value of Pi is 3.14800000000000000000

posted @ 2018-06-28 15:40 鹏达君阅读(363) 评论(0) 编辑收藏举报

刷新页面返回顶部

鹏达君

CDH5.7Hadoop集群搭建（离线版）

公告