hadoop2.X集群安装与应用
可参考此文档：hadoop（2.x）以hadoop2.2为例完全分布式最新高可靠安装文档（非常详细）http://www.aboutyun.com/thread-7684-1-1.html
步骤一：下载并安装JDK
JDK下载地址：http://www.oracle.com/technetwork/java/javase/downloads/jdk8-downloads-2133151.html
[root@master vmware-share-folder]# cp * /usr/local/src/
[root@master src]# chmod +x jdk-6u45-linux-x64.bin
[root@master src]# ./jdk-6u45-linux-x64.bin
完成后设置环境变量：
[root@master src]# vim /etc/profile.d/java.sh
export JAVA_HOME=/usr/local/src/jdk1.8.0_141/
export PATH=$PATH:$JAVA_HOME/bin
[root@master src]# source /etc/profile.d/java.sh
[root@slave1 hadoop]# java -version
java version "1.8.0_141"
Java(TM) SE Runtime Environment (build 1.8.0_141-b15)
Java HotSpot(TM) 64-Bit Server VM (build 25.141-b15, mixed mode)
表示JDK安装成功！！！！
在slave1和slave2做同样的操作： 如果没有么有scp 命令：yum install -y openssh-clients openssh
[root@master src]# scp -r jdk1.8.0_141 slave1:/usr/local/src/
[root@master src]# scp -r jdk1.8.0_141 slave2:/usr/local/src/
之后操作如同master即可！！！！！！
步骤二：编辑hosts文件（每台机器上都操作）
[root@master src]# cat /etc/hosts
192.168.244.200 master
192.168.244.201 slave1
192.168.244.202 slave2
步骤三：关闭防火墙（每台机器上都操作）
[root@master src]# /etc/init.d/iptables stop
[root@master src]# chkconfig iptables off
[root@master src]# vim /etc/sysconfig/selinux
SELINUX=disabled
步骤四：部署免密码（SSH）
[root@master src]# ssh-keygen -t rsa
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:
d6:9f:53:20:59:93:a4:08:c2:2d:b6:68:2e:01:a1:32 root@master
The key's randomart image is:
+--[ RSA 2048]----+
|.. .... .+. |
|o +... . +.. |
|E o o . + . |
|o.o . . . . |
| + S . . |
|. . . . o |
| . + |
| . |
| |
+-----------------+
[root@master src]# cd /root/.ssh/
[root@master .ssh]# ll
total 12
-rw------- 1 root root 1675 Jun 29 02:37 id_rsa
-rw-r--r-- 1 root root 393 Jun 29 02:37 id_rsa.pub
-rw-r--r-- 1 root root 794 Jun 29 02:20 known_hosts
[root@master .ssh]# cp id_rsa.pub authorized_keys
测试：
[root@master .ssh]# ssh slave1
[root@master .ssh]# ssh slave2
成功即可！！！！
步骤五：下载hadoop2.x 并解压
https://dist.apache.org/repos/dist/release/hadoop/common/hadoop-2.7.3/
[root@master src]# tar xf hadoop-2.7.3.tar.gz
步骤六：修改配置文件
涉及到的配置文件有7个：
~/hadoop-2.2.0/etc/hadoop/hadoop-env.sh
~/hadoop-2.2.0/etc/hadoop/yarn-env.sh
~/hadoop-2.2.0/etc/hadoop/slaves
~/hadoop-2.2.0/etc/hadoop/core-site.xml
~/hadoop-2.2.0/etc/hadoop/hdfs-site.xml
~/hadoop-2.2.0/etc/hadoop/mapred-site.xml
~/hadoop-2.2.0/etc/hadoop/yarn-site.xml
以上个别文件默认不存在的，可以复制相应的template文件获得。
1.修改hadoop-env.sh配置文件
[root@master hadoop]# pwd
/usr/local/src/hadoop-2.7.3/etc/hadoop
[root@master hadoop]# cat hadoop-env.sh |grep -i java_home
export JAVA_HOME=/usr/local/src/jdk1.6.0_45/
2.修改yarn-env.sh配置文件
[root@master hadoop]# cat yarn-env.sh
export JAVA_HOME=/usr/local/src/jdk1.6.0_45/
3.修改slaves配置文件
[root@master hadoop]# cat slaves
slave1
slave2
4.修改core-site.xml配置文件
[root@master hadoop]# cat core-site.xml
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://master:9000</value>
</property>
<property>
<name>io.file.buffer.size</name>
<value>131072</value>
</property>
<property>
<name>hadoop.proxyuser.aboutyun.hosts</name>
<value>*</value>
</property>
<property>
<name>hadoop.proxyuser.aboutyun.groups</name>
<value>*</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>file:/usr/local/src/hadoop-2.7.3/tmp</value>
<description>Abase forother temporary directories.</description>
</property>
</configuration>
5.修改hdfs-site.xml配置文件
[root@master hadoop-2.7.3]# mkdir dfs/{name,data} -p
[root@master hadoop]# cat hdfs-site.xml
<configuration>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>master:9001</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:/usr/local/src/hadoop-2.7.3/dfs/name</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:/usr/local/src/hadoop-2.7.3/dfs/data</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
</configuration>
6.修改mapred-site.xml配置文件
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>mapreduce.jobhistory.address</name>
<value>master:10020</value>
</property>
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>master:19888</value>
</property>
</configuration>
7.修改yarn-site.xml配置文件
<configuration>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>
<property>
<name>yarn.resourcemanager.address</name>
<value>master:8032</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address</name>
<value>master:8030</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address</name>
<value>master:8035</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address</name>
<value>master:8033</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address</name>
<value>master:8088</value>
</property>
</configuration>
8.将master的hadoop 目录复制到slave1和slave2节点上：
[root@master src]# scp -r hadoop-2.7.3 root@slave1:/usr/local/src/
[root@master src]# scp -r hadoop-2.7.3 root@slave2:/usr/local/src/
9.设置环境变量
[root@master profile.d]# cat hadoop2.sh
export HADOOP2_HOME=/usr/local/src/hadoop-2.7.3
export PATH=$PATH:$HADOOP2_HOME/bin:HADOOP2_HOME/sbin
[root@master profile.d]# source hadoop2.sh
10 .启动Hadoop
先格式化：hadoop namenode -format
[root@master sbin]# ./start-dfs.sh
[root@master sbin]# ./start-yarn.sh
[root@master sbin]# jps
2714 NameNode
3051 ResourceManager
2892 SecondaryNameNode
3310 Jps
[root@slave1 hadoop]# jps
1904 NodeManager
2004 Jps
1797 DataNode
特别注意点：如果hadoop 版本是2.7 JDK一定要用1.7 以上版本，不然格式化namenode 会出现各种类找不到
hadoop 2.6 可以使用jdk 1.6 版本
########快照案例#################
HDFS快照是对目录进行设定，是某个目录的某一个时刻的镜像
1 [root@master ~]# jps 2 3604 Jps 3 2714 NameNode 4 3051 ResourceManager 5 2892 SecondaryNameNode 6 [root@master ~]# hadoop fs -ls / 7 [root@master ~]# hadoop fs -mkdir /kuaizhao_dir 8 [root@master ~]# hadoop fs -ls / 9 Found 1 items 10 drwxr-xr-x - root supergroup 0 2017-07-20 11:02 /kuaizhao_dir 11 [root@master ~]# hadoop fs -mkdir /kuaizhao_dir/kz_test 12 [root@master ~]# hadoop fs /etc/passwd 13 passwd passwd- 14 [root@master ~]# hadoop fs -put /etc/passwd /kuaizhao_dir/kz_test 15 [root@master ~]# hadoop fs -cat /kuaizhao_dir/kz_test/passwd |head 16 root:x:0:0:root:/root:/bin/bash 17 bin:x:1:1:bin:/bin:/sbin/nologin 18 daemon:x:2:2:daemon:/sbin:/sbin/nologin 19 adm:x:3:4:adm:/var/adm:/sbin/nologin 20 lp:x:4:7:lp:/var/spool/lpd:/sbin/nologin 21 sync:x:5:0:sync:/sbin:/bin/sync 22 shutdown:x:6:0:shutdown:/sbin:/sbin/shutdown 23 halt:x:7:0:halt:/sbin:/sbin/halt 24 mail:x:8:12:mail:/var/spool/mail:/sbin/nologin 25 uucp:x:10:14:uucp:/var/spool/uucp:/sbin/nologin
1 [root@master ~]# hdfs dfsadmin -allowSnapshot /kuaizhao_dir/kz_test 2 Allowing snaphot on /kuaizhao_dir/kz_test succeeded 3 [root@master ~]# hdfs dfs -createSnapshot /kuaizhao_dir/kz_test s0 4 Created snapshot /kuaizhao_dir/kz_test/.snapshot/s0 5 [root@master ~]# hadoop fs -ls /kuaizhao_dir/kz_test/.snapshot/s0 6 Found 1 items 7 -rw-r--r-- 3 root supergroup 854 2017-07-20 11:07 /kuaizhao_dir/kz_test/.snapshot/s0/passwd
