0. Hadoop源码包下载
http://mirror.bit.edu.cn/apache/hadoop/common
1. 集群环境
Master xxx.xxx.xxx.xxx
Slave1 xxx.xxx.xxx.xxx
Slave2 xxx.xxx.xxx.xxx
vim /etc/hosts 里追加
2. 下载安装包
#Master
wget http://mirror.bit.edu.cn/apache/hadoop/common/hadoop-2.6.5/hadoop-2.6.5.tar.gz
tar zxvf hadoop-2.6.5.tar.gz
2.1关闭系统防火墙及内核防火墙
#Master、Slave1、Slave2
#清空系统防火墙
iptables -F
#保存防火墙配置
service iptables save
# 临时关闭防火墙
service iptables stop
# 永久关闭防火墙
chkconfig iptables off
#临时关闭内核防火墙
setenforce 0
#永久关闭内核防火墙
vim /etc/selinux/config
SELINUX=disabled
3. 修改Hadoop配置文件
#Master
cd hadoop-2.6.5/etc/hadoop
vim hadoop-env.sh
export JAVA_HOME=/usr/local/src/jdk1.8.0_152
vim yarn-env.sh
export JAVA_HOME=/usr/local/src/jdk1.8.0_152
vim slaves
slave1slave2
vim core-site.xml
<configuration><property><name>fs.defaultFS</name><value>hdfs://master:9000</value></property><property><name>hadoop.tmp.dir</name><value>file:/usr/local/src/hadoop-2.6.5/tmp/</value></property>
</configuration>
vim 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-2.6.5/dfs/name/</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:/usr/local/src/hadoop-2.6.5/dfs/data/</value>
</property>
<property>
<name>dfs.replication</name>
<value>2</value>
</property>
</configuration>
vim mapred-site.xml
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property><property><name>mapreduce.jobhistory.address</name><value>http://master:10020</value></property><property><name>mapreduce.jobhistory.webapp.address</name><value>http://master:19888</value></property>
</configuration>
vim yarn-site.xml
<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>
<!-- 关闭虚拟内存检查-->
<property><name>yarn.nodemanager.vmem-check-enabled</name><value>false</value>
</property>
</configuration>
#创建临时目录和文件目录
mkdir /usr/local/src/hadoop-2.6.5/tmp
mkdir -p /usr/local/src/hadoop-2.6.5/dfs/name
mkdir -p /usr/local/src/hadoop-2.6.5/dfs/data
4. 配置环境变量
#Master、Slave1、Slave2
vim ~/.bashrc
export HADOOP_HOME=/usr/local/src/hadoop-2.6.5
export PATH=$PATH:$HADOOP_HOME/bin
#刷新环境变量
source ~/.bashrc
5. 拷贝安装包
#Master
scp -r /usr/local/src/hadoop-2.6.5 root@slave1:/usr/local/src/hadoop-2.6.5
scp -r /usr/local/src/hadoop-2.6.5 root@slave2:/usr/local/src/hadoop-2.6.5
6. 启动集群
#Master
#初始化Namenode
hadoop namenode -format
#启动集群
./sbin/start-all.sh
6. 集群状态
jps
#Master
#Slave1
#Slave2
7.启动历史服务器
sbin/mr-jobhistory-daemon.sh start historyserver
8.监控网页
http://master:8088(使用非系统自带浏览器打开)
8. 操作命令
#和Hadoop1.0操作命令是一样的
9. 关闭集群
./sbin/hadoop stop-all.sh