0. 环境条件 (基于以下版本 且 ssh 授信免密登录已设置):
1.下载安装包
cd /usr/local
wget http://mirror.bit.edu.cn/apache/hadoop/common/hadoop-2.10.1/hadoop-2.10.1.tar.gz
tar zvxf hadoop-2.10.1.tar.gz
2.关闭系统防火墙及内核防火墙
#Master、Slave1、Slave2
systemctl stop firewalld
#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
#创建临时目录和HDFS文件目录
cd /usr/local/hadoop-2.10.1
mkdir tmp
mkdir -p dfs/name dfs/data
#指定Hadoop依赖的JDK
cd /usr/local/hadoop-2.10.1/etc/hadoop
vim hadoop-env.sh
export JAVA_HOME=/usr/local/jdk1.8.0_121
#指定Hadoop集群从节点
vim slaves
slave1
slave2
#修改Hadoop核心配置文件(依赖HDFS)
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/hadoop-2.10.1/tmp/</value>
</property>
</configuration>
#配置HDFS
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/hadoop-2.10.1/dfs/name</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:/usr/local/hadoop-2.10.1/dfs/data</value>
</property>
<property>
<name>dfs.replication</name>
<value>2</value>
</property>
</configuration>
#配置MapReduce
cp mapred-site.xml.template mapred-site.xml
vim mapred-site.xml
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
</configuration>
#配置YARN资源管理调度中心
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>
4.配置hadoop环境变量
#Master、Slave1、Slave2
vim ~/.bashrc
export HADOOP_HOME=/usr/local/hadoop-2.10.1
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/hadoop-2.10.1 root@slave1:/usr/local/hadoop-2.10.1
scp -r /usr/local/hadoop-2.10.1 root@slave2:/usr/local/hadoop-2.10.1
6.启动集群
#Master
#初始化Namenode
hadoop namenode -format
#启动集群
cd /usr/local/hadoop-2.10.1
./sbin/start-all.sh
7.集群状态
#Master
jps
#Slave1
jps
#Slave2
jps
8.监控网页(如果不能访问,需要再次确认是否关闭了防火墙)
YARN页面:
http://master:8088 (需要更改本地host 域名解析)
或
HDFS页面(namenode):
http://192.168.111.10:50070/dfshealth.html#tab-overview
9.关闭集群
cd /usr/local/hadoop-2.10.1
./sbin/stop-all.sh