1、准备三台机器,每天机器关闭防火墙,设置hosts文件,配置免密登录
- 关闭防火墙
servie iptables stop
chkconfig iptables off && setenforce 0
- 设置hosts
192.168.140.128 node01 zk01 kafka01 storm01 maven flume
192.168.140.129 node02 zk02 kafka02 storm02 redis
192.168.140.130 node03 zk03 kafka03 storm03 mysql
- 免密登录,在node01执行以下命令。
ssh-keygen 四个回车
ssh-copy-id node1
ssh-copy-id node2
ssh-copy-id node3
如果免密登录失败,在每台机器上执行以下命令,然后在重试。
yum -y install openssh-clients
2、下载Hadoop安装包,也可以编译自己编译
- 自己编译参见《Linux的下编译Hadoop2.7.3源码》
- 下载请到官网下载
3、配置文件部分
- core-site.xml
<configuration>
<!-- 指定hdfs的nameservice为ns1 -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://ns1/</value>
</property>
<!-- 指定hadoop临时目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/export/data/hdp/</value>
</property>
<!-- 指定zookeeper地址 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>node01:2181,node02:2181,node03:2181</value>
</property>
</configuration>
- hdfs-site.xml
<configuration>
<!--指定hdfs的nameservice为ns1,需要和core-site.xml中的保持一致 -->
<property>
<name>dfs.nameservices</name>
<value>ns1</value>
</property>
<!-- ns1下面有两个NameNode,分别是nn1,nn2 -->
<property>
<name>dfs.ha.namenodes.ns1</name>
<value>nn1,nn2</value>
</property>
<!-- nn1的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.ns1.nn1</name>
<value>node01:9000</value>
</property>
<!-- nn1的http通信地址 -->
<property>
<name>dfs.namenode.http-address.ns1.nn1</name>
<value>node01:50070</value>
</property>
<!-- nn2的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.ns1.nn2</name>
<value>node03:9000</value>
</property>
<!-- nn2的http通信地址 -->
<property>
<name>dfs.namenode.http-address.ns1.nn2</name>
<value>node03:50070</value>
</property>
<!-- 指定NameNode的edits元数据在JournalNode上的存放位置 -->
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://node01:8485;node02:8485;node03:8485/ns1</value>
</property>
<!-- 指定JournalNode在本地磁盘存放数据的位置 -->
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/export/data/journaldata</value>
</property>
<!-- 开启NameNode失败自动切换 -->
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<!-- 配置失败自动切换实现方式 -->
<property>
<name>dfs.client.failover.proxy.provider.ns1</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<!-- 配置隔离机制方法,多个机制用换行分割,即每个机制暂用一行-->
<property>
<name>dfs.ha.fencing.methods</name>
<value>
sshfence
shell(/bin/true)
</value>
</property>
<!-- 使用sshfence隔离机制时需要ssh免登陆 -->
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/root/.ssh/id_rsa</value>
</property>
<!-- 配置sshfence隔离机制超时时间 -->
<property>
<name>dfs.ha.fencing.ssh.connect-timeout</name>
<value>30000</value>
</property>
</configuration>
- yarn-site.xml
<?xml version="1.0"?>
<configuration>
<property>
<name>yarn.resourcemanager.hostname</name>
<value>node01</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
</configuration>
- hadoop-env.sh
# export JAVA_HOME=${JAVA_HOME}
export JAVA_HOME=/export/servers/jdk
- mapred-site.xml 配置JDK
# export JAVA_HOME=/home/y/libexec/jdk1.6.0/
export JAVA_HOME=/export/servers/jdk
- slaves
node01
node02
node03
4、初始化服务并启动
- 拷贝安装包到其他节点
scp -r /export/servers/hadoop/ node02:/export/servers/
scp -r /export/servers/hadoop/ node03:/export/servers/
- 配置环境变量,每台机器,并生效
export HADOOP_HOME=/export/servers/hadoop
export PATH=${HADOOP_HOME}/sbin:${HADOOP_HOME}/bin:$PATH
让环境变量生效
source /etc/profile
- 初始化zookeeper里面的信息
start-dfs.sh
hadoop namenode -format
scp -r /export/data/hdp/dfs node03:/export/data/hdp/
stop-dfs.sh
-
startzk.sh 说明:这个是一键启动zk的脚本
hdfs zkfc -formatZK
- 启动集群
start-dfs.sh