思路通过vm 虚拟机实现，创建一台linux虚拟机（在此使用CentOS-6.5-x86_64-minimal.iso，配置1核2G）当作主节点，其他节点主机通过克隆主节点虚拟机创建，虚拟机网络模式为NAT。
| 角色 | 主机名 | IP |
|---|---|---|
| ActiveNameNode | master | 172.16.152.130 |
| StandbyNameNode | slave | 172.16.152.131 |
| DataNode | slave1 | 172.16.152.132 |
附录1: 修改网络IP
vi /etc/sysconfig/network-scripts/ifcfg-eth0
// 删除其中 UUID、HWADDR
// 修改或添加如下：
// IPADDR=172.16.152.131
// NATMASK=255.255.255.0
// GATEWAY=172.16.152.2
// DNS1=192.168.0.1
附录2: 修改主机名
vi /etc/sysconfig/network
附录3: ssh 免密登陆
如果B想免密登陆A，则在A上生成的公钥（id_rsa.pub）给B就可免密登陆
// A上操作
// 一路回车生成密钥
ssh-keygen -t rsa
scp ~/.ssh/id_rsa.pub root@xxx:～
// B上操作
cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
附录4: 查看端口进程占用
netstat -ntulp | grep 80 //查看所有80端口使用情况
搭建zookeeper集群
mv zoo.fig zoo_sample.cfg
vi zoo.fig
// 修改或添加
dataDir=/opt/zookeeper/data
server.1=master:2888:3888
server.2=slave:2888:3888
server.3=slave1:2888:3888
//在dataDir 下创建myid，myid中的数字必须是server.1/2/3 对应
vi /opt/zookeeper/data/myid
//启动， 注意每个节点实例都要启动才能正确开启
cd /usr/local/software/zookeeper-3.4.6/bin/
./ zkServer.sh start
// 查看状态
./zkServer.sh status
//停止
./zkServer.sh stop
// 方便启动命令追加bin目录到PATH
export ZOOKEEPER_HOME=usr/local/software/zookeeper-3.4.6
//exprot PATH 后追加
:$ZOOKEEPER_HOME/bin:$ZOOKEEPER_HOME/sbin
// 默认日志
/usr/local/software/zookeeper-3.4.6/bin/zookeeper.out
hadoop环境变量
export HADOOP_HOME=/usr/local/software/hadoop-2.5.1
export PATH=$HADOOP_HOME/sbin:$PATH
core-site.xml 配置
fs.defaultFS
hdfs://mycluster
hadoop.tmp.dir
/opt/hadoop-2.5
ha.zookeeper.quorum
master,slave,slave1
hdfs-site.xml 配置
dfs.nameservices
mycluster
dfs.ha.namenodes.mycluster
nn1,nn2
dfs.namenode.rpc-address.mycluster.nn1
master:8020
dfs.namenode.rpc-address.mycluster.nn2
slave:8020
dfs.namenode.http-address.mycluster.nn1
master:50070
dfs.namenode.http-address.mycluster.nn2
slave:50070
dfs.namenode.shared.edits.dir
qjournal://master:8485;slave:8485;slave1:8485/mycluster
dfs.client.failover.proxy.provider.mycluster
org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider
dfs.ha.fencing.methods
sshfence
dfs.ha.fencing.ssh.private-key-files
/root/.ssh/id_rsa
dfs.journalnode.edits.dir
/opt/journalnode/data
dfs.ha.automatic-failover.enabled
true
cd /usr/local/software/hadoop-2.5.1/etc/hadoop
vi masters
// 添加
master
vi slaves
//写入
master
slave
slave1
将mater修改好的hadoop发送至slave, slave1
scp -r /usr/local/software/hadoop-2.5.1/ root@slave:/usr/local/software/
每个节点都启动journalnode（已配置hadoop环境变量）
cd /usr/local/software/hadoop-2.5.1/sbin
./hadoop-daemon.sh start journalnode
// jps 出现 51190 JournalNode 成功
master上执行，格式化NameNode， 再将生成结果文件拷贝StandbyNameNode
// 生成文件在 core-site.xml 节点hadoop.tmp.dir定义的目录中
hdfs namenode -format
scp -r /opt/hadoop-2.5/ root@slave:/opt
master执行 格式化zookeeper
hdfs zkfc -formatZK
启动hdfs
cd /usr/local/software/hadoop-2.5.1/sbin/
./start-dfs.sh
web 访问
http://masternode:50070/dfshealth.html#tab-overview
end
附录：启动顺序
1 启动所有节点上的zk
cd /usr/local/software/zookeeper-3.4.6/bin/
./zkServer.sh start
2 启动所有节点journalnode
cd /usr/local/software/hadoop-2.5.1/sbin
./hadoop-daemon.sh start journalnode
2 启动master上启动hdfs
cd /usr/local/software/hadoop-2.5.1/sbin/
./start-dfs.sh