HA高可用配置

core-site.xml

<property>
<name>fs.defaultFS</name>
<value>hdfs://cluster1</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/usr/local/src/hadoop/tmp</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>master:2181,slave1:2181,slave2:2181</value>
</property>

hdfs-site.xml

<property>
<name>dfs.nameservices</name>
<value>cluster1</value>
</property>
<property>
<name>dfs.ha.namenodes.cluster1</name>
<value>nn1,nn2</value>
</property>
<property>
<name>dfs.namenode.rpc-address.cluster1.nn1</name>
<value>master:9000</value>
</property>
<property>
<name>dfs.namenode.http-address.cluster1.nn1</name>
<value>master:50070</value>
</property>
<property>
<name>dfs.namenode.rpc-address.cluster1.nn2</name>
<value>slave1:9000</value>
</property>
<property>
<name>dfs.namenode.http-address.cluster1.nn2</name>
<value>slave1:50070</value>
</property>
<property>
<name>dfs.namenodes.shared.edits.dir</name>
<value>qjournal://master:8485;slave1:8485;slave2:8485/cluster1</value>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/usr/local/src/hadoop/journaldata</value>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.client.failover.proxy.provider.cluster1</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfenceshell(/bin/true)</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/home/nana/.ssh/id_rsa</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.connect-timeout</name>
<value>30000</value>
</property>

mapred-site.xml

<property>
<name>maprduce.framework.name</name>
<value>yarn</value>
</property>

yarn-site.xml

<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>yrc</value>
</property>
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>slave1</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>slave2</value>
</property>
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>master:2181,slave1:2181,slave2:2181</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>slave1:8088</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>slave2:8088</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shufel</value>
</property>

slaves

master
slave1
slave2

分发

scp -r /usr/local/src/hadoop slave1:/usr/local/src
scp -r /usr/local/src/hadoop slave2:/usr/local/src

启动

1）之前zk已经启动了现在在master,slave1,slave2上面手动启动journalnode

hadoop-daemon.sh start journalnode（三台）

2）格式化hdfs

hdfs namenode -format（只master）

3）#格式化后会在根据core-site.xml中的hadoop.tmp.dir配置的目录下生成个hdfs初始化文件，把hadoop.tmp.dir配置的目录下所有文件拷贝到另一台namenode节点所在的机器

scp -r /usr/local/src/hadoop/tmp hadoop@slave1:/usr/local/hadoop/src/

4）格式化zkfc以及启动zkfc、hdfs、yarn

#格式化ZKFC
hdfs zkfc -formatZK(在master上执行即可)
#启动zkfc：
hadoop-daemon.sh start zkfc（namenode台）
#启动hdfs 
start-dfs.sh（master）
#启动yarn 
start-yarn.sh
#启动备用yarn
yarn-daemon.sh start resourcemanager（slave2）