在搭建好的 resourceHA的环境下, 配置yarn
yarn是 hadoop2以后的计算框架,
通过ResourceManager的调用, 将我们写的程序包分到各个nodeManager上, 由于hadoop的理念是移动计算, 所以NodeManager和 DataNode是同一个机器
在 ${hadoop_home}/etc/hadoop 下
vim yarn-site.xml
<configuration> <property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>yarncluster</value>
</property>
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>192.168.208.106</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>192.168.208.107</value>
</property>
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>192.168.208.106:,192.168.208.107:,192.168.208.108:</value>
</property> <property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
</configuration>
然后 vim mapred-site.xml
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
</configuration>