hadoop集群高可用配置及问题（下）

之前已经把hdfs高可用配置好了，接下来配置yarn的高可用

1.之前集群规划已提到要在bigdata1和bigdata2上配置resourcemanger服务，在yarn-site.xml中添加

<configuration>

    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>

    <!-- 启用resourcemanager ha -->
    <property>
        <name>yarn.resourcemanager.ha.enabled</name>
        <value>true</value>
    </property>
 
    <!-- 声明两台resourcemanager的地址 -->
    <property>
        <name>yarn.resourcemanager.cluster-id</name>
        <value>cluster-yarn1</value>
    </property>
    <!--指定resourcemanager的逻辑列表-->
    <property>
        <name>yarn.resourcemanager.ha.rm-ids</name>
        <value>rm1,rm2</value>
</property>
<!-- ========== rm1的配置 ========== -->
<!-- 指定rm1的主机名 -->
    <property>
        <name>yarn.resourcemanager.hostname.rm1</name>
        <value>bigdata1</value>
</property>
<!-- 指定rm1的web端地址 -->
<property>
     <name>yarn.resourcemanager.webapp.address.rm1</name>
     <value>bigdata1:8088</value>
</property>
<!-- 指定rm1的内部通信地址 -->
<property>
     <name>yarn.resourcemanager.address.rm1</name>
     <value>bigdata1:8032</value>
</property>
<!-- 指定AM向rm1申请资源的地址 -->
<property>
     <name>yarn.resourcemanager.scheduler.address.rm1</name>  
     <value>bigdata1:8030</value>
</property>
<!-- 指定供NM连接的地址 -->  
<property>
     <name>yarn.resourcemanager.resource-tracker.address.rm1</name>
     <value>bigdata1:8031</value>
</property>
<!-- ========== rm2的配置 ========== -->
    <!-- 指定rm2的主机名 -->
    <property>
        <name>yarn.resourcemanager.hostname.rm2</name>
        <value>bigdata2</value>
</property>
<property>
     <name>yarn.resourcemanager.webapp.address.rm2</name>
     <value>bigdata2:8088</value>
</property>
<property>
     <name>yarn.resourcemanager.address.rm2</name>
     <value>bigdata2:8032</value>
</property>
<property>
     <name>yarn.resourcemanager.scheduler.address.rm2</name>
     <value>bigdata2:8030</value>
</property>
<property>
     <name>yarn.resourcemanager.resource-tracker.address.rm2</name>
     <value>bigdata2:8031</value>
</property>
 
    <!-- 指定zookeeper集群的地址 --> 
    <property>
        <name>yarn.resourcemanager.zk-address</name>
        <value>bigdata1:2181,bigdata2:2181,bigdata3:2181</value>
    </property>

    <!-- 启用自动恢复 --> 
    <property>
        <name>yarn.resourcemanager.recovery.enabled</name>
        <value>true</value>
    </property>
 
    <!-- 指定resourcemanager的状态信息存储在zookeeper集群 --> 
    <property>
        <name>yarn.resourcemanager.store.class</name>
      <value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
	</property>
<!-- 环境变量的继承 -->
 <property>
        <name>yarn.nodemanager.env-whitelist</name>
        <value>JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,CLASSPATH_PREPEND_DISTCACHE,HADOOP_YARN_HOME,HADOOP_MAPRED_HOME</value>
    </property>
	
	
	
	<!-- yarn容器允许分配的最大最小内存 -->
    <property>
        <name>yarn.scheduler.minimum-allocation-mb</name>
        <value>512</value>
    </property>
    <property>
        <name>yarn.scheduler.maximum-allocation-mb</name>
        <value>4096</value>
    </property>
    
    <!-- yarn容器允许管理的物理内存大小 -->
    <property>
        <name>yarn.nodemanager.resource.memory-mb</name>
        <value>4096</value>
    </property>
    
    <!-- 关闭yarn对物理内存和虚拟内存的限制检查 -->
    <property>
        <name>yarn.nodemanager.pmem-check-enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>yarn.nodemanager.vmem-check-enabled</name>
        <value>false</value>
    </property>
	<!-- 开启日志聚集功能 -->
	<property>
		<name>yarn.log-aggregation-enable</name>
		<value>true</value>
	</property>

<!-- 设置日志聚集服务器地址 -->
	<property>  
		<name>yarn.log.server.url</name>  
		<value>http://bigdata1:19888/jobhistory/logs</value>
	</property>

<!-- 设置日志保留时间为7天 -->
<property>
    <name>yarn.log-aggregation.retain-seconds</name>
    <value>604800</value>
</property>

</configuration>

2.启动hdfs

3.启动yarn

在bigdata1上启动yarn

 4.查看服务状态

 

 5.web端查看yarn状态：********（ip地址）：8088

到此，Hadoop高可用配置就完成了