hadoop 2.X HA详细配置

hadoop-daemon.sh与hadoop-daemons.sh区别

hadoop-daemon.sh只能本地执行

hadoop-daemons.sh能远程执行

1. 启动JN

hadoop-daemons.sh start journalnode

hdfs namenode -initializeSharedEdits //复制edits log文件到journalnode节点上，第一次创建得在格式化namenode之后使用

http://hadoop-yarn1:8480来看journal是否正常

2.格式化namenode，并启动Active Namenode

一、Active NameNode节点上格式化namenode

hdfs namenode -format

hdfs namenode -initializeSharedEdits

初始化journalnode完毕

二、启动Active Namenode

hadoop-daemon.sh start namenode

3.启动 Standby namenode

一、Standby namenode节点上格式化Standby节点

复制Active Namenode上的元数据信息拷贝到Standby Namenode节点上

hdfs namenode -bootstrapStandby

二、启动Standby节点

hadoop-daemon.sh start namenode

4.启动Automatic Failover

在zookeeper上创建 /hadoop-ha/ns1这样一个监控节点(ZNode)

hdfs zkfc -formatZK

start-dfs.sh

5.查看namenode状态

hdfs  haadmin -getServiceState nn1
active

6.自动failover

hdfs  haadmin -failover nn1 nn2

配置文件详细信息

core-site.xml

<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://ns1</value>
    </property>
    
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/opt/modules/hadoop-2.2.0/data/tmp</value>
    </property>
    
    <property>
        <name>fs.trash.interval</name>
        <value>60*24</value>
    </property>
    
    <property>
        <name>ha.zookeeper.quorum</name>
        <value>hadoop-yarn1:2181,hadoop-yarn2:2181,hadoop-yarn3:2181</value>
    </property>
    
    <property>  
        <name>hadoop.http.staticuser.user</name>
        <value>yuanhai</value>
    </property>
</configuration>

hdfs-site.xml

<configuration>
    <property>
        <name>dfs.replication</name>
        <value>3</value>
    </property>
    
    <property>
        <name>dfs.nameservices</name>
        <value>ns1</value>
    </property>
    
    <property>
        <name>dfs.ha.namenodes.ns1</name>
        <value>nn1,nn2</value>
        </property>
        
    <property>
        <name>dfs.namenode.rpc-address.ns1.nn1</name>
        <value>hadoop-yarn1:8020</value>
    </property>
    
        <property>
        <name>dfs.namenode.rpc-address.ns1.nn2</name>
        <value>hadoop-yarn2:8020</value>
    </property>
    
    <property>
        <name>dfs.namenode.http-address.ns1.nn1</name>
        <value>hadoop-yarn1:50070</value>
    </property>
    
    <property>
        <name>dfs.namenode.http-address.ns1.nn2</name>
        <value>hadoop-yarn2:50070</value>
    </property>
    
    <property>
        <name>dfs.namenode.shared.edits.dir</name>
        <value>qjournal://hadoop-yarn1:8485;hadoop-yarn2:8485;hadoop-yarn3:8485/ns1</value>
    </property>
    
    <property>
        <name>dfs.journalnode.edits.dir</name>
        <value>/opt/modules/hadoop-2.2.0/data/tmp/journal</value>
    </property>
    
     <property>
        <name>dfs.ha.automatic-failover.enabled</name>
        <value>true</value>
    </property>
    
    <property>
        <name>dfs.client.failover.proxy.provider.ns1</name>
        <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
    </property>
    
    <property>
        <name>dfs.ha.fencing.methods</name>
        <value>sshfence</value>
    </property>
    
    <property>
        <name>dfs.ha.fencing.ssh.private-key-files</name>
        <value>/home/hadoop/.ssh/id_rsa</value>
    </property>
    
    <property>
        <name>dfs.permissions.enabled</name>
        <value>false</value>
    </property>
    

<!--     <property>
        <name>dfs.namenode.http-address</name>
        <value>hadoop-yarn.dragon.org:50070</value>
    </property>

    <property>
        <name>dfs.namenode.secondary.http-address</name>
        <value>hadoop-yarn.dragon.org:50090</value>
    </property>
    
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>file://${hadoop.tmp.dir}/dfs/name</value>
    </property>
    
    <property>
        <name>dfs.namenode.edits.dir</name>
        <value>${dfs.namenode.name.dir}</value>
    </property>
    
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>file://${hadoop.tmp.dir}/dfs/data</value>
    </property>
    
    <property>
        <name>dfs.namenode.checkpoint.dir</name>
        <value>file://${hadoop.tmp.dir}/dfs/namesecondary</value>
    </property>
    
    <property>
        <name>dfs.namenode.checkpoint.edits.dir</name>
        <value>${dfs.namenode.checkpoint.dir}</value>
    </property>
-->    
</configuration>

slaves

hadoop-yarn1
hadoop-yarn2
hadoop-yarn3

yarn-site.xml

<configuration>
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
    
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>hadoop-yarn1</value>
    </property> 
    
    <property>
        <name>yarn.log-aggregation-enable</name>
        <value>true</value>
    </property>

    <property>
        <name>yarn.log-aggregation.retain-seconds</name>
        <value>604800</value>
    </property> 

</configuration>

mapred-site.xml

<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>

    <property>
        <name>mapreduce.jobhistory.address</name>
        <value>hadoop-yarn1:10020</value>
        <description>MapReduce JobHistory Server IPC host:port</description>
    </property>

    <property>
        <name>mapreduce.jobhistory.webapp.address</name>
        <value>hadoop-yarn1:19888</value>
        <description>MapReduce JobHistory Server Web UI host:port</description>
    </property>
    
    <property>
        <name>mapreduce.job.ubertask.enable</name>
        <value>true</value>
    </property>
    
</configuration>

hadoop-env.sh

export JAVA_HOME=/opt/modules/jdk1.6.0_24

其他相关文章：

http://blog.csdn.net/zhangzhaokun/article/details/17892857