hdfs-site.xml 详解

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
	<!--HDFS超级用户 -->
	<property>
		<name>dfs.permissions.superusergroup</name>
		<value>hadoop</value>
	</property>

	<!--开启web hdfs -->
	<property>
		<name>dfs.webhdfs.enabled</name>
		<value>true</value>
	</property>
	<property>
		<name>dfs.namenode.name.dir</name>
		<value>/home/hadoop/data/dfs/name</value>
		<description> namenode 存放name table(fsimage)本地目录（需要修改）</description>
	</property>
	<property>
		<name>dfs.namenode.edits.dir</name>
		<value>${dfs.namenode.name.dir}</value>
		<description>namenode粗放 transaction file(edits)本地目录（需要修改）</description>
	</property>
	<property>
		<name>dfs.datanode.data.dir</name>
		<value>/home/hadoop/data/dfs/data</value>
		<description>datanode存放block本地目录（需要修改）</description>
	</property>
	<property>
		<name>dfs.replication</name>
		<value>3</value>
	</property>
	<!-- 块大小128M （默认128M） -->
	<property>
		<name>dfs.blocksize</name>
		<value>134217728</value>
	</property>
	<!--======================================================================= -->
	<!--HDFS高可用配置 -->
	<!--指定hdfs的nameservice为ruozeclusterg7,需要和core-site.xml中的保持一致 -->
	<property>
		<name>dfs.nameservices</name>
		<value>ruozeclusterg7</value>
	</property>
	<property>
		<!--设置NameNode IDs 此版本最大只支持两个NameNode -->
		<name>dfs.ha.namenodes.ruozeclusterg7</name>
		<value>nn1,nn2</value>
	</property>

	<!-- Hdfs HA: dfs.namenode.rpc-address.[nameservice ID] rpc 通信地址 -->
	<property>
		<name>dfs.namenode.rpc-address.ruozeclusterg7.nn1</name>
		<value>ruozedata001:8020</value>
	</property>
	<property>
		<name>dfs.namenode.rpc-address.ruozeclusterg7.nn2</name>
		<value>ruozedata002:8020</value>
	</property>

	<!-- Hdfs HA: dfs.namenode.http-address.[nameservice ID] http 通信地址 -->
	<property>
		<name>dfs.namenode.http-address.ruozeclusterg7.nn1</name>
		<value>ruozedata001:50070</value>
	</property>
	<property>
		<name>dfs.namenode.http-address.ruozeclusterg7.nn2</name>
		<value>ruozedata002:50070</value>
	</property>

	<!--==================Namenode editlog同步 ============================================ -->
	<!--保证数据恢复 -->
	<property>
		<name>dfs.journalnode.http-address</name>
		<value>0.0.0.0:8480</value>
	</property>
	<property>
		<name>dfs.journalnode.rpc-address</name>
		<value>0.0.0.0:8485</value>
	</property>
	<property>
		<!--设置JournalNode服务器地址，QuorumJournalManager 用于存储editlog -->
		<!--格式：qjournal://<host1:port1>;<host2:port2>;<host3:port3>/<journalId> 端口同journalnode.rpc-address -->
		<name>dfs.namenode.shared.edits.dir</name>
		<value>qjournal://ruozedata001:8485;ruozedata002:8485;ruozedata003:8485/ruozeclusterg7</value>
	</property>

	<property>
		<!--JournalNode存放数据地址 -->
		<name>dfs.journalnode.edits.dir</name>
		<value>/home/hadoop/data/dfs/jn</value>
	</property>
	<!--==================DataNode editlog同步 ============================================ -->
	<property>
		<!--DataNode,Client连接Namenode识别选择Active NameNode策略 -->
                             <!-- 配置失败自动切换实现方式 -->
		<name>dfs.client.failover.proxy.provider.ruozeclusterg7</name>
		<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
	</property>
	<!--==================Namenode fencing：=============================================== -->
	<!--Failover后防止停掉的Namenode启动，造成两个服务 -->
	<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>
		<!--多少milliseconds 认为fencing失败 -->
		<name>dfs.ha.fencing.ssh.connect-timeout</name>
		<value>30000</value>
	</property>

	<!--==================NameNode auto failover base ZKFC and Zookeeper====================== -->
	<!--开启基于Zookeeper  -->
	<property>
		<name>dfs.ha.automatic-failover.enabled</name>
		<value>true</value>
	</property>
	<!--动态许可datanode连接namenode列表 -->
	 <property>
	   <name>dfs.hosts</name>
	   <value>/home/hadoop/app/hadoop/etc/hadoop/slaves</value>
	 </property>
</configuration>