hadoop2.x HA搭建以及相关错误解决

1. 集群节点安排安排

节点名	bigdata-pro01.kfk.com	bigdata-pro02.kfk.com	bigdata-pro02.kfk.com
	namenode	namenode
	datanode	datanode	datanode

2. 配置hdfs-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
  You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License. See accompanying LICENSE file.
-->

<!-- Put site-specific property overrides in this file. -->

<configuration>
<property>
<name>dfs.permissions</name>
<value>false</value>
</property>
<property>
<name>dfs.permissions.enabled</name>
<value>false</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>



<property>
  <name>dfs.nameservices</name>
  <value>ns</value>
</property>

<property>
  <name>dfs.ha.namenodes.ns</name>
  <value>nn1,nn2</value>
</property>

<property>
  <name>dfs.namenode.rpc-address.ns.nn1</name>
  <value>bigdata-pro01.kfk.com:9000</value>
</property>

<property>
  <name>dfs.namenode.rpc-address.ns.nn2</name>
  <value>bigdata-pro02.kfk.com:9000</value>
</property>


<property>
  <name>dfs.namenode.http-address.ns.nn1</name>
  <value>bigdata-pro01.kfk.com:50070</value>
</property>

<property>
  <name>dfs.namenode.http-address.ns.nn2</name>
  <value>bigdata-pro02.kfk.com:50070</value>
</property>

<property>
  <name>dfs.namenode.shared.edits.dir</name>
  <value>qjournal://bigdata-pro01.kfk.com:8485;bigdata-pro02.kfk.com:8485;bigdata-pro03.kfk.com:8485/ns</value>
</property>

<property>
  <name>dfs.journalnode.edits.dir</name>
  <value>/opt/modules/hadoop-2.5.0/data/jn</value>
</property>





<property>
  <name>dfs.client.failover.proxy.provider.ns</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/kfk/.ssh/id_rsa</value>
</property>

<property>    
   <name>dfs.namenode.name.dir</name>    
   <value>file:///opt/modules/hadoop-2.5.0/hdfs/name</value>    
</property>
<property>    
    <name>dfs.datanode.data.dir</name>    
    <value>file:///opt/modules/hadoop-2.5.0/hdfs/data</value>    
</property> 
 <property>
    <name>dfs.ha.automatic-failover.enabled</name>
    <value>true</value>
</property>  

</configuration>

3. core-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
  You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License. See accompanying LICENSE file.
-->

<!-- Put site-specific property overrides in this file. -->

<configuration>
<property>
	  <name>fs.defaultFS</name>
	  <value>hdfs://ns</value>
</property>
<property>
	<name>hadoop.http.staticuser.user</name>
	<value>kfk</value>
</property>

 <property>
         <name>hadoop.tmp.dir</name>
         <value>/opt/modules/hadoop-2.5.0/data/tmp</value>
</property>

 <property>
         <name>dfs.namenode.name.dir</name>
         <value>file://${hadoop.tmp.dir}/dfs/name</value>
</property>

<property>
	<name>ha.zookeeper.quorum.ns</name>
	<value>bigdata-pro01.kfk.com:2181,bigdata-pro02.kfk.com:2181,bigdata-pro03.kfk.com:2181</value>
</property>


</configuration>

4. 将修改的配置分发到其他节点

scp hdfs-site.xml bigdata-pro02.kfk.com:/opt/modules/hadoop-2.5.0/etc/hadoop/
scp hdfs-site.xml bigdata-pro03.kfk.com:/opt/modules/hadoop-2.5.0/etc/hadoop/
scp core-site.xml bigdata-pro02.kfk.com:/opt/modules/hadoop-2.5.0/etc/hadoop/
scp core-site.xml bigdata-pro03.kfk.com:/opt/modules/hadoop-2.5.0/etc/hadoop/

5. HDFS-HA 服务启动及自动故障转移测试
   1）启动所有节点上面的Zookeeper进程
   zkServer.sh start
   2）启动所有节点上面的journalnode进程
   3）在[bigdata-pro01.kfk.com]上，对namenode进行格式化，并启动
   #namenode 格式化
   bin/hdfs namenode -format
   #格式化高可用
   bin/hdfs zkfc -formatZK
   #启动namenode
   bin/hdfs namenode
   4）在[bigdata-pro02.kfk.com]上，同步nn1元数据信息
   bin/hdfs namenode -bootstrapStandby
   5）bigdata-pro02.kfk.com同步完数据后，在bigdata-pro01.kfk.com上，按下ctrl+c来结束namenode进程。然后关闭所有节点上面的journalnode进程
   sbin/hadoop-daemon.sh stop journalnode
   6）一键启动hdfs所有相关进程
   sbin/start-dfs.sh
   hdfs启动之后，kill其中Active状态的namenode，检查另外一个NameNode是否会自动切换为Active状态。同时通过命令上传文件至hdfs，检查hdfs是否可用。