HA运作机制

什么是HA

HADOOP如何实现HA

HDFS-HA详解

HA集群搭建

server01   namenode   zkfc    > start-dfs.sh

server02   namenode   zkfc

server03   resourcemanager    > start-yarn.sh

server04   resourcemanager

server05   datanode   nodemanager

server06   datanode   nodemanager

server07   datanode   nodemanager

server08   journal node    zookeeper

server09   journal node    zookeeper

server10   journal node    zookeeper

server01   namenode    resourcemanager  zkfc   nodemanager  datanode   zookeeper   journal node

server02   namenode    resourcemanager  zkfc   nodemanager  datanode   zookeeper   journal node

server05   datanode    nodemanager     zookeeper    journal node

<configuration>

<!-- 指定hdfs的nameservice为ns1 -->

<property>

<name>fs.defaultFS</name>

<value>hdfs://ns1/</value>

</property>

<!-- 指定hadoop临时目录 -->

<property>

<name>hadoop.tmp.dir</name>

<value>/home/hadoop/app/hadoop-2.4.1/tmp</value>

</property>

<!-- 指定zookeeper地址 -->

<property>

<name>ha.zookeeper.quorum</name>

<value>weekend05:2181,weekend06:2181,weekend07:2181</value>

</property>

</configuration>

configuration>

<!--指定hdfs的nameservice为ns1，需要和core-site.xml中的保持一致 -->

<property>

<name>dfs.nameservices</name>

<value>ns1</value>

</property>

<!-- ns1下面有两个NameNode，分别是nn1，nn2 -->

<property>

<name>dfs.ha.namenodes.ns1</name>

<value>nn1,nn2</value>

</property>

<!-- nn1的RPC通信地址 -->

<property>

<name>dfs.namenode.rpc-address.ns1.nn1</name>

<value>weekend01:9000</value>

</property>

<!-- nn1的http通信地址 -->

<property>

<name>dfs.namenode.http-address.ns1.nn1</name>

<value>weekend01:50070</value>

</property>

<!-- nn2的RPC通信地址 -->

<property>

<name>dfs.namenode.rpc-address.ns1.nn2</name>

<value>weekend02:9000</value>

</property>

<!-- nn2的http通信地址 -->

<property>

<name>dfs.namenode.http-address.ns1.nn2</name>

<value>weekend02:50070</value>

</property>

<!-- 指定NameNode的edits元数据在JournalNode上的存放位置 -->

<property>

<name>dfs.namenode.shared.edits.dir</name>

<value>qjournal://weekend05:8485;weekend06:8485;weekend07:8485/ns1</value>

</property>

<!-- 指定JournalNode在本地磁盘存放数据的位置 -->

<property>

<name>dfs.journalnode.edits.dir</name>

<value>/home/hadoop/app/hadoop-2.4.1/journaldata</value>

</property>

<!-- 开启NameNode失败自动切换 -->

<property>

<name>dfs.ha.automatic-failover.enabled</name>

<value>true</value>

</property>

<!-- 配置失败自动切换实现方式 -->

<property>

<name>dfs.client.failover.proxy.provider.ns1</name>

<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>

</property>

<!-- 配置隔离机制方法，多个机制用换行分割，即每个机制暂用一行-->

<property>

<name>dfs.ha.fencing.methods</name>

<value>

sshfence

shell(/bin/true)

</value>

</property>

<!-- 使用sshfence隔离机制时需要ssh免登陆 -->

<property>

<name>dfs.ha.fencing.ssh.private-key-files</name>

<value>/home/hadoop/.ssh/id_rsa</value>

</property>

<!-- 配置sshfence隔离机制超时时间 -->

<property>

<name>dfs.ha.fencing.ssh.connect-timeout</name>

<value>30000</value>

</property>

/configuration>

hdfs haadmin -getServiceState nn1

hdfs haadmin –transitionToActive nn1

hdfs haadmin –transitionToStandby nn2

/**

* 如果访问的是一个ha机制的集群

* 则一定要把core-site.xml和hdfs-site.xml配置文件放在客户端程序的classpath下

* 以让客户端能够理解hdfs://ns1/中  “ns1”是一个ha机制中的namenode对——nameservice

* 以及知道ns1下具体的namenode通信地址

* @author

*

*/

public class UploadFile {

public static void main(String[] args) throws Exception  {

Configuration conf = new Configuration();

conf.set("fs.defaultFS", "hdfs://ns1/");

FileSystem fs = FileSystem.get(new URI("hdfs://ns1/"),conf,"hadoop");

fs.copyFromLocalFile(new Path("g:/eclipse-jee-luna-SR1-linux-gtk.tar.gz"), new Path("hdfs://ns1/"));

fs.close();

}

}