hadoop高可用集群搭建

Hadoop HA 集群搭建

集群规划:

	HDFS	YARN	zk
hadoop01	namenode+zkfc+journalnode+datanode	nodemanager+resourcemanager	QuorumPeerMain
hadoop02	namenode+zkfc+journalnode+datanode	nodemanager	QuorumPeerMain
hadoop03	journalnode+datanode	nodemanager+resourcemanager	QuorumPeerMain

1.hadoop基础集群环境准备(1-10步)

2.ZooKeeper集群搭建(1-7步)

3.hadoop分布式集群安装(1-3步)

4.修改hadoop配置文件

进入到hadoop配置文件目录

cd /home/hadoop/apps/hadoop-2.7.6/etc/hadoop

4.1修改hadoop-env.sh

改一下JAVA_HOME

export JAVA_HOME=/home/hadoop/apps/jdk1.8.0_73

• 后面的文件都是将所有内容复制到configuration标签中

4.2修改core-site.xml

<property>
<name>fs.defaultFSname>
<value>hdfs://bd1906/value>
property>


<property>
<name>hadoop.tmp.dirname>
<value>/home/hadoop/data/hadoopdata/value>
property>


<property>
<name>ha.zookeeper.quorumname>
<value>hadoop01:2181,hadoop02:2181,hadoop03:2181value>
property>

4.3修改hdfs-site.xml

• data的存储位置可以根据实际情况来修改一下

<property>
 <name>dfs.replicationname>
 <value>2value>
property>


<property>
 <name>dfs.nameservicesname>
 <value>bd1906value>
property>


<property>
 <name>dfs.ha.namenodes.bd1906name>
 <value>nn1,nn2value>
property>


<property>
 <name>dfs.namenode.rpc-address.bd1906.nn1name>
 <value>hadoop01:8020value>
property>


<property>
 <name>dfs.namenode.http-address.bd1906.nn1name>
 <value>hadoop01:50070value>
property>


<property>
 <name>dfs.namenode.rpc-address.bd1906.nn2name>
 <value>hadoop02:8020value>
property>


<property>
 <name>dfs.namenode.http-address.bd1906.nn2name>
 <value>hadoop02:50070value>
property>


<property>
 <name>dfs.namenode.shared.edits.dirname>
<value>qjournal://hadoop01:8485;hadoop02:8485;hadoop03:8485/bd1906value>
property>


<property>
 <name>dfs.journalnode.edits.dirname>
 <value>/home/hadoop/data/hadoopdata/journaldatavalue>
property>


<property>
 <name>dfs.ha.automatic-failover.enabledname>
 <value>truevalue>
property>



<property>
 <name>dfs.client.failover.proxy.provider.bd1906name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvidervalue>
property>


<property>
 <name>dfs.ha.fencing.methodsname>
 <value>
 sshfence
 shell(/bin/true)
 value>
property>


<property>
 <name>dfs.ha.fencing.ssh.private-key-filesname>
 <value>/home/hadoop/.ssh/id_rsavalue>
property>


<property>
 <name>dfs.ha.fencing.ssh.connect-timeoutname>
 <value>30000value>
property>

4.4修改mapred-site.xml

<property>
 <name>mapreduce.framework.namename>
 <value>yarnvalue>
property>


<property>
<name>mapreduce.jobhistory.addressname>
<value>hadoop02:10020value>
property>

<property>
<name>mapreduce.jobhistory.webapp.addressname>
<value>hadoop02:19888value>
property>

4.5修改yarn-site.xml

<property>
 <name>yarn.resourcemanager.ha.enabledname>
 <value>truevalue>
property>

<property>
 <name>yarn.resourcemanager.cluster-idname>
 <value>yarn_bd1906value>
property>

<property>
 <name>yarn.resourcemanager.ha.rm-idsname>
 <value>rm1,rm2value>
property>


<property>
 <name>yarn.resourcemanager.hostname.rm1name>
 <value>hadoop01value>
property>
<property>
 <name>yarn.resourcemanager.hostname.rm2name>
 <value>hadoop03value>
property>

<property>
 <name>yarn.resourcemanager.zk-addressname>
 <value>hadoop01:2181,hadoop02:2181,hadoop03:2181value>
property>


<property>
 <name>yarn.nodemanager.aux-servicesname>
 <value>mapreduce_shufflevalue>
property>


<property>
 <name>yarn.log-aggregation-enablename>
 <value>truevalue>
property>


<property>
 <name>yarn.log-aggregation.retain-secondsname>
 <value>86400value>
property>


<property>
 <name>yarn.resourcemanager.recovery.enabledname>
 <value>truevalue>
property>


<property>
 <name>yarn.resourcemanager.store.classname>
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStorevalue>
property>

4.6增加slaves

vi slaves

加入

hadoop01
hadoop02
hadoop03

5.远程发送安装包

• 先切换到有hadoop-2.7.6文件夹的目录

cd /home/hadoop/apps

发送

scp -r hadoop-2.7.6 hadoop02:/home/hadoop/apps/
scp -r hadoop-2.7.6 hadoop03:/home/hadoop/apps/

6.远程发送配置文件

sudo scp /etc/profile hadoop02:/etc/
sudo scp /etc/profile hadoop03:/etc/

三台机器同时执行

source /etc/profile
hadoop version

7.集群初始化操作

• 必须按照步骤一步一步的来
• 每一步都要成功

7.1启动zookeeper服务

三台机器都要启动

zkServer.sh start

7.2启动journalnode

三台机器都要启动

hadoop-daemon.sh start journalnode

7.3格式化namenode

在hadoop01(任意一个namenode节点)中，看到如图所示的successfully再继续往下

hadoop namenode -format

7.4发送元数据

将hadoop1的元数据发送到hadoop02中

scp -r /home/hadoop/data/hadoopdata/dfs hadoop02:/home/hadoop/data/hadoopdata 

7.5格式化zkfc

在hadoop01(任意一个namenode节点)中，看到如图所示的successfully再继续往下

hdfs zkfc -formatZK

7.6启动

启动hdfs(任意节点)

start-dfs.sh

启动yarn(在hadoop01)

start-yarn.sh

在另一个节点启动resourcemanager(hadoop03)

yarn-daemon.sh start resourcemanager

最后查看一下进程

jps

配置成功！