【Hadoop离线基础总结】完全分布式环境搭建

完全分布式环境搭建

---

服务规划

适用于工作当中正式环境搭建

---

安装步骤

• 第一步：安装包解压
  停止之前的Hadoop集群的所有服务，并删除所有机器的Hadoop安装包，然后重新解压Hadoop压缩包
  
  
  

三台机器都执行
rm -rf /export/servers/hadoop-2.7.5/

在第一台机器解压压缩包
cd /export/softwares

tar -zxvf hadoop-2.7.5.tar.gz -C ../servers/

 

• 第二步：配置文件的修改
  进入到一下文件夹，并用notepad++或者finalshell等脚本编辑工具打开一下文件

cd /export/servers/hadoop-2.7.5/etc/hadoop

修改core-site.xml

<configuration>

	<property>
		<name>ha.zookeeper.quorumname>
		<value>node01:2181,node02:2181,node03:2181value>
	property>
 
	<property>
		<name>fs.defaultFSname>
		<value>hdfs://nsvalue>
	property>
 
	<property>
		<name>hadoop.tmp.dirname>
		<value>/export/servers/hadoop-2.7.5/data/tmpvalue>
	property>
	 
	<property>
		<name>fs.trash.intervalname>
		<value>10080value>
	property>
configuration>

修改hdfs-site.xml

<configuration>

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

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

	
	<property>
		<name>dfs.namenode.rpc-address.ns.nn1name>
		<value>node01:8020value>
	property>
	
	<property>
		<name>dfs.namenode.rpc-address.ns.nn2name>
		<value>node02:8020value>
	property>
	
	<property>
		<name>dfs.namenode.servicerpc-address.ns.nn1name>
		<value>node01:8022value>
	property>
	
	<property>
		<name>dfs.namenode.servicerpc-address.ns.nn2name>
		<value>node02:8022value>
	property>
	
	
	<property>
		<name>dfs.namenode.http-address.ns.nn1name>
		<value>node01:50070value>
	property>
	
	<property>
		<name>dfs.namenode.http-address.ns.nn2name>
		<value>node02:50070value>
	property>
	
	
	<property>
		<name>dfs.namenode.shared.edits.dirname>
		<value>qjournal://node01:8485;node02:8485;node03:8485/ns1value>
	property>
	
	<property>
		<name>dfs.client.failover.proxy.provider.nsname>
		<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvidervalue>
	property>
	
	
	<property>
		<name>dfs.ha.fencing.methodsname>
		<value>sshfencevalue>
	property>
	
	
	<property>
		<name>dfs.ha.fencing.ssh.private-key-filesname>
		<value>/root/.ssh/id_rsavalue>
	property>
	
	<property>
		<name>dfs.journalnode.edits.dirname>
		<value>/export/servers/hadoop-2.7.5/data/dfs/jnvalue>
	property>
	
	<property>
		<name>dfs.ha.automatic-failover.enabledname>
		<value>truevalue>
	property>
	
	<property>
		<name>dfs.namenode.name.dirname>
		<value>file:///export/servers/hadoop-2.7.5/data/dfs/nn/namevalue>
	property>
	
	<property>
		<name>dfs.namenode.edits.dirname>
		<value>file:///export/servers/hadoop-2.7.5/data/dfs/nn/editsvalue>
	property>
	
	<property>
		<name>dfs.datanode.data.dirname>
		<value>file:///export/servers/hadoop-2.7.5/data/dfs/dnvalue>
	property>
	
	<property>
		<name>dfs.permissionsname>
		<value>falsevalue>
	property>
	
	<property>
		<name>dfs.blocksizename>
		<value>134217728value>
	property>
configuration>

修改hadoop-env.sh

# The java implementation to use.
export JAVA_HOME=/export/servers/jdk1.8.0_141

修改mapred-site.xml

<configuration>
	
	<property>
        <name>mapreduce.framework.namename>
        <value>yarnvalue>
	property>
	
	<property>
        <name>mapreduce.jobhistory.addressname>
        <value>node03:10020value>
	property>
	
	<property>
        <name>mapreduce.jobhistory.webapp.addressname>
        <value>node03:19888value>
	property>
	
	<property>
        <name>mapreduce.jobtracker.system.dirname>
        <value>/export/servers/hadoop-2.7.5/data/system/jobtrackervalue>
	property>
	
	<property>
        <name>mapreduce.map.memory.mbname>
        <value>1024value>
	property>
	
	
	<property>
        <name>mapreduce.reduce.memory.mbname>
        <value>1024value>
	property>
	
	
	<property>
        <name>mapreduce.task.io.sort.mbname>
        <value>100value>
	property>
 
	
	
	<property>
        <name>mapreduce.task.io.sort.factorname>
        <value>10value>
	property>
	
	<property>
        <name>mapreduce.reduce.shuffle.parallelcopiesname>
        <value>25value>
	property>
	<property>
        <name>yarn.app.mapreduce.am.command-optsname>
        <value>-Xmx1024mvalue>
	property>
	
	<property>
        <name>yarn.app.mapreduce.am.resource.mbname>
        <value>1536value>
	property>
	
	<property>
        <name>mapreduce.cluster.local.dirname>
        <value>/export/servers/hadoop-2.7.5/data/system/localvalue>
	property>
	configuration>

修改yarn-site.xml

<configuration>






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

	 
	<property>
        <name>yarn.resourcemanager.ha.enabledname>
        <value>truevalue>
	property>
	
	<property>
        <name>yarn.resourcemanager.cluster-idname>
        <value>myclustervalue>
	property>
	
	<property>
        <name>yarn.resourcemanager.ha.rm-idsname>
        <value>rm1,rm2value>
	property>
	
	<property>
        <name>yarn.resourcemanager.hostname.rm1name>
        <value>node03value>
	property>
	
	<property>
        <name>yarn.resourcemanager.hostname.rm2name>
        <value>node02value>
	property>

	
	<property>
        <name>yarn.resourcemanager.address.rm1name>
        <value>node03:8032value>
	property>
	<property>
        <name>yarn.resourcemanager.scheduler.address.rm1name>
        <value>node03:8030value>
	property>
	<property>
        <name>yarn.resourcemanager.resource-tracker.address.rm1name>
        <value>node03:8031value>
	property>
	<property>
        <name>yarn.resourcemanager.admin.address.rm1name>
        <value>node03:8033value>
	property>
	<property>
        <name>yarn.resourcemanager.webapp.address.rm1name>
        <value>node03:8088value>
	property>

	
	<property>
        <name>yarn.resourcemanager.address.rm2name>
        <value>node02:8032value>
	property>
	<property>
        <name>yarn.resourcemanager.scheduler.address.rm2name>
        <value>node02:8030value>
	property>
	<property>
        <name>yarn.resourcemanager.resource-tracker.address.rm2name>
        <value>node02:8031value>
	property>
	<property>
        <name>yarn.resourcemanager.admin.address.rm2name>
        <value>node02:8033value>
	property>
	<property>
        <name>yarn.resourcemanager.webapp.address.rm2name>
        <value>node02:8088value>
	property>
	
	<property>
        <name>yarn.resourcemanager.recovery.enabledname>
        <value>truevalue>
	property>
	
	<property>       
		<name>yarn.resourcemanager.ha.idname>
		<value>rm1value>
       <description>If we want to launch more than one RM in single node, we need this configurationdescription>
	property>
	   
	   
	<property>
        <name>yarn.resourcemanager.store.classname>
        <value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStorevalue>
	property>
	<property>
        <name>yarn.resourcemanager.zk-addressname>
        <value>node02:2181,node03:2181,node01:2181value>
        <description>For multiple zk services, separate them with commadescription>
	property>
	 
	<property>
        <name>yarn.resourcemanager.ha.automatic-failover.enabledname>
        <value>truevalue>
        <description>Enable automatic failover; By default, it is enabled only when HA is enabled.description>
	property>
	<property>
        <name>yarn.client.failover-proxy-providername>
        <value>org.apache.hadoop.yarn.client.ConfiguredRMFailoverProxyProvidervalue>
	property>
	
	<property>
        <name>yarn.nodemanager.resource.cpu-vcoresname>
        <value>4value>
	property>
	
	<property>
        <name>yarn.nodemanager.resource.memory-mbname>
        <value>512value>
	property>
	
	<property>
        <name>yarn.scheduler.minimum-allocation-mbname>
        <value>512value>
	property>
	
	<property>
        <name>yarn.scheduler.maximum-allocation-mbname>
        <value>512value>
	property>
	
	<property>
        <name>yarn.log-aggregation.retain-secondsname>
        <value>2592000value>
	property>
	
	<property>
        <name>yarn.nodemanager.log.retain-secondsname>
        <value>604800value>
	property>
	
	<property>
        <name>yarn.nodemanager.log-aggregation.compression-typename>
        <value>gzvalue>
	property>
	
	<property>
        <name>yarn.nodemanager.local-dirsname>
        <value>/export/servers/hadoop-2.7.5/yarn/localvalue>
	property>
	
	<property>
        <name>yarn.resourcemanager.max-completed-applicationsname>
        <value>1000value>
	property>
	
	<property>
        <name>yarn.nodemanager.aux-servicesname>
        <value>mapreduce_shufflevalue>
	property>

	 
	<property>
        <name>yarn.resourcemanager.connect.retry-interval.msname>
        <value>2000value>
	property>
configuration>

修改slaves

node01
node02
node03

 

• 第三步：启动集群
  将第一台机器的hadoop安装包分发到第二台、第三台机器上

cd /export/servers

scp -r hadoop-2.7.5/ node02:$PWD
scp -r hadoop-2.7.5/ node03:$PWD

三台机器都创建一下所需的文件夹

mkdir -p /export/servers/hadoop-2.7.5/data/dfs/nn/name
mkdir -p /export/servers/hadoop-2.7.5/data/dfs/nn/edits
mkdir -p /export/servers/hadoop-2.7.5/data/dfs/nn/name
mkdir -p /export/servers/hadoop-2.7.5/data/dfs/nn/edits

更改node的rm2

在第二台机器执行
cd /export/servers/hadoop-2.7.5/etc/hadoop
vim yarn-site.xml

	
	<property>       
		<name>yarn.resourcemanager.ha.idname>
		<value>rm2value>
       <description>If we want to launch more than one RM in single node, we need this configurationdescription>
	property>

启动HDFS

在第一台机器执行
cd /export/servers/hadoop-2.7.5

bin/hdfs zkfc -formatZK		-> 格式化zk
sbin/hadoop-daemons.sh start journalnode		-> 启动journalnode
bin/hdfs namenode -format		-> 格式化NameNode上面所有的数据
bin/hdfs namenode -initializeSharedEdits -force			-> 强制初始化元数据信息
sbin/start-dfs.sh

在第二台机器执行
cd /export/servers/hadoop-2.7.5

bin/hdfs namenode -bootstrapStandby		-> 设置NameNode为StandBy状态
sbin/hadoop-daemon.sh start namenode

启动YARN

在第三台机器上执行
cd /export/servers/hadoop-2.7.5
sbin/start-yarn.sh

在第二台机器上执行
cd /export/servers/hadoop-2.7.5
sbin/start-yarn.sh

查看resourceManager状态

在第三台机器上执行
cd /export/servers/hadoop-2.7.5
bin/yarn rmadmin -getServiceState rm1

cd /export/servers/hadoop-2.7.5
bin/yarn rmadmin -getServiceState rm2

在node03启动JobHistory

cd /export/servers/hadoop-2.7.5
sbin/mr-jobhistory-daemon.sh start historyserver

---

tips

node01机器查看hdfs状态：node01:50070
node02机器查看hdfs状态：node02:50070
yarn集群访问查看：node03:8088
历史任务浏览界面：node03:19888