Hadoop（2）安装集群

服务器配置

服务器 IP 配置
hadoop1 192.168.3.51 OpenJDK11
hadoop2 192.168.3.52 OpenJDK11
hadoop3 192.168.3.53 OpenJDK11

所有主机安装

1、安装hadoop

useradd -r -m hadoop -s /bin/bash
su - hadoop
tar zxvf hadoop-3.3.3.tar.gz

2、配置相关的环境变量

bash> vim /home/hadoop/.profile

export HADOOP_HOME=/home/hadoop/hadoop-3.3.3/
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME

export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
export PATH=$PATH:$HADOOP_HOME/sbin:$HADOOP_HOME/bin
export HADOOP_INSTALL=$HADOOP_HOME

export PATH=${PATH}:${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin

3、配置core-site.xml

bash> vim /home/hadoop/hadoop-3.3.3/etc/hadoop/core-site.xml

<configuration>
    <!-- 指定 NameNode 的地址 -->
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://cluster</value>
    </property>

    <property>
        <name>ha.zookeeper.quorum</name>
        <value>hadoop1:2181,hadoop2:2181,hadoop3:2181</value>
    </property>

    <property>
        <name>hadoop.tmp.dir</name>
        <value>/home/hadoop/data/tmp</value>
    </property>

    <property>
        <name>dfs.journalnode.edits.dir</name>
        <value>/home/hadoop/data/journal/local/data</value>
    </property>
</configuration>

4、配置hdfs-site.xml

bash> vim /home/hadoop/hadoop-3.3.3/etc/hadoop/hdfs-site.xml

<configuration>
    <property>
        <name>dfs.nameservices</name>
        <value>cluster</value>
    </property>

    <!-- 集群bi1的相关配置 -->
    <property>
        <name>dfs.ha.namenodes.cluster</name>
        <value>nn1,nn2,nn3</value>
    </property>
    <property>
        <name>dfs.namenode.rpc-address.cluster.nn1</name>
        <value>hadoop1:8020</value>
    </property>
    <property>
        <name>dfs.namenode.rpc-address.cluster.nn2</name>
        <value>hadoop2:8020</value>
    </property>
    <property>
        <name>dfs.namenode.rpc-address.cluster.nn3</name>
        <value>hadoop3:8020</value>
    </property>

    <property>
        <name>dfs.namenode.http-address.cluster.nn1</name>
        <value>hadoop1:9870</value>
    </property>
    <property>
        <name>dfs.namenode.http-address.cluster.nn2</name>
        <value>hadoop2:9870</value>
    </property>
    <property>
        <name>dfs.namenode.http-address.cluster.nn3</name>
        <value>hadoop3:9870</value>
    </property>
    <property>
         <name>dfs.namenode.shared.edits.dir</name>
         <value>qjournal://hadoop1:8485;hadoop2:8485;hadoop3:8485/cluster</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/data/tmp/journaldata</value>
    </property>

    <!-- 开启NameNode失败自动切换 -->
    <property>
        <name>dfs.ha.automatic-failover.enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>dfs.client.failover.proxy.provider.cluster</name>
        <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
    </property>
    <!-- 配置隔离fence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>
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>/home/hadoop/data/tmp/datadir</value>
    </property>
    <property>
        <name>ha.zookeeper.session-timeout.ms</name>
        <value>5000</value>
    </property>
    <!-- true，则打开前文所述的权限系统。如果是 false，权限检查 就是关闭的-->
    <property>
        <name>dfs.permission</name>
        <value>false</value>
    </property>
    <!--webhdfs的LISTSTATUS、LISTFILESTATUS等需要列出文件、文件夹状态的命令-->
    <property>
        <name>dfs.webhdfs.enabled</name>
        <value>true</value>
    </property>
    <!--给文件追加内容-->
    <property>
        <name>dfs.support.append</name>
        <value>true</value>
    </property>
    <property>
        <name>hadoop.proxyuser.hduser.hosts</name>
        <value>*</value>
    </property>
    <property>
        <name>hadoop.proxyuser.hduser.groups</name>
        <value>*</value>
    </property>
</configuration>

5、配置yarn-site.xml

bash> vim /home/hadoop/hadoop-3.3.3/etc/hadoop/yarn-site.xml

<configuration>
    <!-- Site specific YARN configuration properties -->

    <property>
        <name>yarn.resourcemanager.ha.enabled</name>
        <value>true</value>
    </property>
    <!-- 指定RM的cluster id -->
    <property>
        <name>yarn.resourcemanager.cluster-id</name>
        <value>cluster1</value>
    </property>
    <!-- 指定RM的名字 -->
    <property>
        <name>yarn.resourcemanager.ha.rm-ids</name>
        <value>rm1,rm2,rm3</value>
    </property>
    <!-- 分别指定RM的地址 -->
    <property>
        <name>yarn.resourcemanager.hostname.rm1</name>
        <value>hadoop1</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname.rm2</name>
        <value>hadoop2</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname.rm3</name>
        <value>hadoop3</value>
    </property>

    <property>
        <name>yarn.resourcemanager.webapp.address.rm1</name>
        <value>hadoop1:8088</value>
    </property>
    <property>
        <name>yarn.resourcemanager.webapp.address.rm2</name>
        <value>hadoop2:8088</value>
    </property>
    <property>
        <name>yarn.resourcemanager.webapp.address.rm3</name>
        <value>hadoop3:8088</value>
    </property>

    <!-- 指定zk集群地址 -->
    <property>
        <name>yarn.resourcemanager.zk-address</name>
        <value>hadoop1:2181,hadoop2:2181,hadoop3:2181</value>
    </property>
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
    <property>
        <name>yarn.application.classpath</name>
        <value>/home/hadoop/hadoop-3.3.3/etc/hadoop:/home/hadoop/hadoop-3.3.3/share/hadoop/common/lib/*:/home/hadoop/hadoop-3.3.3/share/hadoop/common/*:/home/hadoop/hadoop-3.3.3/share/hadoop/hdfs:/home/hadoop/hadoop-3.3.3/share/hadoop/hdfs/lib/*:/home/hadoop/hadoop-3.3.3/share/hadoop/hdfs/*:/home/hadoop/hadoop-3.3.3/share/hadoop/mapreduce/lib/*:/home/hadoop/hadoop-3.3.3/share/hadoop/mapreduce/*:/home/hadoop/hadoop-3.3.3/share/hadoop/yarn:/home/hadoop/hadoop-3.3.3/share/hadoop/yarn/lib/*:/home/hadoop/hadoop-3.3.3/share/hadoop/yarn/*</value>
    </property>
</configuration>

6、配置mapred-site.xml

bash> vim /home/hadoop/hadoop-3.3.3/etc/hadoop/mapred-site.xml

<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
</configuration>

7、将对应的配置拷贝到其他的节点

bash> vim /home/hadoop/scp.sh

#!/bin/bash

scp /home/hadoop/.profile hadoop2:/home/hadoop/.profile
scp /home/hadoop/.profile hadoop3:/home/hadoop/.profile

scp /home/hadoop/hadoop-3.3.3/etc/hadoop/workers  hadoop2:/home/hadoop/hadoop-3.3.3/etc/hadoop/
scp /home/hadoop/hadoop-3.3.3/etc/hadoop/workers  hadoop3:/home/hadoop/hadoop-3.3.3/etc/hadoop/

scp /home/hadoop/hadoop-3.3.3/etc/hadoop/core-site.xml  hadoop2:/home/hadoop/hadoop-3.3.3/etc/hadoop/
scp /home/hadoop/hadoop-3.3.3/etc/hadoop/core-site.xml  hadoop3:/home/hadoop/hadoop-3.3.3/etc/hadoop/

scp /home/hadoop/hadoop-3.3.3/etc/hadoop/hdfs-site.xml  hadoop2:/home/hadoop/hadoop-3.3.3/etc/hadoop/
scp /home/hadoop/hadoop-3.3.3/etc/hadoop/hdfs-site.xml  hadoop3:/home/hadoop/hadoop-3.3.3/etc/hadoop/

scp /home/hadoop/hadoop-3.3.3/etc/hadoop/mapred-site.xml  hadoop2:/home/hadoop/hadoop-3.3.3/etc/hadoop/
scp /home/hadoop/hadoop-3.3.3/etc/hadoop/mapred-site.xml  hadoop3:/home/hadoop/hadoop-3.3.3/etc/hadoop/

scp /home/hadoop/hadoop-3.3.3/etc/hadoop/yarn-site.xml  hadoop2:/home/hadoop/hadoop-3.3.3/etc/hadoop/
scp /home/hadoop/hadoop-3.3.3/etc/hadoop/yarn-site.xml  hadoop3:/home/hadoop/hadoop-3.3.3/etc/hadoop/

8、配置环境变量hadoop-env.sh

bash> vim /home/hadoop/hadoop-3.3.3/etc/hadoop/hadoop-env.sh

export JAVA_HOME=/opt/jdk-11/
export HADOOP_HOME=/home/hadoop/hadoop-3.3.3/
export HADOOP_OS_TYPE=${HADOOP_OS_TYPE:-$(uname -s)}

9、配置workers

bash> vim /home/hadoop/hadoop-3.3.3/etc/hadoop/workers

hadoop1
hadoop2
hadoop3

初始化

1、启动jounalnode

在hadoop1、hadoop2和hadoop3上执行

/home/hadoop/hadoop-3.3.3/bin/hdfs --daemon start journalnode

2、初始化namenode

在hadoop1上执行

/home/hadoop/hadoop-3.3.3/bin/hdfs namenode -format

3、格式化zkfs

在hadoop1上执行

/home/hadoop/hadoop-3.3.3/bin/hdfs zkfc -formatZK

查看创建是否成功

# 进入任何一个zookeeper的节点
/home/zookeeper/apache-zookeeper-3.7.1-bin/bin/zkCli.sh
   [zk: localhost:2181(CONNECTED) 1] ls /
   [hadoop-ha, zookeeper]

4、启动

在hadoop1上执行即可

/home/hadoop/hadoop-3.3.3/sbin/start-dfs.sh
/home/hadoop/hadoop-3.3.3/sbin/start-yarn.sh

测试

留下评论

您的邮箱地址不会被公开。 必填项已用 * 标注