012 hadoop集群HA搭建(namenode+resourcemanager)

1.创建普通用户

for i in {1..3};do ssh node$i 'useradd hadoop;echo "123456" | passwd --stdin hadoop';done

2.将普通用户加入至sudoers 文件中（可以免密使用sudo指令）。

   vim  /etc/sudoers  追加以下内容

hadoop    ALL=(ALL)       NOPASSWD: ALL

  将/etc/sudoers拷贝至其他节点

for i in {2..3};do scp /etc/sudoers node$i:/etc/sudoers;done

3.修改/usr/modules的所有者为hadoop

#修改权限
for i in {1..3};do ssh node$i 'chown hadoop:hadoop /usr/modules/';done

4.所有节点切换至普通用户hadoop

      su - hadoop

5.上传安装包至node1节点/usr/modules/software

6.免密登录(node1免密登录node1,node2,node3    node3免密登录node1,node2,node3)

      免密登录

      安装psmisc（解决主备无法正常切换）

      sudo yum install psmisc -y

7.解压

     tar -zxf hadoop-2.9.2.tar.gz -C /usr/modules/

8.配置hadoop环境变量

   su - root

  vim  /etc/profile 

export JAVA_HOME=/usr/modules/jdk1.8.0_191
export HADOOP_HOME=/usr/modules/hadoop-2.9.2
export PATH=$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$JAVA_HOME/bin:$JAVA_HOME/jre/bin:$PATH

将/etc/profile拷贝至另外2台节点，所有节点重新加载环境变量

  for i in {2..3};do scp /etc/profile node$i:/etc/profile;done

.   /etc/profile

9.修改配置文件

   vim  /usr/modules/hadoop-2.9.2/etc/hadoop/hadoop-env.sh

#修改25行如下
export JAVA_HOME=/usr/modules/jdk1.8.0_191

   vim  /usr/modules/hadoop-2.9.2/etc/hadoop/core-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
   <!-- 指定集群的虚拟名称 -->
   <property>
        <name>fs.defaultFS</name>
        <value>hdfs://mycluster</value>
    </property>

    <property>
        <name>hadoop.tmp.dir</name>
        <value>/usr/modules/hadoop-2.9.2/data</value>
    </property>
    <property>
        <name>ha.zookeeper.quorum</name>
        <value>node1:2181,node2:2181,node3:2181</value>
    </property>
</configuration>

    vim  /usr/modules/hadoop-2.9.2/etc/hadoop/hdfs-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>dfs.replication</name>
        <value>2</value>
    </property>
    <property>
        <name>dfs.nameservices</name>
        <value>mycluster</value>
    </property>
    <property>
        <name>dfs.ha.namenodes.mycluster</name>
        <value>nn1,nn2</value>
    </property>
    <property>
        <name>dfs.namenode.rpc-address.mycluster.nn1</name>
        <value>node1:8020</value>
    </property>
    <property>
        <name>dfs.namenode.rpc-address.mycluster.nn2</name>
        <value>node3:8020</value>
    </property>
    <property>
        <name>dfs.namenode.http-address.mycluster.nn1</name>
        <value>node1:50070</value>
    </property>
    <property>
        <name>dfs.namenode.http-address.mycluster.nn2</name>
        <value>node3:50070</value>
    </property>
    <property>
        <name>dfs.namenode.shared.edits.dir</name>
        <value>qjournal://node1:8485;node2:8485/mycluster</value>
    </property>
    <property>
        <name>dfs.journalnode.edits.dir</name>
        <value>/usr/modules/hadoop-2.9.2/jn/data</value>
    </property>
    <property>
        <name>dfs.client.failover.proxy.provider.mycluster</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/hadoop/.ssh/id_rsa</value>
    </property>
    <property>
        <name>dfs.ha.automatic-failover.enabled</name>
        <value>true</value>
    </property>
</configuration>

  vim  /usr/modules/hadoop-2.9.2/etc/hadoop/slaves

node1
node2
node3

 

10.集群拷贝

  for i in {2,3};do scp -r /usr/modules/hadoop-2.9.2 node$i:/usr/modules;done > /dev/null

11.启动集群

1、启动zookeeper集群
2、分别启动journalnode
 hadoop-daemon.sh start journalnode
3、其中一个namenode上格式化集群
 hdfs namenode -format
4、启动
 hadoop-daemon.sh start namenode
5、另外一台namenode同步数据
 hdfs namenode -bootstrapStandby
6、格式化zookeeper
 hdfs zkfc -formatZK
7、启动hadoop集群
 start-dfs.sh

12.单独启动 namenode、datanode

     hadoop-daemon.sh start namenode|datanode

     单独启动进程

13.yarn的HA配置

     vim /usr/modules/hadoop-2.9.2/etc/hadoop/yarn-site.xml

<?xml version="1.0"?>
<configuration>
<!-- Site specific YARN configuration properties -->
 <property>
   <name>yarn.nodemanager.aux-services</name>
   <value>mapreduce_shuffle</value>
 </property>
 <!-- 启动yarn HA -->
 <property>
   <name>yarn.resourcemanager.ha.enabled</name>
   <value>true</value>
 </property>
 <!-- id不能和nameservice id重复 -->
 <property>
   <name>yarn.resourcemanager.cluster-id</name>
   <value>rmha</value>
 </property>
 <property>
   <name>yarn.resourcemanager.ha.rm-ids</name>
   <value>rm1,rm2</value>
 </property>
 <property>
   <name>yarn.resourcemanager.hostname.rm1</name>
   <value>node1</value>
 </property>
 <property>
   <name>yarn.resourcemanager.hostname.rm2</name>
   <value>node2</value>
 </property>
 <property>
   <name>yarn.resourcemanager.webapp.address.rm1</name>
   <value>node1:8088</value>
 </property>
 <property>
   <name>yarn.resourcemanager.webapp.address.rm2</name>
   <value>node2:8088</value>
 </property>
 <property>
   <name>yarn.resourcemanager.zk-address</name>
   <value>node1:2181,node2:2181,node3:2181</value>
 </property>
</configuration>

   vim /usr/modules/hadoop-2.9.2/etc/hadoop/mapred-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
</configuration>

14.yarn的HA配置文件拷贝

 for i in {2..3}; do scp /usr/modules/hadoop-2.9.2/etc/hadoop/yarn-site.xml node$i:/usr/modules/hadoop-2.9.2/etc/hadoop/yarn-site.xml;done

 for i in {2..3}; do scp /usr/modules/hadoop-2.9.2/etc/hadoop/mapred-site.xml node$i:/usr/modules/hadoop-2.9.2/etc/hadoop/mapred-site.xml;done

15.yarn的HA启动

 主节点：start-yarn.sh

 从节点：yarn-daemon.sh start resourcemanager