五、搭建高可用集群

tar -xvf zookeeper-3.5.7.tar.gz

vim /etc/profile

export ZOOKEEPER_HOME=/usr/local/soft/zookeeper-3.5.7
export PATH=$PATH:$ZOOKEEPER_HOME/bin


source /etc/profile

cd conf
cp  zoo_sample.cfg zoo.cfg

修改
dataDir=/usr/local/soft/zookeeper-3.5.7/data

增加
server.0=master:2888:3888
server.1=node1:2888:3888
server.2=node2:2888:3888

scp -r zookeeper-3.5.7node1:`pwd`
scp -r zookeeper-3.5.7 node2:`pwd`

配置node1和node2的环境变量
scp /etc/profile node1:/etc/
scp /etc/profile node2:/etc/ 

 

在所有节点执行
source /etc/profile

 

mkdir /usr/local/soft/zookeeper-3.5.7/data

在data目录下创建myid文件
vim myid 
master,node1,node2分别加上0，1，2

zkServer.sh status 查看状态

当有一个leader的时候启动成功

创建目录
create /test test
create /test/a 1

获取数据
get /test
 
ls /test

delete 只能删除没有子节点的节点
rmr /test  删除节点

添加
<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://cluster</value>
    </property>
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/usr/local/soft/hadoop-3.1.1/tmp</value>
    </property>
    <property>
        <name>fs.trash.interval</name>
        <value>1440</value>
    </property>
    <property>
          <name>ha.zookeeper.quorum</name>
          <value>master:2181,node1:2181,node2:2181</value>
    </property>
</configuration>

<configuration>
<!-- 指定hdfs元数据存储的路径 （文件夹会自动创建）-->
<property>
<name>dfs.namenode.name.dir</name>
<value>/usr/local/soft/hadoop-3.1.1/data/namenode</value>
</property>

<!-- 指定hdfs数据存储的路径 -->
<property>
<name>dfs.datanode.data.dir</name>
<value>/usr/local/soft/hadoop-3.1.1/data/datanode</value>
</property>

<!-- 数据备份的个数 -->
<property>
<name>dfs.replication</name>
<value>1</value>
</property>

<!-- 关闭权限验证 -->
<property>
<name>dfs.permissions.enabled</name>
<value>false</value>
</property>

<!-- 开启WebHDFS功能（基于REST的接口服务） -->
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>

<!-- //////////////以下为HDFS HA的配置////////////// -->
<!-- 指定hdfs的nameservices名称为mycluster -->
<property>
<name>dfs.nameservices</name>
<value>cluster</value>
</property>

<!-- 指定cluster的两个namenode的名称分别为nn1,nn2 -->
<property>
<name>dfs.ha.namenodes.cluster</name>
<value>nn1,nn2</value>
</property>

<!-- 配置nn1,nn2的rpc通信端口 -->
<property>
<name>dfs.namenode.rpc-address.cluster.nn1</name>
<value>master:8020</value>
</property>
<property>
<name>dfs.namenode.rpc-address.cluster.nn2</name>
<value>node1:8020</value>
</property>

<!-- 配置nn1,nn2的http通信端口 -->
<property>
<name>dfs.namenode.http-address.cluster.nn1</name>
<value>master:9870</value>
</property>
<property>
<name>dfs.namenode.http-address.cluster.nn2</name>
<value>node1:9870</value>
</property>

<!-- 指定namenode元数据存储在journalnode中的路径 -->
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://master:8485;node1:8485;node2:8485/cluster</value>
</property>

<!-- 指定journalnode日志文件存储的路径 -->
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/usr/local/soft/hadoop-3.1.1/data/journal</value>
</property>

<!-- 指定HDFS客户端连接active namenode的java类 -->
<property>
<name>dfs.client.failover.proxy.provider.cluster</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>

<!-- 配置隔离机制为ssh -->
<property>
<name>dfs.ha.fencing.methods</name>
<value>
sshfence
shell(/bin/true)
</value>
</property>

<!-- 指定秘钥的位置 -->
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/root/.ssh/id_rsa</value>
</property>

<!-- 开启自动故障转移 -->
<property>  
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
</configuration>

添加
<configuration>
<!-- NodeManager上运行的附属服务，需配置成mapreduce_shuffle才可运行MapReduce程序 -->
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>

<!-- 开启日志 -->
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>

<!-- 配置日志删除时间为7天，-1为禁用，单位为秒 -->
<property>
<name>yarn.log-aggregation.retain-seconds</name>
<value>604800</value>
</property>


<!-- //////////////以下为YARN HA的配置////////////// -->
<!-- 开启YARN HA -->
<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>

<!-- 启用自动故障转移 -->
<property>
<name>yarn.resourcemanager.ha.automatic-failover.enabled</name>
<value>true</value>
</property>

<!-- 指定YARN HA的名称 -->
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>yarncluster</value>
</property>

<!-- 指定两个resourcemanager的名称 -->
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>

<!-- 配置rm1，rm2的主机 -->
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>master</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>node1</value>
</property>

<!-- 配置YARN的http端口 -->
<property>
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>master:8088</value>
</property>    
<property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>node1:8088</value>
</property>

<!-- 配置zookeeper的地址 -->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>master:2181,node1:2181,node2:2181</value>
</property>

<!-- 配置zookeeper的存储位置 -->
<property>
<name>yarn.resourcemanager.zk-state-store.parent-path</name>
<value>/rmstore</value>
</property>

<!-- 开启yarn resourcemanager restart -->
<property>
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property>

<!-- 配置resourcemanager的状态存储到zookeeper中 -->
<property>
<name>yarn.resourcemanager.store.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
</property>

<!-- 配置nodemanager IPC的通信端口 -->
<property>
<name>yarn.nodemanager.address</name>
<value>0.0.0.0:45454</value>
</property>
</configuration>