高可用Hadoop集群搭建

配置

1. 配置hosts

在/etc/hosts中配置ip与机器名关系

192.168.0.1   lc2
192.168.0.2   lc3
192.168.0.3   lc4

2. 配置无秘钥登录

• 生成秘钥

ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa

• 拷贝
  ssh-copy-id -i ~/.ssh/id_rsa.pub user@st1

3. 配置java环境

省略

4. Zookeeper集群搭建

集群搭建

5. Hadoop配置

• core.xml

<configuration>
        <!--nameservices-->
        <property>
            <name>fs.defaultFS</name>
            <value>hdfs://ns</value>
        </property>
    
        <property>
            <name>hadoop.tmp.dir</name>
            <value>/data/hadoop/tmp</value>
        </property>
        
        <!--zookeeper集群-->
        <property>
            <name>ha.zookeeper.quorum</name>
            <value>lc2:2181,lc3:2181,lc4:2181</value>
        </property>
</configuration>

• hdfs-site.xml

<configuration>
    <!--指定hdfs的nameservice为ns，需要和core-site.xml中的保持一致 -->
    <property>
        <name>dfs.nameservices</name>
        <value>ns</value>
    </property>
    <!-- ns下面有两个NameNode，分别是nn1，nn2 -->
    <property>
        <name>dfs.ha.namenodes.ns</name>
        <value>nn1,nn2</value>
    </property>
    <!-- nn1的RPC通信地址 -->
    <property>
        <name>dfs.namenode.rpc-address.ns.nn1</name>
        <value>lc2:9000</value>
    </property>
    <!-- nn1的http通信地址 -->
    <property>
        <name>dfs.namenode.http-address.ns.nn1</name>
        <value>lc2:50070</value>
    </property>
    <!-- nn2的RPC通信地址 -->
    <property>
        <name>dfs.namenode.rpc-address.ns.nn2</name>
        <value>lc3:9000</value>
    </property>
    <!-- nn2的http通信地址 -->
    <property>
        <name>dfs.namenode.http-address.ns.nn2</name>
        <value>lc3:50070</value>
    </property>
    <!-- 指定NameNode的元数据在JournalNode上的存放位置 -->
    <property>
        <name>dfs.namenode.shared.edits.dir</name>
        <value>qjournal://lc2:8485;lc3:8485;lc4:8485/ns</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>/data/hadoop/journal</value>
    </property>
    <!-- 开启NameNode故障时自动切换 -->
    <property>
        <name>dfs.ha.automatic-failover.enabled</name>
        <value>true</value>
    </property>
    <!-- 配置失败自动切换实现方式 -->
    <property>
        <name>dfs.client.failover.proxy.provider.ns</name>
        <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
    </property>
    <!-- 配置隔离机制 -->
    <property>
        <name>dfs.ha.fencing.methods</name>
        <value>sshfence</value>
    </property>
    <!-- 使用隔离机制时需要ssh免登陆 -->
    <property>
        <name>dfs.ha.fencing.ssh.private-key-files</name>
        <value>/home/magneto/.ssh/id_rsa</value>
    </property>

    <!-- 在NN和DN上开启WebHDFS (REST API)功能,不是必须 -->
    <property>
        <name>dfs.webhdfs.enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>dfs.permissions</name>
        <value>false</value>
    </property>
    <property>
        <name>dfs.replication</name>
        <value>3</value>
    </property>
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>file:///data/hadoop/name</value>
    </property>
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>file:///data/hadoop/data</value>
    </property>
</configuration>

• yarn-site.xml

<configuration>
    <property>
        <name>yarn.resourcemanager.ha.enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>yarn.resourcemanager.cluster-id</name>
        <value>rs</value>
    </property>
    <property>
        <name>yarn.resourcemanager.ha.rm-ids</name>
        <value>rm1,rm2</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname.rm1</name>
        <value>lc3</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname.rm2</name>
        <value>lc4</value>
    </property>
    <property>
        <name>yarn.resourcemanager.webapp.address.rm1</name>
        <value>lc3:8088</value>
    </property>
    <property>
        <name>yarn.resourcemanager.webapp.address.rm2</name>
        <value>lc4:8088</value>
    </property>
    <property>
        <name>yarn.resourcemanager.zk-address</name>
        <value>lc2:2181,lc3:2181,lc4:2181</value>
    </property>
    <property>
        <name>yarn.nodemanager.vmem-pmem-ratio</name>
        <value>1.5</value>
    </property>

    <property>
        <name>yarn.nodemanager.resource.memory-mb</name>
        <value>50000</value>
    </property>

    <property>
        <name>yarn.nodemanager.resource.cpu-vcores</name>
        <value>80</value>
    </property>

    <property>
        <name>yarn.resourcemanager.scheduler.class</name>
        <value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler</value>
    </property>

    <property>
        <name>yarn.scheduler.minimum-allocation-mb</name>
        <value>2048</value>
    </property>
    <property>
        <name>yarn.scheduler.maximum-allocation-mb</name>
        <value>32768</value>
    </property>
    <property>
        <name>yarn.scheduler.maximum-allocation-vcores</name>
        <value>24</value>
    </property>
    <property>
        <name>yarn.scheduler.minimum-allocation-vcores</name>
        <value>1</value>
    </property>
    <property>
        <name>yarn.acl.enable</name>
        <value>true</value>
        <description>使用使用ACL，默认是false</description>
    </property>

    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
</configuration>

• mapred-site.xml

<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
    <property>
        <name>mapreduce.cluster.acls.enabled</name>
        <value>true</value>
    </property>
</configuration>

• slaves

lc2
lc3
lc4

6. 配置Hadoop环境变量

export HADOOP_HOME=/usr/local/hadoop
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
export YARN_HOME=$HADOOP_HOME
export YARN_CONF_DIR=$HADOOP_HOME/etc/hadoop
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin

接下来拷贝hadoop目录到所有机器上。

启动

1.启动zookeeper集群

在所有配置了zookeeper机器上执行sh zkServer.sh start

2.启动journalno

在所有journalnode上执行sbin/hadoop-daemons.sh start journalnode

4.格式化zkfc,让在zookeeper中生成ha节点

在lc2上执行如下命令，完成格式化
hdfs zkfc –formatZK
格式化hdfs，执行hadoop namenode –format

5.启动namenode

首先在lc2上启动active节点，在lc2上执行如下命令sbin/hadoop-daemon.sh start namenode
在lc3上同步namenode的数据，执行hdfs namenode –bootstrapStandby
启动lc3上的namenode作为standby，执行sbin/hadoop-daemon.sh start namenode

6.启动datanode

执行sbin/hadoop-daemons.sh start datanode

7.启动ZKFC

在lc2上执行如下命令，完成ZKFC的启动
执行sbin/hadoop-daemons.sh start zkfc

8.启动yarn

执行start-yarn.sh
yarn-daemons.sh start resourcemanager