Hadoop HA 搭建
程序员文章站
2022-07-06 16:20:44
...
主机名 | IP | 软件包 |
001 | 192.168.xxx.xx | jdk,hadoop,zk |
002 | 192.168.xxx.xx | jdk,hadoop,zk |
003 | 192.168.xxx.xx | jdk,hadoop,zk |
安装Zookeeper见————ZOOKEEPER搭建
安装Hadoop
1、解压安装包
$> tar -zxvf xxxxxx -C /soft/
2、修改环境变量
HADOOP_HOME=/soft/hadoop-2.7.2/
PATH=$HADOOP_HOME/bin:$PATH
export PATH
测试环境变量
which hadoop
3、修改配置文件(/soft/hadoop-2.7.2/etc/hadoop)
【hadoop-env.sh】
export JAVA_HOME=/etc/tdng/jdk1.8.0_101
【core-site.xml】
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://mycluster</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/etc/tdng/hadoop-2.7.2/tmp</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>td23001:2181,td23002:2181,td23003:2181</value>
</property>
</configuration>
【hdfs-site.xml】<configuration>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file://${hadoop.tmp.dir}/dfs/name1,file://${hadoop.tmp.dir}/dfs/name2</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file://${hadoop.tmp.dir}/dfs/data1,file://${hadoop.tmp.dir}/dfs/data2</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>td23003:50090</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>td23001:8020</value>
</property>
<property>
<name>dfs.namenode.rpc-address.mycluster.nn2</name>
<value>td23002:8020</value>
</property>
<property>
<name>dfs.namenode.http-address.mycluster.nn1</name>
<value>td23001:50070</value>
</property>
<property>
<name>dfs.namenode.http-address.mycluster.nn2</name>
<value>td23002:50070</value>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://td23001:8485;td23002:8485;td23003:8485/mycluster</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
shell(/bin/true)
</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/root/.ssh/id_rsa</value>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/etc/tdng/hadoop-2.7.2/journal</value>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
</configuration>
【mapred-site.xml】
<configuration>
<!--通知框架MR使用YARN -->
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
</configuration>
【yarn-site.xml】
<configuration>
<!-- Site specific YARN configuration properties -->
<!--指定YARN的RM的地址-->
<property>
<name>yarn.resourcemanager.hostname</name>
<value>td23003</value>
</property>
<!--reducer取数据的方式是mapreduce_shuffle-->
<protery>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</protery>
</configuration>
【slaves】
001
002
003
创建目录在hadoop-2.7.2的根目录:
$>mkdir tmp
分发
启动
启动的时候注意启动顺序
1、启动zookeeper(在所在集群 )
2、启动journal node(在配置文件中所设置的集群)
#hadoop-2.7.2/sbin下
./sbin/hadoop-daemon.sh start journalnode
3、格式化HDFS(namenode)第一次要格式化(在namenode中任意一台)
./bin/hdfs namenode -format
并把tmp 文件夹拷贝到另一台namenode的目录下
scp -r tmp [email protected]:/etc/tdng/hadoop-2.7.2/
4、格式化 zk(在namenode1即可)
./bin/hdfs zkfc -formatZK
5、启动zkfc来监控NN状态(在所有的namenode)
./sbin/hadoop-daemon.sh start zkfc
6、启动HDFS(namenode)(在namenode1即可)
#hadoop-2.7.2/sbin下
./sbin/start-dfs.sh
7、启动YARN(MR)(在配置文件中设置的节点上)
#hadoop-2.7.2/sbin下
./sbin/start-yarn.sh
查看进程
$> jps
查看web页面
192.168.xxx.xx:50070
192.168.xxx.xx:8088