Hadoop HA文件参数配置
1.hadoop环境变量 vim /etc/profile
#hadoop enviroment
export HADOOP_HOME=/usr/local/src/hadoop #HADOOP_HOME指向JAVA安装目录
export HADOOP_PREFIX=$HADOOP_HOME
export HADOOP_MAPRED_HOME=$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 HADOOP_INSTALL=$HADOOP_HOME
export HADOOP_OPTS="-Djava.library.path=$HADOOP_INSTALL/lib:$HADOOP_COMMON_LIB_NATIVE_DIR"
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
2.配置hdfs-site.xml配置文件
1.<property>
<name>dfs.qjournal.start-segment.timeout.ms</name>
<value>60000</value>
</property>
2 <property>
<name>dfs.nameservices</name>
<value>mycluster</value>
</property>
3 <property>
<name>dfs.ha.namenodes.mycluster</name>
<value>master,slave1</value>
</property>
<!-- master的RPC通信地址 -->
4 <property>
<name>dfs.namenode.rpc-address.mycluster.master</name>
<value>master:8020</value>
</property>
<!-- slave1的RPC通信地址 -->
<property> 5
<name>dfs.namenode.rpc-address.mycluster.slave1</name>
<value>slave1:8020</value>
</property>
<!-- master的http通信地址 -->
<property>6
<name>dfs.namenode.http-address.mycluster.master</name>
<value>master:50070</value>
</property>
<!-- slave1的http通信地址 -->
7 <property>
<name>dfs.namenode.http-address.mycluster.slave1</name>
<value>slave1:50070</value>
</property>
<!-- 指定NameNode的edits元数据的共享存储位置。也就是JournalNode列表
该url的配置格式:qjournal://host1:port1;host2:port2;host3:port3/journalId
journalId推荐使用nameservice,默认端口号是:8485 -->
8 <property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://master:8485;slave1:8485;slave2:8485/mycluster</value>
</property>
<!-- 配置失败自动切换实现方式 -->
9 <property>
<name>dfs.client.failover.proxy.provider.mycluster</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<!-- 配置隔离机制方法,多个机制用换行分割,即每个机制暂用一行 -->
10<property>
<name>dfs.ha.fencing.methods</name>
<value>
sshfence
shell(/bin/true)
</value>
</property>
11 <property>
<name>dfs.permissions.enabled</name>
<value>false</value>
</property>
12<property>
<name>dfs.support.append</name>
<value>true</value>
</property>
<!-- 使用sshfence隔离机制时需要ssh免登陆 -->
13<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/home/hadoop/.ssh/id_rsa</value>
</property>
<!-- 指定副本数 -->
14<property>
<name>dfs.replication</name>
<value>2</value>
</property>
15<property>
<name>dfs.namenode.name.dir</name>
<value>/usr/local/src/hadoop/tmp/hdfs/nn</value>
</property>
16<property>
<name>dfs.datanode.data.dir</name>
<value>/usr/local/src/hadoop/tmp/hdfs/dn</value>
</property>
<!-- 指定JournalNode在本地磁盘存放数据的位置 -->
17<property>
<name>dfs.journalnode.edits.dir</name>
<value>/usr/local/src/hadoop/tmp/hdfs/jn</value>
</property>
<!-- 开启NameNode失败自动切换 -->
18<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<!-- 启用webhdfs -->
19<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
<!-- 配置sshfence隔离机制超时时间 -->
20<property>
<name>dfs.ha.fencing.ssh.connect-timeout</name>
<value>30000</value>
</property>
21<property>
<name>ha.failover-controller.cli-check.rpc-timeout.ms</name>
<value>60000</value>
</property>
保存并退出
配置yarn-site.xml配置文件
<!-- Site specific YARN configuration properties -->
<!-- 开启RM高可用 -->
<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>yrc</value>
</property>
<!-- 指定RM的名字 -->
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<!-- 分别指定RM的地址 -->
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>master</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>slave1</value>
</property>
<!-- 指定zk集群地址 -->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>master:2181,slave1:2181,slave2:2181</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<property>
<name>yarn.log-aggregation.retain-seconds</name>
<value>86400</value>
</property>
<!-- 启用自动恢复 -->
<property>
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property>
<!-- 制定resourcemanager的状态信息存储在zookeeper集群上 -->
<property>
<name>yarn.resourcemanager.store.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
</property>
保存并退出
配置core-site.xml配置文件
添加如下配置:
<property>
<name>fs.defaultFS</name>
<value>hdfs://mycluster</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>file:/usr/local/src/hadoop/tmp</value>
</property>
<!-- 指定zookeeper地址 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>master:2181,slave1:2181,slave2:2181</value>
</property>
<!-- hadoop链接zookeeper的超时时长设置 -->
<property>
<name>ha.zookeeper.session-timeout.ms</name>
<value>30000</value>
<description>ms</description>
</property>
<property>
<name>fs.trash.interval</name>
<value>1440</value>
</property>
保存并退出
配置mapred-site.xml配置文件
进行如下配置:
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<!-- 指定mapreduce jobhistory地址 -->
<property>
<name>mapreduce.jobhistory.address</name>
<value>master:10020</value>
</property>
<!-- 任务历史服务器的web地址 -->
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>master:19888</value>
</property>
保存并退出
配置hadoop-env.sh
export JAVA_HOME=/usr/local/src/java
配置slaves配置文件
master
slave1
slave2
建立目录
namenode、datanode、journalnode等存放数据的
公共目录为/usr/local/src/hadoop/tmp;
在master上执行如下:
[root@master hadoop]# mkdir -p /usr/local/src/hadoop/tmp/hdfs/nn
[root@master hadoop]# mkdir -p /usr/local/src/hadoop/tmp/hdfs/dn
[root@master hadoop]# mkdir -p /usr/local/src/hadoop/tmp/hdfs/jn
[root@master hadoop]# mkdir -p /usr/local/src/hadoop/tmp/logs
分发文件 scp
启动HA
步骤一:启动journalnode守护进程
[hadoop@master hadoop]$ hadoop-daemons.sh start journalnode
步骤二:初始化namenode
[hadoop@master ~]$ hdfs namenode -format
步骤三:注册ZNode
[hadoop@master ~]$ hdfs zkfc -formatZK
步骤四:启动集群
[hadoop@master ~]$ start-all.sh
步骤六:同步master数据
[hadoop@master ~]$ scp -r /usr/local/src/hadoop/tmp/hdfs/nn/* slave1:/usr/local/src/hadoop/tmp/hdfs/nn/
[hadoop@master ~]$ scp -r /usr/local/src/hadoop/tmp/hdfs/nn/* slave2:/usr/local/src/hadoop/tmp/hdfs/nn/
步骤七:在slave1上启动resourcemanager和namenode进程
[hadoop@slave1 ~]$ yarn-daemon.sh start resourcemanager
[hadoop@slave1 ~]$ hadoop-daemon.sh start namenode
步骤九:启动 MapReduce任务历史服务器
[hadoop@master ~]$ yarn-daemon.sh start proxyserver
[hadoop@master ~]$ mr-jobhistory-daemon.sh start historyserver