-环境准备
-
3台centos机器
-
分别为master1和master2,slave master1和master2分别作为active nn和standby nn slave为从节点 假设ip分别为 master1 192.168.0.1 master2 192.168.0.2 slave 192.168.0.3
-
ip和hostname绑定
-
三台机子分别修改/etc/hosts文件添加如下三行 192.168.0.1 master在这里插入代码片1 192.168.0.2 master2 192.168.0.3 slave
-
建立ssh信任
-
3台机器分别执行ssh-keygen -t rsa命令后一路回车 执行完成后会在当前用户的根目录添加一个隐藏文件.ssh 在.ssh文件下创建authorized_keys文件。 分别将各自的.ssh文件加下的id_rsa.pub文件追加到自己和其它机器的authorized_keys文件中。 修改文件的权限, chmod 666 authorized_keys 通过ssh host确认ssh信任成功。 ssh hostname 执行无需输入密码即为成功。
-
jdk安装
解压jdk 配置环境变量: vim /etc/profile 或当前用的文件 ~/.bash_profile 在文件末尾添加如下两行 export JAVA_HOME= Java文件的根目录绝对路径 export PATH=\$PATH/bin:\$PATH 执行source /etc/profile 使环境变量生效(如果配置的是.bash_profile文件则执行source ~/.bash_profile) 执行java -version 能够看到版本号即为成功。
修改用户组
chown -R user:user /usr/java/* -
zookeeper安装
-
解压
-
tar -zxvf zookeeper-3.4.5-cdh5.15.1.tar.gz -C /home/user/app/
-
cd ~/app
-
创建软连接
-
ln -s zookeeper-3.4.5-cdh5.15.1 zookeeper
-
配置环境变量
-
vim ~/.bash_profile
-
添加如下两行
-
export ZOOKEEPER_HOME=/home/hadoop/app/zookeeper export PATH=$ZOOKEEPER_HOME/bin:$PATH
-
拷贝一份zoo_sample.cfg 到 zoo.cfg 并编辑
-
vi zoo.cfg
-
修改dataDir路径
-
dataDir=/home/user/data/zookeeper #根据自己环境设置
-
添加server地址
-
server.1=master1.2888:3888
-
server.2=master2.2888:3888
-
server.3=master3.2888.3888
-
将zoo.cfg配置文件分别拷贝到其他机器上
-
scp zoo.cfg master2:/$ZOOKEEPER_HOME/conf/ scp zoo.cfg master2:/$ZOOKEEPER_HOME/conf/
-
创建dataDir
-
启动zookeeper使用jps命令检查
-
./zkServer.sh start
-
jps
-
存在即为成功
-
三台都要启动
-
安装hadoop
配置master1机器
先解压hadoop安装包建立软连接,步骤同zookeeper和和jdk
进入hadoop的etc/hadoop文件夹下
修改hadoop-env.sh文件
export JAVA_HOME=/usr/java/jdk8 #自己的java安装路径 -
配置core-site.xml
-
<?xml version="1.0" encoding="UTF-8"?>
<!--指定hadoop临时目录, hadoop.tmp.dir 是hadoop文件系统依赖的基础配置,很多路径都依赖它。如果hdfs-site.xml中不配 置namenode和datanode的存放位置,默认就放在这>个路径中 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/home/hadoop/tmp/hadoop</value>
</property>
<!-- 指定zookeeper地址 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>MASTER1:2181,MASTER2:2181,SLAVE78:2181</value>
</property>
<!--指定ZooKeeper超时间隔,单位毫秒 -->
<property>
<name>ha.zookeeper.session-timeout.ms</name>
<value>2000</value>
</property>
<property>
<name>hadoop.proxyuser.hadoop.hosts</name>
<value>*</value>
</property>
<property>
<name>hadoop.proxyuser.hadoop.groups</name>
<value>*</value>
</property>
<property>
<name>io.compression.codecs</name>
<value>org.apache.hadoop.io.compress.GzipCodec,
org.apache.hadoop.io.compress.DefaultCodec,
org.apache.hadoop.io.compress.BZip2Codec,
org.apache.hadoop.io.compress.SnappyCodec
</value>
</property>
-配置hdfs-site.xml文件
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<!--HDFS超级用户 -->
<property>
<name>dfs.permissions.superusergroup</name>
<value>zpark</value>
</property>
<!--开启web hdfs -->
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>/home/zpark/data/dfs/name</value>
<description> namenode 存放name table(fsimage)本地目录(需要修改)</description>
</property>
<property>
<name>dfs.namenode.edits.dir</name>
<value>${dfs.namenode.name.dir}</value>
<description>namenode粗放 transaction file(edits)本地目录(需要修改)</description>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>/home/zpark/data/dfs/data</value>
<description>datanode存放block本地目录(需要修改)</description>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<!-- 块大小128M (默认128M) -->
<property>
<name>dfs.blocksize</name>
<value>134217728</value>
</property>
<!--======================================================================= -->
<!--HDFS高可用配置 -->
<!--指定hdfs的nameservice为ruozeclusterg7,需要和core-site.xml中的保持一致 -->
<property>
<name>dfs.nameservices</name>
<value>hadoopha</value>
</property>
<property>
<!--设置NameNode IDs 此版本最大只支持两个NameNode -->
<name>dfs.ha.namenodes.hadoopha</name>
<value>nn1,nn2</value>
</property>
<!-- Hdfs HA: dfs.namenode.rpc-address.[nameservice ID] rpc 通信地址 -->
<property>
<name>dfs.namenode.rpc-address.hadoopha.nn1</name>
<value>MASTER1:8020</value>
</property>
<property>
<name>dfs.namenode.rpc-address.hadoopha.nn2</name>
<value>MASTER2:8020</value>
</property>
<!-- Hdfs HA: dfs.namenode.http-address.[nameservice ID] http 通信地址 -->
<property>
<name>dfs.namenode.http-address.hadoopha.nn1</name>
<value>MASTER1:50070</value>
</property>
<property>
<name>dfs.namenode.http-address.hadoopha.nn2</name>
<value>MASTER2:50070</value>
</property>
<!--==================Namenode editlog同步 ============================================ -->
<!--保证数据恢复 -->
<property>
<name>dfs.journalnode.http-address</name>
<value>0.0.0.0:8480</value>
</property>
<property>
<name>dfs.journalnode.rpc-address</name>
<value>0.0.0.0:8485</value>
</property>
<property>
<!--设置JournalNode服务器地址,QuorumJournalManager 用于存储editlog -->
<!--格式:qjournal://<host1:port1>;<host2:port2>;<host3:port3>/<journalId> 端口同journalnode.rpc-address -->
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://MASTER1:8485;MASTER2:8485;SLAVE78:8485/hadoopha</value>
</property>
<property>
<!--JournalNode存放数据地址 -->
<name>dfs.journalnode.edits.dir</name>
<value>/home/zpark/data/dfs/jn</value>
</property>
<!--==================DataNode editlog同步 ============================================ -->
<property>
<!--DataNode,Client连接Namenode识别选择Active NameNode策略 -->
<!-- 配置失败自动切换实现方式 -->
<name>dfs.client.failover.proxy.provider.hadoopha</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<!--==================Namenode fencing:=============================================== -->
<!--Failover后防止停掉的Namenode启动,造成两个服务 -->
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/home/zpark/.ssh/id_rsa</value>
</property>
<property>
<!--多少milliseconds 认为fencing失败 -->
<name>dfs.ha.fencing.ssh.connect-timeout</name>
<value>30000</value>
</property>
<!--==================NameNode auto failover base ZKFC and Zookeeper====================== -->
<!--开启基于Zookeeper -->
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<!--动态许可datanode连接namenode列表 -->
<property>
<name>dfs.hosts</name>
<value>/home/zpark/app/hadoop/etc/hadoop/slaves</value>
</property>
</configuration>
- 配置mapred-site.xml文件
-
<?xml version="1.0" encoding="UTF-8"?> <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> <configuration> <!-- 配置 MapReduce Applications --> <property> <name>mapreduce.framework.name</name> <value>yarn</value> </property> <!-- JobHistory Server ============================================================== --> <!-- 配置 MapReduce JobHistory Server 地址 ,默认端口10020 --> <property> <name>mapreduce.jobhistory.address</name> <value>ruozedata001:10020</value> </property> <!-- 配置 MapReduce JobHistory Server web ui 地址, 默认端口19888 --> <property> <name>mapreduce.jobhistory.webapp.address</name> <value>ruozedata001:19888</value> </property> <!-- 配置 Map段输出的压缩,snappy--> <property> <name>mapreduce.map.output.compress</name> <value>true</value> </property> <property> <name>mapreduce.map.output.compress.codec</name> <value>org.apache.hadoop.io.compress.SnappyCodec</value> </property> </configuration>
配置yarn-site.xml文件
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
yarn.nodemanager.aux-services mapreduce_shuffle yarn.nodemanager.aux-services.mapreduce.shuffle.class org.apache.hadoop.mapred.ShuffleHandler yarn.nodemanager.localizer.address 0.0.0.0:23344 Address where the localizer IPC is. yarn.nodemanager.webapp.address 0.0.0.0:23999 NM Webapp address.
<!-- HA 配置 =============================================================== -->
<!-- Resource Manager Configs -->
<property>
<name>yarn.resourcemanager.connect.retry-interval.ms</name>
<value>2000</value>
</property>
<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<!-- 使嵌入式自动故障转移。HA环境启动,与 ZKRMStateStore 配合 处理fencing -->
<property>
<name>yarn.resourcemanager.ha.automatic-failover.embedded</name>
<value>true</value>
</property>
<!-- 集群名称,确保HA选举时对应的集群 -->
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>yarn-cluster</value>
</property>
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<!--这里RM主备结点需要单独指定,(可选)
<property>
<name>yarn.resourcemanager.ha.id</name>
<value>rm2</value>
</property>
-->
<property>
<name>yarn.resourcemanager.scheduler.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler</value>
</property>
<property>
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.app.mapreduce.am.scheduler.connection.wait.interval-ms</name>
<value>5000</value>
</property>
<!-- ZKRMStateStore 配置 -->
<property>
<name>yarn.resourcemanager.store.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
</property>
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>MASTER1:2181,MASTER2:2181,SLAVE78:2181</value>
</property>
<property>
<name>yarn.resourcemanager.zk.state-store.address</name>
<value>MASTER1:2181,MASTER2:2181,SLAVE78:2181</value>
</property>
<!-- Client访问RM的RPC地址 (applications manager interface) -->
<property>
<name>yarn.resourcemanager.address.rm1</name>
<value>MASTER1:23140</value>
</property>
<property>
<name>yarn.resourcemanager.address.rm2</name>
<value>MASTER2:23140</value>
</property>
<!-- AM访问RM的RPC地址(scheduler interface) -->
<property>
<name>yarn.resourcemanager.scheduler.address.rm1</name>
<value>MASTER1:23130</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address.rm2</name>
<value>MASTER2:23130</value>
</property>
<!-- RM admin interface -->
<property>
<name>yarn.resourcemanager.admin.address.rm1</name>
<value>MASTER1:23141</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address.rm2</name>
<value>MASTER2:23141</value>
</property>
<!--NM访问RM的RPC端口 -->
<property>
<name>yarn.resourcemanager.resource-tracker.address.rm1</name>
<value>MASTER1:23125</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address.rm2</name>
<value>MASTER2:23125</value>
</property>
<!-- RM web application 地址 -->
<property>
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>MASTER1:8088</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>MASTER2:8088</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.https.address.rm1</name>
<value>MASTER1:23189</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.https.address.rm2</name>
<value>MASTER2:23189</value>
</property>
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<property>
<name>yarn.log.server.url</name>
<value>http://MASTER1:19888/jobhistory/logs</value>
</property>
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>2048</value>
</property>
<property>
<name>yarn.scheduler.minimum-allocation-mb</name>
<value>1024</value>
<discription>单个任务可申请最少内存,默认1024MB</discription>
</property>
<property>
<name>yarn.scheduler.maximum-allocation-mb</name>
<value>2048</value>
<discription>单个任务可申请最大内存,默认8192MB</discription>
</property>
<property>
<name>yarn.nodemanager.resource.cpu-vcores</name>
<value>2</value>
</property>
</configuration>
-
配置slaves文件
MASTER1
MASTER2
SLAVE -
启动JournalNode
-
三台机器分别执行hadoop-daemon.sh start journalnode
- 启动集群前需要格式化
-
hadoop namenode -format
- 格式化后需要手动同步元数据
-
scp data MASTER2:~/ #data为hdfs-site.xml文件中配置的hdfs文件路径
- 初始化zkfc
-
hdfs zkfc -formatZK
- 启动start-dfs.sh
-
./start-dfs.sh
- 启动yarn
-
./start-yarn.sh
- 查看是否部署成功