需知
本文仅为记录hadoop高可用平台搭建过程,作者新手,凭记忆写的,如果有失败的请不要见怪。。仅为交流
准备
jdk: jdk1.8.0_144
hadoop: hadoop-3.1.2
zookeeper: apache-zookeeper-3.5.7-bin
虚拟机: Vmware15
Linux: centos-7
登录权限:
root
文件存放
#hadoop,jdk,zookeeper均再root目录下新建文件夹bigdata然后在bigdata中新建三个文件夹存放
#data 和 name的数据都在hadoop文件的hdfs下
#temp临时文件也在hadoop下
#zkdata和zklogs也都在hadoop下
开始
基础五步
- 修改hostname
- 修改/etc/hosts
- ssh免密(每台机子都互相免密)
- jdk安装以及环境变量配置
- 关闭防火墙
以上五步骤在每台机子都要操作,不做过多叙述。附一些linux命令
#centos-7 关闭防火墙
systemctl status firewalld.service(查看状态)
systemctl stop firewalld.service(关闭)
systemctl status firewalld.service
systemctl disable firewalld.service(永久关闭)
#ssh免密码
##本机
ssh-keygen -t rsa
cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
##将公钥复制到其他机器
ssh-dopy-id -i hostname
#分发文件
scp -rq hadoop-3.1.2 slave1:/root/bigdata/hadoop/
#启动zookeeper集群
##启动之前需要在zkdata下建立一个myid来存放server对应的序号
zkServer.sh status(查看状态)
zkServer.sh start(启动zookeeper集群)
zkServer.sh stop(停止)
#启动journalnode
sbin/hdfs --daemon start journalnode
#格式化ZKFC
hdfs -daemon formatZK
#启动ZKFC
hdfs --daemon start zkfc
#启动hdfs
sbin/hdfs --daemon start namenode
sbin/hdfs --daemon start datanode
sbin/hdfs --daemon start namenode
#启动yarn
yarn --daemon start resourcemanager
start-yarn.sh
zookeeper集群搭建
首先将conf目录下的zoo_sample文件改成zoo
然后修改dataDir路径并添加dataLogDir路径
dataDir=/root/bigdata/hadoop/hadoop-3.1.2/zkdata
dataLogDir=/root/bigdata/hadoop/hadoop-3.1.2/zklogs
在最后添加server配置,牢记这个序号,会在zkdata中vim一个myid里面需要填写对应的数字
server.1=masternode:2888:3888
server.2=namenode:2888:3888
server.3=slave0:2888:3888
hadoop集群配置
进入zkdata目录下创建一个myid文件,里面放上server的序号
vim myid
进入/etc/hadoop下修改 hadoop-env.sh 文件,增加环境变量信息
[root@hadoop100 hadoop]# vi hadoop-env.sh
export JAVA_HOME=/root/bigdata/jdk/jdk1.8.0_144
export HDFS_DATANODE_USER="root"
export YARN_RESOURCEMANAGER_USER="root"
export YARN_NODEMANAGER_USER="root"
export HDFS_ZKFC_USER="root"
export HDFS_JOURNALNODE_USER="root"
修改 workers 文件,增加所有datanode节点的主机名,一个一行
[root@hadoop100 hadoop]# vi workers
masternode
namenode
slave0
slave1
修改xml文件
#hdfi-site,xml
------------------------------------------------------------------------------------------------
<configuration>
<!-- 指定副本数 -->
<property>
<name>dfs.replication</name>
<value>2</value>
</property>
<!-- 配置namenode和datanode的工作目录-数据存储目录 -->
<property>
<name>dfs.namenode.name.dir</name>
<value>/root/bigdata/hadoop/hadoop-3.1.2/hdfs/name</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>/root/bigdata/hadoop/hadoop-3.1.2/hdfs/data</value>
</property>
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.nameservices</name>
<value>namenodes</value>
</property>
<!-- namenodes下面有两个NameNode,分别是nn1,nn2 -->
<property>
<name>dfs.ha.namenodes.namenodes</name>
<value>nn1,nn2</value>
</property>
<!-- nn1的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.namenodes.nn1</name>
<value>masternode:9000</value>
</property>
<!-- nn1的http通信地址 -->
<property>
<name>dfs.namenode.http-address.namenodes.nn1</name>
<value>masternode:9870</value>
</property>
<!-- nn2的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.namenodes.nn2</name>
<value>namenode:9000</value>
</property>
<!-- nn2的http通信地址 -->
<property>
<name>dfs.namenode.http-address.namenodes.nn2</name>
<value>namenode:9870</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 -->
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://masternode:8485;namenode:8485;slave0:8485/namenodes</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>/root/bigdata/hadoop/hadoop-3.1.2/journaldata</value>
</property>
<!-- 开启NameNode失败自动切换 -->
<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.namenodes</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 -->
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<!-- 使用sshfence隔离机制时需要ssh免登陆 -->
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/root/.ssh/id_rsa</value>
</property>
<!-- 配置sshfence隔离机制超时时间 -->
<property>
<name>dfs.ha.fencing.ssh.connect-timeout</name>
<value>30000</value>
</property>
<property>
<name>ha.failover-controller.cli-check.rpc-timeout.ms</name>
<value>60000</value>
</property>
</configuration>
------------------------------------------------------------------------------------------------
#core-site.xml
------------------------------------------------------------------------------------------------
<configuration>
<!-- 指定hdfs的nameservice为masternode -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://namenodes/</value>
</property>
<!-- 指定hadoop临时目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/root/bigdata/hadoop/hadoop-3.1.2/temp</value>
</property>
<!-- 指定zookeeper地址 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>masternode:2181,namenode:2181,slave0:2181</value>
</property>
<!-- hadoop链接zookeeper的超时时长设置 -->
<property>
<name>ha.zookeeper.session-timeout.ms</name>
<value>1000</value>
<description>ms</description>
</property>
<property>
<name>hadoop.http.staticuser.user</name>
<value>root</value>
</property>
</configuration>
------------------------------------------------------------------------------------------------
#yarn-site.xml
------------------------------------------------------------------------------------------------
<configuration>
<!-- 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>masternode</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>namenode</value>
</property>
<!-- 指定zk集群地址 -->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>masternode:2181,namenode:2181,slave0:2181</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>
</configuration>
#修改启动脚本
#进入sbin目录修改 start-dfs.sh,stop-dfs.sh 这两个脚本文件,在文件前面增加如下内容
[root@hadoop100 sbin]# vi start-dfs.sh
HDFS_DATANODE_USER=root
HDFS_DATANODE_SECURE_USER=hdfs
HDFS_NAMENODE_USER=root
HDFS_SECONDARYNAMENODE_USER=root
[root@hadoop100 sbin]# vi stop-dfs.sh
HDFS_DATANODE_USER=root
HDFS_DATANODE_SECURE_USER=hdfs
HDFS_NAMENODE_USER=root
HDFS_SECONDARYNAMENODE_USER=root
#修改 start-yarn.sh,stop-yarn.sh 这两个脚本文件,在文件前面增加如下内容
[root@hadoop100 sbin]# vi start-yarn.sh
YARN_RESOURCEMANAGER_USER=root
HADOOP_SECURE_DN_USER=yarn
YARN_NODEMANAGER_USER=root
[root@hadoop100 sbin]# vi stop-yarn.sh
YARN_RESOURCEMANAGER_USER=root
HADOOP_SECURE_DN_USER=yarn
YARN_NODEMANAGER_USER=root
然后分发jdk,hadoop,zookeeper
配置环境变量:
#java hadoop
export JAVA_HOME=/root/bigdata/jdk/jdk1.8.0_144
export HADOOP_HOME=/root/bigdata/hadoop/hadoop-3.1.2
export PATH=.:$JAVA_HOME/bin:$HADOOP_HOME/bin:$PATH
#zookeeper
export ZOOKEEPER_HOME=/root/bigdata/zookeeper/apache-zookeeper-3.5.7-bin
export PATH=$PATH:$ZOOKEEPER_HOME/bin
按照顺序启动集群
启动zookeeper
zkServer.sh status(查看状态)
zkServer.sh start(启动zookeeper集群)
zkServer.sh stop(停止)
启动 zookeeper/bin/zkCli.sh,登录后ls / 能看到hadoop-ha即可
quit退出登录
在journalnode上分别启动
sbin/hdfs --daemon start journalnode
格式化namenode
bin/hdfs namenode -format
启动namenode
sbin/hadoop-daemon.sh start namenode
nn2上拉取namenode数据
bin/hdfs namenode -bootstrapStandby
格式化ZKFC
hdfs -daemon formatZK
启动集群
sbin/start-all.sh
查看进程:jps
masternode
namenode
slave0
slave1
查看Web UI
两个NN一个active一个standby
四个datanode