Hadoop的高可用
一、架构
| HadoopNode01 | HadoopNode02 | HadoopNode03 |
|---|---|---|
| nn1 | nn2 | |
| journal node | journal node | journal node |
| zkfc | zkfc | |
| datanode | datanode | datanode |
| zk01 | zk02 | zk03 |
| rm1 | rm2 | |
| nodemanager | nodemanager | nodemanager |
二、HDFS HA
1)基础环境准备
（1）配置主机名和IP的映射关系
[root@HadoopNodeX ~]# vi /etc/hosts
192.168.11.20 HadoopNode00
192.168.11.21 HadoopNode01
192.168.11.22 HadoopNode02
192.168.11.23 HadoopNode03
192.168.11.31 ZK01
192.168.11.32 ZK02
192.168.11.33 ZK03
（2）关闭防火墙
[root@HadoopNodeX ~]# service iptables stop
[root@HadoopNodeX ~]# chkconfig iptables off（3）同步时钟
[root@HadoopNodeX ~]# yum -y install ntpdate
[root@HadoopNodeX ~]# ntpdate -u ntp.api.bz
25 Sep 11:19:26 ntpdate[1749]: step time server 114.118.7.163 offset 201181.363384 sec
[root@HadoopNodeX ~]# date
Wed Sep 25 11:19:52 CST 2019（4）配置SSH 免密登陆
[root@HadoopNodeX ~]# ssh-keygen -t rsa # 现在三台机器上都运行次命令，在运行下面的
[root@HadoopNodeX ~]# ssh-copy-id HadoopNode01
[root@HadoopNodeX ~]# ssh-copy-id HadoopNode02
[root@HadoopNodeX ~]# ssh-copy-id HadoopNode03（5）Java 环境
export JAVA_HOME=/home/java/jdk1.8.0_181
export PATH=$PATH:$JAVA_HOME/bin
2）ZK集群启动
3）安装配置Hadoop
（1）解压配置环境变量
export HADOOP_HOME=/home/hadoop/hadoop-2.6.0
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
（2）配置core-site.xml
fs.defaultFS
hdfs://mycluster
hadoop.tmp.dir
/home/hadoop/hadoop-2.6.0/hadoop-${user.name}
fs.trash.interval
30
net.topology.script.file.name
/home/hadoop/hadoop-2.6.0/etc/hadoop/rack.sh
（3）创建机架脚本
在对应的文件夹中/home/hadoop/hadoop-2.6.0/etc/hadoop/ 创建一个rack.sh文件，将下方内容粘贴进入
while [ $# -gt 0 ] ; do
nodeArg=$1
exec</home/hadoop/hadoop-2.6.0/etc/hadoop/topology.data
result=""
while read line ; do
ar=( $line )
if [ "${ar[0]}" = "$nodeArg" ] ; then
result="${ar[1]}"
fi
done
shift
if [ -z "$result" ] ; then
echo -n "/default-rack"
else
echo -n "$result "
fi
done另外 需要对机架文件进行权限控制，chmod u+x /home/hadoop/hadoop-2.6.0/etc/hadoop/rack.sh
（4）创建机架映射文件
创建 /home/hadoop/hadoop-2.6.0/etc/hadoop/topology.data
192.168.11.21 /rack1
192.168.11.22 /rack1
192.168.11.23 /rack2
（5）配置 hdfs-site.xml
<configuration>
<property>
<name>dfs.replicationname>
<value>3value>
property>
<property>
<name>dfs.ha.automatic-failover.enabledname>
<value>truevalue>
property>
<property>
<name>ha.zookeeper.quorumname>
<value>zk01:2181,zk02:2181,zk03:2181value>
property>
<property>
<name>dfs.nameservicesname>
<value>myclustervalue>
property>
<property>
<name>dfs.ha.namenodes.myclustername>
<value>nn1,nn2value>
property>
<property>
<name>dfs.namenode.rpc-address.mycluster.nn1name>
<value>HadoopNode01:9000value>
property>
<property>
<name>dfs.namenode.rpc-address.mycluster.nn2name>
<value>HadoopNode02:9000value>
property>
<property>
<name>dfs.namenode.shared.edits.dirname>
<value>qjournal://HadoopNode01:8485;HadoopNode02:8485;HadoopNode03:8485/myclustervalue>
property>
<property>
<name>dfs.client.failover.proxy.provider.myclustername>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvidervalue>
property>
<property>
<name>dfs.ha.fencing.methodsname>
<value>sshfencevalue>
property>
<property>
<name>dfs.ha.fencing.ssh.private-key-filesname>
<value>/root/.ssh/id_rsavalue>
property>
configuration>
（6）编辑slaves信息
HadoopNode01
HadoopNode02
HadoopNode03
（7）启动
1）启动HDFS服务（初始化）
[root@HadoopNodeX ~]# rm -rf /home/hadoop/hadoop-2.6.0/hadoop-root/*
[root@HadoopNodeX ~]# hadoop-daemons.sh start journalnode # 在任意节点中运行即可
[root@HadoopNode01 ~]# hdfs namenode -format
[root@HadoopNode01 ~]# hadoop-daemon.sh start namenode
[root@HadoopNode02 ~]# hdfs namenode -bootstrapStandby # 下载主namenode的元数据
[root@HadoopNode02 ~]# hadoop-daemon.sh start namenode
[root@HadoopNode01|02 ~]# hdfs zkfc -formatZK #在任意的一个01|02 节点上格式化即可
[root@HadoopNode01 ~]# hadoop-daemon.sh start zkfc
[root@HadoopNode02 ~]# hadoop-daemon.sh start zkfc
[root@HadoopNodeX ~]# hadoop-daemon.sh start datanode
[root@HadoopNode01 ~]# jps
2324 JournalNode
2661 DFSZKFailoverController
2823 Jps
2457 NameNode
2746 DataNode
[root@HadoopNode02 ~]# jps
2595 DataNode
2521 DFSZKFailoverController
2681 Jps
2378 NameNode
2142 JournalNode
[root@HadoopNode03 .ssh]# jps
2304 Jps
2146 JournalNode
2229 DataNode
2）日常维护
[root@HadoopNode01 ~]# stop-dfs.sh
[root@HadoopNode01 ~]# start-dfs.sh三、YARN 高可用
（1）配置 yarn-site.xml
<property>
<name>yarn.nodemanager.aux-servicesname>
<value>mapreduce_shufflevalue>
property>
<property>
<name>yarn.resourcemanager.ha.enabledname>
<value>truevalue>
property>
<property>
<name>yarn.resourcemanager.zk-addressname>
<value>zk01:2181,zk02:2181,zk03:2181value>
property>
<property>
<name>yarn.resourcemanager.cluster-idname>
<value>rmcluster01value>
property>
<property>
<name>yarn.resourcemanager.ha.rm-idsname>
<value>rm1,rm2value>
property>
<property>
<name>yarn.resourcemanager.hostname.rm1name>
<value>HadoopNode02value>
property>
<property>
<name>yarn.resourcemanager.hostname.rm2name>
<value>HadoopNode03value>
property>（2）配置 mapred-site.xml
<property>
<name>mapreduce.framework.namename>
<value>yarnvalue>
property>（3）启动
[root@HadoopNode02 ~]# yarn-daemon.sh start resourcemanager
[root@HadoopNode03 ~]# yarn-daemon.sh start resourcemanager
[root@HadoopNodeX ~]# yarn-daemon.sh start nodemanager