HA完整结构：
安装配置高可用集群： 1、节点名称：集群每个节点的名称都得能互相解析 /etc/hosts hosts中主机名的正反解析结果必须跟“uname -n”的结果保持一致； 2、时间必须得同步 使用网络时间服务器同步时间 3、并非必须：各节点间能基于ssh密钥认证通信；
安装：
[root@marvin heartbeat]# yum install corosync -y
配置：
[root@sherry heartbeat]# cd /etc/corosync/
[root@sherry corosync]# ls
corosync.conf.example corosync.conf.example.udpu service.d uidgid.d
[root@sherry corosync]# cp corosync.conf.example corosync.conf
[root@sherry corosync]# vim corosync.conf
compatibility: whitetank #是否兼容0.8以前的版本
totem {
version: 2 ＃通信协议
secauth: on ＃安全认证功能 off别人知道多波地址 就可以加入 最好开启
threads: 0 #0表示默认 认证时候并行线程
interface {
ringnumber: 0 ＃定义环号，防止心跳信息循环发送 就有一块网卡就用0
bindnetaddr: 192.168.1.0 ＃绑定网络地址
mcastaddr: 225.122.111.111 ＃224.0.1.0～238.255.255.255 建议用这组临时
mcastport: 5405 ＃多波端口
ttl:1 #只发一次 避免环路
}
}
logging {
fileline: off
to_stderr: no ＃标准错误输出
to_logfile: yes
logfile: /var/log/cluster/corosync.log
to_syslog: no #日志开启一项即可
debug: off
timestamp: no #是否记录时间戳
logger_subsys {
subsys: AMF
debug: off
}
}
amf {
mode:disabled #编程相关
}安装pacemaker：
[root@sherry corosync]# yum install pacemaker -y
自动启动pacemaker：（服务不会启动，还是需要手动启动）
[root@sherry corosync]# vim corosync.conf
service {
ver:1 ＃以插件方式运行pacemaker
name:pacemaker
}
aisexec{
user:root
group:root
}密钥文件：
#生产环境请手敲密钥 [root@sherry corosync]# mv /dev/random /dev/random.bak [root@sherry corosync]# mv /dev/urandom /dev/random [root@sherry corosync]# corosync-keygen [root@sherry corosync]# mv /dev/random /dev/urandom [root@sherry corosync]# mv /dev/random.bak /dev/random
密钥生产：（权限400）
[root@sherry corosync]# ll total 24 -r-------- 1 root root 128 May 31 20:54 authkey -rw-r--r-- 1 root root 476 May 31 20:50 corosync.conf -rw-r--r-- 1 root root 2663 May 11 06:27 corosync.conf.example -rw-r--r-- 1 root root 1073 May 11 06:27 corosync.conf.example.udpu drwxr-xr-x 2 root root 4096 May 11 06:27 service.d drwxr-xr-x 2 root root 4096 May 11 06:27 uidgid.d
配置文件复制到对应节点：
[root@sherry corosync]# scp -P6789 -p authkey corosync.conf root@marvin:/etc/corosync/
crmsh安装：
[root@sherry yum.repos.d]# cd /etc/yum.repos.d/ [root@sherry yum.repos.d]# wget http://download.opensuse.org/repositories/network:ha-clustering:Stable/CentOS_CentOS-6/network:ha-clustering:Stable.repo [root@sherry yum.repos.d]# yum install crmsh -y
启动脚本：
[root@sherry corosync]# /etc/init.d/corosync start [root@sherry corosync]# /etc/init.d/pacemaker start #停止时候次序相反
实验服务器：marvin sherry
初始化：
corosync默认启用了stonith，而当前集群并没有相应的stonith设备 我们里可以通过如下命令先禁用stonith：
crm(live)# configure crm(live)configure# property stonith-enabled=false crm(live)configure# verify crm(live)configure# commit
设置投票
crm(live)configure# property no-quorum-policy=ignore crm(live)configure# verify crm(live)configure# commit
查看配置所有信息：
crm(live)configure# show node marvin node sherry property cib-bootstrap-options: have-watchdog=false dc-version=1.1.14-8.el6-70404b0 cluster-infrastructure="classic openais (with plugin)" expected-quorum-votes=2 stonith-enabled=false no-quorum-policy=ignore
定义资源：
定义一个ip：
crm(live)configure# primitive webip ocf:heartbeat:IPaddr params ip=192.168.1.199 crm(live)configure# verify crm(live)configure# commit crm(live)configure# show node marvin node sherry primitive webip IPaddr params ip=192.168.1.199 property cib-bootstrap-options: have-watchdog=false dc-version=1.1.14-8.el6-70404b0 cluster-infrastructure="classic openais (with plugin)" expected-quorum-votes=2 stonith-enabled=false
[root@marvin ~]# ip addr show eth1 3: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000 link/ether 00:0c:29:0c:34:2c brd ff:ff:ff:ff:ff:ff inet 192.168.1.220/24 brd 192.168.1.255 scope global eth1 inet 192.168.1.199/24 brd 192.168.1.255 scope global secondary eth1 inet6 fe80::20c:29ff:fe0c:342c/64 scope link valid_lft forever preferred_lft forever
后期定义监控：kill后会自动启动
crm(live)configure# monitor webserver 30s:15s #删除可直接edit 30s监控一次15s延迟 crm(live)configure# verify crm(live)configure# commit crm(live)configure# show primitive webserver lsb:nginx meta target-role=Stopped op monitor interval=30s timeout=15s
nfs:（定义监控） （定义正确，未提交）
crm(live)configure# primitive webstore ocf:heartbeat:Filesystem params device="sherry:/nfsshared/node1" directory="/mnt/nfs/node1" fstype=‘nfs‘ op monitor interval=20s timeout=40s op start timeout=60s op stop timeout=60s on-fail=restart crm(live)configure# verify
nginx:（定义监控）
crm(live)configure# primitive webserver lsb:nginx op monitor interval=30s timeout=15s on-fail=restart crm(live)configure# verify crm(live)configure# commit crm(live)configure# show node marvin node sherry primitive webip IPaddr params ip=192.168.1.199 primitive webserver lsb:nginx property cib-bootstrap-options: have-watchdog=false dc-version=1.1.14-8.el6-70404b0 cluster-infrastructure="classic openais (with plugin)" expected-quorum-votes=2 stonith-enabled=false
status：
crm(live)# status Last updated: Wed Jun 1 20:38:32 2016 Last change: Wed Jun 1 20:36:32 2016 by root via cibadmin on sherry Stack: classic openais (with plugin) Current DC: marvin (version 1.1.14-8.el6-70404b0) - partition with quorum 2 nodes and 2 resources configured, 2 expected votes Online: [ marvin sherry ] Full list of resources: webip (ocf::heartbeat:IPaddr): Started marvin webserver (lsb:nginx): Started sherry
资源停止：
crm(live)# resource crm(live)resource# stop webserver crm(live)resource# status webip (ocf::heartbeat:IPaddr): Started webserver (lsb:nginx): (target-role:Stopped) Stopped
清理资源状态：
crm(live)resource# cleanup webserver Cleaning up webserver on marvin, removing fail-count-webserver Cleaning up webserver on sherry, removing fail-count-webserver * The configuration specifies that ‘webserver‘ should remain stopped Waiting for 2 replies from the CRMd.. OK
组操作：
先定义好资源，在加入组
crm(live)# status Last updated: Wed Jun 1 20:38:32 2016 Last change: Wed Jun 1 20:36:32 2016 by root via cibadmin on sherry Stack: classic openais (with plugin) Current DC: marvin (version 1.1.14-8.el6-70404b0) - partition with quorum 2 nodes and 2 resources configured, 2 expected votes Online: [ marvin sherry ] Full list of resources: webip (ocf::heartbeat:IPaddr): Started marvin webserver (lsb:nginx): Started sherry crm(live)# configure crm(live)configure# group webservice webip webserver crm(live)configure# verify crm(live)configure# commit crm(live)configure# show node marvin node sherry primitive webip IPaddr params ip=192.168.1.199 primitive webserver lsb:nginx group webservice webip webserver property cib-bootstrap-options: have-watchdog=false dc-version=1.1.14-8.el6-70404b0 cluster-infrastructure="classic openais (with plugin)" expected-quorum-votes=2 stonith-enabled=false
删除组：
crm(live)resource# stop webservice crm(live)configure# delete webservice #组下面的资源还是存在
节点操作：
节点离线：
crm(live)# node crm(live)node# standby marvin ＃资源自动转移
节点上线：
crm(live)node# online marvin
节点清理：（节点上资源信息清理）
crm(live)node# clearstate marvin
位置约束：
绑定在一起：
crm(live)configure# colocation webserver_and_webip inf: webserver webip crm(live)configure# verify crm(live)configure# commit
查看
crm(live)configure# show node marvin attributes standby=off node sherry primitive webip IPaddr params ip=192.168.1.199 primitive webserver lsb:nginx colocation webserver_and_webip inf: webserver webip property cib-bootstrap-options: have-watchdog=false dc-version=1.1.14-8.el6-70404b0 cluster-infrastructure="classic openais (with plugin)" expected-quorum-votes=2 stonith-enabled=false
具体查看：
crm(live)configure# show xml <rsc_colocation id="webserver_and_webip" score="INFINITY" rsc="webserver" with-rsc="webip"/> #webserver跟着webip
顺序约束：
crm(live)configure# order webip-before-webserver mandatory: webip webserver ＃依次顺序 crm(live)configure# verify crm(live)configure# commit crm(live)configure# status order webip-before-webserver Mandatory: webip webserver crm(live)configure# show xml <rsc_order id="webip-before-webserver" kind="Mandatory" first="webip" then="webserver"/>
位置约束
crm(live)configure# location webip_on_marvin webip 200: marvin crm(live)configure# verify crm(live)configure# commit
查看：
crm(live)# status Last updated: Wed Jun 1 21:11:58 2016 Last change: Wed Jun 1 21:11:32 2016 by root via cibadmin on sherry Stack: classic openais (with plugin) Current DC: marvin (version 1.1.14-8.el6-70404b0) - partition with quorum 2 nodes and 2 resources configured, 2 expected votes Online: [ marvin sherry ] Full list of resources: webip (ocf::heartbeat:IPaddr): Started marvin webserver (lsb:nginx): Started marvin
over
原文地址：http://marvin89.blog.51cto.com/9163436/1785326
