corosync+pacemaker实现pg流复制自动切换

一、环境 
$ cat /etc/redhat-release 
CentOS Linux release 7.0.1406 (Core) 
node1: 192.168.111.128
node2: 192.168.111.129
vip-master: 192.168.111.228
vip-slave:  192.168.111.229
配置主机名
hostnamectl set-hostname postgres128
hostnamectl set-hostname postgres129

[root@postgres128 ~]# vi /etc/hosts
192.168.111.128 postgres128
192.168.111.129 postgres129

二、配置Linux集群环境 
1. 安装Pacemaker和Corosync
在所有节点执行：
[root@postgres128 ~]# yum install -y pacemaker pcs psmisc policycoreutils-python

2. 禁用防火墙 
在所有节点执行：
[root@postgres128 ~]# systemctl disable firewalld.service
[root@postgres128 ~]# systemctl stop firewalld.service

 3. 启用pcs

在所有节点执行：
[root@postgres128 ~]# systemctl start pcsd.service
[root@postgres128 ~]# systemctl enable pcsd.service
[root@postgres128 ~]# echo hacluster | sudo passwd hacluster --stdin

 4. 集群认证 
在任何一个节点上执行，这里选择node1： 
[root@postgres128 ~]# pcs cluster auth -u hacluster -p hacluster 192.168.111.128 192.168.111.129

5. 同步配置 

在node1上执行： 
[root@postgres128 ~]# pcs cluster setup --last_man_standing=1 --name pgcluster 192.168.111.128 192.168.111.129
Shutting down pacemaker/corosync services...
Redirecting to /bin/systemctl stop  pacemaker.service
Redirecting to /bin/systemctl stop  corosync.service
Killing any remaining services...
Removing all cluster configuration files...
192.168.111.128: Succeeded
192.168.111.129: Succeeded

6. 启动集群 
在node1上执行： 
[root@postgres128 ~]# pcs cluster start --all
192.168.111.128: Starting Cluster...
192.168.111.129: Starting Cluster...

7. 检验 
1）检验corosync 
在node1上执行： 
$ sudo pcs status corosync
Membership information
----------------------
    Nodeid      Votes Name
         1          1 192.168.111.128 (local)
         2          1 192.168.111.129
         
2）检验pacemaker 
[root@postgres128 ~]#  pcs status
Cluster name: pgcluster
WARNING: no stonith devices and stonith-enabled is not false
Last updated: Wed Sep  6 02:20:28 2017
Last change: 
Current DC: NONE
0 Nodes configured
0 Resources configured

Full list of resources:

PCSD Status:
  192.168.111.128: Online
  192.168.111.129: Online

Daemon Status:
  corosync: active/disabled
  pacemaker: active/disabled
  pcsd: active/enabled
  
三、安装和配置PostgreSQL
配置参考
查看PG流复制结果。
[postgres@localhost ~]$ psql
psql (9.6.0)
Type "help" for help.

postgres=# \x
Expanded display is on.
postgres=# select * from pg_stat_replication ;
-[ RECORD 1 ]----+------------------------------
pid              | 2111
usesysid         | 16384
usename          | replica
application_name | standby01
client_addr      | 192.168.111.129
client_hostname  | 
client_port      | 45608
backend_start    | 2017-09-06 05:13:29.766227-04
backend_xmin     | 1756
state            | streaming
sent_location    | 0/50000D0
write_location   | 0/50000D0
flush_location   | 0/50000D0
replay_location  | 0/5000098
sync_priority    | 1
sync_state       | sync

停止PostgreSQL服务
$ pg_stop
waiting for server to shut down...... done
server stopped
  
四、配置自动切换 
1. 配置
在node1执行：
将配置步骤先写到脚本
# 将cib配置保存到文件
[root@postgres128 postgres]# vi cluster_setup.sh
pcs cluster cib pgsql_cfg                                                                   
# 在pacemaker级别忽略quorum
pcs -f pgsql_cfg property set no-quorum-policy="ignore"        
# 禁用STONITH           
pcs -f pgsql_cfg property set stonith-enabled="false"                    
# 设置资源粘性，防止节点在故障恢复后发生迁移     
pcs -f pgsql_cfg resource defaults resource-stickiness="INFINITY"       
# 设置多少次失败后迁移
pcs -f pgsql_cfg resource defaults migration-threshold="3"                 
# 设置master节点虚ip
pcs -f pgsql_cfg resource create vip-master IPaddr2 ip="192.168.111.228" cidr_netmask="24"    op start   timeout="60s" interval="0s"  on-fail="restart"    op monitor timeout="60s" interval="10s" on-fail="restart"    op stop    timeout="60s" interval="0s"  on-fail="block"                             
# 设置slave节点虚ip                       
pcs -f pgsql_cfg resource create vip-slave IPaddr2 ip="192.168.111.229" cidr_netmask="24"    op start   timeout="60s" interval="0s"  on-fail="restart"    op monitor timeout="60s" interval="10s" on-fail="restart"    op stop    timeout="60s" interval="0s"  on-fail="block"                                                        
# 设置pgsql集群资源
# pgctl、psql、pgdata和config等配置根据自己的环境修改,node list填写节点的hostname，master_ip填写虚master_ip
pcs -f pgsql_cfg resource create pgsql pgsql pgctl="/opt/pgsql96/bin/pg_ctl" psql="/opt/pgsql96/bin/psql" pgdata="/home/postgres/data" config="/home/postgres/data/postgresql.conf" rep_mode="sync" node_list="postgres128 postgres129" master_ip="192.168.111.228"  repuser="replica" primary_conninfo_opt="password=replica keepalives_idle=60 keepalives_interval=5 keepalives_count=5" restore_command="cp /home/postgres/arch/%f %p" restart_on_promote=‘true‘ op start   timeout="60s" interval="0s"  on-fail="restart" op monitor timeout="60s" interval="4s" on-fail="restart" op monitor timeout="60s" interval="3s"  on-fail="restart" role="Master" op promote timeout="60s" interval="0s"  on-fail="restart" op demote  timeout="60s" interval="0s"  on-fail="stop" op stop    timeout="60s" interval="0s"  on-fail="block"       
 # 设置master/slave模式，clone-max=2，两个节点
pcs -f pgsql_cfg resource master pgsql-cluster pgsql master-max=1 master-node-max=1 clone-max=2 clone-node-max=1 notify=true                                                                  
# 配置master ip组
pcs -f pgsql_cfg resource group add master-group vip-master
# 配置slave ip组     
pcs -f pgsql_cfg resource group add slave-group vip-slave         
# 配置master ip组绑定master节点
pcs -f pgsql_cfg constraint colocation add master-group with master pgsql-cluster INFINITY    
# 配置启动master节点
pcs -f pgsql_cfg constraint order promote pgsql-cluster then start master-group symmetrical=false score=INFINITY                                 
# 配置停止master节点                                                                   
pcs -f pgsql_cfg constraint order demote  pgsql-cluster then stop  master-group symmetrical=false score=0                                                                                                                
# 配置slave ip组绑定slave节点
pcs -f pgsql_cfg constraint colocation add slave-group with slave pgsql-cluster INFINITY         
# 配置启动slave节点
pcs -f pgsql_cfg constraint order promote pgsql-cluster then start slave-group symmetrical=false score=INFINITY                               
# 配置停止slave节点                                                                         
pcs -f pgsql_cfg constraint order demote  pgsql-cluster then stop  slave-group symmetrical=false score=0                                                                                                                  
# 把配置文件push到cib
pcs cluster cib-push pgsql_cfg

2. 执行加载命令
[root@postgres128 postgres]# chmod +x cluster_setup.sh 
[root@postgres128 postgres]# ./cluster_setup.sh 
Adding pgsql-cluster master-group (score: INFINITY) (Options: symmetrical=false score=INFINITY first-action=promote then-action=start)
Adding pgsql-cluster master-group (score: 0) (Options: symmetrical=false score=0 first-action=demote then-action=stop)
Adding pgsql-cluster slave-group (score: INFINITY) (Options: symmetrical=false score=INFINITY first-action=promote then-action=start)
Adding pgsql-cluster slave-group (score: 0) (Options: symmetrical=false score=0 first-action=demote then-action=stop)
CIB updated

3. 启动数据库


3查看pcs status
[root@postgres129 ~]# pcs status
Cluster name: pgcluster
Last updated: Wed Sep  6 22:13:39 2017
Last change: Wed Sep  6 06:00:26 2017 via cibadmin on postgres128
Stack: corosync
Current DC: postgres128 (1) - partition with quorum
Version: 1.1.10-29.el7-368c726
2 Nodes configured
4 Resources configured


Online: [ postgres128 postgres129 ]

Full list of resources:

 Master/Slave Set: pgsql-cluster [pgsql]
     Stopped: [ postgres128 postgres129 ]
 Resource Group: master-group
     vip-master (ocf::heartbeat:IPaddr2):       Started postgres128 
 Resource Group: slave-group
     vip-slave  (ocf::heartbeat:IPaddr2):       Started postgres129 

PCSD Status:
  192.168.111.128: Unable to authenticate
  192.168.111.129: Unable to authenticate

Daemon Status:
  corosync: active/disabled
  pacemaker: active/disabled
  pcsd: active/enabled