一、环境
ip：192.168.11.68（主）
192.168.11.70（备）
数据库版本：postgresql9.4.4
二、双机热备的过程
两台系统之中安装postgresql （过程这里就不写了）
1.配置主节点
[root@node1 ~]# su - postgres
[postgres@node1 ~]#cd /opt/pgsql/data
[postgres@node1 data]#vi postgresql.conf
--------------------------------------------------修改以下参数：
#wal_level = minimal
#max_wal_senders = 0
//wal 发送进程数，有几个备库就设置为几
#wal_keep_segments = 0
//WAL日志文件的大小，设置一个足够大的值，以防主库生成WAL日志太快，日志还没有来得及传送到standby，就会循环覆盖
#hot_standby = off
//开启日志记录功能
#logging_collector = off
#log_directory = 'pg_log' //日志目录
#log_filename = 'postgresql-%Y-%m-%d_%H%M%S.log' //日志名
--------------------------------------------------最终修改为：
wal_level = hot_standby
max_wal_senders = 1
wal_keep_segments = 500
hot_standby = on
logging_collector = on
log_directory = 'pg_log'
log_filename = 'postgresql-%Y-%m-%d_%H%M%S.log'
[postgres@node1 data]$ psql
Password:
psql (postgresql 9.4.4)
Type "help" for help.
postgres=# create user standby SUPERUSER LOGIN password 'standby';
CREATE ROLE
//配置pg_hba.conf，添加如下：
# IPv4 local connections:
host all all 127.0.0.1/32 md5
host replication standby 192.168.0.0/24 md5
重启数据库，使参数生效
[postgres@node1 data]# pg_ctl restart -m fast
2.进行基础备份
//开启备份功能
[postgres@node1 data]$psql -c "select pg_start_backup('backup0001')"
//将data目录下的数据远程拷贝到备库的data目录下
[postgres@node1 data]$scp -r /opt/pgsql/data/* 192.168.11.70:/opt/pgsql/data/
//关闭备份功能
[postgres@node1 data]$psql -c "select pg_stop_backup()"
注意: 没有启用WAL归档；您必须确保所有的WAL段已通过其他的方法拷贝，这样才能完成备份
pg_stop_backup
----------------
0/110000E0
(1 row)
3.配置备节点
//删除data目录下的postmaster.pid文件
[postgres@node2 ~]$ cd /opt/pgsql/data
[postgres@node2 data]$ rm -rf postmaster.pid
//在data目录下新建recovery.conf文件
[postgres@node2 data]$ vi recovery.conf
standby_mode='on'
recovery_target_timeline = 'latest'
primary_conninfo='host=192.168.11.70 port=5866 user=standby password=standby'
trigger_file='opt/pgsql/trigger_node'
启动数据库
[postgres@node2 data]$ pg_ctl start
在主节点上创建表测试
[postgrs@node1 ~]$ psql
psql (9.4.4)
Type "help" for help.
postgres=# create table a (a int);
CREATE TABLLE
postgres=# insert into a values (123);
INSERT 0 1
postgres=#select * from a ;
a
-----
123
(1 rows)
在备节点上查看数据是否同步
[postgrs@node2 ~]$ psql
psql (9.4.4)
Type "help" for help.
List of relations
Schema | Name | Type | Owner
----------------+------+-------+--------
public | a | table | postgres
postgres=#select * from a ;
a
-----
123
(1 rows)
数据同步，流复制配置成功！
三、主备切换
首先要把系统的网卡添加一个eth0:1的网络
方法：
[root@node1 network-scripts]# cd /etc/sysconfig/network-scripts/
[root@node1 network-scripts]# ls
ifcfg-eth0 ifdown ifdown-ippp ifdown-post ifdown-sit ifup-aliases ifup-ippp ifup-plip ifup-ppp ifup-tunnel net.hotplug
ifdown-bnep ifdown-ipv6 ifdown-ppp ifdown-tunnel ifup-bnep ifup-ipv6 ifup-plusb ifup-routes ifup-wireless network-functions
ifcfg-lo ifdown-eth ifdown-isdn ifdown-routes ifup ifup-eth ifup-isdn ifup-post ifup-sit init.ipv6-global network-functions-ipv6
[root@node1 network-scripts]# cp ifcfg-eth0 ifcfg-eth0:1
[root@node1 network-scripts]# vi ifcfg-eth0:1
DEVICE=eth0:1 #修改名字
HWADDR=00:0c:29:a2:99:01
TYPE=Ethernet
UUID=2f2ab65e-e86d-4897-8fcd-0601f6fd7f46
ONBOOT=yes
NM_CONTROLLED=yes
BOOTPROTO=none
IPADDR=192.168.11.40 #选择一个ip地址
NETMASK=255.255.255.0
GATEWAY=192.168.11.0
IPV6INIT=no
USERCTL=no
重启网络服务
[root@node1 network-scripts]# service network restart
Shutting down interface eth0: Device state: 3 (disconnected)
[ OK ]
Shutting down loopback interface: [ OK ]
Bringing up loopback interface: [ OK ]
Bringing up interface eth0: Active connection state: activated
Active connection path: /org/freedesktop/NetworkManager/ActiveConnection/3
[ OK ]
[root@node1 network-scripts]# ifconfig
eth0 Link encap:Ethernet HWaddr 00:0C:29:A2:99:01
inet addr:192.168.11.68 Bcast:192.168.11.255 Mask:255.255.255.0
inet6 addr: fe80::20c:29ff:fea2:9901/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:141173 errors:0 dropped:0 overruns:0 frame:0
TX packets:29124 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:198747523 (189.5 MiB) TX bytes:2168654 (2.0 MiB)
eth0:1 Link encap:Ethernet HWaddr 00:0C:29:A2:99:01
inet addr:192.168.11.40 Bcast:192.168.11.255 Mask:255.255.255.0
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
lo Link encap:Local Loopback
inet addr:127.0.0.1 Mask:255.0.0.0
inet6 addr: ::1/128 Scope:Host
UP LOOPBACK RUNNING MTU:16436 Metric:1
RX packets:636 errors:0 dropped:0 overruns:0 frame:0
TX packets:636 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:139280 (136.0 KiB) TX bytes:139280 (136.0 KiB)
备库做同样的操作，完成后将eth0:1关闭
[root@node2 ~]# ifdown eth0:1
[root@node2 network-scripts]# ifconfig
eth0 Link encap:Ethernet HWaddr 00:0C:29:A2:99:01
inet addr:192.168.11.70 Bcast:192.168.11.255 Mask:255.255.255.0
inet6 addr: fe80::20c:29ff:fea2:9901/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:141173 errors:0 dropped:0 overruns:0 frame:0
TX packets:29124 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:198747523 (189.5 MiB) TX bytes:2168654 (2.0 MiB)
lo Link encap:Local Loopback
inet addr:127.0.0.1 Mask:255.0.0.0
inet6 addr: ::1/128 Scope:Host
UP LOOPBACK RUNNING MTU:16436 Metric:1
RX packets:636 errors:0 dropped:0 overruns:0 frame:0
TX packets:636 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:139280 (136.0 KiB) TX bytes:139280 (136.0 KiB)
利用ip地址漂移实现主备切换
切换前观察ip地址情况和数据库的主备情况
ip地址：主端
[root@node1 ~]# ifconfig
eth0 Link encap:Ethernet HWaddr 00:0C:29:EA:AF:6E
inet addr:192.168.11.68 Bcast:192.168.11.255 Mask:255.255.255.0
inet6 addr: fe80::20c:29ff:feea:af6e/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:29953 errors:0 dropped:0 overruns:0 frame:0
TX packets:141299 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:2174739 (2.0 MiB) TX bytes:198989432 (189.7 MiB)
eth0:1 Link encap:Ethernet HWaddr 00:0C:29:EA:AF:6E
inet addr:192.168.11.40 Bcast:192.168.11.255 Mask:255.255.255.0
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
lo Link encap:Local Loopback
inet addr:127.0.0.1 Mask:255.0.0.0
inet6 addr: ::1/128 Scope:Host
UP LOOPBACK RUNNING MTU:16436 Metric:1
RX packets:308 errors:0 dropped:0 overruns:0 frame:0
TX packets:308 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:55374 (54.0 KiB) TX bytes:55374 (54.0 KiB)
备端
[root@node2 ~]# ifconfig
eth0 Link encap:Ethernet HWaddr 00:0C:29:EA:AF:6E
inet addr:192.168.11.70 Bcast:192.168.11.255 Mask:255.255.255.0
inet6 addr: fe80::20c:29ff:feea:af6e/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:29953 errors:0 dropped:0 overruns:0 frame:0
TX packets:141299 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:2174739 (2.0 MiB) TX bytes:198989432 (189.7 MiB)
lo Link encap:Local Loopback
inet addr:127.0.0.1 Mask:255.0.0.0
inet6 addr: ::1/128 Scope:Host
UP LOOPBACK RUNNING MTU:16436 Metric:1
RX packets:308 errors:0 dropped:0 overruns:0 frame:0
TX packets:308 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:55374 (54.0 KiB) TX bytes:55374 (54.0 KiB)
数据库情况
(./pg_controldata /postgresql/pgsql_data/ #查看数据库状态 ,需要加数据库目录！)
主端
[postgres@node1 ~]$ pg_controldata
pg_control version number: 922
Catalog version number: 201204301
Database system identifier: 6377220794669856238
Database cluster state:in production
pg_control last modified: Mon 23 Jan 2017 09:13:29 AM CST
Latest checkpoint location: 0/12015CD0
Prior checkpoint location: 0/12015C70
Latest checkpoint's REDO location: 0/12015CD0
Latest checkpoint's TimeLineID: 2
Latest checkpoint's full_page_writes: on
Latest checkpoint's NextXID: 0/1822
Latest checkpoint's NextOID: 16397
Latest checkpoint's NextMultiXactId: 1
Latest checkpoint's NextMultiOffset: 0
Latest checkpoint's oldestXID: 1802
Latest checkpoint's oldestXID's DB: 1
Latest checkpoint's oldestActiveXID: 0
Time of latest checkpoint: Mon 23 Jan 2017 09:11:41 AM CST
Minimum recovery ending location: 0/0
Backup start location: 0/0
Backup end location: 0/0
End-of-backup record required: no
Current wal_level setting: hot_standby
Current max_connections setting: 100
Current max_prepared_xacts setting: 0
Current max_locks_per_xact setting: 64
Maximum data alignment: 8
Database block size: 8192
Blocks per segment of large relation: 131072
WAL block size: 8192
Bytes per WAL segment: 16777216
Maximum length of identifiers: 64
Maximum columns in an index: 32
Maximum size of a TOAST chunk: 1996
Date/time type storage: 64-bit integers
Float4 argument passing: by value
Float8 argument passing: by value
[postgres@node2 ~]$ pg_controldata
pg_control version number: 922
Catalog version number: 201204301
Database system identifier: 6377220794669856238
Database cluster state:in archive recovery
pg_control last modified: Mon 23 Jan 2017 09:13:09 AM CST
Latest checkpoint location: 0/12015D30
Prior checkpoint location: 0/12015C10
Latest checkpoint's REDO location: 0/12015D30
Latest checkpoint's TimeLineID: 3
Latest checkpoint's full_page_writes: on
Latest checkpoint's NextXID: 0/1822
Latest checkpoint's NextOID: 16397
Latest checkpoint's NextMultiXactId: 1
Latest checkpoint's NextMultiOffset: 0
Latest checkpoint's oldestXID: 1802
Latest checkpoint's oldestXID's DB: 1
Latest checkpoint's oldestActiveXID: 0
Time of latest checkpoint: Mon 23 Jan 2017 09:13:09 AM CST
Minimum recovery ending location: 0/0
Backup start location: 0/0
Backup end location: 0/0
End-of-backup record required: no
Current wal_level setting: hot_standby
Current max_connections setting: 100
Current max_prepared_xacts setting: 0
Current max_locks_per_xact setting: 64
Maximum data alignment: 8
Database block size: 8192
Blocks per segment of large relation: 131072
WAL block size: 8192
Bytes per WAL segment: 16777216
Maximum length of identifiers: 64
Maximum columns in an index: 32
Maximum size of a TOAST chunk: 1996
Date/time type storage: 64-bit integers
Float4 argument passing: by value
Float8 argument passing: by value
备端情况
首先，关闭主库
[postgres@node1 data]$ pg_ctl stop -m fast
[root@node1 ~]# ifdown eth0:1
[root@node1 ~]# ifconfig
eth0 Link encap:Ethernet HWaddr 00:0C:29:EA:AF:6E
inet addr:192.168.11.68 Bcast:192.168.11.255 Mask:255.255.255.0
inet6 addr: fe80::20c:29ff:feea:af6e/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:30248 errors:0 dropped:0 overruns:0 frame:0
TX packets:141525 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:2199137 (2.0 MiB) TX bytes:199102358 (189.8 MiB)
lo Link encap:Local Loopback
inet addr:127.0.0.1 Mask:255.0.0.0
inet6 addr: ::1/128 Scope:Host
UP LOOPBACK RUNNING MTU:16436 Metric:1
RX packets:348 errors:0 dropped:0 overruns:0 frame:0
TX packets:348 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:60247 (58.8 KiB) TX bytes:60247 (58.8 KiB)
备库
[root@node2 ~]# ifup eth0:1
Active connection state: activating
Active connection path: /org/freedesktop/NetworkManager/ActiveConnection/1
state: activated
Connection activated
[root@node2 ~]# ifconfig
eth0 Link encap:Ethernet HWaddr 00:0C:29:EA:AF:6E
inet addr:192.168.11.70 Bcast:192.168.11.255 Mask:255.255.255.0
inet6 addr: fe80::20c:29ff:feea:af6e/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:29953 errors:0 dropped:0 overruns:0 frame:0
TX packets:141299 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:2174739 (2.0 MiB) TX bytes:198989432 (189.7 MiB)
eth0:1 Link encap:Ethernet HWaddr 00:0C:29:EA:AF:6E
inet addr:192.168.11.40 Bcast:192.168.11.255 Mask:255.255.255.0
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
lo Link encap:Local Loopback
inet addr:127.0.0.1 Mask:255.0.0.0
inet6 addr: ::1/128 Scope:Host
UP LOOPBACK RUNNING MTU:16436 Metric:1
RX packets:308 errors:0 dropped:0 overruns:0 frame:0
TX packets:308 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:55374 (54.0 KiB) TX bytes:55374 (54.0 KiB)
备库进行切换
[postgres@node2 ~]$ pg_ctl promote -D /data/pgdata(要加数据库目录)
server promoting
原备库状态
[highgo@node2 ~]$ pg_controldata
pg_control version number: 922、
Catalog version number: 201204301
Database system identifier: 6377220794669856238
Database cluster state:in production
pg_control last modified: Mon 23 Jan 2017 09:13:09 AM CST
Latest checkpoint location: 0/12015D30
Prior checkpoint location: 0/12015C10
Latest checkpoint's REDO location: 0/12015D30
Latest checkpoint's TimeLineID: 3
Latest checkpoint's full_page_writes: on
Latest checkpoint's NextXID: 0/1822
Latest checkpoint's NextOID: 16397
Latest checkpoint's NextMultiXactId: 1
Latest checkpoint's NextMultiOffset: 0
Latest checkpoint's oldestXID: 1802
Latest checkpoint's oldestXID's DB: 1
Latest checkpoint's oldestActiveXID: 0
Time of latest checkpoint: Mon 23 Jan 2017 09:13:09 AM CST
Minimum recovery ending location: 0/0
Backup start location: 0/0
Backup end location: 0/0
End-of-backup record required: no
Current wal_level setting: hot_standby
Current max_connections setting: 100
Current max_prepared_xacts setting: 0
Current max_locks_per_xact setting: 64
Maximum data alignment: 8
Database block size: 8192
Blocks per segment of large relation: 131072
WAL block size: 8192
Bytes per WAL segment: 16777216
Maximum length of identifiers: 64
Maximum columns in an index: 32
Maximum size of a TOAST chunk: 1996
Date/time type storage: 64-bit integers
Float4 argument passing: by value
Float8 argument passing: by value
[postgres@node2 ~]$ ps -ef | grep postgres
postgres 2538 1 0 09:11 pts/0 00:00:00 /opt/pgsql/bin/postgres
postgres 2539 2538 0 09:11 ? 00:00:00 postgres: logger process
postgres 2541 2538 0 09:11 ? 00:00:00 postgres: checkpointer process
postgres 2542 2538 0 09:11 ? 00:00:00 postgres: writer process
postgres 2543 2538 0 09:11 ? 00:00:00 postgres: stats collector process
postgres 2625 2538 0 09:13 ? 00:00:00postgres: wal writer process
postgres 2626 2538 0 09:13 ? 00:00:00 postgres: autovacuum launcher process
postgres 2432 2425 0 09:06 ? 00:00:00 postgres: stats collector process
postgrs 2435 2425 0 09:06 ? 00:00:00postgres: archiver process last was 000000.4history
root 3348 1992 0 10:06 pts/0 00:00:00 su - postgres
postgres 3349 3348 0 10:06 pts/0 00:00:00 -bash
postgres 3395 3349 0 10:13 pts/0 00:00:00 ps -ef
postgres 3396 3349 0 10:13 pts/0 00:00:00 grep postgres
在原主库配置recovery.conf文件
[postgres@node1 data]$ vi recovery.conf
standby_mode='on'
recovery_target_timeline = 'latest'
primary_conninfo='host=192.168.11.68 port=5866 user=standby password=standby'
trigger_file='opt/pgsql/trigger_node'
启动原主库
[postgres@node2 ~]$ pg_ctl start
[postgres@node2 ~]$ ps -ef | grep postgres
postgres 2169 1 0 09:04 pts/0 00:00:00 /opt/pgsql/bin/postgres
postgres 2170 2169 0 09:04 ? 00:00:00 postgres: logger process
postgres 2171 2169 0 09:04 ? 00:00:00 postgres: startup process waiting for 000000020000000000000012
postgres 2172 2169 0 09:04 ? 00:00:00 postgres: checkpointer process
postgres 2173 2169 0 09:04 ? 00:00:00 postgres: writer process
postgres 2175 2169 0 09:04 ? 00:00:00 postgres: stats collector process
root 2241 1992 0 09:06 pts/0 00:00:00 su - postgres
postgres 2242 2241 0 09:06 pts/0 00:00:00 -bash
postgres 2283 2169 0 09:07 ? 00:00:00postgres: wal receiver process
postgres 2288 2242 0 09:09 pts/0 00:00:00 ps -ef
postgres 2289 2242 0 09:09 pts/0 00:00:00 grep postgres
测试：建表插入数据
能实现主备同步说明切换成功！
