1、准备三台服务器
10.0.0.12
10.0.0.13
10.0.0.14
2、在三台服务器上执行操作
时间同步
[root@ c7m01 ~]# echo "*/5* * * * /usr/sbin/ntpdate ntp1.aliyun.com >/dev/null 2>&1" >>/var/spool/cron/root
修改主机名（主）
[root@ c7m01 ~]# vim /etc/hostname
c7m01
修改主机名（从）
[root@ c702 ~]# vim /etc/hostname
c702
修改主机名（从）
[root@ c703 ~]# vim /etc/hostname
c703
修改完主机名重启机子就可以
3、三台服务器配置hosts解析（这里的主机名要和自己的一样，以便于区分）
[root@ c7m01 ~]# vim /etc/hostsEOF c7m01 10.0.0.12 c702 10.0.0.13 c703 10.0.0.14
4、关闭防火墙和selinux （三台服务器执行同样的操作）
systemctl stop firewalld
systemctl disable firewalld
setenforce 0
[root@ c7m01 ~]# sed -i ' /^SELINUX/s#enforcing#disabled#g' /etc/selinux/config
5、配置免密登录（三台服务器执行同样的操作）
[root@ c7m01 ~]# vim ssh.sh #!/bin/bash yum -y install sshpass &> /dev/null read -p "请输入服务器密码：" passwd UserName=root IP="10.0.0." #创建密钥 ssh-keygen -t dsa -f ~/.ssh/id_dsa -P "" &>/dev/null #分发公钥 for i in 12 13 14 #这里的要改成自己机子的ip do sshpass -p "$passwd" ssh-copy-id -i ~/.ssh/id_dsa.pub -p 22 -o StrictHostKeyChecking=no $UserName@$IP$i &>/dev/null done
6、执行脚本配置，并连接其中一台服务器
[root@ c7m01 ~]# sh ssh.sh 请输入服务器密码：123456 [root@ c7m01 ~]# [root@ c7m01 ~]# ssh root@10.0.0.13 Last login: Fri Feb 14 00:14:41 2020 from 10.0.0.1 [root@ c702 ~]# exit logout Connection to 10.0.0.13 closed.
7、mysql安装yum repo（三台服务器执行同样的操作）
[root@ c7m01 ~]# wget http://repo.mysql.com/mysql-community-release-el7-5.noarch.rpm [root@ c7m01 ~]# rpm -ivh mysql-community-release-el7-5.noarch.rpm [root@ c7m01 ~]# yum -y install mysql-server
8、启动MySQL，三台服务器执行同样的操作
[root@ c7m01 ~]# systemctl restart mysql
9、修改MySQL密码，三台服务器执行同样的操作
mysql> update mysql.user set password=password('123456') where user='root' and host='localhost'; Query OK, 1 row affected (0.00 sec) Rows matched: 1 Changed: 1 Warnings: 0 mysql> flush privileges; Query OK, 0 rows affected (0.00 sec) mysql>
主服务器上操作
10、在c7m01服务器上更改mysql配置文件
vim /etc/my.cnf [mysqld] server-id=1 log-bin=mysql-bin #禁止mysql自动删除relaylog工能 relay_log_purge = 0 #mysql5.6已上的特性，开启gtid，必须主从全开 gtid_mode = on enforce_gtid_consistency = 1 log_slave_updates = 1
更改完成后重启mysql
systemctl restart mysql
11、创建同步用户
[root@ c7m01 ~]# mysql -uroot -p123456 Warning: Using a password on the command line interface can be insecure. Welcome to the MySQL monitor. Commands end with ; or \g. Your MySQL connection id is 2 Server version: 5.6.47-log MySQL Community Server (GPL) Copyright (c) 2000, 2020, Oracle and/or its affiliates. All rights reserved. Oracle is a registered trademark of Oracle Corporation and/or its affiliates. Other names may be trademarks of their respective owners. Type 'help;' or '\h' for help. Type '\c' to clear the current input statement. mysql> grant replication slave on *.* to 'rep'@'10.0.0.%' identified by '123456'; Query OK, 0 rows affected (0.01 sec) mysql> flush privileges; Query OK, 0 rows affected (0.00 sec)
12、查看MySQL主库的master状态
mysql> show master status\G *************************** 1. row *************************** File: mysql-bin.000002 Position: 530 Binlog_Do_DB: Binlog_Ignore_DB: Executed_Gtid_Set: f45fe1ec-53a4-11ea-899f-000c29d39f7e:1-2 1 row in set (0.00 sec) mysql> show master status; +------------------+----------+--------------+------------------+------------------------------------------+ | File | Position | Binlog_Do_DB | Binlog_Ignore_DB | Executed_Gtid_Set | +------------------+----------+--------------+------------------+------------------------------------------+ | mysql-bin.000002 | 530 | | | f45fe1ec-53a4-11ea-899f-000c29d39f7e:1-2 | +------------------+----------+--------------+------------------+------------------------------------------+ 1 row in set (0.00 sec)
13、查看GTID状态
mysql> show global variables like '%gtid%'; +---------------------------------+------------------------------------------+ | Variable_name | Value | +---------------------------------+------------------------------------------+ | binlog_gtid_simple_recovery | OFF | | enforce_gtid_consistency | ON | #执行GTID模块 | gtid_executed | f45fe1ec-53a4-11ea-899f-000c29d39f7e:1-2 | | gtid_mode | ON | #开启GTID模块 | gtid_owned | | | gtid_purged | | | simplified_binlog_gtid_recovery | OFF | +---------------------------------+------------------------------------------+ 7 rows in set (0.00 sec)
c702从服务器上操作
14、在c702服务器上更改mysql配置文件
vim /etc/my.cnf [mysqld] server-id=2 log-bin=mysql-bin #禁止mysql自动删除relaylog工能 relay_log_purge = 0 #mysql5.6已上的特性，开启gtid，必须主从全开 gtid_mode = on enforce_gtid_consistency = 1 log_slave_updates = 1 更改完成后重启mysql systemctl restart mysql
15、创建同步用户
[root@ c702 ~]# mysql -uroot -p123456 Warning: Using a password on the command line interface can be insecure. Welcome to the MySQL monitor. Commands end with ; or \g. Your MySQL connection id is 2 Server version: 5.6.47-log MySQL Community Server (GPL) Copyright (c) 2000, 2020, Oracle and/or its affiliates. All rights reserved. Oracle is a registered trademark of Oracle Corporation and/or its affiliates. Other names may be trademarks of their respective owners. Type 'help;' or '\h' for help. Type '\c' to clear the current input statement. mysql> grant replication slave on *.* to 'rep'@'10.0.0.%' identified by '123456'; Query OK, 0 rows affected (0.00 sec) mysql> flush privileges; Query OK, 0 rows affected (0.00 sec)
16、关闭复制功能，配置指向master，开启服务器复制状态，检查复制状态，出现俩个yes状态表示成功
mysql> stop slave; Query OK, 0 rows affected, 1 warning (0.00 sec) mysql> change master to -> master_host='10.0.0.12', -> master_user='rep', -> master_password='123456', -> master_log_file='mysql-bin.000002', -> master_log_pos=530; Query OK, 0 rows affected, 2 warnings (0.06 sec) mysql> flush privileges; Query OK, 0 rows affected (0.00 sec) mysql> start slave; Query OK, 0 rows affected (0.01 sec)
mysql> show slave status\G *************************** 1. row *************************** Slave_IO_State: Waiting for master to send event Master_Host: 10.0.0.12 Master_User: rep Master_Port: 3306 Connect_Retry: 60 Master_Log_File: mysql-bin.000002 Read_Master_Log_Pos: 530 Relay_Log_File: mysqld-relay-bin.000002 Relay_Log_Pos: 314 Relay_Master_Log_File: mysql-bin.000002 Slave_IO_Running: Yes Slave_SQL_Running: Yes Replicate_Do_DB: Replicate_Ignore_DB: Replicate_Do_Table: Replicate_Ignore_Table: Replicate_Wild_Do_Table: Replicate_Wild_Ignore_Table: Last_Errno: 0 Last_Error: Skip_Counter: 0 Exec_Master_Log_Pos: 530 Relay_Log_Space: 519 Until_Condition: None Until_Log_File: Until_Log_Pos: 0 Master_SSL_Allowed: No Master_SSL_CA_File: Master_SSL_CA_Path: Master_SSL_Cert: Master_SSL_Cipher: Master_SSL_Key: Seconds_Behind_Master: 0 Master_SSL_Verify_Server_Cert: No Last_IO_Errno: 0 Last_IO_Error: Last_SQL_Errno: 0 Last_SQL_Error: Replicate_Ignore_Server_Ids: Master_Server_Id: 1 Master_UUID: f45fe1ec-53a4-11ea-899f-000c29d39f7e Master_Info_File: /var/lib/mysql/master.info SQL_Delay: 0 SQL_Remaining_Delay: NULL Slave_SQL_Running_State: Slave has read all relay log; waiting for the slave I/O thread to update it Master_Retry_Count: 86400 Master_Bind: Last_IO_Error_Timestamp: Last_SQL_Error_Timestamp: Master_SSL_Crl: Master_SSL_Crlpath: Retrieved_Gtid_Set: Executed_Gtid_Set: fdcedb5b-53a4-11ea-899f-000c2927e658:1-5 Auto_Position: 0 1 row in set (0.00 sec) mysql>
c703服务器
17、在c702服务器上更改mysql配置文件
vim /etc/my.cnf [mysqld] server-id=3 log-bin=mysql-bin #禁止mysql自动删除relaylog工能 relay_log_purge = 0 #mysql5.6已上的特性，开启gtid，必须主从全开 gtid_mode = on enforce_gtid_consistency = 1 log_slave_updates = 1 更改完成后重启mysql systemctl restart mysql
18、创建同步用户
[root@ c703 ~]# mysql -uroot -p123456 Warning: Using a password on the command line interface can be insecure. Welcome to the MySQL monitor. Commands end with ; or \g. Your MySQL connection id is 2 Server version: 5.6.47-log MySQL Community Server (GPL) Copyright (c) 2000, 2020, Oracle and/or its affiliates. All rights reserved. Oracle is a registered trademark of Oracle Corporation and/or its affiliates. Other names may be trademarks of their respective owners. Type 'help;' or '\h' for help. Type '\c' to clear the current input statement. mysql> grant replication slave on *.* to 'rep'@'10.0.0.%' identified by '123456'; Query OK, 0 rows affected (0.00 sec) mysql> flush privileges; Query OK, 0 rows affected (0.00 sec)
19、关闭复制功能，配置指向master，开启服务器复制状态，检查复制状态，出现俩个yes状态表示成功
mysql> stop slave; Query OK, 0 rows affected (0.00 sec) mysql> change master to -> master_host='10.0.0.12', -> master_user='rep', -> master_password='123456', -> master_log_file='mysql-bin.000002', -> master_log_pos=530; Query OK, 0 rows affected, 2 warnings (0.00 sec) mysql> flush privileges; Query OK, 0 rows affected (0.00 sec) mysql> start slave; Query OK, 0 rows affected (0.00 sec)
mysql> show slave status \G *************************** 1. row *************************** Slave_IO_State: Waiting for master to send event Master_Host: 10.0.0.12 Master_User: rep Master_Port: 3306 Connect_Retry: 60 Master_Log_File: mysql-bin.000002 Read_Master_Log_Pos: 530 Relay_Log_File: mysqld-relay-bin.000002 Relay_Log_Pos: 314 Relay_Master_Log_File: mysql-bin.000002 Slave_IO_Running: Yes Slave_SQL_Running: Yes Replicate_Do_DB: Replicate_Ignore_DB: Replicate_Do_Table: Replicate_Ignore_Table: Replicate_Wild_Do_Table: Replicate_Wild_Ignore_Table: Last_Errno: 0 Last_Error: Skip_Counter: 0 Exec_Master_Log_Pos: 530 Relay_Log_Space: 519 Until_Condition: None Until_Log_File: Until_Log_Pos: 0 Master_SSL_Allowed: No Master_SSL_CA_File: Master_SSL_CA_Path: Master_SSL_Cert: Master_SSL_Cipher: Master_SSL_Key: Seconds_Behind_Master: 0 Master_SSL_Verify_Server_Cert: No Last_IO_Errno: 0 Last_IO_Error: Last_SQL_Errno: 0 Last_SQL_Error: Replicate_Ignore_Server_Ids: Master_Server_Id: 1 Master_UUID: f45fe1ec-53a4-11ea-899f-000c29d39f7e Master_Info_File: /var/lib/mysql/master.info SQL_Delay: 0 SQL_Remaining_Delay: NULL Slave_SQL_Running_State: Slave has read all relay log; waiting for the slave I/O thread to update it Master_Retry_Count: 86400 Master_Bind: Last_IO_Error_Timestamp: Last_SQL_Error_Timestamp: Master_SSL_Crl: Master_SSL_Crlpath: Retrieved_Gtid_Set: Executed_Gtid_Set: 0033cbb6-53a5-11ea-899f-000c298eeea7:1-4 Auto_Position: 0 1 row in set (0.00 sec)
20、在三台服务器装MHA的依赖
yum -y install perl-dbd-mysql
yum -y install per-Config-Tiny epel-release perl-Log-Dispatch perl-Parallel-ForKManager perl-Time-HiRes
21、授权MHA管理用户（三台服务器执行同样的操作）
mysql> grant all privileges on *.* to mha@'10.0.0.%' identified by 'mha'; Query OK, 0 rows affected (0.00 sec) mysql> flush privileges; Query OK, 0 rows affected (0.00 sec)
22、安装MHA node节点
[root@ c7m01 ~]# ll total 140 -rw-------. 1 root root 1277 2019-09-17 22:18 anaconda-ks.cfg -rw-r--r-- 1 root root 81024 2020-02-13 16:32 mha4mysql-manager-0.58-0.el7.centos.noarch.rpm -rw-r--r-- 1 root root 36328 2020-02-13 16:32 mha4mysql-node-0.58-0.el7.centos.noarch.rpm -rw-r--r-- 1 root root 6140 2015-11-12 15:58 mysql-community-release-el7-5.noarch.rpm -rw-r--r-- 1 root root 6140 2015-11-12 15:58 mysql-community-release-el7-5.noarch.rpm.1 -rw-r--r-- 1 root root 349 2020-02-13 16:53 ssh.sh [root@ c7m01 ~]# rpm -ivh mha4mysql-node-0.58-0.el7.centos.noarch.rpm Preparing... ################################# [100%] Updating / installing... 1:mha4mysql-node-0.58-0.el7.centos ################################# [100%] [root@ c7m01 ~]#
在c703上执行
如果安装到错误的机器上可以撤销掉，否则后期vip漂移会出错
[root@ c7m01 ~]# rpm -qa |grep mha4mysql-manager-0.58-0.el7.centos.noarch.rpm [root@ c7m01 ~]# rpm -e mha4mysql-manager
23、安装管理MHA的管理节点
[root@ c703 ~]# ll total 132 -rw-------. 1 root root 1277 2019-09-17 22:18 anaconda-ks.cfg -rw-r--r-- 1 root root 81024 2020-02-13 16:32 mha4mysql-manager-0.58-0.el7.centos.noarch.rpm -rw-r--r-- 1 root root 36328 2020-02-13 16:32 mha4mysql-node-0.58-0.el7.centos.noarch.rpm -rw-r--r-- 1 root root 6140 2015-11-12 15:58 mysql-community-release-el7-5.noarch.rpm -rw-r--r-- 1 root root 349 2020-02-13 16:37 ssh.sh [root@ c703 ~]# rpm -ivh mha4mysql-manager-0.58-0.el7.centos.noarch.rpm Preparing... ################################# [100%] Updating / installing... 1:mha4mysql-manager-0.58-0.el7.cent################################# [100%]
24、配置MHA
[root@ c703 ~]# mkdir -p /etc/mha [root@ c703 ~]# mkdir -p /var/log/mha/app1 [root@ c703 ~]# vim /etc/mha/app1.cnf [server default] manager_log=/var/log/mha/app1/manager.log manager_workdir=/var/log/mha/app1 master_binlog_dir=/var/lib/mysql #binlog的目录，如果说miysql的环境不一样，binlog位置不同，每台服务器的binlog的位置写在server标签里面即可 user=mha password=mha ping_interval=2 repl_password=123456 repl_user=rep ssh_user=root [server1] hostname=10.0.0.12 port=3306 [server2] hostname=10.0.0.13 port=3306 [server3] hostname=10.0.0.14 port=3306 ignore_fail=1 #如果这个节点挂了，mha将不可用，加上这个参数，slave挂了一样可以用 no_master=1 #从不将这台主机转换为master #candidate_master=1 #如果候选master有延迟的话，relay日志超过100m，failover切换不能成功，加上此参数后会忽略延迟日志大小。 #check_repl_delay=0 #用防止master故障时,切换时slave有延迟,卡在那里切不过来
#注意这里的配置要把注释和空格全部删除
检查ssh
[root@ c703 ~]# masterha_check_ssh --conf=/etc/mha/app1.cnf Fri Feb 21 13:37:37 2020 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping. Fri Feb 21 13:37:37 2020 - [info] Reading application default configuration from /etc/mha/app1.cnf.. Fri Feb 21 13:37:37 2020 - [info] Reading server configuration from /etc/mha/app1.cnf.. Fri Feb 21 13:37:37 2020 - [info] Starting SSH connection tests.. Fri Feb 21 13:37:38 2020 - [debug] Fri Feb 21 13:37:37 2020 - [debug] Connecting via SSH from root@10.0.0.12(10.0.0.12:22) to root@10.0.0.13(10.0.0.13:22).. Fri Feb 21 13:37:38 2020 - [debug] ok. Fri Feb 21 13:37:38 2020 - [debug] Connecting via SSH from root@10.0.0.12(10.0.0.12:22) to root@10.0.0.14(10.0.0.14:22).. Fri Feb 21 13:37:38 2020 - [debug] ok. Fri Feb 21 13:37:39 2020 - [debug] Fri Feb 21 13:37:37 2020 - [debug] Connecting via SSH from root@10.0.0.13(10.0.0.13:22) to root@10.0.0.12(10.0.0.12:22).. Fri Feb 21 13:37:39 2020 - [debug] ok. Fri Feb 21 13:37:39 2020 - [debug] Connecting via SSH from root@10.0.0.13(10.0.0.13:22) to root@10.0.0.14(10.0.0.14:22).. Fri Feb 21 13:37:39 2020 - [debug] ok. Fri Feb 21 13:37:40 2020 - [debug] Fri Feb 21 13:37:38 2020 - [debug] Connecting via SSH from root@10.0.0.14(10.0.0.14:22) to root@10.0.0.12(10.0.0.12:22).. Fri Feb 21 13:37:39 2020 - [debug] ok. Fri Feb 21 13:37:39 2020 - [debug] Connecting via SSH from root@10.0.0.14(10.0.0.14:22) to root@10.0.0.13(10.0.0.13:22).. Fri Feb 21 13:37:40 2020 - [debug] ok. Fri Feb 21 13:37:40 2020 - [info] All SSH connection tests passed successfully. [root@ c703 ~]#
这里放一个报错的
解决办法就是在三台服务器的mysql配置文件加一个跳过域名解析
skip-name-resolve
[root@ c703 ~]# masterha_check_repl --conf=/etc/mha/app1.cnf
25、启动MHA
[root@ c703 ~]# nohup masterha_manager --conf=/etc/mha/app1.cnf --remove_dead_master_conf --ignore_last_failover < /dev/null > /var/log/mha/app1/manager.log 2>&1 &
[1] 6041
[root@ c703 ~]# ps -ef |grep mha
root 6041 4852 0 14:37 pts/0 00:00:00 perl /usr/bin/masterha_manager --conf=/etc/mha/app1.cnf --remove_dead_master_conf --ignore_last_failover
root 6066 4852 0 14:38 pts/0 00:00:00 grep --color=auto mha
26、查看MHA状态
[root@ c703 ~]# masterha_check_status --conf=/etc/mha/app1.cnf app1 (pid:6041) is running(0:PING_OK), master:10.0.0.12
27、关闭MHA
[root@ c703 ~]# masterha_stop --conf=/etc/mha/app1.cnf Stopped app1 successfully. [1]+ Exit 1 nohup masterha_manager --conf=/etc/mha/app1.cnf --remove_dead_master_conf --ignore_last_failover < /dev/null > /var/log/mha/app1/manager.log 2>&1
28、从库从新加入新生
[root@ c703 ~]# grep -i "CHANGE MASTER TO MASTER" /var/log/mha/app1/manager.log | tail -1
29、测试MHA故障转移
停掉c7m01上的mysql 10.0.0.12
[root@ c7m01 ~]# systemctl stop mysql
30、在c703上查看slave的状态，发现master_host变成10.0.0.13
[root@ c703 ~]# mysql -uroot -p123456 -e 'show slave status\G'; Warning: Using a password on the command line interface can be insecure. *************************** 1. row *************************** Slave_IO_State: Reconnecting after a failed master event read Master_Host: 10.0.0.13 Master_User: rep Master_Port: 3306 Connect_Retry: 60 Master_Log_File: mysql-bin.000003 Read_Master_Log_Pos: 191 Relay_Log_File: mysqld-relay-bin.000006 Relay_Log_Pos: 401 Relay_Master_Log_File: mysql-bin.000003 Slave_IO_Running: Connecting Slave_SQL_Running: Yes Replicate_Do_DB: Replicate_Ignore_DB: Replicate_Do_Table: Replicate_Ignore_Table: Replicate_Wild_Do_Table: Replicate_Wild_Ignore_Table: Last_Errno: 0 Last_Error: Skip_Counter: 0 Exec_Master_Log_Pos: 191 Relay_Log_Space: 2309 Until_Condition: None Until_Log_File: Until_Log_Pos: 0 Master_SSL_Allowed: No Master_SSL_CA_File: Master_SSL_CA_Path: Master_SSL_Cert: Master_SSL_Cipher: Master_SSL_Key: Seconds_Behind_Master: NULL Master_SSL_Verify_Server_Cert: No Last_IO_Errno: 2003 Last_IO_Error: error reconnecting to master 'rep@10.0.0.12:3306' - retry-time: 60 retries: 4 Last_SQL_Errno: 0 Last_SQL_Error: Replicate_Ignore_Server_Ids: Master_Server_Id: 1 Master_UUID: f45fe1ec-53a4-11ea-899f-000c29d39f7e Master_Info_File: /var/lib/mysql/master.info SQL_Delay: 0 SQL_Remaining_Delay: NULL Slave_SQL_Running_State: Slave has read all relay log; waiting for the slave I/O thread to update it Master_Retry_Count: 86400 Master_Bind: Last_IO_Error_Timestamp: 200221 14:48:05 Last_SQL_Error_Timestamp: Master_SSL_Crl: Master_SSL_Crlpath: Retrieved_Gtid_Set: f45fe1ec-53a4-11ea-899f-000c29d39f7e:3-4 Executed_Gtid_Set: 0033cbb6-53a5-11ea-899f-000c298eeea7:1-6, f45fe1ec-53a4-11ea-899f-000c29d39f7e:3-4 Auto_Position: 0
31、查看c703的配置文件
[root@ c703 ~]# cat /etc/mha/app1.cnf [server default] manager_log=/var/log/mha/app1/manager.log manager_workdir=/var/log/mha/app1 master_binlog_dir=/var/lib/mysql user=mha password=mha ping_interval=2 repl_password=123456 repl_user=rep ssh_user=root [server2] hostname=10.0.0.13 port=3306 [server3] hostname=10.0.0.14 port=3306 ignore_fail=1 no_master=1 #candidate_master=1 #check_repl_delay=0
当c7m01上的主库荡机之后，MHA会自动检查，发现主库mysql停机，立刻会把从库上提升为主库，然后另一台服务器会把mysql主从复制的master_host改为新提升的主库
32、MHA故障还原
先在c703上查看一下
[root@c703 ~]# grep "CHANGE MASTER TO MASTER" /var/log/mha/app1/manager.log | tail -1 Fri Feb 14 01:25:18 2020 - [info] All other slaves should start replication from here. Statement should be: CHANGE MASTER TO MASTER_HOST='10.0.0.12', MASTER_PORT=3306, MASTER_AUTO_POSITION=1, MASTER_USER='rep', MASTER_PASSWORD='xxx';
33、在c7m01上执行
[root@c7m01 ~]# mysql -uroot -p123456 -e "CHANGE MASTER TO MASTER_HOST='10.0.0.13',MASTER_PORT=3306, MASTER_AUTO_POSITION=1,MASTER_USER='rep',MASTER_PASSWORD='123456';"
[root@c7m01 ~]# mysql -uroot -p123456 -e "start slave;" [root@c7m01 ~]# mysql -uroot -p123456 -e "show slave status \G"
这个时候的MHA是一次性的，当12上的mysql荡掉之后，就会把13的mysql变成主库，当再次荡机之后，不会在发生改变
在c703上执行
34、修复mysql，将server1标签加入到app1的配置文件中
[root@ c703 ~]# cat /etc/mha/app1.cnf [server default] manager_log=/var/log/mha/app1/manager.log manager_workdir=/var/log/mha/app1 master_binlog_dir=/var/lib/mysql user=mha password=mha ping_interval=2 repl_password=123456 repl_user=rep ssh_user=root [server1] hostname=10.0.0.12 port=3306 [server2] hostname=10.0.0.13 port=3306 [server3] hostname=10.0.0.14 port=3306 ignore_fail=1 no_master=1 #candidate_master=1 #check_repl_delay=0
34、重新启动MHA
[root@ c703 ~]# nohup masterha_manager --conf=/etc/mha/app1.cnf --remove_dead_master_conf --ignore_last_failover < /dev/null > /var/log/mha/app1/manager.log 2>&1 & [1] 6041
配置vip漂移，有俩种方式
第一种是keepalived的方式，管理虚拟ip的漂移
第二种是MHA自带脚本的方式，管理虚拟ip的漂移（这个漂移就是那个服务器的mysql库提升为主库，就漂移到那个上面，要根据binlog的最新slave方式提升）
35、MHA脚本方式
修改app1配置文件，添加
[root@ c703 ~]# vim /etc/mha/app1.cnf [server default] master_ip_failover_script=/usr/bin/master_ip_failover #添加这一行
编写脚本
[root@ c703 ~]# vim /usr/bin/master_ip_failover #!/usr/bin/env perl use strict; use warnings FATAL => 'all'; use Getopt::Long; my ( $command, $ssh_user, $orig_master_host, $orig_master_ip, $orig_master_port, $new_master_host, $new_master_ip, $new_master_port ); my $vip = '10.0.0.100/24'; #这里的vip地址写一个与自己IP地址相同的IP段 my $key = '1'; my $ssh_start_vip = "/sbin/ifconfig ens33:$key $vip"; #这里的网卡要看自己外网的外卡是不是ens33，不是的话要改成自己的外网网卡 my $ssh_stop_vip = "/sbin/ifconfig ens33:$key down"; GetOptions( 'command=s' => \$command, 'ssh_user=s' => \$ssh_user, 'orig_master_host=s' => \$orig_master_host, 'new_master_ip=s' => \$new_master_ip, 'new_master_port=i' => \$new_master_port, ); exit &main(); sub main { print "\n\nIN SCRIPT TEST====$ssh_stop_vip==$ssh_start_vip===\n\n"; if ( $command eq "stop" || $command eq "stopssh" ) { my $exit_code = 1; eval { print "Disabling the VIP on old master: $orig_master_host \n"; &stop_vip(); $exit_code = 0; }; if ($@) { warn "Got Error: $@\n"; exit $exit_code; } exit $exit_code; } elsif ( $command eq "start" ) { my $exit_code = 10; eval { print "Enabling the VIP - $vip on the new master - $new_master_host \n"; &start_vip(); $exit_code = 0; }; if ($@) { warn $@; exit $exit_code; } exit $exit_code; } elsif ( $command eq "status" ) { print "Checking the Status of the script.. OK \n"; exit 0; } else { &usage(); exit 1; } } sub start_vip() { `ssh $ssh_user\@$new_master_host \" $ssh_start_vip \"`; } sub stop_vip() { return 0 unless ($ssh_user); `ssh $ssh_user\@$orig_master_host \" $ssh_stop_vip \"`; } sub usage { print "Usage: master_ip_failover --command=start|stop|stopssh|status --orig_master_host=host --orig_master_ip=ip --orig_master_port=port --new_master_host=host --new_master_ip=ip --new_master_port=port\n"; }
36、给脚本加权限
[root@ c703 ~]# chmod +x /usr/bin/master_ip_failover
37、手动添加vip，绑定到主库的机子上，我这里是10.0.0.13
[root@ c702 ~]# ifconfig ens33:1 10.0.0.100/24 [root@ c702 ~]# ip a show ens33 2: ens33: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000 link/ether 00:0c:29:d3:9f:7e brd ff:ff:ff:ff:ff:ff inet 10.0.0.13/24 brd 10.0.0.255 scope global ens33 valid_lft forever preferred_lft forever inet 10.0.0.100/24 brd 10.0.0.255 scope global secondary ens33:1 valid_lft forever preferred_lft forever inet6 fe80::20c:29ff:fed3:9f7e/64 scope link valid_lft forever preferred_lft forever
38、重启MHA
[root@ c703 ~]# masterha_stop --conf=/etc/mha/app1.cnf Stopped app1 successfully. [1]+ Exit 1 nohup masterha_manager --conf=/etc/mha/app1.cnf --remove_dead_master_conf --ignore_last_failover < /dev/null > /var/log/mha/app1/manager.log 2>&1 [root@ c703 ~]# nohup masterha_manager --conf=/etc/mha/app1.cnf --remove_dead_master_conf --ignore_last_failover < /dev/null > /var/log/mha/app1/manager.log 2>&1 & [1] 6468
模拟主库宕机vip飘移
在c702上操作
[root@ c702 ~]# systemctl stop mysql [root@ c702 ~]# ip a show ens33 2: ens33: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000 link/ether 00:0c:29:d3:9f:7e brd ff:ff:ff:ff:ff:ff inet 10.0.0.12/24 brd 10.0.0.255 scope global ens33 valid_lft forever preferred_lft forever inet6 fe80::20c:29ff:fed3:9f7e/64 scope link valid_lft forever preferred_lft forever
这个时候vip已经漂移到另一台服务器上，将另一台服务器做为主库
查看c7m01上是否有vip漂移
[root@ c7m01 ~]# ip a show ens33 2: ens33: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000 link/ether 00:0c:29:27:e6:58 brd ff:ff:ff:ff:ff:ff inet 10.0.0.13/24 brd 10.0.0.255 scope global ens33 valid_lft forever preferred_lft forever inet 10.0.0.100/24 brd 10.0.0.255 scope global secondary ens33:1 valid_lft forever preferred_lft forever inet6 fe80::20c:29ff:fe27:e658/64 scope link valid_lft forever preferred_lft forever
当vip漂移到另一台服务器上表示成功，然后查看MHA的服务器上是否改变到另一台服务器上的master_host
[root@ c703 ~]# mysql -uroot -p123456 -e 'show slave status\G'; Warning: Using a password on the command line interface can be insecure. *************************** 1. row *************************** Slave_IO_State: Waiting for master to send event Master_Host: 10.0.0.12 Master_User: rep Master_Port: 3306 Connect_Retry: 60 Master_Log_File: mysql-bin.000003 Read_Master_Log_Pos: 231 Relay_Log_File: mysqld-relay-bin.000004 Relay_Log_Pos: 401 Relay_Master_Log_File: mysql-bin.000003 Slave_IO_Running: Yes Slave_SQL_Running: Yes Replicate_Do_DB: Replicate_Ignore_DB: Replicate_Do_Table: Replicate_Ignore_Table: Replicate_Wild_Do_Table: Replicate_Wild_Ignore_Table: Last_Errno: 0 Last_Error: Skip_Counter: 0 Exec_Master_Log_Pos: 231 Relay_Log_Space: 2892 Until_Condition: None Until_Log_File: Until_Log_Pos: 0 Master_SSL_Allowed: No Master_SSL_CA_File: Master_SSL_CA_Path: Master_SSL_Cert: Master_SSL_Cipher: Master_SSL_Key: Seconds_Behind_Master: 0 Master_SSL_Verify_Server_Cert: No Last_IO_Errno: 0 Last_IO_Error: Last_SQL_Errno: 0 Last_SQL_Error: Replicate_Ignore_Server_Ids: Master_Server_Id: 2 Master_UUID: fdcedb5b-53a4-11ea-899f-000c2927e658 Master_Info_File: /var/lib/mysql/master.info SQL_Delay: 0 SQL_Remaining_Delay: NULL Slave_SQL_Running_State: Slave has read all relay log; waiting for the slave I/O thread to update it Master_Retry_Count: 86400 Master_Bind: Last_IO_Error_Timestamp: Last_SQL_Error_Timestamp: Master_SSL_Crl: Master_SSL_Crlpath: Retrieved_Gtid_Set: fdcedb5b-53a4-11ea-899f-000c2927e658:1-7 Executed_Gtid_Set: 0033cbb6-53a5-11ea-899f-000c298eeea7:1-6, f45fe1ec-53a4-11ea-899f-000c29d39f7e:3-4, fdcedb5b-53a4-11ea-899f-000c2927e658:1-7 Auto_Position: 1 [1]+ Done nohup masterha_manager --conf=/etc/mha/app1.cnf --remove_dead_master_conf --ignore_last_failover < /dev/null > /var/log/mha/app1/manager.log 2>&1
这个时候MHA上app1配置文件里server2已经被诶剔除了
[root@ c703 ~]# cat /etc/mha/app1.cnf [server default] manager_log=/var/log/mha/app1/manager.log manager_workdir=/var/log/mha/app1 master_binlog_dir=/var/lib/mysql master_ip_failover_script=/usr/bin/master_ip_failover password=mha ping_interval=2 repl_password=123456 repl_user=rep ssh_user=root user=mha [server1] hostname=10.0.0.12 port=3306 [server3] hostname=10.0.0.14 ignore_fail=1 no_master=1 port=3306
这个时候开始修复，手动操作，将他恢复到之前的状态
[root@ c703 ~]# grep "CHANGE MASTER TO MASTER" /var/log/mha/app1/manager.log | tail -1 Fri Feb 21 16:19:25 2020 - [info] All other slaves should start replication from here. Statement should be: CHANGE MASTER TO MASTER_HOST='10.0.0.13', MASTER_PORT=3306, MASTER_AUTO_POSITION=1, MASTER_USER='rep', MASTER_PASSWORD='xxx';
[root@c702 ~]#systemctl restart mysql
[root@c702 ~]# mysql -uroot -p123456 -e "CHANGE MASTER TO MASTER_HOST='10.0.0.12',MASTER_PORT=3306, MASTER_AUTO_POSITION=1,MASTER_USER='rep',MASTER_PASSWORD='123456';"
[root@c702 ~]# mysql -uroot -p123456 -e "start slave;" [root@c702 ~]# mysql -uroot -p123456 -e "show slave status \G"
#重启MHA
nohup masterha_manager --conf=/etc/mha/app1.cnf --remove_dead_master_conf --ignore_last_failover < /dev/null > /var/log/mha/app1/manager.log 2>&1 &