1、编写脚本，支持让用户自主选择，使用mysqldump还是xtraback全量备份。
安装xtrabackup:
[root@centos7 ~]# yum install percona-xtrabackup-24-2.4.9-1.el7.x86_64.rpm -y注：percona-xtrabackup-24-2.4.9-1.el7.x86_64.rpm 需在percona官网下载
自主选择备份工具备份:
[root@centos7 ~]# cat backup.sh
#!/bin/bash
#
cat <mysqldump.sql
;;
2)
innobackupex --user=root --password=centos /space/mysqlbak/ >/dev/null
;;
*)
echo "Please choose 1 or 2"
;;
esac 2、配置Mysql主从同步
1)安装主mysql
[root@master ~]# yum install mariadb* -y2)修改配置文件
[root@master ~]# cat /etc/my.cnf |grep -v "#"
[mysqld]
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
symbolic-links=0
log_bin=master-bin #启用binlog
server_id=1 #设置id号
skip_name_resolve=13) 创建有复制权限的账号
[root@master ~]# systemctl start mariadb #启动数据库
[root@master ~]# mysql
Welcome to the MariaDB monitor. Commands end with ; or \g.
Your MariaDB connection id is 2
Server version: 5.5.64-MariaDB MariaDB Server
Copyright (c) 2000, 2018, Oracle, MariaDB Corporation Ab and others.
Type 'help;' or '\h' for help. Type '\c' to clear the current input statement.
MariaDB [(none)]> GRANT REPLICATION SLAVE ON *.* TO 'repluser'@'%' IDENTIFIED BY 'replpass';
Query OK, 0 rows affected (0.00 sec)
MariaDB [(none)]> flush privileges;
Query OK, 0 rows affected (0.00 sec)4)安装从mysql
[root@slave1 ~]# yum install mariadb* -y5)修改配置文件
[root@slave1 ~]# cat /etc/my.cnf |grep -v "#"
[mysqld]
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
symbolic-links=0
server_id=2
read_only=ON #设置从库只读
relay_log=relay-log #启用中继日志
skip_name_resolve=1
relay_log_purge=0
log-bin6)查看主mysql的binlog位置
MariaDB [(none)]> show master logs;
+--------------------+-----------+
| Log_name | File_size |
+--------------------+-----------+
| mariadb-bin.000001 | 245 |
+--------------------+-----------+
1 row in set (0.00 sec)7)使用有复制权限的用户账号连接至主服务器，并启动复制线程
[root@jumpserver ~]# systemctl start mariadb #启动数据库
[root@jumpserver ~]# mysql
Welcome to the MariaDB monitor. Commands end with ; or \g.
Your MariaDB connection id is 2
Server version: 5.5.64-MariaDB MariaDB Server
Copyright (c) 2000, 2018, Oracle, MariaDB Corporation Ab and others.
Type 'help;' or '\h' for help. Type '\c' to clear the current input statement.
MariaDB [(none)]> CHANGE MASTER TO MASTER_HOST='10.1.1.109', MASTER_USER='repluser', MASTER_PASSWORD='replpass', MASTER_LOG_FILE='master-bin.000001', MASTER_LOG_POS=245;
Query OK, 0 rows affected (0.00 sec)
MariaDB [(none)]> start slave;
MariaDB [(none)]> show slave status\G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 10.1.1.109
Master_User: repluser
Master_Port: 3306
Connect_Retry: 60
Master_Log_File: master-bin.000001
Read_Master_Log_Pos: 245
Relay_Log_File: relay-log.000002
Relay_Log_Pos: 530
Relay_Master_Log_File: master-bin.000001
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: 468
Relay_Log_Space: 818
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
1 row in set (0.00 sec)8)测试主从复制
主mysql:
MariaDB [(none)]> show databases;
+--------------------+
| Database |
+--------------------+
| information_schema |
| mysql |
| performance_schema |
| test |
+--------------------+
4 rows in set (0.00 sec)
MariaDB [(none)]> source hellodb_innodb.sql;
MariaDB [hellodb]> show databases;
+--------------------+
| Database |
+--------------------+
| information_schema |
| hellodb |
| mysql |
| performance_schema |
| test |
+--------------------+
5 rows in set (0.00 sec)从mysql：
MariaDB [(none)]> show databases;
+--------------------+
| Database |
+--------------------+
| information_schema |
| hellodb |
| mysql |
| performance_schema |
| test |
+--------------------+
5 rows in set (0.00 sec)3、使用MHA实现Mysql高可用。
在2实验的基础上再安装一个从mysql：
1)安装从mysql
[root@slave2 ~]# yum install mariadb* -y2)修改配置文件
[root@slave2 ~]# cat /etc/my.cnf |grep -v "#"
[mysqld]
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
symbolic-links=0
log-bin
server_id=3
read_only=ON #设置从库只读
relay_log=relay-log #启用中继日志
skip_name_resolve=1
relay_log_purge=03)查看主mysql的binlog位置
MariaDB [(none)]> show master logs;
+--------------------+-----------+
| Log_name | File_size |
+--------------------+-----------+
| mariadb-bin.000001 | 245 |
+--------------------+-----------+
1 row in set (0.00 sec)4)使用有复制权限的用户账号连接至主服务器，并启动复制线程
[root@slave2 ~]# systemctl start mariadb #启动数据库
[root@slave2 ~]# mysql
Welcome to the MariaDB monitor. Commands end with ; or \g.
Your MariaDB connection id is 2
Server version: 5.5.64-MariaDB MariaDB Server
Copyright (c) 2000, 2018, Oracle, MariaDB Corporation Ab and others.
Type 'help;' or '\h' for help. Type '\c' to clear the current input statement.
MariaDB [(none)]> CHANGE MASTER TO MASTER_HOST='10.1.1.109', MASTER_USER='repluser', MASTER_PASSWORD='replpass', MASTER_LOG_FILE=' mariadb-bin.000001', MASTER_LOG_POS=245;
Query OK, 0 rows affected (0.00 sec)
MariaDB [(none)]> start slave;
MariaDB [(none)]> show slave status\G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 10.1.1.109
Master_User: repluser
Master_Port: 3306
Connect_Retry: 60
Master_Log_File: master-bin.000001
Read_Master_Log_Pos: 468
Relay_Log_File: relay-log.000002
Relay_Log_Pos: 530
Relay_Master_Log_File: master-bin.000001
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: 468
Relay_Log_Space: 818
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
1 row in set (0.00 sec)5)安装mha-manage
安装mha需要epel源安装依赖包，所以先安装epel源：
[root@mha ~]# wget -O /etc/yum.repos.d/epel.repo http://mirrors.aliyun.com/repo/epel-6.repo
--2020-04-15 21:20:05-- http://mirrors.aliyun.com/repo/epel-6.repo
Resolving mirrors.aliyun.com... 124.225.134.230, 14.215.23.250, 124.225.134.225, ...
Connecting to mirrors.aliyun.com|124.225.134.230|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 664 [application/octet-stream]
Saving to: “/etc/yum.repos.d/epel.repo”
100%[=========================================================================================>] 664 --.-K/s in 0s
2020-04-15 21:20:05 (84.6 MB/s) - “/etc/yum.repos.d/epel.repo” saved [664/664]
[root@mha ~]# yum repolist #验证epel源
Loaded plugins: fastestmirror, refresh-packagekit, security
Loading mirror speeds from cached hostfile
* base: mirrors.aliyun.com
* extras: mirrors.aliyun.com
* updates: mirrors.aliyun.com
epel | 4.7 kB 00:00
epel/primary_db | 6.1 MB 00:01
repo id repo name status
base CentOS-6 - Base 6,713
epel Extra Packages for Enterprise Linux 6 - x86_64 12,587
extras CentOS-6 - Extras 47
updates CentOS-6 - Updates 952
repolist: 20,299
安装mha：
先在官网下载：mha4mysql-manager-0.56-0.el6.noarch.rpm mha4mysql-node-0.56-0.el6.noarch.rpm
[root@mha ~]# ls
1.txt centos6.10_ks.cfg Downloads mha4mysql-manager-0.56-0.el6.noarch.rpm Pictures Templates
anaconda-ks.cfg Desktop install.log mha4mysql-node-0.56-0.el6.noarch.rpm Public Videos
centos_6.10ks.cfg Documents install.log.syslog Music selinux.sh
[root@mha ~]# ^C
[root@mha ~]# yum install mha*.rpm -y6)在其他节点安装mha4mysql-node
[root@master ~]# yum install mha4mysql-node-0.56-0.el6.noarch.rpm -y
[root@slave1 ~]# yum install mha4mysql-node-0.56-0.el6.noarch.rpm -y
[root@slave2 ~]# yum install mha4mysql-node-0.56-0.el6.noarch.rpm -y7)在所有节点实现相互之间ssh key验证
[root@mha ~]# ssh-keygen
Generating public/private rsa key pair.
Enter file in which to save the key (/root/.ssh/id_rsa):
Enter passphrase (empty for no passphrase):
Enter same passphrase again:
Your identification has been saved in /root/.ssh/id_rsa.
Your public key has been saved in /root/.ssh/id_rsa.pub.
The key fingerprint is:
7c:eb:33:49:5a:28:b8:f8:46:36:6d:ba:81:37:bd:c7 root@mha
The key's randomart image is:
+--[ RSA 2048]----+
| |
| |
| |
| . |
| o S.. |
| .=.+ ..o. |
| .++=.o +.. |
| ..+o .E.+ |
| oo... .o |
+-----------------+
###先设置免密ssh登录自己
[root@mha ~]# ssh-copy-id 10.1.1.110
The authenticity of host '10.1.1.110 (10.1.1.110)' can't be established.
RSA key fingerprint is 87:2f:51:55:b3:ce:9c:f7:5f:f3:86:91:a2:42:bf:04.
Are you sure you want to continue connecting (yes/no)? yes
Warning: Permanently added '10.1.1.110' (RSA) to the list of known hosts.
[email protected]'s password:
Permission denied, please try again.
[email protected]'s password:
Now try logging into the machine, with "ssh '10.1.1.110'", and check in:
.ssh/authorized_keys
to make sure we haven't added extra keys that you weren't expecting.
[root@mha ~]# ssh localhost
Last login: Wed Apr 15 21:17:09 2020 from 10.1.1.16
[root@mha ~]# exit
logout
Connection to localhost closed.
###把key传给远程主机，实现免密ssh远程主机
[root@mha ~]# scp -r .ssh/ 10.1.1.107:
The authenticity of host '10.1.1.107 (10.1.1.107)' can't be established.
RSA key fingerprint is 98:ad:3e:af:a2:47:8a:89:91:ae:36:5d:7d:84:46:5d.
Are you sure you want to continue connecting (yes/no)? yes
Warning: Permanently added '10.1.1.107' (RSA) to the list of known hosts.
[email protected]'s password:
id_rsa.pub 100% 390 0.4KB/s 00:00
id_rsa 100% 1675 1.6KB/s 00:00 known_hosts 100% 1567 1.5KB/s 00:00
[root@mha ~]# scp -r .ssh/ 10.1.1.108:
The authenticity of host '10.1.1.108 (10.1.1.108)' can't be established.
RSA key fingerprint is 20:13:b4:f6:cd:39:46:df:a7:7d:0f:61:c5:1d:17:be.
Are you sure you want to continue connecting (yes/no)? yes
Warning: Permanently added '10.1.1.108' (RSA) to the list of known hosts.
[email protected]'s password:
Permission denied, please try again.
[email protected]'s password:
id_rsa.pub 100% 390 0.4KB/s 00:00 id_rsa 100% 1675 1.6KB/s 00:00 known_hosts 100% 1959 1.9KB/s 00:00 [root@mha ~]# scp -r .ssh/ 10.1.1.109:
[email protected]'s password:
id_rsa.pub 100% 390 0.4KB/s 00:00 id_rsa 100% 1675 1.6KB/s 00:00 known_hosts 100% 1959 1.9KB/s 00:00 8)在master上创建管理账号
[root@master ~]# mysql
Welcome to the MariaDB monitor. Commands end with ; or \g.
Your MariaDB connection id is 8
Server version: 5.5.64-MariaDB MariaDB Server
Copyright (c) 2000, 2018, Oracle, MariaDB Corporation Ab and others.
Type 'help;' or '\h' for help. Type '\c' to clear the current input statement.
MariaDB [mysql]> grant all on *.* to 'mhauser'@'%' identified by 'magedu';
Query OK, 0 rows affected (0.00 sec)
MariaDB [(none)]>9)准备mha管理节点的配置文件
[root@mha ~]# cat /etc/mastermha/mha.cnf
[server default]
user=mhauser
password=magedu
manager_workdir=/data/mastermha/mha1/
manager_log=/data/mastermha/mha1/manager.log
remote_workdir=/data/mastermha/mha1/
ssh_user=root
repl_user=repluser
repl_password=replpass
ping_interval=1
[server1]
hostname=10.1.1.109
candidate_master=1
[server2]
hostname=10.1.1.107
candidate_master=1
[server3]
hostname=10.1.1.10810)Mha验证和启动
###Mha验证
[root@mha ~]# masterha_check_ssh --conf=/etc/mastermha/mha.cnf
Wed Apr 15 22:00:51 2020 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Wed Apr 15 22:00:51 2020 - [info] Reading application default configuration from /etc/mastermha/mha.cnf..
Wed Apr 15 22:00:51 2020 - [info] Reading server configuration from /etc/mastermha/mha.cnf..
Wed Apr 15 22:00:51 2020 - [info] Starting SSH connection tests..
Wed Apr 15 22:00:53 2020 - [debug]
Wed Apr 15 22:00:51 2020 - [debug] Connecting via SSH from [email protected](10.1.1.109:22) to [email protected](10.1.1.107:22)..
Wed Apr 15 22:00:52 2020 - [debug] ok.
Wed Apr 15 22:00:52 2020 - [debug] Connecting via SSH from [email protected](10.1.1.109:22) to [email protected](10.1.1.108:22)..
Wed Apr 15 22:00:52 2020 - [debug] ok.
Wed Apr 15 22:00:54 2020 - [debug]
Wed Apr 15 22:00:52 2020 - [debug] Connecting via SSH from [email protected](10.1.1.107:22) to [email protected](10.1.1.109:22)..
Wed Apr 15 22:00:53 2020 - [debug] ok.
Wed Apr 15 22:00:53 2020 - [debug] Connecting via SSH from [email protected](10.1.1.107:22) to [email protected](10.1.1.108:22)..
Wed Apr 15 22:00:53 2020 - [debug] ok.
Wed Apr 15 22:00:54 2020 - [debug]
Wed Apr 15 22:00:52 2020 - [debug] Connecting via SSH from [email protected](10.1.1.108:22) to [email protected](10.1.1.109:22)..
Wed Apr 15 22:00:53 2020 - [debug] ok.
Wed Apr 15 22:00:53 2020 - [debug] Connecting via SSH from [email protected](10.1.1.108:22) to [email protected](10.1.1.107:22)..
Wed Apr 15 22:00:53 2020 - [debug] ok.
Wed Apr 15 22:00:54 2020 - [info] All SSH connection tests passed successfully.
[root@mha ~]# masterha_check_repl --conf=/etc/mastermha/mha.cnf
Wed Apr 15 22:22:29 2020 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Wed Apr 15 22:22:29 2020 - [info] Reading application default configuration from /etc/mastermha/mha.cnf..
Wed Apr 15 22:22:29 2020 - [info] Reading server configuration from /etc/mastermha/mha.cnf..
Wed Apr 15 22:22:29 2020 - [info] MHA::MasterMonitor version 0.56.
Wed Apr 15 22:22:30 2020 - [info] GTID failover mode = 0
Wed Apr 15 22:22:30 2020 - [info] Dead Servers:
Wed Apr 15 22:22:30 2020 - [info] Alive Servers:
Wed Apr 15 22:22:30 2020 - [info] 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:22:30 2020 - [info] 10.1.1.107(10.1.1.107:3306)
Wed Apr 15 22:22:30 2020 - [info] 10.1.1.108(10.1.1.108:3306)
Wed Apr 15 22:22:30 2020 - [info] Alive Slaves:
Wed Apr 15 22:22:30 2020 - [info] 10.1.1.107(10.1.1.107:3306) Version=5.5.64-MariaDB (oldest major version between slaves) log-bin:enabled
Wed Apr 15 22:22:30 2020 - [info] Replicating from 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:22:30 2020 - [info] Primary candidate for the new Master (candidate_master is set)
Wed Apr 15 22:22:30 2020 - [info] 10.1.1.108(10.1.1.108:3306) Version=5.5.64-MariaDB (oldest major version between slaves) log-bin:enabled
Wed Apr 15 22:22:30 2020 - [info] Replicating from 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:22:30 2020 - [info] Current Alive Master: 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:22:30 2020 - [info] Checking slave configurations..
Wed Apr 15 22:22:30 2020 - [info] Checking replication filtering settings..
Wed Apr 15 22:22:30 2020 - [info] binlog_do_db= , binlog_ignore_db=
Wed Apr 15 22:22:30 2020 - [info] Replication filtering check ok.
Wed Apr 15 22:22:30 2020 - [info] GTID (with auto-pos) is not supported
Wed Apr 15 22:22:30 2020 - [info] Starting SSH connection tests..
Wed Apr 15 22:22:33 2020 - [info] All SSH connection tests passed successfully.
Wed Apr 15 22:22:33 2020 - [info] Checking MHA Node version..
Wed Apr 15 22:22:34 2020 - [info] Version check ok.
Wed Apr 15 22:22:34 2020 - [info] Checking SSH publickey authentication settings on the current master..
Wed Apr 15 22:22:35 2020 - [info] HealthCheck: SSH to 10.1.1.109 is reachable.
Wed Apr 15 22:22:35 2020 - [info] Master MHA Node version is 0.56.
Wed Apr 15 22:22:35 2020 - [info] Checking recovery script configurations on 10.1.1.109(10.1.1.109:3306)..
Wed Apr 15 22:22:35 2020 - [info] Executing command: save_binary_logs --command=test --start_pos=4 --binlog_dir=/var/lib/mysql,/var/log/mysql --output_file=/data/mastermha/mha1//save_binary_logs_test --manager_version=0.56 --start_file=master-bin.000002
Wed Apr 15 22:22:35 2020 - [info] Connecting to [email protected](10.1.1.109:22)..
Creating /data/mastermha/mha1 if not exists.. Creating directory /data/mastermha/mha1.. done.
ok.
Checking output directory is accessible or not..
ok.
Binlog found at /var/lib/mysql, up to master-bin.000002
Wed Apr 15 22:22:36 2020 - [info] Binlog setting check done.
Wed Apr 15 22:22:36 2020 - [info] Checking SSH publickey authentication and checking recovery script configurations on all alive slave servers..
Wed Apr 15 22:22:36 2020 - [info] Executing command : apply_diff_relay_logs --command=test --slave_user='mhauser' --slave_host=10.1.1.107 --slave_ip=10.1.1.107 --slave_port=3306 --workdir=/data/mastermha/mha1/ --target_version=5.5.64-MariaDB --manager_version=0.56 --relay_log_info=/var/lib/mysql/relay-log.info --relay_dir=/var/lib/mysql/ --slave_pass=xxx
Wed Apr 15 22:22:36 2020 - [info] Connecting to [email protected](10.1.1.107:22)..
Creating directory /data/mastermha/mha1/.. done.
Checking slave recovery environment settings..
Opening /var/lib/mysql/relay-log.info ... ok.
Relay log found at /var/lib/mysql, up to relay-log.000006
Temporary relay log file is /var/lib/mysql/relay-log.000006
Testing mysql connection and privileges.. done.
Testing mysqlbinlog output.. done.
Cleaning up test file(s).. done.
Wed Apr 15 22:22:36 2020 - [info] Executing command : apply_diff_relay_logs --command=test --slave_user='mhauser' --slave_host=10.1.1.108 --slave_ip=10.1.1.108 --slave_port=3306 --workdir=/data/mastermha/mha1/ --target_version=5.5.64-MariaDB --manager_version=0.56 --relay_log_info=/var/lib/mysql/relay-log.info --relay_dir=/var/lib/mysql/ --slave_pass=xxx
Wed Apr 15 22:22:36 2020 - [info] Connecting to [email protected](10.1.1.108:22)..
Creating directory /data/mastermha/mha1/.. done.
Checking slave recovery environment settings..
Opening /var/lib/mysql/relay-log.info ... ok.
Relay log found at /var/lib/mysql, up to relay-log.000005
Temporary relay log file is /var/lib/mysql/relay-log.000005
Testing mysql connection and privileges.. done.
Testing mysqlbinlog output.. done.
Cleaning up test file(s).. done.
Wed Apr 15 22:22:36 2020 - [info] Slaves settings check done.
Wed Apr 15 22:22:36 2020 - [info]
10.1.1.109(10.1.1.109:3306) (current master)
+--10.1.1.107(10.1.1.107:3306)
+--10.1.1.108(10.1.1.108:3306)
Wed Apr 15 22:22:36 2020 - [info] Checking replication health on 10.1.1.107..
Wed Apr 15 22:22:36 2020 - [info] ok.
Wed Apr 15 22:22:36 2020 - [info] Checking replication health on 10.1.1.108..
Wed Apr 15 22:22:36 2020 - [info] ok.
Wed Apr 15 22:22:36 2020 - [warning] master_ip_failover_script is not defined.
Wed Apr 15 22:22:36 2020 - [warning] shutdown_script is not defined.
Wed Apr 15 22:22:36 2020 - [info] Got exit code 0 (Not master dead).
MySQL Replication Health is OK.
###mha启动
[root@mha ~]nohup masterha_manager --conf=/etc/mastermha/mha.cnf &
[1] 2233
[root@mha ~]# nohup: ignoring input and appending output to `nohup.out'
[root@mha ~]#
[root@mha ~]#
[root@mha ~]#
[root@mha ~]# ps aux |grep masterha_manager
root 2233 1.6 1.9 194908 19380 pts/0 S 22:35 0:00 perl /usr/bin/masterha_manager --conf=/etc/mastermha/mha.cnf
root 2287 0.0 0.0 103324 852 pts/0 S+ 22:35 0:00 grep masterha_manager
[root@mha ~]# 11)验证
停止master的mysql服务，然后看mha日志：
###mha日志包含了整个主mysql切换到新的主mysql
[root@mha ~]# tailf /data/mastermha/mha1/manager.log
10.1.1.109(10.1.1.109:3306) (current master)
+--10.1.1.107(10.1.1.107:3306)
+--10.1.1.108(10.1.1.108:3306)
Wed Apr 15 22:35:28 2020 - [warning] master_ip_failover_script is not defined.
Wed Apr 15 22:35:28 2020 - [warning] shutdown_script is not defined.
Wed Apr 15 22:35:28 2020 - [info] Set master ping interval 1 seconds.
Wed Apr 15 22:35:28 2020 - [warning] secondary_check_script is not defined. It is highly recommended setting it to check master reachability from two or more routes.
Wed Apr 15 22:35:28 2020 - [info] Starting ping health check on 10.1.1.109(10.1.1.109:3306)..
Wed Apr 15 22:35:28 2020 - [info] Ping(SELECT) succeeded, waiting until MySQL doesn't respond..
Wed Apr 15 22:37:09 2020 - [warning] Got error on MySQL select ping: 2006 (MySQL server has gone away)
Wed Apr 15 22:37:09 2020 - [info] Executing SSH check script: save_binary_logs --command=test --start_pos=4 --binlog_dir=/var/lib/mysql,/var/log/mysql --output_file=/data/mastermha/mha1//save_binary_logs_test --manager_version=0.56 --binlog_prefix=master-bin
Wed Apr 15 22:37:09 2020 - [info] HealthCheck: SSH to 10.1.1.109 is reachable.
Wed Apr 15 22:37:10 2020 - [warning] Got error on MySQL connect: 2013 (Lost connection to MySQL server at 'reading initial communication packet', system error: 111)
Wed Apr 15 22:37:10 2020 - [warning] Connection failed 2 time(s)..
Wed Apr 15 22:37:11 2020 - [warning] Got error on MySQL connect: 2013 (Lost connection to MySQL server at 'reading initial communication packet', system error: 111)
Wed Apr 15 22:37:11 2020 - [warning] Connection failed 3 time(s)..
Wed Apr 15 22:37:12 2020 - [warning] Got error on MySQL connect: 2013 (Lost connection to MySQL server at 'reading initial communication packet', system error: 111)
Wed Apr 15 22:37:12 2020 - [warning] Connection failed 4 time(s)..
Wed Apr 15 22:37:12 2020 - [warning] Master is not reachable from health checker!
Wed Apr 15 22:37:12 2020 - [warning] Master 10.1.1.109(10.1.1.109:3306) is not reachable!
Wed Apr 15 22:37:12 2020 - [warning] SSH is reachable.
Wed Apr 15 22:37:12 2020 - [info] Connecting to a master server failed. Reading configuration file /etc/masterha_default.cnf and /etc/mastermha/mha.cnf again, and trying to connect to all servers to check server status..
Wed Apr 15 22:37:12 2020 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Wed Apr 15 22:37:12 2020 - [info] Reading application default configuration from /etc/mastermha/mha.cnf..
Wed Apr 15 22:37:12 2020 - [info] Reading server configuration from /etc/mastermha/mha.cnf..
Wed Apr 15 22:37:13 2020 - [info] GTID failover mode = 0
Wed Apr 15 22:37:13 2020 - [info] Dead Servers:
Wed Apr 15 22:37:13 2020 - [info] 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:37:13 2020 - [info] Alive Servers:
Wed Apr 15 22:37:13 2020 - [info] 10.1.1.107(10.1.1.107:3306)
Wed Apr 15 22:37:13 2020 - [info] 10.1.1.108(10.1.1.108:3306)
Wed Apr 15 22:37:13 2020 - [info] Alive Slaves:
Wed Apr 15 22:37:13 2020 - [info] 10.1.1.107(10.1.1.107:3306) Version=5.5.64-MariaDB (oldest major version between slaves) log-bin:enabled
Wed Apr 15 22:37:13 2020 - [info] Replicating from 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:37:13 2020 - [info] Primary candidate for the new Master (candidate_master is set)
Wed Apr 15 22:37:13 2020 - [info] 10.1.1.108(10.1.1.108:3306) Version=5.5.64-MariaDB (oldest major version between slaves) log-bin:enabled
Wed Apr 15 22:37:13 2020 - [info] Replicating from 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:37:13 2020 - [info] Checking slave configurations..
Wed Apr 15 22:37:13 2020 - [info] Checking replication filtering settings..
Wed Apr 15 22:37:13 2020 - [info] Replication filtering check ok.
Wed Apr 15 22:37:13 2020 - [info] Master is down!
Wed Apr 15 22:37:13 2020 - [info] Terminating monitoring script.
Wed Apr 15 22:37:13 2020 - [info] Got exit code 20 (Master dead).
Wed Apr 15 22:37:13 2020 - [info] MHA::MasterFailover version 0.56.
Wed Apr 15 22:37:13 2020 - [info] Starting master failover.
Wed Apr 15 22:37:13 2020 - [info]
Wed Apr 15 22:37:13 2020 - [info] * Phase 1: Configuration Check Phase..
Wed Apr 15 22:37:13 2020 - [info]
Wed Apr 15 22:37:14 2020 - [info] GTID failover mode = 0
Wed Apr 15 22:37:14 2020 - [info] Dead Servers:
Wed Apr 15 22:37:14 2020 - [info] 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:37:14 2020 - [info] Checking master reachability via MySQL(double check)...
Wed Apr 15 22:37:14 2020 - [info] ok.
Wed Apr 15 22:37:14 2020 - [info] Alive Servers:
Wed Apr 15 22:37:14 2020 - [info] 10.1.1.107(10.1.1.107:3306)
Wed Apr 15 22:37:14 2020 - [info] 10.1.1.108(10.1.1.108:3306)
Wed Apr 15 22:37:14 2020 - [info] Alive Slaves:
Wed Apr 15 22:37:14 2020 - [info] 10.1.1.107(10.1.1.107:3306) Version=5.5.64-MariaDB (oldest major version between slaves) log-bin:enabled
Wed Apr 15 22:37:14 2020 - [info] Replicating from 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:37:14 2020 - [info] Primary candidate for the new Master (candidate_master is set)
Wed Apr 15 22:37:14 2020 - [info] 10.1.1.108(10.1.1.108:3306) Version=5.5.64-MariaDB (oldest major version between slaves) log-bin:enabled
Wed Apr 15 22:37:14 2020 - [info] Replicating from 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:37:14 2020 - [info] Starting Non-GTID based failover.
Wed Apr 15 22:37:14 2020 - [info]
Wed Apr 15 22:37:14 2020 - [info] ** Phase 1: Configuration Check Phase completed.
Wed Apr 15 22:37:14 2020 - [info]
Wed Apr 15 22:37:14 2020 - [info] * Phase 2: Dead Master Shutdown Phase..
Wed Apr 15 22:37:14 2020 - [info]
Wed Apr 15 22:37:14 2020 - [info] Forcing shutdown so that applications never connect to the current master..
Wed Apr 15 22:37:14 2020 - [warning] master_ip_failover_script is not set. Skipping invalidating dead master IP address.
Wed Apr 15 22:37:14 2020 - [warning] shutdown_script is not set. Skipping explicit shutting down of the dead master.
Wed Apr 15 22:37:15 2020 - [info] * Phase 2: Dead Master Shutdown Phase completed.
Wed Apr 15 22:37:15 2020 - [info]
Wed Apr 15 22:37:15 2020 - [info] * Phase 3: Master Recovery Phase..
Wed Apr 15 22:37:15 2020 - [info]
Wed Apr 15 22:37:15 2020 - [info] * Phase 3.1: Getting Latest Slaves Phase..
Wed Apr 15 22:37:15 2020 - [info]
Wed Apr 15 22:37:15 2020 - [info] The latest binary log file/position on all slaves is master-bin.000002:2345
Wed Apr 15 22:37:15 2020 - [info] Latest slaves (Slaves that received relay log files to the latest):
Wed Apr 15 22:37:15 2020 - [info] 10.1.1.107(10.1.1.107:3306) Version=5.5.64-MariaDB (oldest major version between slaves) log-bin:enabled
Wed Apr 15 22:37:15 2020 - [info] Replicating from 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:37:15 2020 - [info] Primary candidate for the new Master (candidate_master is set)
Wed Apr 15 22:37:15 2020 - [info] 10.1.1.108(10.1.1.108:3306) Version=5.5.64-MariaDB (oldest major version between slaves) log-bin:enabled
Wed Apr 15 22:37:15 2020 - [info] Replicating from 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:37:15 2020 - [info] The oldest binary log file/position on all slaves is master-bin.000002:2345
Wed Apr 15 22:37:15 2020 - [info] Oldest slaves:
Wed Apr 15 22:37:15 2020 - [info] 10.1.1.107(10.1.1.107:3306) Version=5.5.64-MariaDB (oldest major version between slaves) log-bin:enabled
Wed Apr 15 22:37:15 2020 - [info] Replicating from 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:37:15 2020 - [info] Primary candidate for the new Master (candidate_master is set)
Wed Apr 15 22:37:15 2020 - [info] 10.1.1.108(10.1.1.108:3306) Version=5.5.64-MariaDB (oldest major version between slaves) log-bin:enabled
Wed Apr 15 22:37:15 2020 - [info] Replicating from 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:37:15 2020 - [info]
Wed Apr 15 22:37:15 2020 - [info] * Phase 3.2: Saving Dead Master's Binlog Phase..
Wed Apr 15 22:37:15 2020 - [info]
Wed Apr 15 22:37:15 2020 - [info] Fetching dead master's binary logs..
Wed Apr 15 22:37:15 2020 - [info] Executing command on the dead master 10.1.1.109(10.1.1.109:3306): save_binary_logs --command=save --start_file=master-bin.000002 --start_pos=2345 --binlog_dir=/var/lib/mysql,/var/log/mysql --output_file=/data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog --handle_raw_binlog=1 --disable_log_bin=0 --manager_version=0.56
Creating /data/mastermha/mha1 if not exists.. ok.
Concat binary/relay logs from master-bin.000002 pos 2345 to master-bin.000002 EOF into /data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog ..
Dumping binlog format description event, from position 0 to 245.. ok.
Dumping effective binlog data from /var/lib/mysql/master-bin.000002 position 2345 to tail(2364).. ok.
Concat succeeded.
Wed Apr 15 22:37:16 2020 - [info] scp from [email protected]:/data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog to local:/data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog succeeded.
Wed Apr 15 22:37:16 2020 - [info] HealthCheck: SSH to 10.1.1.107 is reachable.
Wed Apr 15 22:37:16 2020 - [info] HealthCheck: SSH to 10.1.1.108 is reachable.
Wed Apr 15 22:37:17 2020 - [info]
Wed Apr 15 22:37:17 2020 - [info] * Phase 3.3: Determining New Master Phase..
Wed Apr 15 22:37:17 2020 - [info]
Wed Apr 15 22:37:17 2020 - [info] Finding the latest slave that has all relay logs for recovering other slaves..
Wed Apr 15 22:37:17 2020 - [info] All slaves received relay logs to the same position. No need to resync each other.
Wed Apr 15 22:37:17 2020 - [info] Searching new master from slaves..
Wed Apr 15 22:37:17 2020 - [info] Candidate masters from the configuration file:
Wed Apr 15 22:37:17 2020 - [info] 10.1.1.107(10.1.1.107:3306) Version=5.5.64-MariaDB (oldest major version between slaves) log-bin:enabled
Wed Apr 15 22:37:17 2020 - [info] Replicating from 10.1.1.109(10.1.1.109:3306)
Wed Apr 15 22:37:17 2020 - [info] Primary candidate for the new Master (candidate_master is set)
Wed Apr 15 22:37:17 2020 - [info] Non-candidate masters:
Wed Apr 15 22:37:17 2020 - [info] Searching from candidate_master slaves which have received the latest relay log events..
Wed Apr 15 22:37:17 2020 - [info] New master is 10.1.1.107(10.1.1.107:3306)
Wed Apr 15 22:37:17 2020 - [info] Starting master failover..
Wed Apr 15 22:37:17 2020 - [info]
From:
10.1.1.109(10.1.1.109:3306) (current master)
+--10.1.1.107(10.1.1.107:3306)
+--10.1.1.108(10.1.1.108:3306)
To:
10.1.1.107(10.1.1.107:3306) (new master)
+--10.1.1.108(10.1.1.108:3306)
Wed Apr 15 22:37:17 2020 - [info]
Wed Apr 15 22:37:17 2020 - [info] * Phase 3.3: New Master Diff Log Generation Phase..
Wed Apr 15 22:37:17 2020 - [info]
Wed Apr 15 22:37:17 2020 - [info] This server has all relay logs. No need to generate diff files from the latest slave.
Wed Apr 15 22:37:17 2020 - [info] Sending binlog..
Wed Apr 15 22:37:17 2020 - [info] scp from local:/data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog to [email protected]:/data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog succeeded.
Wed Apr 15 22:37:17 2020 - [info]
Wed Apr 15 22:37:17 2020 - [info] * Phase 3.4: Master Log Apply Phase..
Wed Apr 15 22:37:17 2020 - [info]
Wed Apr 15 22:37:17 2020 - [info] *NOTICE: If any error happens from this phase, manual recovery is needed.
Wed Apr 15 22:37:17 2020 - [info] Starting recovery on 10.1.1.107(10.1.1.107:3306)..
Wed Apr 15 22:37:17 2020 - [info] Generating diffs succeeded.
Wed Apr 15 22:37:17 2020 - [info] Waiting until all relay logs are applied.
Wed Apr 15 22:37:17 2020 - [info] done.
Wed Apr 15 22:37:17 2020 - [info] Getting slave status..
Wed Apr 15 22:37:17 2020 - [info] This slave(10.1.1.107)'s Exec_Master_Log_Pos equals to Read_Master_Log_Pos(master-bin.000002:2345). No need to recover from Exec_Master_Log_Pos.
Wed Apr 15 22:37:17 2020 - [info] Connecting to the target slave host 10.1.1.107, running recover script..
Wed Apr 15 22:37:17 2020 - [info] Executing command: apply_diff_relay_logs --command=apply --slave_user='mhauser' --slave_host=10.1.1.107 --slave_ip=10.1.1.107 --slave_port=3306 --apply_files=/data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog --workdir=/data/mastermha/mha1/ --target_version=5.5.64-MariaDB --timestamp=20200415223713 --handle_raw_binlog=1 --disable_log_bin=0 --manager_version=0.56 --slave_pass=xxx
Wed Apr 15 22:37:17 2020 - [info]
Applying differential binary/relay log files /data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog on 10.1.1.107:3306. This may take long time...
Applying log files succeeded.
Wed Apr 15 22:37:17 2020 - [info] All relay logs were successfully applied.
Wed Apr 15 22:37:17 2020 - [info] Getting new master's binlog name and position..
Wed Apr 15 22:37:17 2020 - [info] mariadb-bin.000001:245
Wed Apr 15 22:37:17 2020 - [info] All other slaves should start replication from here. Statement should be: CHANGE MASTER TO MASTER_HOST='10.1.1.107', MASTER_PORT=3306, MASTER_LOG_FILE='mariadb-bin.000001', MASTER_LOG_POS=245, MASTER_USER='repluser', MASTER_PASSWORD='xxx';
Wed Apr 15 22:37:17 2020 - [warning] master_ip_failover_script is not set. Skipping taking over new master IP address.
Wed Apr 15 22:37:17 2020 - [info] Setting read_only=0 on 10.1.1.107(10.1.1.107:3306)..
Wed Apr 15 22:37:17 2020 - [info] ok.
Wed Apr 15 22:37:17 2020 - [info] ** Finished master recovery successfully.
Wed Apr 15 22:37:17 2020 - [info] * Phase 3: Master Recovery Phase completed.
Wed Apr 15 22:37:17 2020 - [info]
Wed Apr 15 22:37:17 2020 - [info] * Phase 4: Slaves Recovery Phase..
Wed Apr 15 22:37:17 2020 - [info]
Wed Apr 15 22:37:17 2020 - [info] * Phase 4.1: Starting Parallel Slave Diff Log Generation Phase..
Wed Apr 15 22:37:17 2020 - [info]
Wed Apr 15 22:37:17 2020 - [info] -- Slave diff file generation on host 10.1.1.108(10.1.1.108:3306) started, pid: 2420. Check tmp log /data/mastermha/mha1//10.1.1.108_3306_20200415223713.log if it takes time..
Wed Apr 15 22:37:18 2020 - [info]
Wed Apr 15 22:37:18 2020 - [info] Log messages from 10.1.1.108 ...
Wed Apr 15 22:37:18 2020 - [info]
Wed Apr 15 22:37:17 2020 - [info] This server has all relay logs. No need to generate diff files from the latest slave.
Wed Apr 15 22:37:18 2020 - [info] End of log messages from 10.1.1.108.
Wed Apr 15 22:37:18 2020 - [info] -- 10.1.1.108(10.1.1.108:3306) has the latest relay log events.
Wed Apr 15 22:37:18 2020 - [info] Generating relay diff files from the latest slave succeeded.
Wed Apr 15 22:37:18 2020 - [info]
Wed Apr 15 22:37:18 2020 - [info] * Phase 4.2: Starting Parallel Slave Log Apply Phase..
Wed Apr 15 22:37:18 2020 - [info]
Wed Apr 15 22:37:18 2020 - [info] -- Slave recovery on host 10.1.1.108(10.1.1.108:3306) started, pid: 2422. Check tmp log /data/mastermha/mha1//10.1.1.108_3306_20200415223713.log if it takes time..
Wed Apr 15 22:37:19 2020 - [info]
Wed Apr 15 22:37:19 2020 - [info] Log messages from 10.1.1.108 ...
Wed Apr 15 22:37:19 2020 - [info]
Wed Apr 15 22:37:18 2020 - [info] Sending binlog..
Wed Apr 15 22:37:19 2020 - [info] scp from local:/data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog to [email protected]:/data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog succeeded.
Wed Apr 15 22:37:19 2020 - [info] Starting recovery on 10.1.1.108(10.1.1.108:3306)..
Wed Apr 15 22:37:19 2020 - [info] Generating diffs succeeded.
Wed Apr 15 22:37:19 2020 - [info] Waiting until all relay logs are applied.
Wed Apr 15 22:37:19 2020 - [info] done.
Wed Apr 15 22:37:19 2020 - [info] Getting slave status..
Wed Apr 15 22:37:19 2020 - [info] This slave(10.1.1.108)'s Exec_Master_Log_Pos equals to Read_Master_Log_Pos(master-bin.000002:2345). No need to recover from Exec_Master_Log_Pos.
Wed Apr 15 22:37:19 2020 - [info] Connecting to the target slave host 10.1.1.108, running recover script..
Wed Apr 15 22:37:19 2020 - [info] Executing command: apply_diff_relay_logs --command=apply --slave_user='mhauser' --slave_host=10.1.1.108 --slave_ip=10.1.1.108 --slave_port=3306 --apply_files=/data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog --workdir=/data/mastermha/mha1/ --target_version=5.5.64-MariaDB --timestamp=20200415223713 --handle_raw_binlog=1 --disable_log_bin=0 --manager_version=0.56 --slave_pass=xxx
Wed Apr 15 22:37:19 2020 - [info]
Applying differential binary/relay log files /data/mastermha/mha1//saved_master_binlog_from_10.1.1.109_3306_20200415223713.binlog on 10.1.1.108:3306. This may take long time...
Applying log files succeeded.
Wed Apr 15 22:37:19 2020 - [info] All relay logs were successfully applied.
Wed Apr 15 22:37:19 2020 - [info] Resetting slave 10.1.1.108(10.1.1.108:3306) and starting replication from the new master 10.1.1.107(10.1.1.107:3306)..
Wed Apr 15 22:37:19 2020 - [info] Executed CHANGE MASTER.
Wed Apr 15 22:37:19 2020 - [info] Slave started.
Wed Apr 15 22:37:19 2020 - [info] End of log messages from 10.1.1.108.
Wed Apr 15 22:37:19 2020 - [info] -- Slave recovery on host 10.1.1.108(10.1.1.108:3306) succeeded.
Wed Apr 15 22:37:19 2020 - [info] All new slave servers recovered successfully.
Wed Apr 15 22:37:19 2020 - [info]
Wed Apr 15 22:37:19 2020 - [info] * Phase 5: New master cleanup phase..
Wed Apr 15 22:37:19 2020 - [info]
Wed Apr 15 22:37:19 2020 - [info] Resetting slave info on the new master..
Wed Apr 15 22:37:19 2020 - [info] 10.1.1.107: Resetting slave info succeeded.
Wed Apr 15 22:37:19 2020 - [info] Master failover to 10.1.1.107(10.1.1.107:3306) completed successfully.
Wed Apr 15 22:37:19 2020 - [info]
----- Failover Report -----
mha: MySQL Master failover 10.1.1.109(10.1.1.109:3306) to 10.1.1.107(10.1.1.107:3306) succeeded
Master 10.1.1.109(10.1.1.109:3306) is down!
Check MHA Manager logs at mha:/data/mastermha/mha1/manager.log for details.
Started automated(non-interactive) failover.
The latest slave 10.1.1.107(10.1.1.107:3306) has all relay logs for recovery.
Selected 10.1.1.107(10.1.1.107:3306) as a new master.
10.1.1.107(10.1.1.107:3306): OK: Applying all logs succeeded.
10.1.1.108(10.1.1.108:3306): This host has the latest relay log events.
Generating relay diff files from the latest slave succeeded.
10.1.1.108(10.1.1.108:3306): OK: Applying all logs succeeded. Slave started, replicating from 10.1.1.107(10.1.1.107:3306)
10.1.1.107(10.1.1.107:3306): Resetting slave info succeeded.
Master failover to 10.1.1.107(10.1.1.107:3306) completed successfully.
###masterha_manager已经自动退出
[root@mha ~]# ps aux |grep masterha_manager |grep -v grep
[root@mha ~]#