1、如果主节点已经运行了一段时间，且有大量数据时，如何配置并启动slave节点（写出操作步骤）
-
1、通过备份恢复数据至从服务器
1、在主服务器完全备份 mysqldump -A -F --single-transaction --master-data=1 > /backup/fullbackup.sql 2、将备份的数据拷贝到新的从节点服务器相关目录下 -
2、复制起始位置为备份时，二进制日志文件及其POS
1、从节点服务器进行相关配置 注意：先查看完全备份的二进制文件的节点位置，从完全备份的位置之后开始复制 2、在从节点进行完全备份恢复 3、从节点启动slave服务
2、当master服务器宕机，提升一个slave成为新的master（写出操作步骤）
-
1、找到哪个从节点的数据库是最新，让它成为新master
-
2、新master修改配置文件，关闭read-only配置
vim /etc/my.cnf.d/mariadb-server.cnf read-only=OFF -
3、清除旧的master复制信息
# 登录MySQL set global read_only=off; stop slave; reset slave all; -
4、在新master上完全备份
-
mysqldump -A --single-transaction --master-data=1 -F > backup.sql -
分析旧的master 的二进制日志，将未同步到至新master的二进制日志导出来，恢复到新master,尽可能 恢复数据
-
-
5、其它所有 slave 重新还原数据库，指向新的master
-
注意：同步恢复数据时，暂时停用二进制文件
set sql_log_bin=off;
-
3、通过 MHA 0.58 搭建一个数据库集群结构
MySQL8.0-基于MHA的MySQL高可用架构搭建
（1）从宕机崩溃的master保存二进制日志事件（binlog events）;
（2）识别含有最新更新的slave；
（3）应用差异的中继日志（relay log）到其他的slave；
（4）应用从master保存的二进制日志事件（binlog events）；
（5）提升一个slave为新的master；
（6）使其他的slave连接新的master进行复制；
相关命令
# 检查ssh连接
[root@centos771 ~]# masterha_check_ssh --conf=/etc/masterha/app1.cnf
# 检查MySQL复制状况
[root@centos771 ~]# masterha_check_repl --conf=/etc/masterha/app1.cnf
# 启动MHA
[root@centos771 ~]# masterha_manager --conf=/etc/masterha/app1.cnf
# 检测当前MHA运行状态
[root@centos771 ~]# masterha_check_status --conf=/etc/masterha/app1.cnf
# 启动MHA
[root@centos771 ~]# masterha_manager --conf=/etc/masterha/app1.cnf
# 检测master是否gangji
[root@centos771 ~]# masterha_master_monitor --conf=/etc/masterha/app1.cnf
# 手动切换master
[root@centos771 ~]# masterha_master_switch --conf=/etc/masterha/app1.cnf --master_state=alive --new_master_host=10.0.0.80 --new_master_port=3306 --orig_master_is_new_slave --running_updates_limit=10000
注意：MHA目前不支持mariadb数据库
实验环境：虚拟机四台
SQL文件：hellodb.sql
-
master：centos80
-
ip：10.0.0.80
-
MySQL8.0
-
-
slave1（备用master）：centos81
-
ip：10.0.0.81
-
MySQL8.0
-
-
slave2：centos82
-
ip：10.0.0.82
-
MySQL8.0
-
-
slave3（MHA）：centos77
- ip：10.0.0.77
- MySQL8.0
前期准备
# 关闭防火墙，关闭selinux
[root@80 ~]# systemctl disable --now firewalld
[root@80 ~]# sed -ri '/^SELINUX=/s/(^SELINUX=)(.*)/\1disabled/' /etc/selinux/config
# 安装MySQL8.0
[root@80 ~]# yum -y install mysql-server
[root@80 ~]# systemctl enable mysqld
[root@80 ~]# systemctl start mysqld
1 首先配置好，基于GTID的主从半同步复制（一主两从）
master
[root@hah ~]# vim /etc/my.cnf.d/mysql-server.cnf
[mysqld]
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
log-error=/var/log/mysql/mysqld.log
pid-file=/run/mysqld/mysqld.pid
server_id=80
gtid_mode=ON
enforce_gtid_consistency=ON
log_bin
log_slave_updates=ON
[root@hah ~]# systemctl restart mysqld
slave1
[root@81 ~]# vim /etc/my.cnf.d/mysql-server.cnf
[mysqld]
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
log-error=/var/log/mysql/mysqld.log
pid-file=/run/mysqld/mysqld.pid
server_id=81
gtid_mode=ON
enforce_gtid_consistency=ON
log_bin
log_slave_updates=ON
[root@81 ~]# systemctl restart mysqld
slave2
[root@82 ~]# vim /etc/my.cnf.d/mysql-server.cnf
[mysqld]
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
log-error=/var/log/mysql/mysqld.log
pid-file=/run/mysqld/mysqld.pid
server_id=82
gtid_mode=ON
enforce_gtid_consistency=ON
log_bin
log_slave_updates=ON
[root@82 ~]# systemctl restart mysqld
master
# 创建复制用户并授权
mysql> create user centos@'10.0.0.%' identified by '123456';
Query OK, 0 rows affected (0.17 sec)
mysql> grant replication slave on *.* to 'centos'@'10.0.0.%';
Query OK, 0 rows affected (0.06 sec)
# 安装插件
mysql> install plugin rpl_semi_sync_master soname 'semisync_master.so';
Query OK, 0 rows affected (0.04 sec)
mysql> install plugin rpl_semi_sync_slave soname 'semisync_slave.so';
Query OK, 0 rows affected (0.06 sec)
mysql> set global rpl_semi_sync_master_enabled=1;
Query OK, 0 rows affected (0.00 sec)
mysql> set global rpl_semi_sync_master_timeout=3000;
Query OK, 0 rows affected (0.00 sec)
mysql> show variables like '%rpl%';
+-------------------------------------------+------------+
| Variable_name | Value |
+-------------------------------------------+------------+
| rpl_read_size | 8192 |
| rpl_semi_sync_master_enabled | ON |
| rpl_semi_sync_master_timeout | 3000 |
| rpl_semi_sync_master_trace_level | 32 |
| rpl_semi_sync_master_wait_for_slave_count | 1 |
| rpl_semi_sync_master_wait_no_slave | ON |
| rpl_semi_sync_master_wait_point | AFTER_SYNC |
| rpl_semi_sync_slave_enabled | OFF |
| rpl_semi_sync_slave_trace_level | 32 |
| rpl_stop_slave_timeout | 31536000 |
+-------------------------------------------+------------+
10 rows in set (0.01 sec)
slave1
# 复制线程
mysql> change master to master_host='10.0.0.80',master_user='centos',master_password='123456',master_auto_position=1;
Query OK, 0 rows affected, 2 warnings (0.04 sec)
# 安装插件
mysql> install plugin rpl_semi_sync_master soname 'semisync_master.so';
Query OK, 0 rows affected (0.08 sec)
mysql> install plugin rpl_semi_sync_slave soname 'semisync_slave.so';
Query OK, 0 rows affected (0.10 sec)
mysql> set global rpl_semi_sync_slave_enabled=1;
Query OK, 0 rows affected (0.00 sec)
# 启动从线程
mysql> start slave;
Query OK, 0 rows affected (0.10 sec)
mysql> show slave status\G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 10.0.0.80
Master_User: centos
Master_Port: 3306
Connect_Retry: 60
Master_Log_File: hah-bin.000003
Read_Master_Log_Pos: 672
Relay_Log_File: 81-relay-bin.000002
Relay_Log_Pos: 882
Relay_Master_Log_File: hah-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: 672
Relay_Log_Space: 1087
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: 80
Master_UUID: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6
Master_Info_File: mysql.slave_master_info
SQL_Delay: 0
SQL_Remaining_Delay: NULL
Slave_SQL_Running_State: Slave has read all relay log; waiting for more updates
Master_Retry_Count: 86400
Master_Bind:
Last_IO_Error_Timestamp:
Last_SQL_Error_Timestamp:
Master_SSL_Crl:
Master_SSL_Crlpath:
Retrieved_Gtid_Set: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-2
Executed_Gtid_Set: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-2
Auto_Position: 1
Replicate_Rewrite_DB:
Channel_Name:
Master_TLS_Version:
Master_public_key_path:
Get_master_public_key: 0
1 row in set (0.00 sec)
slave2
mysql> change master to master_host='10.0.0.80',master_user='centos',master_password='123456',master_auto_position=1;
Query OK, 0 rows affected, 2 warnings (0.05 sec)
mysql> install plugin rpl_semi_sync_master soname 'semisync_master.so';
Query OK, 0 rows affected (0.01 sec)
mysql> install plugin rpl_semi_sync_slave soname 'semisync_slave.so';
Query OK, 0 rows affected (0.10 sec)
mysql> set global rpl_semi_sync_slave_enabled=1;
Query OK, 0 rows affected (0.00 sec)
mysql> start slave;
Query OK, 0 rows affected (0.05 sec)
mysql> show slave status\G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 10.0.0.80
Master_User: centos
Master_Port: 3306
Connect_Retry: 60
Master_Log_File: hah-bin.000003
Read_Master_Log_Pos: 672
Relay_Log_File: 82-relay-bin.000002
Relay_Log_Pos: 882
Relay_Master_Log_File: hah-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: 672
Relay_Log_Space: 1087
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: 80
Master_UUID: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6
Master_Info_File: mysql.slave_master_info
SQL_Delay: 0
SQL_Remaining_Delay: NULL
Slave_SQL_Running_State: Slave has read all relay log; waiting for more updates
Master_Retry_Count: 86400
Master_Bind:
Last_IO_Error_Timestamp:
Last_SQL_Error_Timestamp:
Master_SSL_Crl:
Master_SSL_Crlpath:
Retrieved_Gtid_Set: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-2
Executed_Gtid_Set: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-2
Auto_Position: 1
Replicate_Rewrite_DB:
Channel_Name:
Master_TLS_Version:
Master_public_key_path:
Get_master_public_key: 0
1 row in set (0.00 sec)
测试主从复制
# master
mysql> create database student;
Query OK, 1 row affected (0.02 sec)
# slave1
mysql> show databases;
+--------------------+
| Database |
+--------------------+
| information_schema |
| mysql |
| performance_schema |
| student |
| sys |
+--------------------+
5 rows in set (0.01 sec)
# slave2
mysql> show databases;
+--------------------+
| Database |
+--------------------+
| information_schema |
| mysql |
| performance_schema |
| student |
| sys |
+--------------------+
5 rows in set (0.00 sec)
2 配置ssh免密登录
1、生成ssh登录密钥
# MAH
[root@centos771 ~]# 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:
SHA256:aEKIhERoMc+c7LhcmHHfz04TtkXZ5mvexBq7y/g2QPE root@83
The key's randomart image is:
+---[RSA 2048]----+
|=*. |
|+o*.. .o |
|o..B. ooo |
| B.. .. ..oE |
| + o..o.So.. . |
|. o o + +. o |
| o * .+ o |
| o . =o* |
| . .oO+. |
+----[SHA256]-----+
[root@centos771 ~]# ssh-copy-id 10.0.0.71
# 生成公钥和私钥发送到server1，2，3上，使之互相之间可以进行免密登录
[root@centos771 ~]# scp -r .ssh 10.0.0.80:/root/
[root@centos771 ~]# scp -r .ssh 10.0.0.81:/root/
[root@centos771 ~]# scp -r .ssh 10.0.0.82:/root/
3 配置MHA
相关下载链接
- https://github.com/yoshinorim/mha4mysql-node/releases/download/v0.58/mha4mysql-node-0.58-0.el7.centos.noarch.rpm
- https://github.com/yoshinorim/mha4mysql-manager/releases/download/v0.58/mha4mysql-manager-0.58-0.el7.centos.noarch.rpm
- https://github.com/yoshinorim/mha4mysql-manager/releases/download/v0.58/mha4mysql-manager-0.58.tar.gz
[root@centos771 ~]# yum -y install mha4mysql-node-0.58-0.el7.centos.noarch.rpm
[root@centos771 ~]# yum -y install mha4mysql-manager-0.58-0.el7.centos.noarch.rpm
# 将mha4mysql-node发送到另外三台主机
[root@centos771 ~]# rsync /data/mha4mysql-node-0.58-0.el7.centos.noarch.rpm 10.0.0.80:/root/
[root@centos771 ~]# rsync /data/mha4mysql-node-0.58-0.el7.centos.noarch.rpm 10.0.0.81:/root/
[root@centos771 ~]# rsync /data/mha4mysql-node-0.58-0.el7.centos.noarch.rpm 10.0.0.82:/root/
# master,slave1,slave2 安装node
编写配置文件
[root@centos771 ~]# mkdir /etc/masterha/
[root@centos771 ~]# vim /etc/masterha/app.cnf
[server default]
manager_workdir=/etc/masterha
manager_log=/var/log/masterha.log
master_binlog_dir=/var/lib/mysql
user=root
password=123456
ping_interval=1
remote_workdir=/tmp
repl_password=123456
repl_user=centos
ssh_user=root
[server1]
hostname=10.0.0.80
port=3306
[server2]
hostname=10.0.0.81
port=3306
candidate_master=1
check_repl_delay=0
[server3]
hostname=10.0.0.82
port=3306
no_master=1
测试连接
[root@centos771 ~]# masterha_check_ssh --conf=/etc/masterha/app.cnf
Thu Oct 15 17:17:59 2020 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Thu Oct 15 17:17:59 2020 - [info] Reading application default configuration from /etc/masterha/app.cnf..
Thu Oct 15 17:17:59 2020 - [info] Reading server configuration from /etc/masterha/app.cnf..
Thu Oct 15 17:17:59 2020 - [info] Starting SSH connection tests..
Thu Oct 15 17:18:00 2020 - [debug]
Thu Oct 15 17:17:59 2020 - [debug] Connecting via SSH from root@10.0.0.80(10.0.0.80:22) to root@10.0.0.81(10.0.0.81:22)..
Thu Oct 15 17:17:59 2020 - [debug] ok.
Thu Oct 15 17:17:59 2020 - [debug] Connecting via SSH from root@10.0.0.80(10.0.0.80:22) to root@10.0.0.82(10.0.0.82:22)..
Thu Oct 15 17:18:00 2020 - [debug] ok.
Thu Oct 15 17:18:01 2020 - [debug]
Thu Oct 15 17:17:59 2020 - [debug] Connecting via SSH from root@10.0.0.81(10.0.0.81:22) to root@10.0.0.80(10.0.0.80:22)..
Thu Oct 15 17:18:00 2020 - [debug] ok.
Thu Oct 15 17:18:00 2020 - [debug] Connecting via SSH from root@10.0.0.81(10.0.0.81:22) to root@10.0.0.82(10.0.0.82:22)..
Thu Oct 15 17:18:01 2020 - [debug] ok.
Thu Oct 15 17:18:01 2020 - [debug]
Thu Oct 15 17:18:00 2020 - [debug] Connecting via SSH from root@10.0.0.82(10.0.0.82:22) to root@10.0.0.80(10.0.0.80:22)..
Thu Oct 15 17:18:00 2020 - [debug] ok.
Thu Oct 15 17:18:00 2020 - [debug] Connecting via SSH from root@10.0.0.82(10.0.0.82:22) to root@10.0.0.81(10.0.0.81:22)..
Thu Oct 15 17:18:01 2020 - [debug] ok.
Thu Oct 15 17:18:01 2020 - [info] All SSH connection tests passed successfully.
master
# 添加授权
mysql> create user root@'10.0.0.%' identified by '123456';
Query OK, 0 rows affected (0.02 sec)
mysql> grant all on *.* to 'root'@'10.0.0.%';
Query OK, 0 rows affected (0.05 sec)
slave
#slave1
mysql> set global read_only=1;
Query OK, 0 rows affected (0.01 sec)
#slave2
mysql> set global read_only=1;
Query OK, 0 rows affected (0.01 sec)
检查整个复制环境状况(健康检查)
[root@centos771 ~]# masterha_check_repl --conf=/etc/masterha/app.cnf
Thu Oct 15 17:27:13 2020 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Thu Oct 15 17:27:13 2020 - [info] Reading application default configuration from /etc/masterha/app.cnf..
Thu Oct 15 17:27:13 2020 - [info] Reading server configuration from /etc/masterha/app.cnf..
Thu Oct 15 17:27:13 2020 - [info] MHA::MasterMonitor version 0.58.
Thu Oct 15 17:27:18 2020 - [info] GTID failover mode = 1
Thu Oct 15 17:27:18 2020 - [info] Dead Servers:
Thu Oct 15 17:27:18 2020 - [info] Alive Servers:
Thu Oct 15 17:27:18 2020 - [info] 10.0.0.80(10.0.0.80:3306)
Thu Oct 15 17:27:18 2020 - [info] 10.0.0.81(10.0.0.81:3306)
Thu Oct 15 17:27:18 2020 - [info] 10.0.0.82(10.0.0.82:3306)
Thu Oct 15 17:27:18 2020 - [info] Alive Slaves:
Thu Oct 15 17:27:18 2020 - [info] 10.0.0.81(10.0.0.81:3306) Version=8.0.13 (oldest major version between slaves) log-bin:enabled
Thu Oct 15 17:27:18 2020 - [info] GTID ON
Thu Oct 15 17:27:18 2020 - [info] Replicating from 10.0.0.80(10.0.0.80:3306)
Thu Oct 15 17:27:18 2020 - [info] Primary candidate for the new Master (candidate_master is set)
Thu Oct 15 17:27:18 2020 - [info] 10.0.0.82(10.0.0.82:3306) Version=8.0.13 (oldest major version between slaves) log-bin:enabled
Thu Oct 15 17:27:18 2020 - [info] GTID ON
Thu Oct 15 17:27:18 2020 - [info] Replicating from 10.0.0.80(10.0.0.80:3306)
Thu Oct 15 17:27:18 2020 - [info] Not candidate for the new Master (no_master is set)
Thu Oct 15 17:27:18 2020 - [info] Current Alive Master: 10.0.0.80(10.0.0.80:3306)
Thu Oct 15 17:27:18 2020 - [info] Checking slave configurations..
Thu Oct 15 17:27:18 2020 - [info] Checking replication filtering settings..
Thu Oct 15 17:27:18 2020 - [info] binlog_do_db= , binlog_ignore_db=
Thu Oct 15 17:27:18 2020 - [info] Replication filtering check ok.
Thu Oct 15 17:27:18 2020 - [info] GTID (with auto-pos) is supported. Skipping all SSH and Node package checking.
Thu Oct 15 17:27:18 2020 - [info] Checking SSH publickey authentication settings on the current master..
Thu Oct 15 17:27:19 2020 - [info] HealthCheck: SSH to 10.0.0.80 is reachable.
Thu Oct 15 17:27:19 2020 - [info]
10.0.0.80(10.0.0.80:3306) (current master)
+--10.0.0.81(10.0.0.81:3306)
+--10.0.0.82(10.0.0.82:3306)
Thu Oct 15 17:27:19 2020 - [info] Checking replication health on 10.0.0.81..
Thu Oct 15 17:27:19 2020 - [info] ok.
Thu Oct 15 17:27:19 2020 - [info] Checking replication health on 10.0.0.82..
Thu Oct 15 17:27:19 2020 - [info] ok.
Thu Oct 15 17:27:19 2020 - [warning] master_ip_failover_script is not defined.
Thu Oct 15 17:27:19 2020 - [warning] shutdown_script is not defined.
Thu Oct 15 17:27:19 2020 - [info] Got exit code 0 (Not master dead).
MySQL Replication Health is OK.
测试
手动同步
（1）手动关闭server1（master）
[root@hah ~]# systemctl stop mysqld
（2）在server4（mha）上将master从server1手动同步到server1上
[root@centos771 ~]# masterha_master_switch --master_state=dead --conf=/etc/masterha/app.cnf --dead_master_ip=10.0.0.80 --dead_master_host=10.0.0.80 --dead_master_port=3306 --new_master_host=10.0.0.81 --new_master_port=3306
Thu Oct 15 17:31:29 2020 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Thu Oct 15 17:31:29 2020 - [info] Reading application default configuration from /etc/masterha/app.cnf..
Thu Oct 15 17:31:29 2020 - [info] Reading server configuration from /etc/masterha/app.cnf..
Thu Oct 15 17:31:29 2020 - [info] MHA::MasterFailover version 0.58.
Thu Oct 15 17:31:29 2020 - [info] Starting master failover.
Thu Oct 15 17:31:29 2020 - [info]
Thu Oct 15 17:31:29 2020 - [info] * Phase 1: Configuration Check Phase..
Thu Oct 15 17:31:29 2020 - [info]
Thu Oct 15 17:31:30 2020 - [info] GTID failover mode = 1
Thu Oct 15 17:31:30 2020 - [info] Dead Servers:
Thu Oct 15 17:31:30 2020 - [info] 10.0.0.80(10.0.0.80:3306)
Thu Oct 15 17:31:30 2020 - [info] Checking master reachability via MySQL(double check)...
Thu Oct 15 17:31:30 2020 - [info] ok.
Thu Oct 15 17:31:30 2020 - [info] Alive Servers:
Thu Oct 15 17:31:30 2020 - [info] 10.0.0.81(10.0.0.81:3306)
Thu Oct 15 17:31:30 2020 - [info] 10.0.0.82(10.0.0.82:3306)
Thu Oct 15 17:31:30 2020 - [info] Alive Slaves:
Thu Oct 15 17:31:30 2020 - [info] 10.0.0.81(10.0.0.81:3306) Version=8.0.13 (oldest major version between slaves) log-bin:enabled
Thu Oct 15 17:31:30 2020 - [info] GTID ON
Thu Oct 15 17:31:30 2020 - [info] Replicating from 10.0.0.80(10.0.0.80:3306)
Thu Oct 15 17:31:30 2020 - [info] Primary candidate for the new Master (candidate_master is set)
Thu Oct 15 17:31:30 2020 - [info] 10.0.0.82(10.0.0.82:3306) Version=8.0.13 (oldest major version between slaves) log-bin:enabled
Thu Oct 15 17:31:30 2020 - [info] GTID ON
Thu Oct 15 17:31:30 2020 - [info] Replicating from 10.0.0.80(10.0.0.80:3306)
Thu Oct 15 17:31:30 2020 - [info] Not candidate for the new Master (no_master is set)
Master 10.0.0.80(10.0.0.80:3306) is dead. Proceed? (yes/NO): yes
Thu Oct 15 17:31:34 2020 - [info] Starting GTID based failover.
Thu Oct 15 17:31:34 2020 - [info]
Thu Oct 15 17:31:34 2020 - [info] ** Phase 1: Configuration Check Phase completed.
Thu Oct 15 17:31:34 2020 - [info]
Thu Oct 15 17:31:34 2020 - [info] * Phase 2: Dead Master Shutdown Phase..
Thu Oct 15 17:31:34 2020 - [info]
Thu Oct 15 17:31:34 2020 - [info] HealthCheck: SSH to 10.0.0.80 is reachable.
Thu Oct 15 17:31:34 2020 - [error][/usr/share/perl5/vendor_perl/MHA/ManagerUtil.pm, ln122] Got error when getting node version. Error:
Thu Oct 15 17:31:34 2020 - [error][/usr/share/perl5/vendor_perl/MHA/ManagerUtil.pm, ln123]
bash: apply_diff_relay_logs: command not found
Thu Oct 15 17:31:34 2020 - [warning] Failed to get MHA Node version from dead master. Guessing that SSH is NOT reachable.
Thu Oct 15 17:31:34 2020 - [info] Forcing shutdown so that applications never connect to the current master..
Thu Oct 15 17:31:34 2020 - [warning] master_ip_failover_script is not set. Skipping invalidating dead master IP address.
Thu Oct 15 17:31:34 2020 - [warning] shutdown_script is not set. Skipping explicit shutting down of the dead master.
Thu Oct 15 17:31:34 2020 - [info] * Phase 2: Dead Master Shutdown Phase completed.
Thu Oct 15 17:31:34 2020 - [info]
Thu Oct 15 17:31:34 2020 - [info] * Phase 3: Master Recovery Phase..
Thu Oct 15 17:31:34 2020 - [info]
Thu Oct 15 17:31:34 2020 - [info] * Phase 3.1: Getting Latest Slaves Phase..
Thu Oct 15 17:31:34 2020 - [info]
Thu Oct 15 17:31:34 2020 - [info] The latest binary log file/position on all slaves is hah-bin.000003:1372
Thu Oct 15 17:31:34 2020 - [info] Retrieved Gtid Set: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-5
Thu Oct 15 17:31:34 2020 - [info] Latest slaves (Slaves that received relay log files to the latest):
Thu Oct 15 17:31:34 2020 - [info] 10.0.0.81(10.0.0.81:3306) Version=8.0.13 (oldest major version between slaves) log-bin:enabled
Thu Oct 15 17:31:34 2020 - [info] GTID ON
Thu Oct 15 17:31:34 2020 - [info] Replicating from 10.0.0.80(10.0.0.80:3306)
Thu Oct 15 17:31:34 2020 - [info] Primary candidate for the new Master (candidate_master is set)
Thu Oct 15 17:31:34 2020 - [info] 10.0.0.82(10.0.0.82:3306) Version=8.0.13 (oldest major version between slaves) log-bin:enabled
Thu Oct 15 17:31:34 2020 - [info] GTID ON
Thu Oct 15 17:31:34 2020 - [info] Replicating from 10.0.0.80(10.0.0.80:3306)
Thu Oct 15 17:31:34 2020 - [info] Not candidate for the new Master (no_master is set)
Thu Oct 15 17:31:34 2020 - [info] The oldest binary log file/position on all slaves is hah-bin.000003:1372
Thu Oct 15 17:31:34 2020 - [info] Retrieved Gtid Set: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-5
Thu Oct 15 17:31:34 2020 - [info] Oldest slaves:
Thu Oct 15 17:31:34 2020 - [info] 10.0.0.81(10.0.0.81:3306) Version=8.0.13 (oldest major version between slaves) log-bin:enabled
Thu Oct 15 17:31:34 2020 - [info] GTID ON
Thu Oct 15 17:31:34 2020 - [info] Replicating from 10.0.0.80(10.0.0.80:3306)
Thu Oct 15 17:31:34 2020 - [info] Primary candidate for the new Master (candidate_master is set)
Thu Oct 15 17:31:34 2020 - [info] 10.0.0.82(10.0.0.82:3306) Version=8.0.13 (oldest major version between slaves) log-bin:enabled
Thu Oct 15 17:31:34 2020 - [info] GTID ON
Thu Oct 15 17:31:34 2020 - [info] Replicating from 10.0.0.80(10.0.0.80:3306)
Thu Oct 15 17:31:34 2020 - [info] Not candidate for the new Master (no_master is set)
Thu Oct 15 17:31:34 2020 - [info]
Thu Oct 15 17:31:34 2020 - [info] * Phase 3.3: Determining New Master Phase..
Thu Oct 15 17:31:34 2020 - [info]
Thu Oct 15 17:31:34 2020 - [info] 10.0.0.81 can be new master.
Thu Oct 15 17:31:34 2020 - [info] New master is 10.0.0.81(10.0.0.81:3306)
Thu Oct 15 17:31:34 2020 - [info] Starting master failover..
Thu Oct 15 17:31:34 2020 - [info]
From:
10.0.0.80(10.0.0.80:3306) (current master)
+--10.0.0.81(10.0.0.81:3306)
+--10.0.0.82(10.0.0.82:3306)
To:
10.0.0.81(10.0.0.81:3306) (new master)
+--10.0.0.82(10.0.0.82:3306)
Starting master switch from 10.0.0.80(10.0.0.80:3306) to 10.0.0.81(10.0.0.81:3306)? (yes/NO): yes
Thu Oct 15 17:31:41 2020 - [info] New master decided manually is 10.0.0.81(10.0.0.81:3306)
Thu Oct 15 17:31:41 2020 - [info]
Thu Oct 15 17:31:41 2020 - [info] * Phase 3.3: New Master Recovery Phase..
Thu Oct 15 17:31:41 2020 - [info]
Thu Oct 15 17:31:41 2020 - [info] Waiting all logs to be applied..
Thu Oct 15 17:31:41 2020 - [info] done.
Thu Oct 15 17:31:41 2020 - [info] Getting new master's binlog name and position..
Thu Oct 15 17:31:41 2020 - [info] 81-bin.000002:1407
Thu Oct 15 17:31:41 2020 - [info] All other slaves should start replication from here. Statement should be: CHANGE MASTER TO MASTER_HOST='10.0.0.81', MASTER_PORT=3306, MASTER_AUTO_POSITION=1, MASTER_USER='centos', MASTER_PASSWORD='xxx';
Thu Oct 15 17:31:41 2020 - [info] Master Recovery succeeded. File:Pos:Exec_Gtid_Set: 81-bin.000002, 1407, 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-5
Thu Oct 15 17:31:41 2020 - [warning] master_ip_failover_script is not set. Skipping taking over new master IP address.
Thu Oct 15 17:31:41 2020 - [info] Setting read_only=0 on 10.0.0.81(10.0.0.81:3306)..
Thu Oct 15 17:31:41 2020 - [info] ok.
Thu Oct 15 17:31:41 2020 - [info] ** Finished master recovery successfully.
Thu Oct 15 17:31:41 2020 - [info] * Phase 3: Master Recovery Phase completed.
Thu Oct 15 17:31:41 2020 - [info]
Thu Oct 15 17:31:41 2020 - [info] * Phase 4: Slaves Recovery Phase..
Thu Oct 15 17:31:41 2020 - [info]
Thu Oct 15 17:31:41 2020 - [info]
Thu Oct 15 17:31:41 2020 - [info] * Phase 4.1: Starting Slaves in parallel..
Thu Oct 15 17:31:41 2020 - [info]
Thu Oct 15 17:31:41 2020 - [info] -- Slave recovery on host 10.0.0.82(10.0.0.82:3306) started, pid: 17318. Check tmp log /etc/masterha/10.0.0.82_3306_20201015173129.log if it takes time..
Thu Oct 15 17:31:43 2020 - [info]
Thu Oct 15 17:31:43 2020 - [info] Log messages from 10.0.0.82 ...
Thu Oct 15 17:31:43 2020 - [info]
Thu Oct 15 17:31:41 2020 - [info] Resetting slave 10.0.0.82(10.0.0.82:3306) and starting replication from the new master 10.0.0.81(10.0.0.81:3306)..
Thu Oct 15 17:31:42 2020 - [info] Executed CHANGE MASTER.
Thu Oct 15 17:31:43 2020 - [info] Slave started.
Thu Oct 15 17:31:43 2020 - [info] gtid_wait(2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-5) completed on 10.0.0.82(10.0.0.82:3306). Executed 0 events.
Thu Oct 15 17:31:43 2020 - [info] End of log messages from 10.0.0.82.
Thu Oct 15 17:31:43 2020 - [info] -- Slave on host 10.0.0.82(10.0.0.82:3306) started.
Thu Oct 15 17:31:43 2020 - [info] All new slave servers recovered successfully.
Thu Oct 15 17:31:43 2020 - [info]
Thu Oct 15 17:31:43 2020 - [info] * Phase 5: New master cleanup phase..
Thu Oct 15 17:31:43 2020 - [info]
Thu Oct 15 17:31:43 2020 - [info] Resetting slave info on the new master..
Thu Oct 15 17:31:44 2020 - [info] 10.0.0.81: Resetting slave info succeeded.
Thu Oct 15 17:31:44 2020 - [info] Master failover to 10.0.0.81(10.0.0.81:3306) completed successfully.
Thu Oct 15 17:31:44 2020 - [info]
----- Failover Report -----
app: MySQL Master failover 10.0.0.80(10.0.0.80:3306) to 10.0.0.81(10.0.0.81:3306) succeeded
Master 10.0.0.80(10.0.0.80:3306) is down!
Check MHA Manager logs at centos771 for details.
Started manual(interactive) failover.
Selected 10.0.0.81(10.0.0.81:3306) as a new master.
10.0.0.81(10.0.0.81:3306): OK: Applying all logs succeeded.
10.0.0.82(10.0.0.82:3306): OK: Slave started, replicating from 10.0.0.81(10.0.0.81:3306)
10.0.0.81(10.0.0.81:3306): Resetting slave info succeeded.
Master failover to 10.0.0.81(10.0.0.81:3306) completed successfully.
（3）测试在server1上查看slave状态为空，server2上的master显示是server2，说明手动转换成功
server2：
mysql> show slave status\G
Empty set (0.00 sec)
server3：
mysql> show slave status\G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 10.0.0.81
Master_User: centos
Master_Port: 3306
Connect_Retry: 60
Master_Log_File: 81-bin.000002
Read_Master_Log_Pos: 1407
Relay_Log_File: 82-relay-bin.000002
Relay_Log_Pos: 407
Relay_Master_Log_File: 81-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: 1407
Relay_Log_Space: 612
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: 81
Master_UUID: 711d79aa-0eb8-11eb-b3dc-000c299dcf4d
Master_Info_File: mysql.slave_master_info
SQL_Delay: 0
SQL_Remaining_Delay: NULL
Slave_SQL_Running_State: Slave has read all relay log; waiting for more updates
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: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-5
Auto_Position: 1
Replicate_Rewrite_DB:
Channel_Name:
Master_TLS_Version:
Master_public_key_path:
Get_master_public_key: 0
1 row in set (0.00 sec)
（4）然后打开server1的mysqld，在sever1上重新添加master，查看slave的状态，显示master是server2，切换成功
[root@hah ~]# systemctl start mysqld
mysql> change master to master_host='10.0.0.81',master_port=3306,master_auto_position=1,master_user='centos',master_password='123456';
Query OK, 0 rows affected, 2 warnings (0.20 sec)
mysql> start slave;
Query OK, 0 rows affected (0.03 sec)
mysql> show slave status\G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 10.0.0.81
Master_User: centos
Master_Port: 3306
Connect_Retry: 60
Master_Log_File: 81-bin.000002
Read_Master_Log_Pos: 1407
Relay_Log_File: hah-relay-bin.000002
Relay_Log_Pos: 407
Relay_Master_Log_File: 81-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: 1407
Relay_Log_Space: 613
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: 81
Master_UUID: 711d79aa-0eb8-11eb-b3dc-000c299dcf4d
Master_Info_File: mysql.slave_master_info
SQL_Delay: 0
SQL_Remaining_Delay: NULL
Slave_SQL_Running_State: Slave has read all relay log; waiting for more updates
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: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-5
Auto_Position: 1
Replicate_Rewrite_DB:
Channel_Name:
Master_TLS_Version:
Master_public_key_path:
Get_master_public_key: 0
1 row in set (0.00 sec)
两个主备master都开启
（1）首先删除server4的app1.failover.complete，否则再次转换不能成功
[root@centos771 ~]# ll /etc/masterha/
total 4
-rw-r--r--. 1 root root 444 Oct 15 17:00 app.cnf
-rw-r--r--. 1 root root 0 Oct 15 17:31 app.failover.complete
[root@centos771 ~]# rm -rf /etc/masterha/app.failover.complete
（2）手动切换新的master——>server1
[root@centos771 ~]# masterha_master_switch --conf=/etc/masterha/app.cnf --master_state=alive --new_master_host=10.0.0.80 --new_master_port=3306 --orig_master_is_new_slave --running_updates_limit=10000
Thu Oct 15 17:40:52 2020 - [info] MHA::MasterRotate version 0.58.
Thu Oct 15 17:40:52 2020 - [info] Starting online master switch..
Thu Oct 15 17:40:52 2020 - [info]
Thu Oct 15 17:40:52 2020 - [info] * Phase 1: Configuration Check Phase..
Thu Oct 15 17:40:52 2020 - [info]
Thu Oct 15 17:40:52 2020 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Thu Oct 15 17:40:52 2020 - [info] Reading application default configuration from /etc/masterha/app.cnf..
Thu Oct 15 17:40:52 2020 - [info] Reading server configuration from /etc/masterha/app.cnf..
Thu Oct 15 17:40:53 2020 - [info] GTID failover mode = 1
Thu Oct 15 17:40:53 2020 - [info] Current Alive Master: 10.0.0.81(10.0.0.81:3306)
Thu Oct 15 17:40:53 2020 - [info] Alive Slaves:
Thu Oct 15 17:40:53 2020 - [info] 10.0.0.80(10.0.0.80:3306) Version=8.0.13 (oldest major version between slaves) log-bin:enabled
Thu Oct 15 17:40:53 2020 - [info] GTID ON
Thu Oct 15 17:40:53 2020 - [info] Replicating from 10.0.0.81(10.0.0.81:3306)
Thu Oct 15 17:40:53 2020 - [info] 10.0.0.82(10.0.0.82:3306) Version=8.0.13 (oldest major version between slaves) log-bin:enabled
Thu Oct 15 17:40:53 2020 - [info] GTID ON
Thu Oct 15 17:40:53 2020 - [info] Replicating from 10.0.0.81(10.0.0.81:3306)
Thu Oct 15 17:40:53 2020 - [info] Not candidate for the new Master (no_master is set)
It is better to execute FLUSH NO_WRITE_TO_BINLOG TABLES on the master before switching. Is it ok to execute on 10.0.0.81(10.0.0.81:3306)? (YES/no): yes
Thu Oct 15 17:40:56 2020 - [info] Executing FLUSH NO_WRITE_TO_BINLOG TABLES. This may take long time..
Thu Oct 15 17:40:56 2020 - [info] ok.
Thu Oct 15 17:40:56 2020 - [info] Checking MHA is not monitoring or doing failover..
Thu Oct 15 17:40:56 2020 - [info] Checking replication health on 10.0.0.80..
Thu Oct 15 17:40:56 2020 - [info] ok.
Thu Oct 15 17:40:56 2020 - [info] Checking replication health on 10.0.0.82..
Thu Oct 15 17:40:56 2020 - [info] ok.
Thu Oct 15 17:40:56 2020 - [info] 10.0.0.80 can be new master.
Thu Oct 15 17:40:56 2020 - [info]
From:
10.0.0.81(10.0.0.81:3306) (current master)
+--10.0.0.80(10.0.0.80:3306)
+--10.0.0.82(10.0.0.82:3306)
To:
10.0.0.80(10.0.0.80:3306) (new master)
+--10.0.0.82(10.0.0.82:3306)
+--10.0.0.81(10.0.0.81:3306)
Starting master switch from 10.0.0.81(10.0.0.81:3306) to 10.0.0.80(10.0.0.80:3306)? (yes/NO): yes
Thu Oct 15 17:40:59 2020 - [info] Checking whether 10.0.0.80(10.0.0.80:3306) is ok for the new master..
Thu Oct 15 17:40:59 2020 - [info] ok.
Thu Oct 15 17:40:59 2020 - [info] 10.0.0.81(10.0.0.81:3306): SHOW SLAVE STATUS returned empty result. To check replication filtering rules, temporarily executing CHANGE MASTER to a dummy host.
Thu Oct 15 17:40:59 2020 - [info] 10.0.0.81(10.0.0.81:3306): Resetting slave pointing to the dummy host.
Thu Oct 15 17:40:59 2020 - [info] ** Phase 1: Configuration Check Phase completed.
Thu Oct 15 17:40:59 2020 - [info]
Thu Oct 15 17:40:59 2020 - [info] * Phase 2: Rejecting updates Phase..
Thu Oct 15 17:40:59 2020 - [info]
master_ip_online_change_script is not defined. If you do not disable writes on the current master manually, applications keep writing on the current master. Is it ok to proceed? (yes/NO): yes
Thu Oct 15 17:41:02 2020 - [info] Locking all tables on the orig master to reject updates from everybody (including root):
Thu Oct 15 17:41:02 2020 - [info] Executing FLUSH TABLES WITH READ LOCK..
Thu Oct 15 17:41:02 2020 - [info] ok.
Thu Oct 15 17:41:02 2020 - [info] Orig master binlog:pos is 81-bin.000002:1407.
Thu Oct 15 17:41:02 2020 - [info] Waiting to execute all relay logs on 10.0.0.80(10.0.0.80:3306)..
Thu Oct 15 17:41:02 2020 - [info] master_pos_wait(81-bin.000002:1407) completed on 10.0.0.80(10.0.0.80:3306). Executed 0 events.
Thu Oct 15 17:41:02 2020 - [info] done.
Thu Oct 15 17:41:02 2020 - [info] Getting new master's binlog name and position..
Thu Oct 15 17:41:02 2020 - [info] hah-bin.000004:195
Thu Oct 15 17:41:02 2020 - [info] All other slaves should start replication from here. Statement should be: CHANGE MASTER TO MASTER_HOST='10.0.0.80', MASTER_PORT=3306, MASTER_AUTO_POSITION=1, MASTER_USER='centos', MASTER_PASSWORD='xxx';
Thu Oct 15 17:41:02 2020 - [info]
Thu Oct 15 17:41:02 2020 - [info] * Switching slaves in parallel..
Thu Oct 15 17:41:02 2020 - [info]
Thu Oct 15 17:41:02 2020 - [info] -- Slave switch on host 10.0.0.82(10.0.0.82:3306) started, pid: 17333
Thu Oct 15 17:41:02 2020 - [info]
Thu Oct 15 17:41:04 2020 - [info] Log messages from 10.0.0.82 ...
Thu Oct 15 17:41:04 2020 - [info]
Thu Oct 15 17:41:02 2020 - [info] Waiting to execute all relay logs on 10.0.0.82(10.0.0.82:3306)..
Thu Oct 15 17:41:02 2020 - [info] master_pos_wait(81-bin.000002:1407) completed on 10.0.0.82(10.0.0.82:3306). Executed 0 events.
Thu Oct 15 17:41:02 2020 - [info] done.
Thu Oct 15 17:41:02 2020 - [info] Resetting slave 10.0.0.82(10.0.0.82:3306) and starting replication from the new master 10.0.0.80(10.0.0.80:3306)..
Thu Oct 15 17:41:02 2020 - [info] Executed CHANGE MASTER.
Thu Oct 15 17:41:03 2020 - [info] Slave started.
Thu Oct 15 17:41:04 2020 - [info] End of log messages from 10.0.0.82 ...
Thu Oct 15 17:41:04 2020 - [info]
Thu Oct 15 17:41:04 2020 - [info] -- Slave switch on host 10.0.0.82(10.0.0.82:3306) succeeded.
Thu Oct 15 17:41:04 2020 - [info] Unlocking all tables on the orig master:
Thu Oct 15 17:41:04 2020 - [info] Executing UNLOCK TABLES..
Thu Oct 15 17:41:04 2020 - [info] ok.
Thu Oct 15 17:41:04 2020 - [info] Starting orig master as a new slave..
Thu Oct 15 17:41:04 2020 - [info] Resetting slave 10.0.0.81(10.0.0.81:3306) and starting replication from the new master 10.0.0.80(10.0.0.80:3306)..
Thu Oct 15 17:41:04 2020 - [info] Executed CHANGE MASTER.
Thu Oct 15 17:41:05 2020 - [info] Slave started.
Thu Oct 15 17:41:05 2020 - [info] All new slave servers switched successfully.
Thu Oct 15 17:41:05 2020 - [info]
Thu Oct 15 17:41:05 2020 - [info] * Phase 5: New master cleanup phase..
Thu Oct 15 17:41:05 2020 - [info]
Thu Oct 15 17:41:05 2020 - [info] 10.0.0.80: Resetting slave info succeeded.
Thu Oct 15 17:41:05 2020 - [info] Switching master to 10.0.0.80(10.0.0.80:3306) completed successfully.
（3）master测试结果显示如下（这次server2不用重新添加master）
mysql> show slave status\G
Empty set (0.00 sec)
server1：
mysql> show slave status\G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 10.0.0.80
Master_User: centos
Master_Port: 3306
Connect_Retry: 60
Master_Log_File: hah-bin.000004
Read_Master_Log_Pos: 195
Relay_Log_File: 81-relay-bin.000002
Relay_Log_Pos: 365
Relay_Master_Log_File: hah-bin.000004
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: 195
Relay_Log_Space: 570
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: 80
Master_UUID: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6
Master_Info_File: mysql.slave_master_info
SQL_Delay: 0
SQL_Remaining_Delay: NULL
Slave_SQL_Running_State: Slave has read all relay log; waiting for more updates
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: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-5
Auto_Position: 1
Replicate_Rewrite_DB:
Channel_Name:
Master_TLS_Version:
Master_public_key_path:
Get_master_public_key: 0
1 row in set (0.00 sec)
server2
mysql> show slave status\G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 10.0.0.80
Master_User: centos
Master_Port: 3306
Connect_Retry: 60
Master_Log_File: hah-bin.000004
Read_Master_Log_Pos: 195
Relay_Log_File: 82-relay-bin.000002
Relay_Log_Pos: 365
Relay_Master_Log_File: hah-bin.000004
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: 195
Relay_Log_Space: 570
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: 80
Master_UUID: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6
Master_Info_File: mysql.slave_master_info
SQL_Delay: 0
SQL_Remaining_Delay: NULL
Slave_SQL_Running_State: Slave has read all relay log; waiting for more updates
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: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-5
Auto_Position: 1
Replicate_Rewrite_DB:
Channel_Name:
Master_TLS_Version:
Master_public_key_path:
Get_master_public_key: 0
1 row in set (0.00 sec)
自动切换
（1）自动切换命令如下
[root@centos771 ~]# nohup masterha_manager --conf=/etc/masterha/app.cnf &> /dev/null &
[1] 17335
[root@centos771 ~]# ps a
PID TTY STAT TIME COMMAND
602 tty1 Ss+ 0:00 /sbin/agetty --noclear tty1 linux
17044 pts/0 Ss 0:00 -bash
17335 pts/0 S 0:00 perl /usr/bin/masterha_manager --conf=/etc/masterha/app.cnf
17623 pts/0 R+ 0:00 ps a
（2）然后手动关掉master
[root@hah ~]# systemctl stop mysqld
（3）然后会发现master转到了server1上
server1的slave状态为空
mysql> show slave status\G
Empty set (0.00 sec)
server2显示master转为server1
mysql> show slave status\G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 10.0.0.81
Master_User: centos
Master_Port: 3306
Connect_Retry: 60
Master_Log_File: 81-bin.000002
Read_Master_Log_Pos: 1407
Relay_Log_File: 82-relay-bin.000002
Relay_Log_Pos: 407
Relay_Master_Log_File: 81-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: 1407
Relay_Log_Space: 612
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: 81
Master_UUID: 711d79aa-0eb8-11eb-b3dc-000c299dcf4d
Master_Info_File: mysql.slave_master_info
SQL_Delay: 0
SQL_Remaining_Delay: NULL
Slave_SQL_Running_State: Slave has read all relay log; waiting for more updates
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: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-5
Auto_Position: 1
Replicate_Rewrite_DB:
Channel_Name:
Master_TLS_Version:
Master_public_key_path:
Get_master_public_key: 0
1 row in set (0.00 sec)
（4）master需要开启mysqld，然后添加master
[root@hah ~]# systemctl start mysqld
mysql> change master to master_host='10.0.0.81',master_port=3306,master_auto_position=1,master_user='centos',master_password='123456';
Query OK, 0 rows affected, 2 warnings (0.10 sec)
（5）master查看slave的状态，显示master是server1，切换成功
mysql> show slave status\G
*************************** 1. row ***************************
Slave_IO_State:
Master_Host: 10.0.0.81
Master_User: centos
Master_Port: 3306
Connect_Retry: 60
Master_Log_File:
Read_Master_Log_Pos: 4
Relay_Log_File: hah-relay-bin.000001
Relay_Log_Pos: 4
Relay_Master_Log_File:
Slave_IO_Running: No
Slave_SQL_Running: No
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: 0
Relay_Log_Space: 155
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: 0
Last_IO_Error:
Last_SQL_Errno: 0
Last_SQL_Error:
Replicate_Ignore_Server_Ids:
Master_Server_Id: 0
Master_UUID:
Master_Info_File: mysql.slave_master_info
SQL_Delay: 0
SQL_Remaining_Delay: NULL
Slave_SQL_Running_State:
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: 2f33ae67-0eb8-11eb-b1ec-000c29f9b5e6:1-5
Auto_Position: 1
Replicate_Rewrite_DB:
Channel_Name:
Master_TLS_Version:
Master_public_key_path:
Get_master_public_key: 0
1 row in set (0.00 sec)
VIP的漂移
1.编辑配置文件
[root@centos771 ~]# vim /etc/masterha/app.cnf
# [server default]添加如下一行
master_ip_failover_script=/usr/local/bin/master_ip_failover
2.下载MHA工具包，解压安装包
[root@centos771 ~]# cd /data/
[root@centos771 data]# wget https://github.com/yoshinorim/mha4mysql-manager/releases/download/v0.58/mha4mysql-manager-0.58.tar.gz
[root@centos771 data]# tar zxf mha4mysql-manager-0.58.tar.gz
# 查找脚本
[root@centos771 data]# find / -name "master_ip*"
/data/mha4mysql-manager-0.58/tests/t/master_ip_failover
/data/mha4mysql-manager-0.58/tests/t/master_ip_failover_blank
/data/mha4mysql-manager-0.58/samples/scripts/master_ip_failover
/data/mha4mysql-manager-0.58/samples/scripts/master_ip_online_change
3.在 /usr/local/bin添加1个文件，并给1个文件添加执行权限
[root@centos771 data]# cd mha4mysql-manager-0.58/samples/scripts/
[root@centos771 scripts]# cp master_ip_
master_ip_failover master_ip_online_change
[root@centos771 scripts]# cp master_ip_failover /usr/local/bin/
[root@centos771 scripts]# cd /usr/local/bin
[root@centos771 bin]# ls
master_ip_failover
[root@centos771 bin]# vim 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';#设置Virtual IP
my $gateway = '10.0.0.254';#网关Gateway IP
my $interface = 'ens33'; #指定VIP所在网卡
my $key = "1";
my $ssh_start_vip = "/sbin/ifconfig $interface:$key $vip;/sbin/arping -I
$interface -c 3 -s $vip $gateway >/dev/null 2>&1";
my $ssh_stop_vip = "/sbin/ifconfig $interface:$key down";
GetOptions(
'command=s' => \$command,
'ssh_user=s' => \$ssh_user,
'orig_master_host=s' => \$orig_master_host,
'orig_master_ip=s' => \$orig_master_ip,
'orig_master_port=i' => \$orig_master_port,
'new_master_host=s' => \$new_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";
`ssh $ssh_user\@$orig_master_host \" $ssh_start_vip \"`;
exit 0;
}
else {
&usage();
exit 1;
}
}
sub start_vip() {
`ssh $ssh_user\@$new_master_host \" $ssh_start_vip \"`;
}
sub stop_vip() {
`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";
}
[root@mha-manager ~]#chmod +x /usr/local/bin/master_ip_failover
4.在现在的master上（server1），添加VIP
[root@81 data]# ip addr add 10.0.0.100/24 dev ens33
[root@81 data]# ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
valid_lft forever preferred_lft forever
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: ens33: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel state UP group default qlen 1000
link/ether 00:0c:29:85:98:b8 brd ff:ff:ff:ff:ff:ff
inet 10.0.0.81/8 brd 10.255.255.255 scope global noprefixroute ens33
valid_lft forever preferred_lft forever
inet 10.0.0.100/24 scope global ens33
valid_lft forever preferred_lft forever
inet6 fe80::20c:29ff:fe85:98b8/64 scope link
valid_lft forever preferred_lft forever
测试：自动转换
# 检查MHA的ssh
[root@771 data]# masterha_check_ssh --conf=/etc/masterha/app.cnf
# 检查MHA环境
[root@771 data]# masterha_check_repl --conf=/etc/masterha/app.cnf
# 启动MHA
[root@771 data]# masterha_manager --conf=/etc/masterha/app.cnf &> /dev/null &
[2] 2226
[root@771 data]# masterha_check_status --conf=/etc/masterha/app.cnf
app (pid:2160) is running(0:PING_OK), master:10.0.0.81
[2]+ Exit 1 masterha_manager --conf=/etc/masterha/app.cnf &>/dev/null
# master停止服务
[root@80 data]# systemctl stop mysqld
查看VIP漂移到server1上
# 查看slave1的IP
[root@81 data]# ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
valid_lft forever preferred_lft forever
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: ens33: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel state UP group default qlen 1000
link/ether 00:0c:29:02:89:3c brd ff:ff:ff:ff:ff:ff
inet 10.0.0.81/8 brd 10.255.255.255 scope global noprefixroute ens33
valid_lft forever preferred_lft forever
inet 10.0.0.100/24 brd 10.0.0.255 scope global ens33:1
valid_lft forever preferred_lft forever
inet6 fe80::20c:29ff:fe02:893c/64 scope link
valid_lft forever preferred_lft forever
4、实战案例：Percona XtraDB Cluster(PXC 5.7）
注意：pxc目前支持最高的OS版本是centos7
1 环境准备
四台虚拟机
- pxc1:10.0.0.71
- pxc2:10.0.0.72
- pxc3:10.0.0.73
- pxc4:10.0.0.74
**关闭防火墙和SELinux，保证时间同步 **
注意：如果已经安装MySQL，必须卸载
2 安装 Percona XtraDB Cluster 5.7
# 此处使用清华大学yum源，官方源太慢了
[root@71 ~]# cat > /etc/yum.repos.d/pxc.repo << EOF
[percona]
name=percona_repo
baseurl =https://mirrors.tuna.tsinghua.edu.cn/percona/release/\$releasever/RPMS/\$basearch
enabled = 1
gpgcheck = 0
EOF
[root@71 data]# scp /etc/yum.repos.d/pxc.repo 10.0.0.72:/etc/yum.repos.d/
[root@71 data]# scp /etc/yum.repos.d/pxc.repo 10.0.0.73:/etc/yum.repos.d/
[root@71 data]# scp /etc/yum.repos.d/pxc.repo 10.0.0.74:/etc/yum.repos.d/
#在三个节点都安装好PXC 5.7
[root@71 data]# yum -y install Percona-XtraDB-Cluster-57
[root@72 data]# yum -y install Percona-XtraDB-Cluster-57
[root@73 data]# yum -y install Percona-XtraDB-Cluster-57
[root@74 data]# yum -y install Percona-XtraDB-Cluster-57
3 在各个节点上分别配置mysql及集群配置文件
/etc/my.cnf为主配置文件，当前版本中，其余的配置文件都放在/etc/percona-xtradb-cluster.conf.d目 录里，包括mysqld.cnf，mysqld_safe.cnf，wsrep.cnf 三个文件
pxc1
# 主配置文件不需要修改
[root@71 data]# cat /etc/my.cnf | grep -v "^#"
!includedir /etc/my.cnf.d/
!includedir /etc/percona-xtradb-cluster.conf.d/
[root@71 data]# ls /etc/my.cnf.
my.cnf.d/ my.cnf.old
[root@71 data]# ls /etc/my.cnf.d/
[root@71 data]# ls /etc/percona-xtradb-cluster.conf.d/
mysqld.cnf mysqld_safe.cnf wsrep.cnf
# 下面配置文件不需要修改
[root@71 data]# cat /etc/percona-xtradb-cluster.conf.d/mysqld.cnf | grep -v "^#"
[client]
socket=/var/lib/mysql/mysql.sock
[mysqld]
server-id=71 # 建议各个节点不同,使用IP
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
log-error=/var/log/mysqld.log
pid-file=/var/run/mysqld/mysqld.pid
log-bin # 建议启用，非必须项
log_slave_updates
expire_logs_days=7
symbolic-links=0
# 下面配置文件不需要修改
[root@71 data]# cat /etc/percona-xtradb-cluster.conf.d/mysqld_safe.cnf | grep -v "^#"
[mysqld_safe]
pid-file = /var/run/mysqld/mysqld.pid
socket = /var/lib/mysql/mysql.sock
nice = 0
# PXC的配置文件必须修改
[root@71 data]# vim /etc/percona-xtradb-cluster.conf.d/wsrep.cnf
[root@71 data]# cat /etc/percona-xtradb-cluster.conf.d/wsrep.cnf | grep -v "^#"
[mysqld]
wsrep_provider=/usr/lib64/galera3/libgalera_smm.so
wsrep_cluster_address=gcomm://10.0.0.71,10.0.0.72,10.0.0.73 #三个节点的IP
binlog_format=ROW
default_storage_engine=InnoDB
wsrep_slave_threads= 8
wsrep_log_conflicts
innodb_autoinc_lock_mode=2
wsrep_node_address=10.0.0.71 #取消注释，各个节点，指定自已的IP
wsrep_cluster_name=pxc-cluster
wsrep_node_name=pxc-cluster-node-1 #各个节点，指定自已节点名称
pxc_strict_mode=ENFORCING
wsrep_sst_method=xtrabackup-v2
wsrep_sst_auth="sstuser:s3cretPass" #取消本行注释
pxc2
[root@72 ~]# cat /etc/percona-xtradb-cluster.conf.d/mysqld.cnf | grep -v "^#"
[client]
socket=/var/lib/mysql/mysql.sock
[mysqld]
server-id=72
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
log-error=/var/log/mysqld.log
pid-file=/var/run/mysqld/mysqld.pid
log-bin
log_slave_updates
expire_logs_days=7
symbolic-links=0
[root@72 ~]# cat /etc/percona-xtradb-cluster.conf.d/wsrep.cnf | grep -v "^#"
[mysqld]
wsrep_provider=/usr/lib64/galera3/libgalera_smm.so
wsrep_cluster_address=gcomm://10.0.0.71,10.0.0.72,10.0.0.73
binlog_format=ROW
default_storage_engine=InnoDB
wsrep_slave_threads= 8
wsrep_log_conflicts
innodb_autoinc_lock_mode=2
wsrep_node_address=10.0.0.72
wsrep_cluster_name=pxc-cluster
wsrep_node_name=pxc-cluster-node-2
pxc_strict_mode=ENFORCING
wsrep_sst_method=xtrabackup-v2
wsrep_sst_auth="sstuser:s3cretPass"
pxc3
[root@73 ~]# cat /etc/percona-xtradb-cluster.conf.d/mysqld.cnf | grep -v "^#"
[client]
socket=/var/lib/mysql/mysql.sock
[mysqld]
server-id=73
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
log-error=/var/log/mysqld.log
pid-file=/var/run/mysqld/mysqld.pid
log-bin
log_slave_updates
expire_logs_days=7
symbolic-links=0
[root@73 ~]# cat /etc/percona-xtradb-cluster.conf.d/wsrep.cnf | grep -v "^#"
[mysqld]
wsrep_provider=/usr/lib64/galera3/libgalera_smm.so
wsrep_cluster_address=gcomm://10.0.0.71,10.0.0.72,10.0.0.73
binlog_format=ROW
default_storage_engine=InnoDB
wsrep_slave_threads= 8
wsrep_log_conflicts
innodb_autoinc_lock_mode=2
wsrep_node_address=10.0.0.73
wsrep_cluster_name=pxc-cluster
wsrep_node_name=pxc-cluster-node-3
pxc_strict_mode=ENFORCING
wsrep_sst_method=xtrabackup-v2
wsrep_sst_auth="sstuser:s3cretPass" # 注意此处的用户名，密码
4 启动PXC集群中第一个节点
[root@71 data]# ss -ntul
Netid State Recv-Q Send-Q Local Address:Port Peer Address:Port
tcp LISTEN 0 128 *:22 *:*
tcp LISTEN 0 128 [::]:22 [::]:*
#启动第一个节点
[root@71 data]# systemctl start mysql@bootstrap.service
[root@71 data]# ss -ntul
Netid State Recv-Q Send-Q Local Address:Port Peer Address:Port
tcp LISTEN 0 128 *:22 *:*
tcp LISTEN 0 128 *:4567 *:*
tcp LISTEN 0 80 [::]:3306 [::]:*
tcp LISTEN 0 128 [::]:22 [::]:*
#查看root密码
[root@71 data]# awk -F'root@localhost: ' '/temporary password/{print $2}' /var/log/mysqld.log
0-4l.wwY*u_A
# 修改密码
[root@71 data]# mysql -uroot -p0-4l.wwY*u_A
mysql: [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 11
Server version: 5.7.31-34-57-log
Copyright (c) 2009-2020 Percona LLC and/or its affiliates
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> alter user 'root'@'localhost' identified by '123456';
Query OK, 0 rows affected (0.01 sec)
mysql> select user,host,authentication_string from mysql.user;
+---------------+-----------+-------------------------------------------+
| user | host | authentication_string |
+---------------+-----------+-------------------------------------------+
| root | localhost | *6BB4837EB74329105EE4568DDA7DC67ED2CA2AD9 |
| mysql.session | localhost | *THISISNOTAVALIDPASSWORDTHATCANBEUSEDHERE |
| mysql.sys | localhost | *THISISNOTAVALIDPASSWORDTHATCANBEUSEDHERE |
+---------------+-----------+-------------------------------------------+
3 rows in set (0.00 sec)
#创建相关用户并授权:此处的用户和密码跟配置文件一致
mysql> GRANT RELOAD, LOCK TABLES, PROCESS, REPLICATION CLIENT ON *.* TO
-> 'sstuser'@'localhost' IDENTIFIED BY 's3cretPass';
Query OK, 0 rows affected, 1 warning (0.00 sec)
mysql> select user,host,authentication_string from mysql.user;
+---------------+-----------+-------------------------------------------+
| user | host | authentication_string |
+---------------+-----------+-------------------------------------------+
| root | localhost | *6BB4837EB74329105EE4568DDA7DC67ED2CA2AD9 |
| mysql.session | localhost | *THISISNOTAVALIDPASSWORDTHATCANBEUSEDHERE |
| mysql.sys | localhost | *THISISNOTAVALIDPASSWORDTHATCANBEUSEDHERE |
| sstuser | localhost | *1D3B4419453D37D70EC48955E49473559FF4778E |
+---------------+-----------+-------------------------------------------+
4 rows in set (0.00 sec)
# 查看相关变量
mysql> show variables like 'wsrep%'\G
*************************** 1. row ***************************
Variable_name: wsrep_OSU_method
Value: TOI
*************************** 2. row ***************************
Variable_name: wsrep_RSU_commit_timeout
Value: 5000
*************************** 3. row ***************************
Variable_name: wsrep_auto_increment_control
Value: ON
*************************** 4. row ***************************
Variable_name: wsrep_causal_reads
Value: OFF
*************************** 5. row ***************************
Variable_name: wsrep_certification_rules
Value: strict
*************************** 6. row ***************************
Variable_name: wsrep_certify_nonPK
Value: ON
*************************** 7. row ***************************
Variable_name: wsrep_cluster_address
Value: gcomm://10.0.0.71,10.0.0.72,10.0.0.73
*************************** 8. row ***************************
Variable_name: wsrep_cluster_name
Value: pxc-cluster
*************************** 9. row ***************************
Variable_name: wsrep_convert_LOCK_to_trx
Value: OFF
*************************** 10. row ***************************
Variable_name: wsrep_data_home_dir
Value: /var/lib/mysql/
*************************** 11. row ***************************
Variable_name: wsrep_dbug_option
Value:
*************************** 12. row ***************************
Variable_name: wsrep_debug
Value: OFF
*************************** 13. row ***************************
Variable_name: wsrep_desync
Value: OFF
*************************** 14. row ***************************
Variable_name: wsrep_dirty_reads
Value: OFF
*************************** 15. row ***************************
Variable_name: wsrep_drupal_282555_workaround
Value: OFF
*************************** 16. row ***************************
Variable_name: wsrep_forced_binlog_format
Value: NONE
*************************** 17. row ***************************
Variable_name: wsrep_load_data_splitting
Value: ON
*************************** 18. row ***************************
Variable_name: wsrep_log_conflicts
Value: ON
*************************** 19. row ***************************
Variable_name: wsrep_max_ws_rows
Value: 0
*************************** 20. row ***************************
Variable_name: wsrep_max_ws_size
Value: 2147483647
*************************** 21. row ***************************
Variable_name: wsrep_node_address
Value: 10.0.0.71
*************************** 22. row ***************************
Variable_name: wsrep_node_incoming_address
Value: AUTO
*************************** 23. row ***************************
Variable_name: wsrep_node_name
Value: pxc-cluster-node-1
*************************** 24. row ***************************
Variable_name: wsrep_notify_cmd
Value:
*************************** 25. row ***************************
Variable_name: wsrep_on
Value: ON
*************************** 26. row ***************************
Variable_name: wsrep_preordered
Value: OFF
*************************** 27. row ***************************
Variable_name: wsrep_provider
Value: /usr/lib64/galera3/libgalera_smm.so
*************************** 28. row ***************************
Variable_name: wsrep_provider_options
Value: base_dir = /var/lib/mysql/; base_host = 10.0.0.71; base_port = 4567; cert.log_conflicts = no; cert.optimistic_pa = yes; debug = no; evs.auto_evict = 0; evs.causal_keepalive_period = PT1S; evs.debug_log_mask = 0x1; evs.delay_margin = PT1S; evs.delayed_keep_period = PT30S; evs.inactive_check_period = PT0.5S; evs.inactive_timeout = PT15S; evs.info_log_mask = 0; evs.install_timeout = PT7.5S; evs.join_retrans_period = PT1S; evs.keepalive_period = PT1S; evs.max_install_timeouts = 3; evs.send_window = 10; evs.stats_report_period = PT1M; evs.suspect_timeout = PT5S; evs.use_aggregate = true; evs.user_send_window = 4; evs.version = 0; evs.view_forget_timeout = P1D; gcache.dir = /var/lib/mysql/; gcache.freeze_purge_at_seqno = -1; gcache.keep_pages_count = 0; gcache.keep_pages_size = 0; gcache.mem_size = 0; gcache.name = /var/lib/mysql//galera.cache; gcache.page_size = 128M; gcache.recover = no; gcache.size = 128M; gcomm.thread_prio = ; gcs.fc_debug = 0; gcs.fc_factor = 1; gcs.fc_limit = 100; gcs.fc_master_slave = no; gc
*************************** 29. row ***************************
Variable_name: wsrep_recover
Value: OFF
*************************** 30. row ***************************
Variable_name: wsrep_reject_queries
Value: NONE
*************************** 31. row ***************************
Variable_name: wsrep_replicate_myisam
Value: OFF
*************************** 32. row ***************************
Variable_name: wsrep_restart_slave
Value: OFF
*************************** 33. row ***************************
Variable_name: wsrep_retry_autocommit
Value: 1
*************************** 34. row ***************************
Variable_name: wsrep_slave_FK_checks
Value: ON
*************************** 35. row ***************************
Variable_name: wsrep_slave_UK_checks
Value: OFF
*************************** 36. row ***************************
Variable_name: wsrep_slave_threads
Value: 8
*************************** 37. row ***************************
Variable_name: wsrep_sst_auth
Value: ********
*************************** 38. row ***************************
Variable_name: wsrep_sst_donor
Value:
*************************** 39. row ***************************
Variable_name: wsrep_sst_donor_rejects_queries
Value: OFF
*************************** 40. row ***************************
Variable_name: wsrep_sst_method
Value: xtrabackup-v2
*************************** 41. row ***************************
Variable_name: wsrep_sst_receive_address
Value: AUTO
*************************** 42. row ***************************
Variable_name: wsrep_start_position
Value: 00000000-0000-0000-0000-000000000000:-1
*************************** 43. row ***************************
Variable_name: wsrep_sync_wait
Value: 0
43 rows in set (0.01 sec)
#查看相关状态变量
mysql> show status like 'wsrep%'\G
*************************** 1. row ***************************
Variable_name: wsrep_local_state_uuid
Value: 19eed63b-0fb0-11eb-97c4-4f01a0c74176
*************************** 2. row ***************************
Variable_name: wsrep_protocol_version
Value: 9
*************************** 3. row ***************************
Variable_name: wsrep_last_applied
Value: 2
*************************** 4. row ***************************
Variable_name: wsrep_last_committed
Value: 2
*************************** 5. row ***************************
Variable_name: wsrep_replicated
Value: 2
*************************** 6. row ***************************
Variable_name: wsrep_replicated_bytes
Value: 544
*************************** 7. row ***************************
Variable_name: wsrep_repl_keys
Value: 2
*************************** 8. row ***************************
Variable_name: wsrep_repl_keys_bytes
Value: 64
*************************** 9. row ***************************
Variable_name: wsrep_repl_data_bytes
Value: 348
*************************** 10. row ***************************
Variable_name: wsrep_repl_other_bytes
Value: 0
*************************** 11. row ***************************
Variable_name: wsrep_received
Value: 2
*************************** 12. row ***************************
Variable_name: wsrep_received_bytes
Value: 151
*************************** 13. row ***************************
Variable_name: wsrep_local_commits
Value: 0
*************************** 14. row ***************************
Variable_name: wsrep_local_cert_failures
Value: 0
*************************** 15. row ***************************
Variable_name: wsrep_local_replays
Value: 0
*************************** 16. row ***************************
Variable_name: wsrep_local_send_queue
Value: 0
*************************** 17. row ***************************
Variable_name: wsrep_local_send_queue_max
Value: 1
*************************** 18. row ***************************
Variable_name: wsrep_local_send_queue_min
Value: 0
*************************** 19. row ***************************
Variable_name: wsrep_local_send_queue_avg
Value: 0.000000
*************************** 20. row ***************************
Variable_name: wsrep_local_recv_queue
Value: 0
*************************** 21. row ***************************
Variable_name: wsrep_local_recv_queue_max
Value: 2
*************************** 22. row ***************************
Variable_name: wsrep_local_recv_queue_min
Value: 0
*************************** 23. row ***************************
Variable_name: wsrep_local_recv_queue_avg
Value: 0.500000
*************************** 24. row ***************************
Variable_name: wsrep_local_cached_downto
Value: 1
*************************** 25. row ***************************
Variable_name: wsrep_flow_control_paused_ns
Value: 0
*************************** 26. row ***************************
Variable_name: wsrep_flow_control_paused
Value: 0.000000
*************************** 27. row ***************************
Variable_name: wsrep_flow_control_sent
Value: 0
*************************** 28. row ***************************
Variable_name: wsrep_flow_control_recv
Value: 0
*************************** 29. row ***************************
Variable_name: wsrep_flow_control_interval
Value: [ 100, 100 ]
*************************** 30. row ***************************
Variable_name: wsrep_flow_control_interval_low
Value: 100
*************************** 31. row ***************************
Variable_name: wsrep_flow_control_interval_high
Value: 100
*************************** 32. row ***************************
Variable_name: wsrep_flow_control_status
Value: OFF
*************************** 33. row ***************************
Variable_name: wsrep_cert_deps_distance
Value: 1.000000
*************************** 34. row ***************************
Variable_name: wsrep_apply_oooe
Value: 0.000000
*************************** 35. row ***************************
Variable_name: wsrep_apply_oool
Value: 0.000000
*************************** 36. row ***************************
Variable_name: wsrep_apply_window
Value: 1.000000
*************************** 37. row ***************************
Variable_name: wsrep_commit_oooe
Value: 0.000000
*************************** 38. row ***************************
Variable_name: wsrep_commit_oool
Value: 0.000000
*************************** 39. row ***************************
Variable_name: wsrep_commit_window
Value: 1.000000
*************************** 40. row ***************************
Variable_name: wsrep_local_state
Value: 4
*************************** 41. row ***************************
Variable_name: wsrep_local_state_comment
Value: Synced
*************************** 42. row ***************************
Variable_name: wsrep_cert_index_size
Value: 1
*************************** 43. row ***************************
Variable_name: wsrep_cert_bucket_count
Value: 22
*************************** 44. row ***************************
Variable_name: wsrep_gcache_pool_size
Value: 1944
*************************** 45. row ***************************
Variable_name: wsrep_causal_reads
Value: 0
*************************** 46. row ***************************
Variable_name: wsrep_cert_interval
Value: 0.000000
*************************** 47. row ***************************
Variable_name: wsrep_open_transactions
Value: 0
*************************** 48. row ***************************
Variable_name: wsrep_open_connections
Value: 0
*************************** 49. row ***************************
Variable_name: wsrep_ist_receive_status
Value:
*************************** 50. row ***************************
Variable_name: wsrep_ist_receive_seqno_start
Value: 0
*************************** 51. row ***************************
Variable_name: wsrep_ist_receive_seqno_current
Value: 0
*************************** 52. row ***************************
Variable_name: wsrep_ist_receive_seqno_end
Value: 0
*************************** 53. row ***************************
Variable_name: wsrep_incoming_addresses
Value: 10.0.0.71:3306
*************************** 54. row ***************************
Variable_name: wsrep_cluster_weight
Value: 1
*************************** 55. row ***************************
Variable_name: wsrep_desync_count
Value: 0
*************************** 56. row ***************************
Variable_name: wsrep_evs_delayed
Value:
*************************** 57. row ***************************
Variable_name: wsrep_evs_evict_list
Value:
*************************** 58. row ***************************
Variable_name: wsrep_evs_repl_latency
Value: 0/0/0/0/0
*************************** 59. row ***************************
Variable_name: wsrep_evs_state
Value: OPERATIONAL
*************************** 60. row ***************************
Variable_name: wsrep_gcomm_uuid
Value: 19ec9903-0fb0-11eb-956e-3e998fb96c10
*************************** 61. row ***************************
Variable_name: wsrep_cluster_conf_id
Value: 1
*************************** 62. row ***************************
Variable_name: wsrep_cluster_size
Value: 1
*************************** 63. row ***************************
Variable_name: wsrep_cluster_state_uuid
Value: 19eed63b-0fb0-11eb-97c4-4f01a0c74176
*************************** 64. row ***************************
Variable_name: wsrep_cluster_status
Value: Primary
*************************** 65. row ***************************
Variable_name: wsrep_connected
Value: ON
*************************** 66. row ***************************
Variable_name: wsrep_local_bf_aborts
Value: 0
*************************** 67. row ***************************
Variable_name: wsrep_local_index
Value: 0
*************************** 68. row ***************************
Variable_name: wsrep_provider_name
Value: Galera
*************************** 69. row ***************************
Variable_name: wsrep_provider_vendor
Value: Codership Oy <info@codership.com>
*************************** 70. row ***************************
Variable_name: wsrep_provider_version
Value: 3.45(ra60e019)
*************************** 71. row ***************************
Variable_name: wsrep_ready
Value: ON
71 rows in set (0.00 sec)
#重点关注下面内容
mysql> show status like 'wsrep%';
+----------------------------------+--------------------------------------+
| Variable_name | Value |
+----------------------------------+--------------------------------------+
| wsrep_local_state_uuid | 19eed63b-0fb0-11eb-97c4-4f01a0c74176 |
.............
.............
| wsrep_local_state | 4 |
| wsrep_local_state_comment | Synced |
.............
| wsrep_cluster_size | 1 |
| wsrep_cluster_state_uuid | 19eed63b-0fb0-11eb-97c4-4f01a0c74176 |
| wsrep_cluster_status | Primary |
| wsrep_connected | ON |
..............
| wsrep_ready | ON |
+----------------------------------+--------------------------------------+
71 rows in set (0.00 sec)
说明：
- wsrep_cluster_size表示，该Galera集群中只有一个节点
- wsrep_local_state_comment 状态为Synced(4)，表示数据已同步完成(因为是第一个引导节点，无数 据需要同步)。 如果状态是Joiner, 意味着 SST 没有完成. 只有所有节点状态是Synced，才可以加新节点
- wsrep_cluster_status为Primary，且已经完全连接并准备好
5 启动PXC集群中其它所有节点
pxc2
[root@72 ~]# ss -ntul
Netid State Recv-Q Send-Q Local Address:Port Peer Address:Port
tcp LISTEN 0 128 *:22 *:*
tcp LISTEN 0 128 [::]:22 [::]:*
[root@72 ~]# systemctl start mysql
[root@72 ~]# ss -ntulp
Netid State Recv-Q Send-Q Local Address:Port Peer Address:Port
tcp LISTEN 0 128 *:22 *:* users:(("sshd",pid=804,fd=3))
tcp LISTEN 0 128 *:4567 *:* users:(("mysqld",pid=2029,fd=11))
tcp LISTEN 0 80 [::]:3306 [::]:* users:(("mysqld",pid=2029,fd=34))
tcp LISTEN 0 128 [::]:22 [::]:* users:(("sshd",pid=804,fd=4))
pxc3
[root@73 ~]# ss -ntul
Netid State Recv-Q Send-Q Local Address:Port Peer Address:Port
tcp LISTEN 0 128 *:22 *:*
tcp LISTEN 0 128 [::]:22 [::]:*
[root@73 ~]# systemctl start mysql
[root@73 ~]# ss -ntulp
Netid State Recv-Q Send-Q Local Address:Port Peer Address:Port
tcp LISTEN 0 128 *:22 *:* users:(("sshd",pid=808,fd=3))
tcp LISTEN 0 128 *:4567 *:* users:(("mysqld",pid=1954,fd=11))
tcp LISTEN 0 128 [::]:22 [::]:* users:(("sshd",pid=808,fd=4))
tcp LISTEN 0 80 [::]:3306 [::]:* users:(("mysqld",pid=1954,fd=34))
6 查看集群状态，验证集群是否成功
pxc1
mysql> show variables like 'wsrep_node_name';
+-----------------+--------------------+
| Variable_name | Value |
+-----------------+--------------------+
| wsrep_node_name | pxc-cluster-node-1 |
+-----------------+--------------------+
1 row in set (0.00 sec)
mysql> show variables like 'wsrep_node_address';
+--------------------+-----------+
| Variable_name | Value |
+--------------------+-----------+
| wsrep_node_address | 10.0.0.71 |
+--------------------+-----------+
1 row in set (0.00 sec)
mysql> show variables like 'wsrep_on';
+---------------+-------+
| Variable_name | Value |
+---------------+-------+
| wsrep_on | ON |
+---------------+-------+
1 row in set (0.00 sec)
mysql> SHOW STATUS LIKE 'wsrep_cluster_size';
+--------------------+-------+
| Variable_name | Value |
+--------------------+-------+
| wsrep_cluster_size | 3 |
+--------------------+-------+
1 row in set (0.00 sec)
7 测试
#在任意节点创建数据库
# pxc1
mysql> create database db1;
Query OK, 1 row affected (0.00 sec)
# pxc2
# 注意：登录密码为pxc1修改的密码
[root@72 ~]# mysql -uroot -p123456;history -c
mysql: [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 13
Server version: 5.7.31-34-57-log Percona XtraDB Cluster (GPL), Release rel34, Revision 7359e4f, WSREP version 31.45, wsrep_31.45
Copyright (c) 2009-2020 Percona LLC and/or its affiliates
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> show databases;
+--------------------+
| Database |
+--------------------+
| information_schema |
| db1 |
| mysql |
| performance_schema |
| sys |
+--------------------+
5 rows in set (0.00 sec)
# pxc3
[root@72 ~]# mysql -uroot -p123456;history -c
mysql: [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 14
Server version: 5.7.31-34-57-log Percona XtraDB Cluster (GPL), Release rel34, Revision 7359e4f, WSREP version 31.45, wsrep_31.45
Copyright (c) 2009-2020 Percona LLC and/or its affiliates
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> show databases;
+--------------------+
| Database |
+--------------------+
| information_schema |
| db1 |
| mysql |
| performance_schema |
| sys |
+--------------------+
5 rows in set (0.00 sec)
#利用Xshell软件，同时在三个节点数据库创建数据库，在其中一个节点成功
# pxc2
mysql> create database db2;
ERROR 1007 (HY000): Can't create database 'db2'; database exists
mysql>
# pxc1
mysql> create database db2;
Query OK, 1 row affected (0.01 sec)
# pxc3
mysql> create database db2;
ERROR 1007 (HY000): Can't create database 'db2'; database exists
8 在PXC集群中加入节点
一个节点加入到Galera集群有两种情况：新节点加入集群、暂时离组的成员再次加入集群
1）新节点加入Galera集群
新节点加入集群时，需要从当前集群中选择一个Donor节点来同步数据，也就是所谓的 state_snapshot_tranfer(SST)过程。SST同步数据的方式由选项wsrep_sst_method决定，一般选择的 是xtrabackup。 必须注意，新节点加入Galera时，会删除新节点上所有已有数据，再通过xtrabackup(假设使用的是该 方式)从Donor处完整备份所有数据进行恢复。所以，如果数据量很大，新节点加入过程会很慢。而且， 在一个新节点成为Synced状态之前，不要同时加入其它新节点，否则很容易将集群压垮。 如果是这种情况，可以考虑使用wsrep_sst_method=rsync来做增量同步，既然是增量同步，最好保证 新节点上已经有一部分数据基础，否则和全量同步没什么区别，且这样会对Donor节点加上全局read only锁。
2）旧节点加入Galera集群
如果旧节点加入Galera集群，说明这个节点在之前已经在Galera集群中呆过，有一部分数据基础，缺少 的只是它离开集群时的数据。这时加入集群时，会采用IST(incremental snapshot transfer)传输机制， 即使用增量传输。 但注意，这部分增量传输的数据源是Donor上缓存在GCache文件中的，这个文件有大小限制，如果缺 失的数据范围超过已缓存的内容，则自动转为SST传输。如果旧节点上的数据和Donor上的数据不匹配 (例如这个节点离组后人为修改了一点数据)，则自动转为SST传输。
#在PXC集群中再加一台新的主机PXC4：10.0.0.37
[root@74 ~]# cat /etc/percona-xtradb-cluster.conf.d/mysqld.cnf | grep -v "^#"
[client]
socket=/var/lib/mysql/mysql.sock
[mysqld]
server-id=74
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
log-error=/var/log/mysqld.log
pid-file=/var/run/mysqld/mysqld.pid
log-bin
log_slave_updates
expire_logs_days=7
symbolic-links=0
[root@74 ~]# cat /etc/percona-xtradb-cluster.conf.d/wsrep.cnf | grep -v "^#"
[mysqld]
wsrep_provider=/usr/lib64/galera3/libgalera_smm.so
wsrep_cluster_address=gcomm://10.0.0.71,10.0.0.72,10.0.0.73,10.0.0.74
binlog_format=ROW
default_storage_engine=InnoDB
wsrep_slave_threads= 8
wsrep_log_conflicts
innodb_autoinc_lock_mode=2
wsrep_node_address=10.0.0.74
wsrep_cluster_name=pxc-cluster
wsrep_node_name=pxc-cluster-node-4
pxc_strict_mode=ENFORCING
wsrep_sst_method=xtrabackup-v2
wsrep_sst_auth="sstuser:s3cretPass"
# 启动服务
[root@74 ~]# systemctl restart mysql
[root@74 ~]# ss -ntulp
Netid State Recv-Q Send-Q Local Address:Port Peer Address:Port
tcp LISTEN 0 128 *:22 *:* users:(("sshd",pid=807,fd=3))
tcp LISTEN 0 128 *:4567 *:* users:(("mysqld",pid=15095,fd=11))
tcp LISTEN 0 128 [::]:22 [::]:* users:(("sshd",pid=807,fd=4))
tcp LISTEN 0 80 [::]:3306 [::]:* users:(("mysqld",pid=15095,fd=35))
# 登录数据库
[root@74 ~]# mysql -uroot -p123456
mysql: [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 11
Server version: 5.7.31-34-57-log Percona XtraDB Cluster (GPL), Release rel34, Revision 7359e4f, WSREP version 31.45, wsrep_31.45
Copyright (c) 2009-2020 Percona LLC and/or its affiliates
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> show status like 'wsrep_cluster_size';
+--------------------+-------+
| Variable_name | Value |
+--------------------+-------+
| wsrep_cluster_size | 4 |
+--------------------+-------+
1 row in set (0.00 sec)
mysql> show databases;
+--------------------+
| Database |
+--------------------+
| information_schema |
| db1 |
| db2 |
| mysql |
| performance_schema |
| sys |
+--------------------+
6 rows in set (0.00 sec)
# 将其它节点的配置文件加以修改
# pxc3
[root@73 ~]# sed -ri '/^wsrep_cluster_address/s#(.*)#\1,10.0.0.74#' /etc/percona-xtradb-cluster.conf.d/wsrep.cnf
[root@73 ~]# cat /etc/percona-xtradb-cluster.conf.d/wsrep.cnf | grep -v "^#"
[mysqld]
wsrep_provider=/usr/lib64/galera3/libgalera_smm.so
wsrep_cluster_address=gcomm://10.0.0.71,10.0.0.72,10.0.0.73,10.0.0.74
binlog_format=ROW
default_storage_engine=InnoDB
wsrep_slave_threads= 8
wsrep_log_conflicts
innodb_autoinc_lock_mode=2
wsrep_node_address=10.0.0.73
wsrep_cluster_name=pxc-cluster
wsrep_node_name=pxc-cluster-node-3
pxc_strict_mode=ENFORCING
wsrep_sst_method=xtrabackup-v2
wsrep_sst_auth="sstuser:s3cretPass"
# pxc2
[root@72 ~]# sed -ri '/^wsrep_cluster_address/s#(.*)#\1,10.0.0.74#' /etc/percona-xtradb-cluster.conf.d/wsrep.cnf
# pxc1
[root@71 data]# sed -ri '/^wsrep_cluster_address/s#(.*)#\1,10.0.0.74#' /etc/percona-xtradb-cluster.conf.d/wsrep.cnf
9 在PXC集群中修复故障节点
#在任意节点停止服务
# pxc3
[root@73 ~]# systemctl stop mysql
# pxc2
mysql> show status like 'wsrep_cluster_size';
+--------------------+-------+
| Variable_name | Value |
+--------------------+-------+
| wsrep_cluster_size | 3 |
+--------------------+-------+
1 row in set (0.01 sec)
# pxc1
mysql> show status like 'wsrep_cluster_size';
+--------------------+-------+
| Variable_name | Value |
+--------------------+-------+
| wsrep_cluster_size | 3 |
+--------------------+-------+
1 row in set (0.00 sec)
# 创建数据库
# pxc4
mysql> create database db3;
Query OK, 1 row affected (0.00 sec)
# pxc2
mysql> show databases;
+--------------------+
| Database |
+--------------------+
| information_schema |
| db1 |
| db2 |
| db3 |
| mysql |
| performance_schema |
| sys |
+--------------------+
7 rows in set (0.00 sec)
# pxc3开启服务
[root@73 ~]# systemctl start mysql
[root@73 ~]# mysql -uroot -p123456
mysql: [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 11
Server version: 5.7.31-34-57-log Percona XtraDB Cluster (GPL), Release rel34, Revision 7359e4f, WSREP version 31.45, wsrep_31.45
Copyright (c) 2009-2020 Percona LLC and/or its affiliates
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> show databases;
+--------------------+
| Database |
+--------------------+
| information_schema |
| db1 |
| db2 |
| db3 |
| mysql |
| performance_schema |
| sys |
+--------------------+
7 rows in set (0.00 sec)
# 数据已同步
5、通过 ansible 部署二进制 mysql 8
实验环境准备
| 虚拟机 | IP | |
|---|---|---|
| centos81 | 10.0.0.81 | ansible服务器主控端 |
| centos82 | 10.0.0.82 | 远程主机1 |
| centos83 | 10.0.0.83 | 远程主机2 |
前期准备
1、关闭防火墙：systemctl disable --now firewalld
2、关闭selinux安全机制: sed -ri 's/(^SELINUX=).*/\1disabled/' /etc/selinux/config
3、重启生效：init 6
1、安装ansible
使用EPEL源的rpm包安装
# 使用阿里云镜像站的eple源：https://developer.aliyun.com/mirror/epel?spm=a2c6h.13651102.0.0.3e221b11pyj3r4
# 1、如果之前配置了epel源，则先备份；如果没有就跳过这步
[root@81 ~]# mv /etc/yum.repos.d/epel.repo /etc/yum.repos.d/epel.repo.backup
[root@81 ~]# mv /etc/yum.repos.d/epel-testing.repo /etc/yum.repos.d/epel-testing.repo.backup
# 2. 下载新repo 到/etc/yum.repos.d/
1）安装 epel 配置包
[root@81 ~]# yum install -y https://mirrors.aliyun.com/epel/epel-release-latest-8.noarch.rpm
2）将 repo 配置中的地址替换为阿里云镜像站地址
[root@81 ~]# sed -i 's|^#baseurl=https://download.fedoraproject.org/pub|baseurl=https://mirrors.aliyun.com|' /etc/yum.repos.d/epel*
[root@81 ~]# sed -i 's|^metalink|#metalink|' /etc/yum.repos.d/epel*
# 安装ansible
[root@81 ~]# yum -y install ansible
[root@81 ~]# ansible --version
ansible 2.9.14
config file = /etc/ansible/ansible.cfg
configured module search path = ['/root/.ansible/plugins/modules', '/usr/share/ansible/plugins/modules']
ansible python module location = /usr/lib/python3.6/site-packages/ansible
executable location = /usr/bin/ansible
python version = 3.6.8 (default, Apr 16 2020, 01:36:27) [GCC 8.3.1 20191121 (Red Hat 8.3.1-5)]
2、修改ansible配置文件
# /etc/ansible/ansible.cfg
[root@81 data]# vim /etc/ansible/ansible.cfg
[defaults]
host_key_checking = False # 解开注释
# /etc/ansible/hosts
# 直接设置ssh连接，用户名，密码，执行yaml脚本就不需要加 -k
[root@81 data]# vim /etc/ansible/hosts
[webservser]
10.0.0.81 ansible_connection=local
10.0.0.82 ansible_connection=ssh ansible_user=root ansible_password=123456
10.0.0.83 ansible_connection=ssh ansible_user=root ansible_password=123456
3、准备mysql相关文件
# my.cnf 配置文件
[root@81 data]# cat my.cnf
[mysqld]
# 指定数据库数据存放路径
datadir=/data/mysql
# 指定套间字路径
socket=/data/mysql/mysql.sock
# 设置日志文件路径
log-error=/data/mysql/mysqld.log
#关闭DNS反向解析
skip_name_resolve=on
port=3306
#pid-file=/tmp/mysql.pid
[client]
port=3306
# 指定套间字路径
socket=/data/mysql/mysql.sock
# passwd.sh 修改mysql密码
[root@81 data]# vim passwd.sh
pwd=`awk '/temporary password/{print $NF}' /data/mysql/mysqld.log`
mysqladmin -uroot -p"$pwd" password 12345678
4、编辑yaml脚本
[root@81 data]# vim install_mysql.yml
- hosts: all
remote_user: root
gather_facts: no
vars:
- path: https://dev.mysql.com/get/Downloads/MySQL-8.0/mysql-8.0.21-linux-glibc2.17-x86_64-minimal.tar.xz
tasks:
- name: "关闭初次访问提示询问"
shell: sed -i "s/^.*StrictHostKeyChecking.*$/ StrictHostKeyChecking no/g" /etc/ssh/ssh_config
- name: "删除ssh文件"
file: path=/root/.ssh/ state=absent
- name: "生成公钥私钥对"
shell: ssh-keygen -t rsa -b 2048 -N '' -f /root/.ssh/id_rsa
- name: "删除临时ssh目录"
file: path=/tmp/ssh/ state=absent
run_once: true
- name: "从各宿主机将公钥拷贝到本机"
fetch: src=/root/.ssh/id_rsa.pub dest=/tmp/ssh/
- name: "将各个公钥合并成一个文件"
shell: find /tmp/ssh/* -type f -exec sh -c 'cat { }>>/tmp/ssh/authorized_keys.log' \;
run_once: true
- name: "将合成的公钥进行分发"
copy: src=/tmp/ssh/authorized_keys.log dest=/root/.ssh/authorized_keys mode=0600
tags:
- install ssh
- name: "安装依赖库"
yum: name=libaio,ncurses-compat-libs
- name: "创建组"
group: name=mysql gid=306
- name: "创建用户"
user: name=mysql uid=306 group=mysql shell=/sbin/nologin system=yes create_home=no home=/data/mysql
- name: "创建数据文件"
file: path=/data/mysql state=directory owner=mysql group=mysql recurse=yes
- name: "下载wget"
yum: name=wget state=latest
- name: "下载mysql8.0二进制安装包"
shell: wget -P /data/ { { path }}
- name: "解压缩包到指定目录：/use/local/"
shell: find /data/ -name "*8.0*" | awk -F"/" "{ print $3}" | xargs -I { } tar xf { } -C /usr/local/
- name: "创建MySQL软连接"
shell: find /usr/local/ -maxdepth 1 -type d -name "mysql*" -exec ln -s { } /usr/local/mysql \;
- name: "修改连接权限"
file: dest=/usr/local/mysql owner=root group=root recurse=yes state=directory
- name: "修改MySQL配置文件"
copy: src=/data/my.cnf dest=/etc/ backup=yes
- name: "初始化数据库"
shell: chdir=/usr/local/mysql bin/mysqld --initialize --datadir=/data/mysql --user=mysql
- name: "将mysql添加到服务"
copy: src=/usr/local/mysql/support-files/mysql.server dest=/etc/init.d/mysqld
- name: "设置开机自启"
shell: chkconfig --add mysqld;chkconfig mysqld on
- name: "创建mysql运行软连接"
shell: ln -s /usr/local/mysql/bin/* /usr/bin/
- name: secure script
script: /data/passwd.sh
tags: script
- name: "启动mysql服务"
service: name=mysqld state=started
5、执行脚本
[root@81 data]# ansible-playbook install_mysql.yml
[root@81 ~]# ansible-playbook /data/install_mysql.yml
PLAY [all] *****************************************************************************************
TASK [关闭初次访问提示询问] **********************************************************************************
[WARNING]: Consider using the replace, lineinfile or template module rather than running 'sed'. If
you need to use command because replace, lineinfile or template is insufficient you can add 'warn:
false' to this command task or set 'command_warnings=False' in ansible.cfg to get rid of this
message.
changed: [10.0.0.81]
changed: [10.0.0.82]
changed: [10.0.0.83]
TASK [删除ssh文件] *************************************************************************************
changed: [10.0.0.81]
ok: [10.0.0.82]
ok: [10.0.0.83]
TASK [生成公钥私钥对] *************************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.82]
changed: [10.0.0.83]
TASK [删除临时ssh目录] ***********************************************************************************
ok: [10.0.0.81]
TASK [从各宿主机将公钥拷贝到本机] *******************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.83]
changed: [10.0.0.82]
TASK [将各个公钥合并成一个文件] ********************************************************************************
changed: [10.0.0.81]
TASK [将合成的公钥进行分发] **********************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.82]
changed: [10.0.0.83]
TASK [安装依赖库] ***************************************************************************************
changed: [10.0.0.83]
changed: [10.0.0.81]
changed: [10.0.0.82]
TASK [创建组] *****************************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.82]
changed: [10.0.0.83]
TASK [创建用户] ****************************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.82]
changed: [10.0.0.83]
TASK [创建数据文件] **************************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.83]
changed: [10.0.0.82]
TASK [下载wget] **************************************************************************************
ok: [10.0.0.81]
ok: [10.0.0.82]
ok: [10.0.0.83]
TASK [下载mysql8.0二进制安装包] ****************************************************************************
[WARNING]: Consider using the get_url or uri module rather than running 'wget'. If you need to use
command because get_url or uri is insufficient you can add 'warn: false' to this command task or
set 'command_warnings=False' in ansible.cfg to get rid of this message.
changed: [10.0.0.83]
changed: [10.0.0.81]
changed: [10.0.0.82]
TASK [解压缩包到指定目录：/use/local/] ***********************************************************************
changed: [10.0.0.81]
changed: [10.0.0.83]
changed: [10.0.0.82]
TASK [创建MySQL软连接] **********************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.83]
changed: [10.0.0.82]
TASK [修改连接权限] **************************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.83]
changed: [10.0.0.82]
TASK [修改MySQL配置文件] *********************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.83]
changed: [10.0.0.82]
TASK [初始化数据库] **************************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.83]
changed: [10.0.0.82]
TASK [将mysql添加到服务] *********************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.83]
changed: [10.0.0.82]
TASK [设置开机自启] **************************************************************************************
changed: [10.0.0.81]
changed: [10.0.0.83]
changed: [10.0.0.82]
TASK [创建mysql运行软连接] ********************************************************************************
[WARNING]: Consider using the file module with state=link rather than running 'ln'. If you need to
use command because file is insufficient you can add 'warn: false' to this command task or set
'command_warnings=False' in ansible.cfg to get rid of this message.
changed: [10.0.0.81]
changed: [10.0.0.83]
changed: [10.0.0.82]
TASK [启动mysql服务] ***********************************************************************************
changed: [10.0.0.82]
changed: [10.0.0.83]
changed: [10.0.0.81]
PLAY RECAP *****************************************************************************************
10.0.0.81 : ok=22 changed=20 unreachable=0 failed=0 skipped=0 rescued=0 ignored=0
10.0.0.82 : ok=20 changed=18 unreachable=0 failed=0 skipped=0 rescued=0 ignored=0
10.0.0.83 : ok=20 changed=18 unreachable=0 failed=0 skipped=0 rescued=0 ignored=0
