MHA高可用搭建

1.准备环境

主机名	IP地址	角色
db01	172.16.1.51	master
db02	172.16.1.52	slave1、candidate_master
db03	172.16.1.53	slave2、manager

2.安装数据库

[root@db01 ~]# yum install mariadb-server -y
[root@db02 ~]# yum install mariadb-server -y
[root@db03 ~]# yum install mariadb-server -y

3.修改数据库配置文件

#master节点配置
[root@db01 ~]# vim /etc/my.cnf
skip_name_resolve = ON
innodb_file_per_table = ON
server-id = 1               #复制集群中的各节点的id均必须唯一
log-bin = mysql-bin         #开启二进制日志
relay-log = relay-log       #开启中继日志

#slave节点配置
[root@db02 ~]# vim /etc/my.cnf
skip_name_resolve = ON
innodb_file_per_table = ON
server-id = 2             
log-bin = mysql-bin       
relay-log = relay-log     
#read_only = ON			 #不在配置文件中限定只读，但是要记得在slave上限制只读
relay_log_purge = 0       #禁用自动清空不再需要中继日志
log_slave_updates = 1     #使得更新的数据写进二进制日志中

[root@db03 ~]# vim /etc/my.cnf
skip_name_resolve = ON
innodb_file_per_table = ON
server-id = 3            
log-bin = mysql-bin       
relay-log = relay-log     
#read_only = ON			
relay_log_purge = 0       
log_slave_updates = 1     


#配置完成后，启动数据库(3个节点)
[root@db01 ~]# systemctl restart mariadb

4.配置一主多从复制架构

#master节点
MariaDB [(none)]> grant replication slave on *.* to 'slave'@'172.16.1.%' identified by '123456';
Query OK, 0 rows affected (0.00 sec)

MariaDB [(none)]> grant all on *.* to 'mhaadmin'@'172.16.1.%' identified by 'mhapass';   #很重要
Query OK, 0 rows affected (0.00 sec)

MariaDB [(none)]> show master status;
+------------------+----------+--------------+------------------+
| File             | Position | Binlog_Do_DB | Binlog_Ignore_DB |
+------------------+----------+--------------+------------------+
| mysql-bin.000003 |      397 |              |                  |
+------------------+----------+--------------+------------------+
1 row in set (0.00 sec)


#slave节点（2个）
MariaDB [(none)]> set global read_only=1;		#设置只读（防止意外被写数据，很重要）
Query OK, 0 rows affected (0.00 sec)

MariaDB [(none)]> change master to
    -> master_host='172.16.1.51',
    -> master_user='slave',
    -> master_password='123456',
    -> master_log_file='mysql-bin.000003',
    -> master_log_pos=397;
Query OK, 0 rows affected (0.10 sec)

change master to master_host='172.16.1.51',master_user='slave',master_password='123456',master_log_file='mysql-bin.000003',master_log_pos=397;

MariaDB [(none)]> start slave;
Query OK, 0 rows affected (0.00 sec)

MariaDB [(none)]> show slave status\G
*************************** 1. row ***************************
               Slave_IO_State: Waiting for master to send event
                  Master_Host: 172.16.1.51
                  Master_User: slave
                  Master_Port: 3306
                Connect_Retry: 60
              Master_Log_File: mysql-bin.000003
          Read_Master_Log_Pos: 397
               Relay_Log_File: relay-log.000002
                Relay_Log_Pos: 529
        Relay_Master_Log_File: mysql-bin.000003
             Slave_IO_Running: Yes
            Slave_SQL_Running: Yes
              Replicate_Do_DB: 
          Replicate_Ignore_DB: 
           Replicate_Do_Table: 
       Replicate_Ignore_Table: 
      Replicate_Wild_Do_Table: 
  Replicate_Wild_Ignore_Table: 
                   Last_Errno: 0
                   Last_Error: 
                 Skip_Counter: 0
          Exec_Master_Log_Pos: 397
              Relay_Log_Space: 817
              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.MHA基本环境准备

1）配置三台机器的ssh互信（三台都要操作）

ssh-keygen -t rsa
ssh-copy-id -i /root/.ssh/id_rsa.pub root@172.16.1.51
ssh-copy-id -i /root/.ssh/id_rsa.pub root@172.16.1.52
ssh-copy-id -i /root/.ssh/id_rsa.pub root@172.16.1.53

#或者使用免密、免验证登录
sshpass -p1  ssh-copy-id -i /root/.ssh/id_rsa.pub -o StrictHostKeyChecking=no root@172.16.1.51

2）安装依赖

yum install -y perl perl-DBI perl-DBD-MySQL perl-IO-Socket-SSL perl-Config-Tiny perl-Log-Dispatch perl-Parallel-ForkManager perl-Time-HiRes

3）安装MHA

#三个节点都需安装 mha4mysql-node
yum install -y mha4mysql-node-0.56-0.el6.noarch.rpm

#manager(db03)节点需要在安装 mha4mysql-manager
yum install -y mha4mysql-manager-0.56-0.el6.noarch.rpm

6.配置MHA（在manager节点上操作，即db03）

1）创建目录

mkdir -p /etc/mha/scripts
mkdir -p /var/log/mha/app1

2）配置mha配置文件

[root@db03 ~]# vim /etc/mha/app1.cnf
[server default]
manager_log=/var/log/mha/app1/manager.log		#设置manager的日志
manager_workdir=/var/log/mha/app1				#设置manager的工作目录
master_binlog_dir=/var/lib/mysql				#设置master 保存binlog的位置
master_ip_failover_script= /etc/mha/scripts/master_ip_failover    #设置自动failover时候的切换脚本
master_ip_online_change_script=/etc/mha/scripts/master_ip_online_change 
                                                                       #设置手动切换时候的切换脚本
user=mhaadmin
password=mhapass
ssh_user=root
repl_password=123456
repl_user=slave						#设置复制环境中的复制用户名
ping_interval=1						#发送ping包的时间间隔

[server1]
hostname=172.16.1.51
port=3306

[server2]
hostname=172.16.1.52
port=3306
candidate_master=1				#设置为候选master，如果设置该参数以后，发生主从切换以后将会将此从库提升为							    主库
check_repl_delay=0				#默认情况下如果一个slave落后master 100M的relay logs的话，MHA将不会选择该slave作为一个新的master，因为对于这个slave的恢复需要花费很长时间，通过设置check_repl_delay=0,MHA触发切换在选择一个新的master的时候将会忽略复制延时，这个参数对于设置了candidate_master=1的主机非常有用，因为这个候选主在切换的过程中一定是新的master

[server3]
hostname=172.16.1.53
port=3306

7.配置VIP（manager节点）

1）自动failover脚本 “/etc/mha/scripts/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 = '172.16.1.59/24';
my $key = '1';
my $ssh_start_vip = "/sbin/ifconfig eth1:$key $vip";
my $ssh_stop_vip = "/sbin/ifconfig eth1:$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";
        exit 0;
    }
    else {
        &usage();
        exit 1;
    }
}

sub start_vip() {
    `ssh $ssh_user\@$new_master_host \" $ssh_start_vip \"`;
}
sub stop_vip() {
     return 0  unless  ($ssh_user);
    `ssh $ssh_user\@$orig_master_host \" $ssh_stop_vip \"`;
}

sub usage {
    print
    "Usage: master_ip_failover --command=start|stop|stopssh|status --orig_master_host=host --orig_master_ip=ip --orig_master_port=port --new_master_host=host --new_master_ip=ip --new_master_port=port\n";
}

2）手动 failover “/etc/mha/scripts/master_ip_online_change”

#!/bin/bash
source /root/.bash_profile
vip=`echo '172.16.1.59/24'`  #设置VIP
key=`echo '1'`

command=`echo "$1" | awk -F = '{print $2}'`
orig_master_host=`echo "$2" | awk -F = '{print $2}'`
new_master_host=`echo "$7" | awk -F = '{print $2}'`
orig_master_ssh_user=`echo "${12}" | awk -F = '{print $2}'`
new_master_ssh_user=`echo "${13}" | awk -F = '{print $2}'`

#要求服务的网卡识别名一样，都为eth1(这里是)
stop_vip=`echo "ssh root@$orig_master_host /usr/sbin/ifconfig eth1:$key down"`
start_vip=`echo "ssh root@$new_master_host /usr/sbin/ifconfig eth1:$key $vip"`

if [ $command = 'stop' ]
	 then
	  echo -e "\n\n\n****************************\n"
	   echo -e "Disabled thi VIP - $vip on old master: $orig_master_host \n"
	   $stop_vip
	   if [ $? -eq 0 ]
	     then
		echo "Disabled the VIP successfully"
	      else
		echo "Disabled the VIP failed"
	    fi
	    echo -e "***************************\n\n\n"
	  fi

if [ $command = 'start' -o $command = 'status' ]
	  then
	    echo -e "\n\n\n*************************\n"
	    echo -e "Enabling the VIP - $vip on new master: $new_master_host \n"
	    $start_vip
	    if [ $? -eq 0 ]
	      then
		echo "Enabled the VIP successfully"
	      else
		echo "Enabled the VIP failed"
	   fi
	   echo -e "***************************\n\n\n"
fi

3）将脚本赋予可执行权限

chmod +x /etc/mha/scripts/master_ip_failover 
chmod +x /etc/mha/scripts/master_ip_online_change

8.通过 masterha_check_ssh 验证 ssh 信任登录是否成功

[root@db03 ~]# masterha_check_ssh --conf=/etc/mha/app1.cnf
Wed Apr 16 23:17:58 2020 -  All SSH connection tests passed successfully.		#表示所有都成功

9.通过 masterha_check_repl 验证 mysql 主从复制是否成功（下面输出表示测试通过）

[root@db03 ~]# masterha_check_repl --conf=/etc/mha/app1.cnf
IN SCRIPT TEST====/sbin/ifconfig eth1:1 down==/sbin/ifconfig eth1:1 172.16.1.59/24===
Checking the Status of the script.. OK 
Wed Apr 16 27:15:58 2020 -   OK.
Wed Apr 16 27:15:58 2020 -  shutdown_script is not defined.
Wed Apr 16 27:15:58 2020 -  Got exit code 0 (Not master dead).
MySQL Replication Health is OK.

注意：
#报错一：
Wed Apr  1 17:47:34 2020 - [error][/usr/share/perl5/vendor_perl/MHA/ServerManager.pm, ln301] Got MySQL error when connecting 172.16.1.53(172.16.1.53:3306) :1130:Host '172.16.1.53' is not allowed to connect to this MariaDB server, but this is not a MySQL crash. Check MySQL server settings.
解决方案：
去master节点，给mhaadmin重新授权
grant all on *.* to 'mhaadmin'@'172.16.1.%' identified by 'mhapass';

#报错二：
Wed Apr  1 17:48:05 2020 - [error][/usr/share/perl5/vendor_perl/MHA/Server.pm, ln393] 172.16.1.52(172.16.1.52:3306): User slave does not exist or does not have REPLICATION SLAVE privilege! Other slaves can not start replication from this host.
解决方案：
去master节点，给slave重新授权
grant replication slave on *.* to 'slave'@'172.16.1.%' identified by '123456';

#报错三：
Wed Apr  1 22:32:16 2020 - [info]   /etc/mha/scripts/master_ip_failover --command=status --ssh_user=root --orig_master_host=172.16.1.51 --orig_master_ip=172.16.1.51 --orig_master_port=3306 
Wed Apr  1 22:32:16 2020 - [error][/usr/share/perl5/vendor_perl/MHA/MasterMonitor.pm, ln424] Error happened on checking configurations. Can't exec "/etc/mha/scripts/master_ip_failover": Permission denied at /usr/share/perl5/vendor_perl/MHA/ManagerUtil.pm line 68.
解决方案：
可以看到，上面提示脚本文件/etc/mha/scripts/master_ip_failover权限不足，
chmod +x /etc/mha/scripts/*

10.启动MHA**（注意：MHA监控脚本切换一次就会退出，需要再次启动）**

1）先在master上绑定vip，(只需要在master绑定这一次，以后会自动切换)

[root@db01 ~]# /usr/sbin/ifconfig eth1:1 172.16.1.59/24

2）然后通过 masterha_manager 启动 MHA 监控

#启动mha
[root@db03 ~]# nohup masterha_manager --conf=/etc/mha/app1.cnf --remove_dead_master_conf --ignore_last_failover < /dev/null > /var/log/mha/app1/manager.log 2>&1 &

#关闭mha
[root@db03 ~]# masterha_stop --conf=/etc/masterha/app1.cnf

#检查MHA的启动状态
[root@db03 ~]# tailf /var/log/mha/app1/manager.log

#如果最后一行是如下，表明启动成功
Ping(SELECT) succeeded, waiting until MySQL doesn’t respond..

3）检查集群状态

[root@db03 ~]# masterha_check_status --conf=/etc/mha/app1.cnf
mha (pid:7598) is running(0:PING_OK), master:172.16.1.51

#注：上面的信息中“mha (pid:7598) is running(0:PING_OK)”表示MHA服务运行OK，否则， 则会显示为类似“mha is stopped(1:NOT_RUNNING).”