CentOS下编写shell脚本来监控MySQL主从复制的教程

这篇文章主要介绍了在CentOS系统下编写shell脚本来监控主从复制的教程,文中举了两个发现故障后再次执行复制命令的例子,需要的朋友可以参考下

目的：定时监控MySQL主从数据库是否同步，如果不同步，记录故障时间，并执行命令使主从恢复同步状态

1、创建脚本文件

vi /home/crontab/check_mysql_slave.sh  #编辑，添加下面代码

#!/bin/sh
 
# check_mysql_slave status
 
ip=eth0 #网卡名称
 
mysql_binfile=/usr/local/mysql/bin/mysql
 
mysql_user=root #MySQL数据库账号
 
mysql_pass=123456 #密码
 
mysql_sockfile=/tmp/mysql.sock
 
datetime=`date +"%Y-%m-%d/%H:%M:%S"`  #获取当前时间
 
mysql_slave_logfile=/home/logs/check_mysql_slave.log  #日志文件路径，必须提前创建好
 
slave_ip=`ifconfig $ip|grep "inet addr" | awk -F[:" "]+ '{print $4}'`
 
status=$($mysql_binfile -u$mysql_user -p$mysql_pass -S $mysql_sockfile -e "show slave status\G" | grep -i "running")
 
Slave_IO_Running=`echo $status | grep Slave_IO_Running | awk ' {print $2}'`
 
Slave_SQL_Running=`echo $status | grep Slave_SQL_Running | awk '{print $2}'`
 
if [ "$Slave_IO_Running" = "Yes" -a "$Slave_SQL_Running" = "Yes" ]
 
then echo "Slave is Running!"
 
else
 
echo " $datetime $slave_ip Slave is not running!" >> $mysql_slave_logfile
 
$mysql_binfile -u$mysql_user -p$mysql_pass -S $mysql_sockfile -e "SLAVE STOP;"
 
$mysql_binfile -u$mysql_user -p$mysql_pass -S $mysql_sockfile -e "SET GLOBAL SQL_SLAVE_SKIP_COUNTER=1;"
 
$mysql_binfile -u$mysql_user -p$mysql_pass -S $mysql_sockfile -e "SLAVE START;"
 
$mysql_binfile -u$mysql_user -p$mysql_pass -S $mysql_sockfile -e "EXIT"
 
fi

:wq! #保存退出
 
chmod +x /home/crontab/check_mysql_slave.sh #添加脚本执行权限

2、添加任务计划，修改/etc/crontab

vi /etc/crontab #在最后一行添加
 
*/10 * * * * root /home/crontab/check_mysql_slave.sh #表示每10分钟执行一次
 
:wq! #保存退出

3、重新启动crond使设置生效

/etc/rc.d/init.d/crond restart  #yum install -y vixie-cron安装计划任务，某些系统上可能没有预装
 
chkconfig crond on #设为开机启动
 
service crond start #启动

可以根据日志文件/home/logs/check_mysql_slave.log查看MySQL主从同步状态

PS：接下来这个脚本增加了“当发现同步出现无法同步的时候”会自动提取主库的file号，以及pos,进行同步主库，脚本内容如下：

#!/bin/sh
#set -x
#file is slave_repl.sh
#Author by Kevin
#date is 2011-11-13
 
mstool="/usr/local/mysql-3307/bin/mysql -h 192.168.1.106 -uroot -pw!zl7POg27 -P 3307"
sltool="/usr/local/mysql-3307/bin/mysql -h 192.168.1.107 -uroot -pw!zl7POg27 -P 3307"
declare -a slave_stat
slave_stat=($($sltool -e "show slave status\G"|grep Running |awk '{print $2}'))
if [ "${slave_stat[0]}" = "Yes" -a "${slave_stat[1]}" = "Yes" ]
   then
   echo "OK slave is running"
   exit 0
else
   echo "Critical slave is error"
   echo
   echo "*********************************************************"
   echo "Now Starting replication with Master Mysql!"
    file=`$mstool -e "show master status\G"|grep "File"|awk '{print $2}'`
    pos=`$mstool -e "show master status\G"|grep "Pos"|awk '{print $2}'`
    $sltool -e "slave stop;change master to master_host='192.168.1.106',master_port=3307,master_user='repl',master_password='w!zl7POg27',master_log_file='$file',master_log_pos=$pos;slave start;"
    sleep 3
    $sltool -e "show slave status\G;"|grep Running
  echo
  echo "Now Replication is Finished!"
  echo
  echo "**********************************************************"
    exit 2
fi

 
运行后效果，如下：
 

# ./slave_stop3307.sh
*******************************
Now stop Slave Replication!
      Slave_IO_Running: No
     Slave_SQL_Running: No
*******************************
# ./slave_repl3307.sh
Critical slave is error
*********************************************************
Now Starting replication with Master Mysql!
      Slave_IO_Running: Yes
     Slave_SQL_Running: Yes
Now Replication is Finished!
**********************************************************