对于MySQL数据库主从复制延迟的监控，我们可以借助percona的有力武器pt-heartbeat来实现。pt-heartbeat通过使用时间戳方式在主库上更新特定表，然后在从库上读取被更新的时间戳然后与本地系统时间对比来得出其延迟。本文主要是通过脚本来定期检查从库与主库复制的延迟度并发送邮件，供大家参考。

有关pt-heartbeat工具的安装可以参考：percona-toolkit的安装及简介

1、脚本概述

2、脚本内容

[mysql@SZDB run]$ more ck_slave_lag.sh 
#!/bin/bash
#set -x
if [ $# -ne 3 ];then
      echo "usage:"
      echo "ck_slave_lag.sh <Servier-id> <MaxLag> <LogDir>"
      exit 0;
fi

# Author : Leshami
# Blog   : http://blog.csdn.net/leshami

ServerID=$1
MaxLag=$2
LogDir=$3
Timestamp=`date +%Y%m%d_%H%M%S`
Rentition=7
LogFile=$LogDir/slave_lag_$Timestamp.log
LagDetail=$LogDir/slave_lag_Detail_$Timestamp.log
mailadd=leshami@12306.cn

echo $ServerID
echo $MaxLag
echo $LogDir
echo $LogFile
echo $LagDetail
echo $mailadd

if [ ! -d $LogDir ];then
    mkdir -p $LogDir
fi

Lag=`/usr/bin/pt-heartbeat --user=monitor --password=xxx -S /tmp/mysql.sock -D test --master-server-id=$ServerID --check`
Lag=`echo ${Lag%.*}`
#Lag=3
echo $Lag
ptStatus=`ps -ef|grep pt-heart|grep daemonize`
echo $ptStatus

if [ $Lag -gt $MaxLag ]; then
    echo "The current date is `date` at `hostname`."          >>$LogFile 
    echo "The current lag log file is $LogFile."              >>$LogFile
    echo "The current replication lag is $Lag."               >>$LogFile
    echo "The replication lag is larger than max lag $MaxLag." >>$LogFile
   
    if [ -z "$ptStatus" ] ; then
        echo "Start a monitor daemon with below command: "        >>$LogFile 
        echo "pt-heartbeat --user=monitor --password=xxx -S /tmp/mysql.sock -D test " >>$LogFile
        echo " --master-server-id=11 --monitor --print-master-server-id --daemonize --log=$LagDetail" >>$LogFile
        /usr/bin/pt-heartbeat --user=monitor --password=xxx -S /tmp/mysql.sock -D test \
        --master-server-id=$ServerID --monitor --print-master-server-id --daemonize --log=$LagDetail
        echo "More detail please check lag log from $LagDetail." >>$LogFile
        cat $LogFile | mutt -s "Found slave lag on `hostname`." $mailadd
    fi
fi

if [ -n "$ptStatus" ] ; then
    STime=`ps -ef|grep pt-heart|grep daemonize |gawk '{print $5}'`
    Pid=`ps -ef|grep pt-heart|grep daemonize |gawk '{print $2}'`
    STime=`date '+%Y%m%d'`" "$STime
    s_STime=`date -d "$STime" '+%s'`
    s_ETime=`date +%s`
    DiffSec=`expr $s_ETime - $s_STime`

    echo $STime
    echo $s_STime
    echo $s_ETime
    echo $DiffSec

    if [ "$DiffSec" -gt 1800 ]; then
       echo "kill -9 $Pid"
       kill -9 $Pid
    fi
fi

# Remove history slave lag log.
find $LogDir -name "*slave_lag*" -ctime +$Rentition -delete 
exit

3、部署参考

[mysql@SZDB run]$ crontab -l

#check slave lag
*/1 * * * * /run/ck_slave_lag.sh 11 3 /log/SlaveLag