一、告警系统邮件引擎
1、mail.sh
log=$1
t_s=`date +%s`
t_s2=`date -d "2 hours ago" +%s`
if [ ! -f /tmp/$log ]
then
echo $t_s2 > /tmp/$log
fi
t_s2=`tail -1 /tmp/$log|awk '{print $1}'`
echo $t_s>>/tmp/$log
v=$[$t_s-$t_s2]
echo $v
if [ $v -gt 3600 ]
then
./mail.py $1 $2 $3
echo "0" > /tmp/$log.txt
else
if [ ! -f /tmp/$log.txt ]
then
echo "0" > /tmp/$log.txt
fi
nu=`cat /tmp/$log.txt`
nu2=$[$nu+1]
echo $nu2>/tmp/$log.txt
if [ $nu2 -gt 10 ]
then
./mail.py $1 "trouble continue 10 min $2" "$3"
echo "0" > /tmp/$log.txt
fi
fi
二、运行告警系统
1、可以写到crontab中执行
crontab -e
* * * * * cd /usr/local/sbin/mon/bin;bash main.sh
2、测试
cd /usr/local/sbin/mon/bin/
[root@localhost bin]# sh -x main.sh
+ export send=1
+ send=1
++ grep -A1 'ens33: '
++ awk '/inet/ {print $2}'
++ /sbin/ifconfig
+ export addr=192.168.134.130
+ addr=192.168.134.130
++ pwd
+ dir=/usr/local/sbin/mon/bin
++ echo /usr/local/sbin/mon/bin
++ awk -F/ '{print $NF}'
+ last_dir=bin
+ '[' bin == bin ']'
+ conf_file=../conf/mon.conf
+ exec
3、查看日志，502报错。
[root@localhost bin]# cat ../log/err.log
++ date '+%F %T'
+ echo '2018-04-24 22:32:36 load average'
+ /bin/bash ../shares/load.sh
+ grep -q to_mon_502=1
4、因为502不存在，所以不用监控502。不写入日志
to_mon_502=0
#exec 1>>../log/mon.log 2>>../log/err.log
[root@localhost bin]# sh -x main.sh
+ export send=1
+ send=1
++ /sbin/ifconfig
++ grep -A1 'ens33: '
++ awk '/inet/ {print $2}'
+ export addr=192.168.134.130
+ addr=192.168.134.130
++ pwd
+ dir=/usr/local/sbin/mon/bin
++ echo /usr/local/sbin/mon/bin
++ awk -F/ '{print $NF}'
+ last_dir=bin
+ '[' bin == bin ']'
+ conf_file=../conf/mon.conf
++ date '+%F %T'
+ echo '2018-04-24 22:58:30 load average'
2018-04-24 22:58:30 load average
+ /bin/bash ../shares/load.sh
22:58:30 load is 0
+ grep -q to_mon_502=1 ../conf/mon.conf
[root@localhost bin]# bash ../shares/load.sh
23:04:06 load is 0
