思路:指定一个脚本包,包含主程序,子程序,配置文件,邮件引擎,输出日志等
我们编写一个系统负载的告警系统:
cd /usr/local/sbin/
mkdir mon
cd mon
mkdir bin conf shares log mail
cd bin
vim main.sh
编辑主脚本:
#!/bin/bash
export send=1
export addr=`/sbin/ifconfig |grep -A1 "eth0"|awk '/inet/ {print $ 2}'`
last_dir=`echo $PWD |awk -F '/' '{print $NF}'`
if [ $last_dir == "bin" ] || [ $last_dir == "bin/" ];then
conf_file="../conf/mon.conf"
else
echo "you shoud cd .*/mon/bin/"
exit
fi
exec 1>>../log/mon.log 2>>../log/err.log
echo "`date +"%F %T"` load average"
/bin/bash ../shares/load.sh
if grep -q 'to_mon_502=1' $conf_file;then
export log=`grep 'logfile=' $conf_file |awk -F '=' '{print $2 }' |sed 's/ //g'`
/bin/bash ../shares/502.sh
fi
接着编辑这个脚本的配置文件:
cd …/conf/
vim mon.conf
## mysql
to_mon_cdb=0
db_ip=106.13.219.104
db_port=3306
db_user=username
db_password=passwd
## httpd
to_mon_httpd=0
## php
to_mon_php_socket=0
##http_code_502
to_mon_502=0
logfile=/data/log/www.discuz.com/access.log
to_mon_request_count=0
req_log=/data/log/www.discuz.net/access.log
domainname=www.discuz.net
然后编辑子脚本:
cd ../shares/
vim load.sh
#!/bin/bash
load=`uptime |awk -F 'average: ' '{print $2}'|cut -d ',' -f2 |cut -d . -f2|sed 's/0//g'`
if [ $load -gt 2 ] && [ $send -eq "1" ]
then
echo "$addr `date +%T` load is $load" >../log/load.tmp
/bin/bash ../mail/mail.sh 1694489278@qq.com "$addr\_load:$loa d" `cat ../log/load.tmp`
fi
echo "`date +%T` load is $load"
当然还可以有磁盘使用量的监控负载:
vim disk.sh
#!/bin/bash
rm -f ../log/disk.tmp
for r in `df -h|awk -F '[ %]+' '{print $5}' |grep -v Use`
do
if [ $r -gt 80 ] && [ $send -eq "1" ]
then
echo "$addr `date +%T` disk useage is $r">>../log/disk.tmp
fi
if [ -f ../log/disk.tmp ]
then
df -h >> ../log/disk.tmp
/bin/bash ../mail/mail.sh $addr\_disk $r ../log/disk.tmp
echo "`date +%T` disk useage is not ok"
else
echo "`date +%T` disk useage is ok"
fi
最后编辑邮件告警:
cd ../mail/
vim mail.sh
log=$1
2 t_s=`date +%s`
t_s2=`date -d "2 hours ago" +%s`
if [ ! -f /tmp/$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 mins $2 " "$3"
echo "0" > /tmp/$log.txt
fi
fi
最后编辑mail.py文件:
#!/usr/bin/env python
#-*- coding: UTF-8 -*-
import os,sys
reload(sys)
sys.setdefaultencoding('utf8')
import getopt
import smtplib
from email.MIMEText import MIMEText
from email.MIMEMultipart import MIMEMultipart
from subprocess import *
def sendqqmail(username,password,mailfrom,mailto,subject,content):
gserver = 'smtp.qq.com'
gport = 25
try:
# msg = MIMEText(unicode(content).encode('utf-8')) //如果发送的邮件有乱码,可以尝试把这行改成如下:
msg = MIMEText(content,'plan','utf-8')
msg['from'] = mailfrom
msg['to'] = mailto
msg['Reply-To'] = mailfrom
msg['Subject'] = subject
smtp = smtplib.SMTP(gserver, gport)
smtp.set_debuglevel(0)
smtp.ehlo()
smtp.login(username,password)
smtp.sendmail(mailfrom, mailto, msg.as_string())
smtp.close()
except Exception,err:
print "Send mail failed. Error: %s" % err
def main():
to=sys.argv[1]
subject=sys.argv[2]
content=sys.argv[3]
##定义QQ邮箱的账号和密码,你需要修改成你自己的账号和密码(请不要把真实的用户名和密码放到网上公开,否则你会死的很惨)
sendqqmail('1234567@qq.com','aaaaaaaaaa','1234567@qq.com',to,subject,content)
if __name__ == "__main__":
main()