告警系统主脚本
vim main.sh #!/bin/bash # 是否发送邮件的开关 export send=1 #定义在所有子脚本里 # 过滤ip地址 export addr=`/sbin/ifconfig |grep -A1 "ens33: "|awk '/inet/ {print $2}'` dir=`pwd` # 只需要最后一级目录名 last_dir=`echo $dir|awk -F'/' '{print $NF}'` # 下面的判断目的是，保证执行脚本的时候，我们在bin目录里，不然监控脚本、邮件和日志很有可能找不到 if [ $last_dir == "bin" ] || [ $last_dir == "bin/" ]; then conf_file="../conf/mon.conf" else echo "you shoud cd bin dir" exit fi exec 1>>../log/mon.log 2>>../log/err.log echo "`date +"%F %T"` load average" /bin/bash ../shares/load.sh #先检查配置文件中是否需要监控502 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
告警系统配置文件
vim ../conf/mon.conf ## to config the options if to monitor ## 定义mysql的服务器地址、端口以及user、password to_mon_cdb=0 ##0 or 1, default 0,0 not monitor, 1 monitor db_ip=10.20.3.13 db_port=3315 db_user=username db_pass=passwd ## httpd 如果是1则监控，为0不监控 to_mon_httpd=0 ## php 如果是1则监控，为0不监控 to_mon_php_socket=0 ## http_code_502 需要定义访问日志的路径 to_mon_502=1 logfile=/data/log/xxx.xxx.com/access.log ## request_count 定义日志路径以及域名 to_mon_request_count=0 req_log=/data/log/www.discuz.net/access.log domainname=www.discuz.net
报警系统监控项目
vim /shares/load.sh #! /bin/bash load=`uptime |awk -F 'average:' '{print $2}'|cut -d',' -f1|sed 's/ //g' |cut -d. -f1` if [ $load -gt 10 ] && [ $send -eq "1" ] then echo "$addr `date +%T` load is $load" >../log/load.tmp /bin/bash ../mail/mail.sh aming_test@163.com "$addr\_load:$load" `cat ../log/load.tmp` fi echo "`date +%T` load is $load" vim /shares/502.sh #! /bin/bash d=`date -d "-1 min" +%H:%M` c_502=`grep :$d: $log |grep ' 502 '|wc -l` if [ $c_502 -gt 10 ] && [ $send == 1 ]; then echo "$addr $d 502 count is $c_502">../log/502.tmp /bin/bash ../mail/mail.sh $addr\_502 $c_502 ../log/502.tmp fi echo "`date +%T` 502 $c_502" vim /shares/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 90 ] && [ $send -eq "1" ] then echo "$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 nook" else echo "`date +%T` disk useage is ok" fi
告警系统核心
• mail.py #!/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')) 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 sendqqmail('1234567@qq.com','aaaaaaaaaa','1234567@qq.com',to,subject,content) if __name__ == "__main__": main() #####脚本使用说明###### #1. 首先定义好脚本中的邮箱账号和密码 #2. 脚本执行命令为：python mail.py 目标邮箱 "邮件主题" "邮件内容"
• mail.sh内容 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
执行告警系统
crontab -e * * * * * cd /usr/local/sbin/mon/bin; bash main.sh