shell 监控脚本

 公司采用nagios监控，通过nagios client将需要的数据收集并传给nagios服务器，目前所遇到的问题是我们公司部分机器是再其他机房，例如：东航，是不允许安装客户端并访问外网的，为了更好的检测服务器状态，遇到问题可以发短信和邮件的方式通知运维人员进行处理，与开发人员协商开放了短信、邮件两个接口，通过脚本的方式将监控服务器状态，遇到故障后通过脚本方式发送报警。

目标分析：

  所需的监控资源：

       1、登陆用户数

       2、CPU负载

       3、服务探测

       4、硬盘空间（根分区、应用分区、备份分区）

       5、内存资源

  短信接口、邮件接口

       格式上传至附件

脚本：

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132

#!/bin/bash #监控用户登录 Usermonitor ()  {          LoginUser=`uptime |  awk  '{print $6}' `          if  [ $LoginUser - ge  2 ]                  then                          Critical= "当前系统登录用户人数超过1人，具体人数为：$LoginUser 个,请确认操作者人数。"                          status=0                  else                          echo  "loginuser ok"                          status=1          fi } #监控内存 MemMonitor () {          MemTotal=` free  -m |  grep  Mem |  awk  -F:  '{print $2}'  |  awk  '{print $1}' `          MemFree=` free  -m |  grep  cache |  awk  NR==2 |  awk  '{print $4}' `          MemFreeB=` awk  'BEGIN{printf "%.2f%\n",' $MemFree/$MemTotal\*100 '}' `          MemFreeS=` awk  'BEGIN{printf "%.f",' $MemFree/$MemTotal\*100 '}' `          if  [ $MemFreeS -lt  10 ]                  then                          Critical= "系统可用内存小于10%，实际可用内存为：$MemFreeB ,请处理。"                          status=0                  elif  [ $MemFreeS -lt 20 ]                          then                                  Warning= "系统可用内存小于20%，实际可用内存为：$MemFreeB ，请查看。"                                  WarningT= "内存报警"                                  status=1                          else                                  echo  "Mem OK"                                  status=2          fi } #监控分区空间大小 DiskMonitorG () {          #根分区          DiskGB=` df  -h |  awk  NR==2 |  awk  '{print $5}' `          DiskGS=` df  -h |  awk  NR==2 |  awk  '{print $5}'  |  awk  -F%  '{print $1}' `          if  [ $DiskGS -gt 90 ]                  then                          Critical= "根分区使用率超过90%，实际已使用 $DiskGB ,请处理。"                          status=0                  elif  [ $DiskGS -gt 80 -a $DiskGS -lt 90 ]                  then                          Warning= "根分区使用率超过80%，实际已使用 $DiskGB , 请查看。"                          WarningT= "根分区报警"                          status=1                  else                          echo  "DiskGB Ok"                          status=2          fi                  } DiskMonitorA () {          #应用分区          ApplyB=` df  -h |  awk  NR==4 |  awk  '{print $5}' `          ApplyS=` df  -h |  awk  NR==4 |  awk  '{print $5}'  |  awk  -F%  '{print $1}' `          if  [ $ApplyS -gt 90 ]                  then                          Critical= "应用分区使用率超过90%，实际已使用 $ApplyB ,请处理."                          status=0                  elif  [ $ApplyS -gt 80 -a $ApplyS -lt 90 ]                  then                          Warning= "应用分区使用率超过80%，实际已使用 $ApplyB ，请查看。"                          WarningT= "应用分区报警"                          status=1                  else                          echo  "Apply ok"                          status=2          fi } #监控CPU负载 CPULoad () {          CPULoad1=`uptime |  awk  '{print $10}'  |  awk  -F.  '{print $1}' `          CPULoad2=`uptime`          if  [ $CPULoad1 -gt 5 ]                  then                          Critical= "CPU负载过高，请即使处理。 $CPULoad2 "                          status=0                  elif  [ $CPULoad1 -gt 3 -a $CPULoad1 -lt 5 ]                  then                          Warning= "CPU负载警告， $Warning "                          WarningT= "CPU负载报警"                          status=1                  else                          echo  "CPU OK"                          status=2          fi } #监控服务状态 ServerMonitor () { #服务状态监控          timeout=10          makfails=2          fails=0          success=0          while  true                  do                          /usr/bin/wget  --timeout=$timeout --tries=1 http: //192 .168.20.84/ -q -O  /dev/null                          if  [ $? - ne  0 ]                                  then                                          let  fails=fails+1                                          success=0                                  else                                          fails=0                                          let  success=1                          fi                          if  [ $success - ge  1 ]                                  then                                          exit  0                          fi                          if  [ $fails - ge  1 ]                                  then                                          Critical= "TMS应用服务出现故障，请紧急处理！"                                          echo  $Critical | mutt -s  "服务down"  hao.lulu@chinaebi.com                                          exit  -1                          fi          done } #发送报警短信、报警邮件 for  n  in  Usermonitor MemMonitor DiskMonitorG DiskMonitorA CPULoad ServerMonitor          do                  $n                  if  [ $status - eq  0 ]                          then                                  curl  "http://172.20.36.118/app/tms.do?tranCode=TM0311&content=$Critical"                          elif  [ $status - eq  1 ]                                  then                                  curl  "http://172.20.36.118/app/tms.do?tranCode=TM0310&title=$WarningT&content=Warning"                          else                                  echo  "ok"                  fi done