nagios 监控内存

nagios 版本：nagios-3.2.0
监控端：
1、定义插件
cd /usr/local/nagios/libexec
vim check_mem
把附件内容添加到文件中，这样监控内存的程序就做好了。
赋予权限：
chmod +x /usr/local/nagios/libexec/check_mem
检查命令：
./check_mem -h
[root@wqk1 libexec]# ./check_mem -h
Wrong Syntax: check_mem -h
Usage: check_mem [-w|--warning]<percent free> [-c|--critical]<percent free>
由帮助可以看出是以剩余内存为判断标准
./check_mem -w 90 -c 50
WARNING - 1658 MB (82%) Free Memory
[root@wqk1 libexec]# ./check_mem -w 95 -c 90
CRITICAL - 1658 MB (82%) Free Memory
2、定义命令
vim /usr/local/nagios/etc/objects/commands.cfg
   定义nrpe命令
define command{
       command_name    check_nrpe
       command_line    $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$ -t 30
}
   定义内存命令
define command{
command_name check_mem
command_line $USER1$/check_mem -w $ARG1$ -c $ARG2$
}
3、定义被监控主机
vim /usr/local/nagios/etc/objects/localhost.cfg
define host {
       host_name       wqk_centos-107
       alias           centos-107
       address         192.168.10.107
       check_command   check-host-alive
       notification_options    d,u,r
       check_interval  1
       max_check_attempts      2
       contact_groups  admins
       notification_interval   10
       notification_period     24x7
}
4、定义服务
vim /usr/local/nagios/etc/objects/localhost.cfg
define service {
       host_name       wqk_centos-107
       service_description     check_mem
       check_period    24x7
       normal_check_interval   2
       retry_check_interval    1
       max_check_attempts      5
       notification_period     24x7
       notification_options    w,u,c,r
       check_command     check_nrpe!check_mem //如果没有定义check_nrpe，可以写成check_mem!90!50;而且如果监控端和被监控端的command字段不修改，只修改这里的数值就能影响到nagios监控结果。
}
5、检查排错
cd /usr/local/nagios/libexec
./check_nrpe -H 192.168.10.107 -c check_mem(被监控机命令定义后检查)
/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg
6、重启服务
service nagios restart
==================================================
被监控端：
1、定义插件
cd /usr/local/nagios/libexec
vim check_mem
把附件内容添加到文件中，这样监控内存的程序就做好了。
赋予权限：
chmod +x /usr/local/nagios/libexec/check_mem
检查命令：
./check_mem -h
./check_mem -w 90 -c 50
2、定义命令
编辑nrpe配置文件：
vim /usr/local/nagios/etc/nrpe.cfg

添加：

allowed_host=127.0.0.1,192.168.0.1(本机ip),192.168.0.100(监控机ip)

command[check_mem]=/usr/local/nagios/libexec/check_mem -w 90 -c 50 //设置90是为了看到效果，实际生产中要调低
3、重启服务
ps aux | grep nrpe
kill掉nrpe 进程
/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d  //启动nrpe服务
4、远程测试命令
在监控端测试
cd /usr/local/nagios/libexec
./check_nrpe -H 192.168.10.107 -c check_mem
****************************************************************
check_mem 脚本：
  1. #script to check real memory usage 
  2. # L.Gill 02/05/06 - V.1.0 
  3. # ------------------------------------------ 
  4. # ########  Script Modifications  ########## 
  5. # ------------------------------------------ 
  6. # Who         When           What 
  7. # ---    ----      ---- 
  8. # LGill         17/05/06  "$percent" lt 1% fix - sed edits dc result beggining with "." 
  9. # 
  10. # 
  11. #!/bin/bash 
  12. USAGE="`basename $0` [-w|--warning]<percent free> [-c|--critical]<percent free>"
  13. THRESHOLD_USAGE="WARNING threshold must be greater than CRITICAL: `basename $0` $*"
  14. calc=/tmp/memcalc 
  15. percent_free=/tmp/mempercent 
  16. critical=""
  17. warning=""
  18. STATE_OK=0
  19. STATE_WARNING=1
  20. STATE_CRITICAL=2
  21. STATE_UNKNOWN=3
  22. # print usage 
  23. if [[ $# -lt 4 ]] 
  24. then 
  25.         echo "" 
  26.         echo "Wrong Syntax: `basename $0` $*" 
  27.         echo "" 
  28.         echo "Usage: $USAGE" 
  29.         echo "" 
  30.         exit 0 
  31. fi 
  32. # read input 
  33. while [[ $# -gt 0 ]] 
  34.   do 
  35.         case "$1" in 
  36.                -w|--warning) 
  37.                shift 
  38. warning=$1 
  39.         ;; 
  40.                -c|--critical) 
  41.                shift 
  42. critical=$1 
  43.         ;; 
  44.         esac 
  45.         shift 
  46.   done 
  47. # verify input 
  48. if [[ $warning -eq $critical || $warning -lt $critical ]] 
  49. then 
  50.         echo "" 
  51.         echo "$THRESHOLD_USAGE" 
  52.         echo "" 
  53.         echo "Usage: $USAGE" 
  54.         echo "" 
  55.         exit 0 
  56. fi 
  57. # Total memory available 
  58. total=`free -m | head -2 |tail -1 |gawk '{print $2}'` 
  59. # Total memory used 
  60. used=`free -m | head -2 |tail -1 |gawk '{print $3}'` 
  61. # Calc total minus used 
  62. free=`free -m | head -2 |tail -1 |gawk '{print $4+$7}'` 
  63. # normal values 
  64. #echo "$total"MB total 
  65. #echo "$used"MB used 
  66. #echo "$free"MB free 
  67. # make it into % percent free = ((free mem / total mem) * 100) 
  68. echo "5" > $calc # decimal accuracy 
  69. echo "k" >> $calc # commit 
  70. echo "100" >> $calc # multiply 
  71. echo "$free" >> $calc # division integer 
  72. echo "$total" >> $calc # division integer 
  73. echo "/" >> $calc # division sign 
  74. echo "*" >> $calc # multiplication sign 
  75. echo "p" >> $calc # print 
  76. percent=`/usr/bin/dc $calc|/bin/sed 's/^\./0./'|/usr/bin/tr "." " "|/usr/bin/gawk {'print $1'}` 
  77. #percent1=`/usr/bin/dc $calc` 
  78. #echo "$percent1" 
  79. if [[ "$percent" -le  $critical ]] 
  80.         then 
  81.                 echo "CRITICAL - $free MB ($percent%) Free Memory" 
  82.                 exit 2 
  83. fi 
  84. if [[ "$percent" -le  $warning ]] 
  85.         then 
  86.                 echo "WARNING - $free MB ($percent%) Free Memory" 
  87.                 exit 1 
  88. fi 
  89. if [[ "$percent" -gt  $warning ]] 
  90.         then 
  91.                 echo "OK - $free MB ($percent%) Free Memory" 
  92.                 exit 0 
  93. fi