1、编写python脚本监控nginx

#!/usr/bin/python

# -*- coding: utf-8 -*-

import os, sys, time

import string

import getopt

def usage():

   print """check_nginx is a Nagios to monitor nginx status

   Usage:

   check_nginx [-h|--help][-w|--warning][-c|--critical]

   Options:

          --help|-h)

            print check_nginx help.

          --warning|-w)

            Sets a warning level for nginx Active connections. Default is: off

          --critical|-c)

            Sets a critical level for nginx Active connections. Default is: off

          Example:

            ./check_nginx -w 10 -c 5"""

   sys.exit(3)

try:

        options,args = getopt.getopt(sys.argv[1:],"hw:c:",["help","warning=","critical="])

        #“hw:c:”短格式 --- h 后面没有冒号：表示后面不带参数，p：和 i：后面有冒号表示后面需要参数

        #["help","warning=","critical="]长格式 --- help后面没有等号=，表示后面不带参数，其他三个有=，表示后面需要参数

        #返回值 options 是个包含元祖的列表，每个元祖是分析出来的格式信息，比如 [('-i','127.0.0.1'),('-p','80')] ;

        #args 是个列表，包含那些没有‘-’或‘--’的参数，比如：['55','66']

except getopt.GetoptError:

   usage()

   sys.exit(3)

for name,value in options:

        if name in ("-h","--help"):

                usage()

        if name in ("-w","--warning"):

                warning = int(value)

        if name in ("-c","--critical"):

                critical = int(value)

try:

        ret = os.popen('ps -C nginx -o pid,cmd').readlines()

except Exception:

        print "NGINX STATUS unknown: Error while getting Connection"

        sys.exit(3)

if len(ret) < critical:

        print "Critical-nginx process is killed."

        sys.exit(2)

elif len(ret) < warning:

        print "Warning-nginx process is too low."

        sys.exit(1)

else:

        print "OK-nginx is running"

        sys.exit(0)

2、将脚本check_nginx拷贝到/usr/local/nagios/libexec/下，并chmod +x ./check_nginx

如果你要监控nagios安装本机的nginx进程，请参考如下步骤：

3、在/usr/local/nagios/etc/command中增加如下

　　define command{
        command_name    check_nginx
        command_line    $USER1$/check_nginx -w $ARG1$ -c $ARG2$
        }

4、在自己定义的service.cfg中增加

　　define service{
        use                     generic-service
        host_name               localhost
        service_description     nginx
        check_command           check_nginx!4!2
        max_check_attempts      5
        normal_check_interval   3
        retry_check_interval    2
        check_period            24x7
        notification_interval   10
        notification_period     24x7
        notification_options    w,u,c,r
        contact_groups          admins
        }

如果需要监控远程主机的nginx进程，请先安装nrpe，然后参考如下

3、Vim /etc/nagios/nrpe.cfg

　　加入一行

　　command[check_nginx]=/usr/local/nagios/libexec/check_nginx -w $ARG1$ -c $ARG2$

4、修改/etc/nagios/nrpe.cfg

　　dont_blame_nrpe=1　#打开参数传递

5、重启nrpe

　　/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d

　　测试执行

　　/usr/local/nagios/libexec/check_nrpe -H 127.0.0.1 -c check_nginx -a 4 1

　　如果能够正常返回值就是正常的

6、在/usr/local/nagios/etc/object/command中增加

define command{
        command_name
check_nrpe
        command_line /usr/local/nagios/libexec/check_nrpe –H
$HOSTADDRESS$ -c $ARG1$ -a $ARG2$ $ARG3$
        }

7、在自己定义的service.cfg中增加

define service{
        use                     generic-service
        host_name               localhost
        service_description     nginx
        check_command           check_nrpe!check_nginx!4!2
        max_check_attempts      5
        normal_check_interval   3
        retry_check_interval    2
        check_period            24x7
        notification_interval   10
        notification_period     24x7
        notification_options    w,u,c,r
        contact_groups          admins
        }