nagios监控实例

前面我们写了nagios的server端和client端的安装过程，这里我们写一下nagios的监控范例

添加监控本地服务器磁盘，监控/dev/sda3，即/分区

[[email protected] ~]# df -h
Filesystem            Size  Used Avail Use% Mounted on
/dev/sda3              97G  1.6G   90G   2% /
tmpfs                 495M     0  495M   0% /dev/shm
/dev/sda1             194M   28M  156M  16% /boot
#编辑相应配置文件
[[email protected] ~]# vim /usr/local/nagios/etc/objects/commands.cfg 
#从这个文件中我们知道该监控脚本需要3个参数
define command{
        command_name    check_local_disk
        command_line    $USER1$/check_disk -w $ARG1$ -c $ARG2$ -p $ARG3$
        }
#修改文件，添加要监控的分区
[[email protected] ~]# vim /usr/local/nagios/etc/objects/localhost.cfg 
define service{
        use                             local-service
        host_name                       localhost
        service_description             disk_monitor
        check_command                   check_local_disk!30%!20!/dev/sda3
        notifications_enabled           1
        }
#用命令进行调试
[[email protected] ~]# /usr/local/nagios/libexec/check_disk -w 30% -c 20% /dev/sda3
DISK OK - free space: / 92072 MB (98% inode=99%);| /=1544MB;69038;78900;0;98626

#检查配置文件
[[email protected] ~]# /usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg 

#重启nagios服务
[[email protected] ~]# service nagios restart
Running configuration check...done.
Stopping nagios: done.
Starting nagios: done.

查看结果

这里我们监控我们前一篇文章中的nagios-client:192.168.3.72的sdb

#编辑文件
[[email protected] ~]# vim /usr/local/nagios/etc/nrpe.cfg
command[check_users]=/usr/local/nagios/libexec/check_users -w 5 -c 10
command[check_load]=/usr/local/nagios/libexec/check_load -w 15,10,5 -c 30,25,20
command[check_hda1]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/hda1
#添加sdb这一行
command[check_sdb]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/sdb
command[check_zombie_procs]=/usr/local/nagios/libexec/check_procs -w 5 -c 10 -s Z
command[check_total_procs]=/usr/local/nagios/libexec/check_procs -w 150 -c 200 

#重启nrped服务
[[email protected] ~]# service nrped restart
Stopping NRPE daemon... done.
Starting NRPE daemon... done.
[[email protected] ~]# netstat -anpt |grep nrpe
tcp        0      0 192.168.3.72:5666           0.0.0.0:*                   LISTEN      1492/nrpe

在nagios-server:192.168.3.71进行配置

[[email protected] objects]# pwd
/usr/local/nagios/etc/objects
[[email protected] objects]# vim commands.cfg
#在末尾添加如下内容
define command{
        command_name check_nrpe
        command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
        }
[[email protected] etc]# pwd
/usr/local/nagios/etc
[[email protected] etc]# vim nagios.cfg
#在第36行添加
cfg_file=/usr/local/nagios/etc/objects/192.168.3.72.cfg
[[email protected] objects]# pwd
/usr/local/nagios/etc/objects
[[email protected] objects]# cat 192.168.3.72.cfg 
define host{
	use			linux-server
	host_name		192.168.3.72
	alias			nagios-client
	address			192.168.3.72
	}

define hostgroup{
	hostgroup_name		clients
	alias			linux-servers
	members			192.168.3.72
	}

define service{
	use			local-service
	host_name		192.168.3.72
	service_description	check_disk_sdb
	check_command		check_local_disk!30%!20!/dev/sdb
	notifications_enabled	1
        }
#检查配置文件
[[email protected] objects]# /usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg 

#重启nagios服务
[[email protected] objects]# service nagios restart
Running configuration check...done.
Stopping nagios: done.
Starting nagios: done.

查看结果

1