nagios系列(三)之nagios被动监控模式之添加系统负载load、swap、磁盘iostat及memory内存监控详解

环境：

nagios server:192.168.8.42 host_name:node4.chinasoft.com

nagios client:192.168.8.41 host_name:node3.chinasoft.com





1.编辑nagios.cfg文件

vim /usr/local/nagios/etc/nagios.cfg

添加

cfg_file=/usr/local/nagios/etc/objects/hosts.cfg

cfg_file=/usr/local/nagios/etc/objects/service.cfg





注释掉

# Definitions for monitoring the local (Linux) host

#cfg_file=/usr/local/nagios/etc/objects/localhost.cfg





2.生成hosts.cfg和service.cfg文件

cd /usr/local/nagios/etc/objects/

head -50 localhost.cfg >hosts.cfg

chown nagios.nagios hosts.cfg





# touch service.cfg

[root@node4 objects]# chown -R nagios.nagios service.cfg 





3.编辑hosts.cfg、service.cfg增加被监控的主机





define host{

use linux-server

    host_name
node4.chinasoft.com

alias node4.chinasoft.com

address
192.168.8.42

}

define host{

        use             linux-server

        host_name       node3.chinasoft.com

        alias           node3.chinasoft.com

        address         192.168.8.41

}





# Define an optional hostgroup for Linux machines





define hostgroup{

        hostgroup_name  linux-servers ; The name of the hostgroup

        alias           Linux Servers ; Long name of the group

        members         node4.chinasoft.com,node3.chinasoft.com     ; Comma separated list of hosts that belong to this group

        }





编辑service文件

vim service.cfg 

define service{

use generic-service

host_name node3.chinasoft.com,node4.chinasoft.com

service_descriptiondisk partition

check_command
check_nrpe!check_disk

}





编辑commands.cfg添加check_nrpe命令

# 'check_nrpe" command definition

define command{

command_name
check_nrpe

command_line
$USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$

}





4.编辑nagios启动脚本，打开报错日志

vim /etc/init.d/nagios

改为：$NagiosBin -v $NagiosCfgFile





检测语法是否正确

/etc/init.d/nagios checkconfig

或者

/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg 





5.开启jack用户的访问权限

sed -i 's#nagiosadmin#jack#g' /usr/local/nagios/etc/cgi.cfg





6.client的配置

编辑/usr/local/nagios/etc/cgi.cfg，运行服务端连接

allowed_hosts=127.0.0.1,192.168.8.42





报错：

Connection refused by host 

排错：

/usr/local/nagios/libexec/check_nrpe -H 192.168.8.42 -c check_disk

NRPE: Command 'check_disk' not defined

check_disk命令没有定义

增加相关定义即可，如下：

cp /usr/local/nagios/etc/nrpe.cfg /usr/local/nagios/etc/nrpe.cfg.ori

sed -i '199,203d' /usr/local/nagios/etc/nrpe.cfg





echo "command[check_load]=/usr/local/nagios/libexec/check_load -w 15,10,6 -c 30,25,20">>/usr/local/nagios/etc/nrpe.cfg

echo "command[check_mem]=/usr/local/nagios/libexec/check_memory.pl -w 6% -c 3%">>/usr/local/nagios/etc/nrpe.cfg

echo "command[check_disk]=/usr/local/nagios/libexec/check_disk -w 20% -c 8% -p /">>/usr/local/nagios/etc/nrpe.cfg

echo "command[check_swap]=/usr/local/nagios/libexec/check_swap -w 20% -c 10%">>/usr/local/nagios/etc/nrpe.cfg

echo "command[check_iostat]=/usr/local/nagios/libexec/check_iostat -w 6 -c 10">>/usr/local/nagios/etc/nrpe.cfg





重启nrpe服务

pkill nrpe

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

# ps -ef|grep nrpe

nagios   52207     1  0 15:39 ?        00:00:00 /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d

root     52209  1703  0 15:39 pts/0    00:00:00 grep nrpe





在客户端执行命令：

# /usr/local/nagios/libexec/check_nrpe -H 127.0.0.1 -c check_disk

DISK OK - free space: / 16337 MB (87% inode=95%);| /=2348MB;15748;18110;0;19685

[root@node4 etc]# /usr/local/nagios/libexec/check_nrpe -H 192.168.8.42 -c check_disk

DISK OK - free space: / 16337 MB (87% inode=95%);| /=2348MB;15748;18110;0;19685





通过直接执行相关的脚本可以看出是否ok：/usr/local/nagios/libexec/check_disk -w 20% -c 8% -p /





7、添加新的监控项目：

vim /usr/local/nagios/etc/objects/service.cfg添加相应的监控项即可(监控的check_command必须要和客户端的nrpe.cfg中定义的一致)

define service{

        use generic-service

        host_name node3.chinasoft.com,node4.chinasoft.com

        service_description     memory

        check_command   check_nrpe!check_mem

}

define service{

        use generic-service

        host_name node3.chinasoft.com,node4.chinasoft.com

        service_description     load

        check_command   check_nrpe!check_load

}