nagios远程监控项配置

IP	hostname	备注
192.168.174.128	localhost	关闭防火墙、nagios服务端
192.168.174.129	node1	关闭防火墙、nagios客户端

搭建nagios服务端及客户端

创建cfg文件部署客户端下的监控，参考localhost.cfg，创建一个跟本地监控项一模一样的远程监控文件；
添加监控脚本，设计一个能监控nginx端口的脚本；并添加到远程监控项目中；
添加监控脚本，设计一个能监控mysql端口的脚本；并添加到远程监控项目中；
添加监控脚本，设计一个能监控apache端口的脚本；并添加到远程监控项目中；

在服务端配置文件

[root@localhost ~]# vi /usr/local/nagios/etc/nagios.cfg  //编辑配置文件
cfg_file=/usr/local/nagios/etc/objects/services.cfg		//添加以下
cfg_file=/usr/local/nagios/etc/objects/hosts.cfg		两行
[root@localhost objects]# cd /usr/local/nagios/etc/objects   //进入object目录

编辑hosts.cfg

[root@localhost objects]# cp localhost.cfg hosts.cfg		//复制配置文件
[root@localhost objects]# vi hosts.cfg 				//编辑配置文件
	define hostgroup {			//将hostgroup删除
	...
	}
	
	address                 192.168.174.129		//将address后面的改为客户端ip
	
	
	host_name               node1			//host_name和alias
    alias                   node1			后面的改为客户端主机名
[root@localhost objects]#touch services.cfg
[root@localhost objects]#/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg		//测试配置文件是否有误
[root@localhost objects]# systemctl restart nagios		//重启nagios

访问web端->点击services,添加

客户端

创建监控脚本

[root@node1 ~]# cd /usr/local/nagios/libexec/   	//进入libexec
[root@node1 libexec]# vi check_access 			//创建监控服务端口的脚本
CRITICAL=2
ok=1
name=$1

b=`netstat -ntpl |grep $name|wc -l`
if [ $b == 0 ];then
        echo "$name service is error"
        exit $CRITICAL
else
        echo "$name:$b"
        exit $ok
fi
//name为监控的服务名称
[root@node1 libexec]# chmod +x check_access

配置nrpe.cfg

[root@node1 libexec]# vi /usr/local/nagios/etc/nrpe.cfg 	//编辑nrpe.cfg
//在最末尾加入
command[check_nginx]=/usr/local/nagios/libexec/check_access nginx -c 2
command[check_mysql]=/usr/local/nagios/libexec/check_access mysql -c 2
command[check_httpd]=/usr/local/nagios/libexec/check_access httpd -c 2

重启nrpe

[root@node1 libexec]# pkill nrpe			杀掉nrpe进程
[root@node1 libexec]# /usr/local/nagios/bin/nrpe -d -c /usr/local/nagios/etc/nrpe.cfg			/启动nrpe

在服务端进行测试

[root@localhost objects]# /usr/local/nagios/libexec/check_nrpe -H 192.168.174.129 -c check_nginx
nginx service is error
[root@localhost objects]# /usr/local/nagios/libexec/check_nrpe -H 192.168.174.129 -c check_mysql
mysql service is error
[root@localhost objects]# /usr/local/nagios/libexec/check_nrpe -H 192.168.174.129 -c check_httpd
httpd service is error

服务端

编辑services.cfg

[root@localhost objects]# vi commands.cfg     	//首先编辑监控命令
define command{
command_name    check_nrpe				//命令名称
command_line    $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
}										//在最末尾添加
[root@localhost objects]# vi services.cfg      	//编辑services.cfg
define service{
        use                     generic-service
        host_name               node1		
        service_description     nginx
        check_command           check_nrpe!check_nginx
        }
define service{
        use                     generic-service
        host_name               node1
        service_description     mysql
        check_command           check_nrpe!check_mysql
        }
define service{
        use                     generic-service
        host_name               node1
        service_description     httpd
        check_command           check_nrpe!check_httpd
        }
//注意use、host_name后面的参数都要和hosts.cfg里的一样
service_description是web端的服务名
check_command!前面的是上面commands中定义的命令，后面为客户端nrpe.cfg
中定义的命令
[root@localhost objects]#/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg		//测试配置文件是否有误
[root@localhost objects]# systemctl restart nagios  	//重启

查看web端，增加了三条监控项