实战配置Nagios主机及服务实战

目录

1
在客户服务器上配置... 1

1.1配置nrpe.
1

1)
加入可以监控该服务器的nagios server端的IP。... 1

2)
注释掉或者干脆删除199-203行即下面几行... 1

2
配置 nagios 监控服务... 1

1）nagios.cfg
基本配置... 1

2）注意：需要注释掉如下localhost.cfg
行，否则和我们要配的会冲突原 36 行... 1

3）需要在host.cfg
里添加客户端主机和主机组（HOST GROUP）... 1

4）同理添加要监控的服务配置到service.cfg.
1

5）重启服务...
1

3
错误整理... 1

1）错误1.
1

2）错误2：...
1

3）问题3.
1

4）问题4.
1

1 在客户服务器上配置

1.1配置nrpe

cd /usr/local/nagios/etc

#config nrpe.cfg

vi nrpe.cfg +79

1) 加入可以监控该服务器的nagios server端的IP。

allowed_hosts=127.0.0.1,172.16.1.196,172.16.1.190 ←主机的IP

2) 注释掉或者干脆删除199-203行即下面几行

shift+g到结尾

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

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

#command[check_disk]=/usr/local/nagios/libexec/check_disk-w $ARG1$ -c $ARG2$ -p $ARG3$

#command[check_procs]=/usr/local/nagios/libexec/check_procs-w $ARG1$ -c $ARG2$ -s $ARG3$

同时在下面新添加要监控的内容：

command[check_load]=/usr/local/nagios/libexec/check_load-w 15,10,6 -c 30,25,20

command[check_mem]=/usr/local/nagios/libexec/check_memory.pl-w 6% -c 3%

command[check_disk]=/usr/local/nagios/libexec/check_disk-w 20% -c 8% -p /

command[check_swap]=/usr/local/nagios/libexec/check_swap-w 20% -c 10%

command[check_iostat]=/usr/local/nagios/libexec/check_iostat-w 6 -c 10

或者：

echo"command[check_load]=/usr/local/nagios/libexec/check_load -w 15,10,6 -c30,25,20">>/usr/local/nagios/etc/nrpe.cfg

echo"command[check_mem]=/usr/local/nagios/libexec/check_memory.pl -w 6% -c3%">>/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% -c10%">>/usr/local/nagios/etc/nrpe.cfg

echo"command[check_iostat]=/usr/local/nagios/libexec/check_iostat -w 6 -c10">>/usr/local/nagios/etc/nrpe.cfg

1.2启动：nagios client

[root@client01 etc]#

[root@client01 etc]# pkill nrpe

[root@client01etc]# /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d

[root@client01 etc]# echo"/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d">> /etc/rc.local

[root@client01etc]# ps -ef|grep nrpe

nagios 32431 1 0 12:44 ? 00:00:00 /usr/local/nagios/bin/nrpe -c/usr/local/nagios/etc/nrpe.cfg -d

root 32433 32397 0 12:44 pts/0 00:00:00 grep nrpe

[root@client01 etc]#

注意：

1、#执行完启动命令，进行检查是个良好的习惯

2、tips:重起nagios nrpe组合命令

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

1.3 关闭防火墙

测试环境，建议最好先把iptables关掉，等nagios都测试通了在来调试iptables，否则给学习测试增加了复杂度。

关闭命令

/etc/init.d/iptablesstop

2 配置 nagios 监控服务

以下为server 端的操作

1）nagios.cfg 基本配置

在 nagios.cfg 文件中找到cfg_file 的部分，进行如下设置：

[root@nagios-server etc]# vi/usr/local/nagios/etc/nagios.cfg +34

# You can specify individualobject config files as shown below:

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

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

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

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

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

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

2）注意：需要注释掉如下localhost.cfg行，否则和我们要配的会冲突原 36 行

# Definitions for monitoring the local (Linux) host

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

3）需要在host.cfg 里添加客户端主机和主机组（HOSTGROUP）

[root@nagios-serveretc]# cd /usr/local/nagios/etc/objects/

[root@nagios-server objects]# vihosts.cfg

# Define a host for the local machine

define host{

use linux-server

host_name 18-client01

alias 18-client01

address 192.168.1.18

}

define host{

use linux-server

host_name 19-nagios_server

alias 19-nagios_server

address 192.168.1.19

}

define hostgroup{

hostgroup_name linux-servers ; The name of the hostgroup

alias Linux Servers ; Long name of thegroup

members 18-client01,19-nagios_server

}

4）同理添加要监控的服务配置到service.cfg

[root@nagios-serverobjects]# cd /usr/local/nagios/etc/objects/

[root@nagios-serverobjects]# vi services.cfg

define service {

use generic-service

host_name 18-client01

service_description Disk Partition

check_command check_nrpe!check_disk

}

5）重启服务

[root@nagios-server objects]#/usr/local/nagios/libexec/check_nrpe -H 192.168.l.18 -c check_disk

Invalid host name '192.168.l.18'

[root@nagios-server objects]# ll

[root@nagios-serverobjects]# /etc/init.d/nagios reload

3 错误整理

1）错误1

[root@nagios-server objects]#/etc/init.d/nagios checkconfig

Running configuration check...CONFIG ERROR! Check your Nagiosconfiguration.

[root@nagios-server objects]#/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg

Checking services...

Error: There are no servicesdefined!

Checked 0 services.

Total Warnings: 2

Total Errors: 1

处理方法：

[root@nagios-server objects]# vim/etc/init.d/nagios +178

status)

pid_nagios

printstatus_nagios nagios # /dev/null 2>&1; 这部分去掉；

;;

checkconfig)

2）错误2：

[root@nagios-server objects]#/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg

问题2：

Checking services...

Error: There are no servicesdefined!

Checked 0 services.

处理方法:

[root@nagios-serverobjects]# vi services.cfg

defineservice {

use generic-service

host_name 18-client01

service_description Disk Partition

check_command check_nrpe!check_disk

}

"services.cfg"8L, 138C written

[root@nagios-server objects]# /etc/init.d/nagioscheckconfig

3）问题3

问题3：

Checking services...

Error: Service check command'check_nrpe' specified in service 'Disk Partition' for host '18-client01' notdefined anywhere!

Checked 1 services.

处理方法：

[root@nagios-serverobjects]# vi commands.cfg

#'check_nrpe' command definition

definecommand{

command_name check_nrpe

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

}

4）问题4

打开网页会出现

It appears as though you do not have permission toview information for any of theservices you requested...

解决方法

[root@nagiosserver objects]#cd/usr/local/nagios/etc

[root@nagiosserver objects]#vi cgi.cfg +119

#把在1.6 节建立的用户oldboy 加到后面，注意用逗号隔开。

#default_user_name=oldboy

authorized_for_system_information=nagiosadmin,oldboy

authorized_for_configuration_information=nagiosadmin,oldboy

authorized_for_system_commands=nagiosadmin,oldboy

authorized_for_all_services=nagiosadmin,oldboy

authorized_for_all_hosts=nagiosadmin,oldboy

authorized_for_all_service_commands=nagiosadmin,oldboy

authorized_for_all_host_commands=nagiosadmin,oldboy

记得reload nagios 命令为：/etc/init.d/nagios reload