Linux下Nagios的安裝與配置<< 二 >>

篇幅所限，看“Linux下Nagios的安裝與配置<< 二 >>”之前請先看“Linux下Nagios的安裝與配置<< 一 >>”

未完，還有Linux下Nagios的安裝與配置<< 三 >>

localhost.cfg

Definehost{

Use linux-server ; Name of host template to use

; This host definition will inherit all variables that are defined

; in (or inherited by) the linux-server host template definition.

Host_name Nagios-Server

Alias Nagios-Server

Address 127.0.0.1

}

definehostgroup{

hostgroup_name linux-servers ; The name of the hostgroup

Alias Linux Servers ; Long name of thegroup

members Nagios-Server ; Comma separated listof hosts that belong to this group

}

defineservice{

Use local-service ; Name of service template to use

Host_name Nagios-Server

service_description PING

check_command check_ping!100.0,20%!500.0,60%

}

Defineservice{

use local-service ; Name of service template to use

host_name Nagios-Server

service_description Root Partition

check_command check_local_disk!20%!10%!/

}

defineservice{

use local-service ; Name of service template to use

host_name Nagios-Server

service_description Current Users

check_command check_local_users!20!50

}

defineservice{

use local-service ; Name of service template to use

host_name Nagios-Server

service_description Total Processes

check_command check_local_procs!250!400!RSZDT

}

Defineservice{

Use local-service ; Name of service template to use

host_name Nagios-Server

service_description Current Load

check_command check_local_load!5.0,4.0,3.0!10.0,6.0,4.0

}

defineservice{

use local-service ; Name of service template to use

host_name Nagios-Server

service_description Swap Usage

check_command check_local_swap!20!10

}

defineservice{

Use local-service ; Name of service template to use

host_name Nagios-Server

service_description SSH

check_command check_ssh

notifications_enabled 0

}

defineservice{

Use local-service ; Name of service template to use

host_name Nagios-Server

service_description HTTP

check_command check_http

notifications_enabled 0

}

windows.cfg，本實驗主要采用組進行配置，此文檔不刪掉不使，下面配置供參考。

definehost{

use windows-server ; Inherit default values from a template

host_name Nagios-Windows ; The name we're giving to this host

alias My Windows Server ; A longer name associated with the host

address 192.168.1.113 ; IP address of the host

}

definehostgroup{

hostgroup_name windows-servers ; The name of the hostgroup

alias Windows Servers ; Long name of thegroup

}

defineservice{

use generic-service

host_name Nagios-Windows

service_description NSClient++ Version

check_command check_nt!CLIENTVERSION

}

defineservice{

use generic-service

host_name Nagios-Windows

service_description Uptime

check_command check_nt!UPTIME

}

defineservice{

use generic-service

host_name Nagios-Windows

service_description CPU Load

check_command check_nt!CPULOAD!-l 5,80,90

}

defineservice{

use generic-service

host_name Nagios-Windows

service_description Memory Usage

check_command check_nt!MEMUSE!-w 80 -c 90

}

defineservice{

use generic-service

host_name Nagios-Windows

service_description C:\ Drive Space

check_command check_nt!USEDDISKSPACE!-l c -w 80 -c90

}

defineservice{

use generic-service

host_name Nagios-Windows

service_description W3SVC

check_command check_nt!SERVICESTATE!-d SHOWALL -lW3SVC

}

defineservice{

use generic-service

host_name Nagios-Windows

service_description Explorer

check_command check_nt!PROCSTATE!-d SHOWALL -lExplorer.exe

}

e. services.cfg文件

此文件默認也不存在，需要手動創建，services.cfg文件主要用于定義監控的服務和主機資源，例如監控http服務、ftp服務、主機磁盤空間、主機系統負載等等。Nagios-Server 和Nagios-Windows 相關服務已在相應的配置文件中定義，所以這里只需要定義Nagios-Linux 相關服務即可，這里只定義一個檢測是否存活的服務來驗證配置文件的正確性，其他服務的定義將在后面講到。

define service{

use local-service ; #引用local-service服務的屬性值，local-service在templates.cfg文件中進行了定義。

host_name Nagios-Linux ; #指定要監控哪個主機上的服務，“Nagios-Server”在hosts.cfg文件中進行了定義。

service_description PING ; #對監控服務內容的描述，以供維護人員參考。

contact_groups linuxcontact

check_command check-host-alive ; #指定檢查的命令。

}

define service{

use local-service

host_name Nagios-Linux

service_description CurrentLoad

contact_groups linuxcontact

check_command check_nrpe!check_load

}

define service{

use local-service

host_name Nagios-Linux

service_description TotalProcesses

contact_groups linuxcontact

check_command check_nrpe!check_total_procs

}

define service{

use local-service

host_name Nagios-Linux

service_description CurrentUsers

contact_groups linux contact

check_command check_nrpe!check_users

}

define service{

use local-service

host_name Nagios-Linux

service_description CheckZombie Procs

contact_groups linuxcontact

check_command check_nrpe!check_zombie_procs

}

define service{

use local-service

host_name Nagios-Linux

service_description Check Swap

contact_groups linux contact

check_command check_nrpe!check_swap

}

# SERVICE DEFINITIONS

#

###############################################################################

# Create a service for monitoring the versionof NSCLient++ that is installed

# Change the host_name to match the name ofthe host you defined above

define service{

use generic-service

host_name Nagios-Windows

service_description NSClient++Version

contact_groups windowscontact

check_command check_nt!CLIENTVERSION

}

# Create a service for monitoring the uptimeof the server

# Change the host_name to match the name ofthe host you defined above

define service{

use generic-service

host_name Nagios-Windows

service_description Uptime

contact_groups windowscontact

check_command check_nt!UPTIME

}

# Create a service for monitoring CPU load

# Change the host_name to match the name ofthe host you defined above

define service{

use generic-service

host_name Nagios-Windows

service_description CPU Load

contact_groups windowscontact

check_command check_nt!CPULOAD!-l 5,80,90

}

# Create a service for monitoring memoryusage

# Change the host_name to match the name ofthe host you defined above

define service{

use generic-service

host_name Nagios-Windows

service_description MemoryUsage

contact_groups windowscontact

check_command check_nt!MEMUSE!-w 80 -c 90

}

# Create a service for monitoring C:\ diskusage

# Change the host_name to match the name ofthe host you defined above

define service{

use generic-service

host_name Nagios-Windows

service_description C:\ DriveSpace

contact_groups windowscontact

check_command check_nt!USEDDISKSPACE!-l c -w 80 -c 90

}

# Create a service for monitoring the W3SVCservice

# Change the host_name to match the name ofthe host you defined above

define service{

use generic-service

host_name Nagios-Windows

service_description W3SVC

contact_groups windowscontact

check_command check_nt!SERVICESTATE!-d SHOWALL -l W3SVC

}

# Create a service for monitoring theExplorer.exe process

# Change the host_name to match the name ofthe host you defined above

define service{

use generic-service

host_name Nagios-Windows

service_description Explorer

contact_groups windowscontact

check_command check_nt!PROCSTATE!-d SHOWALL -l Explorer.exe

}

f. contacts.cfg，contactgroup.cfg文件，默認不存在，需手動創建！

contacts.cfg是一個定義聯系人和聯系人組的配置文件，當監控的主機或者服務出現故障，nagios會通過指定的通知方式（郵件或者短信）將信息發給這里指定的聯系人或者使用者。contactgroup.cfg定義聯系人組的配置文件，注意：members選項里面的聯系人在contacts.cfg里面要要定義，多個聯系從之間用逗號隔開。

contacts.cfg下面的配置文檔

definecontact{

contact_name echo ; Short name of user

use generic-contact ; Inheritdefault values from generic-contact template (defined above)

alias linux contact ; Full name of user

email test1@163.com ; <<***** CHANGE THIS TO YOUREMAIL ADDRESS ******

}

definecontact{

contact_name jason ; Short name of user

use generic-contact ; Inheritdefault values from generic-contact template (defined above)

alias windows contact ; Full name of user

email test2@qq.com ; <<***** CHANGE THIS TO YOUREMAIL ADDRESS ******

}

definecontact{

contact_name johnson ; Short name of user

use generic-contact ; Inheritdefault values from generic-contact template (defined above)

alias windows and linuxcontact ; Full name of user

email test3@qq.com ; <<***** CHANGE THIS TOYOUR EMAIL ADDRESS ******

}

contactgroup.cfg下面的配置文檔

# We only have one contact in this simpleconfiguration file, so there is

# no need to create more than one contactgroup.

define contactgroup{

contactgroup_name linuxcontact

alias linuxserver contact

members echo,johnson

}

define contactgroup{

contactgroup_name windows contact

alias windowsserver contact

members jason,johnson

}

define contactgroup{

contactgroup_name allcontact

alias linux andwindows server contact

members jason,echo,johnson

}

g. timeperiods.cfg文件

此文件只要用于定義監控的時間段，下面是一個配置好的實例：也可以根據自己需求監控情況進行配置。

#下面是定義一個名為24x7的時間段，即監控所有時間段

definetimeperiod{

timeperiod_name 24x7 #時間段的名稱,這個地方不要有空格

alias 24 Hours A Day, 7 Days A Week

sunday 00:00-24:00

monday 00:00-24:00

tuesday 00:00-24:00

wednesday 00:00-24:00

thursday 00:00-24:00

friday 00:00-24:00

saturday 00:00-24:00

}

#下面是定義一個名為workhours的時間段，即工作時間段。

definetimeperiod{

timeperiod_name workhours

alias Normal Work Hours

monday 09:00-17:00

tuesday 09:00-17:00

wednesday 09:00-17:00

thursday 09:00-17:00

friday 09:00-17:00

}

h. cgi.cfg文件

此文件用來控制相關cgi腳本，如果想在nagios的web監控界面執行cgi腳本，例如重啟nagios進程、關閉nagios通知、停止nagios主機檢測等，這時就需要配置cgi.cfg文件了。
由于nagios的web監控界面驗證用戶為david，所以只需在cgi.cfg文件中添加此用戶的執行權限就可以了，需要修改的配置信息如下：

default_user_name=david

authorized_for_system_information=nagiosadmin,david

authorized_for_configuration_information=nagiosadmin,david

authorized_for_system_commands=david

authorized_for_all_services=nagiosadmin,david

authorized_for_all_hosts=nagiosadmin,david

authorized_for_all_service_commands=nagiosadmin,david

authorized_for_all_host_commands=nagiosadmin,david

i. nagios.cfg文件

nagios.cfg默認的路徑為/usr/local/nagios/etc/nagios.cfg，是nagios的核心配置文件，所有的對象配置文件都必須在這個文件中進行定義才能發揮其作用，這里只需將對象配置文件在Nagios.cfg文件中進行引用即可。

log_file=/usr/local/nagios/var/nagios.log # 定義nagios日志文件的路徑

#cfg_file=/usr/local/nagios/etc/objects/commands.cfg # “cfg_file”變量用來引用對象配置文件，如果有更多的對象配置文件，在這里依次添加即可。
#cfg_file=/usr/local/nagios/etc/objects/contacts.cfg # 默認開啟，需注銷
#cfg_file=/usr/local/nagios/etc/objects/hosts.cfg # 默認開啟，需注銷
#cfg_file=/usr/local/nagios/etc/objects/services.cfg # 默認開啟，需注銷
#cfg_file=/usr/local/nagios/etc/objects/timeperiods.cfg # 默認開啟，需注銷

#cfg_file=/usr/local/nagios/etc/objects/templates.cfg # 默認開啟，需注銷
#cfg_file=/usr/local/nagios/etc/objects/localhost.cfg # 本機配置文件,默認開啟，需注銷
#cfg_file=/usr/local/nagios/etc/objects/windows.cfg # windows 主機配置文件默認開啟，需注銷

cfg_dir=/usr/local/nagios/etc/servers #servers文件默認不存在，需手動創建

#object_cache_file=/usr/local/nagios/var/objects.cache # 該變量用于指定一個“所有對象配置文件”的副本文件，或者叫對象緩沖文件

precached_object_file=/usr/local/nagios/var/objects.precache
resource_file=/usr/local/nagios/etc/resource.cfg # 該變量用于指定nagios資源文件的路徑，可以在nagios.cfg中定義多個資源文件。

status_file=/usr/local/nagios/var/status.dat # 該變量用于定義一個狀態文件，此文件用于保存nagios的當前狀態、注釋和宕機信息等。

status_update_interval=10 # 該變量用于定義狀態文件（即status.dat）的更新時間間隔，單位是秒，最小更新間隔是1秒。

nagios_user=nagios # 該變量指定了Nagios進程使用哪個用戶運行。
nagios_group=nagios # 該變量用于指定Nagios使用哪個用戶組運行。

check_external_commands=1 # 該變量用于設置是否允許nagios在web監控界面運行cgi命令;
# 也就是是否允許nagios在web界面下執行重啟nagios、停止主機/服務檢查等操作;
# “1”為運行，“0”為不允許。

command_check_interval=10s # 該變量用于設置nagios對外部命令檢測的時間間隔，如果指定了一個數字加一個"s"(如10s);
# 那么外部檢測命令的間隔是這個數值以秒為單位的時間間隔;
# 如果沒有用"s"，那么外部檢測命令的間隔是以這個數值的“時間單位”的時間間隔。
interval_length=60 # 該變量指定了nagios的時間單位，默認值是60秒，也就是1分鐘;
# 即在nagios配置中所有的時間單位都是分鐘。

6.4 驗證Nagios 配置文件的正確性

Nagios 在驗證配置文件方面做的非常到位，只需通過一個命令即可完成：

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

Nagios提供的這個驗證功能非常有用，在錯誤信息中通常會打印出錯誤的配置文件以及文件中的哪一行，這使得nagios的配置變得非常容易，報警信息通常是可以忽略的，因為一般那些只是建議性的。

看到上面這些信息就說明沒問題了，然后啟動Nagios 服務。

七、Nagios的啟動與停止

7.1 啟動Nagios

a. 通過初始化腳本啟動nagios

#/etc/init.d/nagios start
or
# service nagios start

b. 手工方式啟動nagios

通過nagios命令的“-d”參數來啟動nagios守護進程：

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

7.2 重啟Nagios

當修改了配置文件讓其生效時，需要重啟/重載Nagios服務。

a. 通過初始化腳本來重啟nagios

#/etc/init.d/nagios reload
or
# /etc/init.d/nagios restart
or
# service nagios restart

b. 通過web監控頁重啟nagios

可以通過web監控頁的 "ProcessInfo" -> "Restart the Nagios process"來重啟nagios

c. 手工方式平滑重啟

#kill -HUP <nagios_pid>

7.3 停止Nagios

a. 通過初始化腳本關閉nagios服務

#/etc/init.d/nagios stop
or
# service nagios stop

b. 通過web監控頁停止nagios

可以通過web監控頁的 "ProcessInfo" -> "Shutdown the Nagios process"來停止nagios

c. 手工方式停止Nagios

#kill <nagios_pid>

八、查看初步配置情況

8.1 啟動完成之后，登錄Nagios Web監控頁http://192.168.1.108/nagios/查看相關信息。

8.2 點擊左面的Current Status -> Hosts 可以看到所定義的三臺主機已經全部UP了。

8.3 點擊Current Status -> Services 查看服務監控情況。

看到Nagios-Linux和Nagios-Server的服務狀態已經OK了，但是Nagios-Windows的服務狀態為CRITICAL，StatusInformation 提示Connection refused。因為Nagios-Windows上還未安裝插件，內部服務還無法查看，所以出現這種情況。將在下面具體講解。