CentOS 6.4+Nagios+Msmtp+Mutt郵箱報警

環境：

Nagios Server Nagios 6.4

IP：192.168.0.58

Nagios Clint Nagios 6.4

IP：192.168.0.83

另注意：

Nagios需要PHP支援，安裝Apache+PHP步驟略....

=========================================================================================

——安裝Nagios

[root@Nagios ~]# cd /Linux

[root@Nagios Linux]# tar fzvx nagios-4.0.2.tar.gz

[root@Nagios Linux]# cd nagios-4.0.2

[root@Nagios nagios-4.0.2]# useradd -M -s /sbin/nologin nagios

[root@Nagios nagios-4.0.2]# mkdir /usr/local/nagios

[root@Nagios nagios-4.0.2]# chown -R nagios:nagios /usr/local/nagios/

[root@Nagios nagios-4.0.2]# ./configure --prefix=/usr/local/nagios/

[root@Nagios nagios-4.0.2]# make all

[root@Nagios nagios-4.0.2]# make install

[root@Nagios nagios-4.0.2]# make install-init

[root@Nagios nagios-4.0.2]# make install-commandmode

[root@Nagios nagios-4.0.2]# make install-config

[root@Nagios nagios-4.0.2]# chkconfig --add nagios

[root@Nagios nagios-4.0.2]# chkconfig --level 35 nagios on

[root@Nagios nagios-4.0.2]# chkconfig --list nagios

nagios 0:關閉 1:關閉 2:關閉 3:啟用 4:關閉 5:啟用 6:關閉

[root@Nagios nagios-4.0.2]# service nagios restart

=========================================================================================

——服務端安裝Nagios外掛plugins

[root@Nagios Linux]# tar zfvx nagios-plugins-1.5.tar.gz

[root@Nagios Linux]# cd nagios-plugins-1.5

[root@Nagios nagios-plugins-1.5]# ./configure --prefix=/usr/local/nagios/

[root@Nagios nagios-plugins-1.5]# make && make install

----------------------------------------------------------------------------

——服務端安裝nrpe

[root@Nagios Linux]# tar zfvx nrpe-2.15.tar.gz

[root@Nagios Linux]# cd nrpe-2.15

[root@Nagios nrpe-2.15]# ./configure

[root@Nagios nrpe-2.15]# make all

[root@Nagios nrpe-2.15]# make install-plugin

=========================================================================================

——使apache支援nagios [這裡安裝apache的路徑為/usr/local/apache-2.4]

[root@Nagios nagios-plugins-1.5]# vi /usr/local/apache-2.4/conf/httpd.conf

ScriptAlias /nagios/cgi-bin "/usr/local/nagios/sbin"

<Directory "/usr/local/nagios/sbin">

AuthType Basic

Options ExecCGI

AllowOverride None

Order allow,deny

Allow from all

AuthName "Nagios Access"

AuthUserFile /usr/local/nagios/etc/htpasswd

Require valid-user

</Directory>

Alias /nagios "/usr/local/nagios/share"

<Directory "/usr/local/nagios/share">

AuthType Basic

Options None

AllowOverride None

Order allow,deny

Allow from all

AuthName "nagios Access"

AuthUserFile /usr/local/nagios/etc/htpasswd

Require valid-user

</Directory>

=========================================================================================

——新增nagios登陸使用者

[root@Nagios nagios-plugins-1.5]# /usr/local/apache-2.4/bin/htpasswd -c /usr/local/nagios/etc/htpasswd nagios

New password:

Re-type new password:

Adding password for user nagios

——修改apache的使用者和使用者組

[root@Nagios nagios-plugins-1.5]# vi /usr/local/apache-2.4/conf/httpd.conf

User nagios

Group nagios

--------------------------------------------------------------------------

——解決Nagios亂碼問題

[root@Nagios nagios-plugins-1.5]# vi /usr/local/apache-2.4/conf/httpd.conf

LoadModule cgid_module modules/mod_cgid.so

LoadModule actions_module modules/mod_actions.so

[root@Nagios nagios-plugins-1.5]# service httpd restart

——測試訪問

=========================================================================================

——客戶端安裝nagios-plugins

[root@CentOS ~]# cd /Linux

[root@CentOS Linux]# useradd -M -s /sbin/nologin nagios

[root@CentOS Linux]# tar zfvx nagios-plugins-1.5.tar.gz

[root@CentOS Linux]# cd nagios-plugins-1.5

[root@CentOS nagios-plugins-1.5]# ./configure --prefix=/usr/local/nagios/

[root@CentOS nagios-plugins-1.5]# make && make install

——客戶端安裝nrpe

[root@CentOS nagios-plugins-1.5]# cd ..

[root@CentOS Linux]# tar zfvx nrpe-2.15.tar.gz

[root@CentOS Linux]# cd nrpe-2.15

[root@CentOS nrpe-2.15]# ./configure

[root@CentOS nrpe-2.15]# make all

[root@CentOS nrpe-2.15]# make install-plugin

[root@CentOS nrpe-2.15]# make install-daemon

[root@CentOS nrpe-2.15]# make install-daemon-config

[root@CentOS nrpe-2.15]# vi /usr/local/nagios/etc/nrpe.cfg

allowed_hosts=127.0.0.1,192.168.0.58

-----------------------------------------------------------------------------------------

——啟動nrpe

[root@CentOS nrpe-2.15]# /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d

——檢查是否啟動

[root@CentOS nrpe-2.15]# netstat -antup |grep 5666

tcp 0 0 0.0.0.0:5666 0.0.0.0:* LISTEN 48456/nrpe

tcp 0 0 :::5666 :::* LISTEN 48456/nrpe

——開機啟動

[root@CentOS nrpe-2.15]# vi /etc/rc.local

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

——在服務端檢查 [如果返回NRPE版本及成功，相反則檢查配置]

[root@Nagios ~]# /usr/local/nagios/libexec/check_nrpe -H 192.168.0.83

NRPE v2.15

=========================================================================================

——配置nagios

[root@Nagios nrpe-2.15]# cd /usr/local/nagios/etc/

[root@Nagios etc]# vi nagios.cfg

註釋下面的內容

#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/localhost.cfg

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

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

#新增監控主機目錄

cfg_dir=/usr/local/nagios/etc/objects/hosts

#新增模板目錄

cfg_dir=/usr/local/nagios/etc/objects/templates

[root@Nagios etc]# mdkir objects/templates

[root@Nagios etc]# mdkir objects/hosts

——複製所需檔案

[root@Nagios etc]# cp objects/commands.cfg objects/templates/

[root@Nagios etc]# cp objects/timeperiods.cfg objects/templates/

——建立自定義模板

[root@Nagios etc]# vi objects/templates/templates.cfg

#聯絡人模板

define contact{

#聯絡人名稱

name tao

#當服務出現異常時 傳送通知的時間段

service_notification_period 24x7

#當主機出現異常時 傳送通知的時間段

host_notification_period 24x7

#w 表示警告 u 表示不明 c 表示緊急 r 表示恢復

service_notification_options w,u,c,r

#d 表示當機 u 表示不可達 r 表示重新恢復

host_notification_options d,u,r

#服務故障時 傳送通知的方式[郵件]

service_notification_commands notify-service-by-email

#主機故障時 傳送通知的方式[郵件]

host_notification_commands notify-host-by-email

register 0

}

#主機模板

define host{

#定義主機名

name linux-host

#其值為1 Nagios將收集的資料寫入某個檔案中 以備提取

process_perf_data 1

passive_checks_enabled 0

#主機與服務的重新整理檢測 0為關閉

check_freshness 0

#事件處理開啟

event_handler_enabled 1

#開啟抖動感知

flap_detection_enabled 1

active_checks_enabled 1

#傳送通知的時間段

notification_period 24x7

#檢查主機的時間段

check_period 24x7

#對主機的檢查時間間隔/分鐘

check_interval 5

#如果當機重試檢查時間/分鐘

retry_interval 1

#當機後對主機的最大檢查次數

max_check_attempts 2

#檢查主機狀態指令[在commands.cfg中定義]

check_command check-host-alive

#在主機出現異常後 故障一直沒有解決 再次傳送通知的時間/分鐘

notification_interval 5

#d 表示當機 u 表示不可達 r 表示重新恢復

notification_options d,u,r

#1為開啟報警資訊

notifications_enabled 0

#指定聯絡人組[在contacts.cfg中定義]

contact_groups admins

#處理效能資料

#一天重新整理檢測一次，以防止檢測結果不是實時的

freshness_threshold 86400

#0為不註冊，意思是這個作為模板

register 0

}

#服務模板

define service{

#定義一個服務名稱

name linux-service

#啟用主動服務檢查

active_checks_enabled 1

#啟用被動服務檢查

passive_checks_enabled 0

#主機與服務的重新整理檢測

check_freshness 0

#開啟報警資訊

notifications_enabled 1

#重新傳送報警資訊的間隔

notification_interval 5

#事件處理開啟

event_handler_enabled 1

#啟用抖動感知

flap_detection_enabled 1

#處理效能資料

process_perf_data 1

#傳送通知的時間段

notification_period 24x7

#檢查時間段

check_period 24x7

#如果當機最大檢查次數

max_check_attempts 5

#檢查服務時間間隔/分鐘

normal_check_interval 1

#如果當機再次檢查的間隔時間/分鐘

retry_check_interval 1

#一天重新整理檢測一次，以防止檢測結果不是實時的

freshness_threshold 86400

#0為不註冊，意思是這個作為模板

register 0

}

define service {

name test

#1為開啟報警資訊

notifications_enabled 0

#重新傳送報警資訊的間隔

notification_interval 5

notification_options w,u,c,

#事件處理開啟

event_handler_enabled 1

#開啟抖動感知

flap_detection_enabled 1

#傳送通知的時間段

notification_period 24x7

#檢查時間段

check_period 24x7

#每一次檢測的間隔時間

check_interval 1

#如果當機再次檢查的間隔時間

retry_interval 1

#檢測次數,如果2次都是當機的話 就報警

max_check_attempts 2

active_checks_enabled 1

passive_checks_enabled 0

#處理效能資料

process_perf_data 1

#主機與服務的重新整理檢測 0為關閉

check_freshness 0

#一天重新整理檢測一次，以防止檢測結果不是實時的

freshness_threshold 86400

#0為不註冊，意思是這個作為模板

register 0

}

[root@Nagios etc]# vi objects/templates/contacts.cfg

#聯絡人

define contact{

#使用者名稱稱

contact_name nagios

#引用模板

use tao

#別名

alias Nagios Admin

#傳送郵箱

email xxxxxxxx@qq.com

}

#聯絡人組

define contactgroup{

#組名稱

contactgroup_name admins

#組別名

alias Nagios Administrators

#組使用者成員

members nagios

}

——新增監控主機

最好使用被監控機IP為名稱、比如:被監控伺服器為192.168.0.83 [後期伺服器多的時候、容易維護]

這裡為了省事、一臺伺服器監控多種服務。大家測試的時候、可以新增多個伺服器監控不同服務。

[root@Nagios etc]# vi objects/hosts/192.168.0.83.cfg

#監控主機

define host {

host_name 192.168.0.83

address 192.168.0.83

use linux-host

}

#監控SSH

define service {

service_description check_ssh

check_command check_ssh!-p 22

host_name 192.168.0.83

use linux-service

register 1

}

#監控登陸使用者

define service {

service_description check_users

check_command check_nrpe!check_users

host_name 192.168.0.83

use linux-service

register 1

}

#監控mysql [需要在被監控配置、下面有配置說明]

define service {

service_description check_mysql

check_command check_mysql

host_name 192.168.0.83

use linux-service

register 1

}

#監控交換空間

define service {

service_description check_swap

check_command check_nrpe!check_swap

host_name 192.168.0.83

use linux-service

register 1

}

#監控磁碟

define service {

service_description check_disk

check_command check_nrpe!check_disk

host_name 192.168.0.83

use linux-service

register 1

}

#監控HTTP

define service {

service_description check_http

check_command check_http!-p 80

host_name 192.168.0.83

use linux-service

register 1

}

#監控負載

define service {

service_description check_load

check_command check_nrpe!check_load

host_name 192.168.0.83

use linux-service

register

}

=========================================================================================

——重啟啟動nagios、登陸WEB檢視

網上很多人說配置後，執行命令檢查是否有錯誤。個人感覺完全沒必要、因為啟動的時候Nagios預設會自動檢查配置、如果有錯誤Nagios會提示。

[root@Nagios etc]# service nagios restart

——在客戶端 登陸nagios

=========================================================================================

注意：監控MySQL需要在被監控端配置如下

——客戶端連線mysql新增nagios使用者

mysql> create database nagios;

Query OK, 1 row affected (0.00 sec)

mysql> grant select on nagios.* to nagios@'192.168.1.18' identified by 'nagios';

Query OK, 0 rows affected (0.11 sec)

mysql> flush privileges;

Query OK, 0 rows affected (0.00 sec)

mysql> quit

-----------------------------------------------------------------------------------------

——Nagios伺服器端新增mysql監控

[root@Nagios nrpe-2.15]# vi /usr/local/nagios/etc/objects/templates/commands.cfg

# 'check_mysql' command definition

define command{

command_name check_mysql

command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -u nagios -d nagios -p nagios

}

=========================================================================================

——安裝msmtp

[root@Nagios Linux]# cd msmtp-1.4.31

[root@Nagios msmtp-1.4.31]# ./configure --prefix=/usr/local/msmtp

[root@Nagios msmtp-1.4.31]# make && make install

[root@Nagios msmtp-1.4.31]# cd /usr/local/msmtp/

[root@Nagios msmtp]# mkdir etc

[root@Nagios msmtp]# cd etc/

——配置msmtp

[root@Nagios etc]# vi msmtprc

account default

logfile /usr/local/msmtp/msmtp.log

host smtp.163.com  #發件伺服器

from xxxxxx@163.com #從那發郵件，和下面的郵箱是同一個

auth login

user xxxxxx@163.com #發件郵箱

password xxxxxx  #郵箱密碼

----------------------------------------------------------------------------

測試msmtp
/usr/local/msmtp/bin/msmtp sdata@foxmail.com
輸入任意字元，然後按Ctrl+D退出，檢視郵件是否收到。
可以到 /usr/local/msmtp/msmtp.log，檢視日誌，發信成功失敗都會有記錄。

——安裝mutt

[root@Nagios etc]# yum install mutt -y

[root@Nagios etc]# vi /etc/Muttrc

set sendmail="/usr/local/msmtp/bin/msmtp"

set use_from=yes

set realname="YingTao" #真是姓名

set from=hypocriticals@163.com  //發件郵箱

set envelope_from=yes

set editor="vim"

set record="/usr/local/msmtp/etc/sent" #郵件記錄

=========================================================================================

==========================================================================================

——Nagios預設使用sendmail傳送郵件、只需要把 /bin/mail 改為 /usr/bin/mutt即可。

[root@Nagios etc]# vi objects/templates/commands.cfg

# 'notify-host-by-email' command definition

define command{

command_name notify-host-by-email

command_line /usr/bin/printf "%b" "***** Nagios *****\n\nNotification Type: $NOTIFICATIONTYPE$\nHost: $HOSTNAME$\nState: $HOSTSTATE$\nAddress: $HOSTADDRESS$\nInfo: $HOSTOUTPUT$\n\nDate/Time: $LONGDATETIME$\n" | /usr/bin/mutt -s "** $NOTIFICATIONTYPE$ Host Alert: $HOSTNAME$ is $HOSTSTATE$ **" $CONTACTEMAIL$

}

# 'notify-service-by-email' command definition

define command{

command_name notify-service-by-email

command_line /usr/bin/printf "%b" "***** Nagios *****\n\nNotification Type: $NOTIFICATIONTYPE$\n\nService: $SERVICEDESC$\nHost: $HOSTALIAS$\nAddress: $HOSTADDRESS$\nState: $SERVICESTATE$\n\nDate/Time: $LONGDATETIME$\n\nAdditional Info:\n\n$SERVICEOUTPUT$\n" | /usr/bin/mutt -s "** $NOTIFICATIONTYPE$ Service Alert: $HOSTALIAS$/$SERVICEDESC$ is $SERVICESTATE$ **" $CONTACTEMAIL$

}

=========================================================================================

——測試能否通過郵箱報警

1）在被監控端關閉mysql

[root@CentOS ~]# /etc/init.d/mysqld stop

Shutting down MySQL. SUCCESS!

[root@CentOS ~]# netstat -antup |grep 3306

2）登陸WEB Nagios檢視MySQL狀態

3）在服務端檢視日誌 [預設日誌路徑為/usr/local/nagios/var/]

[root@Nagios ~]# cd /usr/local/nagios/var/

[root@Nagios var]# tail -f nagios.log

檢查五次、如果五次服務還是無法檢測到服務是正常的，則發郵件通知。

[1388002399] SERVICE ALERT: 192.168.0.83;check_mysql;CRITICAL;SOFT;1;Can't connect to MySQL server on '192.168.0.83' (111)

[1388002459] SERVICE ALERT: 192.168.0.83;check_mysql;CRITICAL;SOFT;2;Can't connect to MySQL server on '192.168.0.83' (111)

[1388002519] SERVICE ALERT: 192.168.0.83;check_mysql;CRITICAL;SOFT;3;Can't connect to MySQL server on '192.168.0.83' (111)

[1388002579] SERVICE ALERT: 192.168.0.83;check_mysql;CRITICAL;SOFT;4;Can't connect to MySQL server on '192.168.0.83' (111)

[1388002639] SERVICE ALERT: 192.168.0.83;check_mysql;CRITICAL;HARD;5;Can't connect to MySQL server on '192.168.0.83' (111)

[1388002639] SERVICE NOTIFICATION: nagios;192.168.0.83;check_mysql;CRITICAL;notify-service-by-email;Can't connect to MySQL server on '192.168.0.83' (111)

4）登陸郵箱檢視是否收到郵件 [由於是虛擬機器時間沒有調整、和現實時間有差別]

5）重新啟動MySQL

[root@CentOS ~]# /etc/init.d/mysqld start

Starting MySQL.. SUCCESS!

[root@CentOS ~]# netstat -antup |grep 3306

tcp 0 0 0.0.0.0:3306 0.0.0.0:* LISTEN 51040/mysqld

6）檢測服務恢復正常後，是否收到郵件通知