Nagios监控mysql的安装配置及报警

1.Nagios的安装

1）安装编译所需的软件包；

[root@nagios ~]#yum –y install httpd php-* gd-* mysql-devel
[root@nagios ~]#setenforce 0			#关闭selinux
[root@nagios ~]#sed 's/=enforcing/=permissive/' /etc/sysconfig/selinux

　　

2） 创建运行nagios服务的用户；

[root@nagios ~]#useradd nagios             #创建运行nagios服务的用户
[root@nagios ~]#usermod –G nagios apache   #使apache用户对nagios目录具有写权限，不然web页面操作失败

　　

3） Nagios软件安装；

[root@nagios ~]#tar zxf nagios-cn-3.2.3.tar.gz   #释放nagios源码包
[root@nagios ~]#cd nagios-cn-3.2.3
Ps: 若在RHEL6X32位系统中安装nagios-cn-3.2.3.tar.bz2要先执行make clean操作，然后再执行./configure和make all等操作，否则执行make  all时会报错！
[root@nagios nagios-cn-3.2.3]#./configure --enable-embedded-perl   #编译nagios
[root@nagios nagios-cn-3.2.3]#make all
[root@nagios nagios-cn-3.2.3]#make install        #安装主程序,CGI和HTML文件
[root@nagios nagios-cn-3.2.3]#make install-init     #在/etc/rc.d/init.d安装启动脚本
[root@nagios nagios-cn-3.2.3]#make install-commandmode  #配置目录权限
[root@nagios nagios-cn-3.2.3]#make install-config      #安装示例配置文件
[root@nagios nagios-cn-3.2.3]#make install-webconf    #安装nagios的web接口,会在/etc/httpd/conf.d目录中创建nagios.conf文件

　　

4）安装Nagios-plugins插件；

[root@nagios ~]#tar zxf nagios-plugins-1.4.15.tar.gz
[root@nagios ~]#cd nagios-plugins-1.4.15
[root@nagios nagios-plugins-1.4.15]#./configure –with-nagios-user=nagios 
                               --with-nagios-group=nagios –enable-extra-opts 
									--enable-libtap --enable-perl-modules
[root@nagios nagios-plugins-1.4.15]#make && make install
（Ps:会在”/usr/local/nagios/libexec”目录下多出一些文件，这里存放nagios所有插件）

　　

5） 修改nagios的主配置文件nagios.cfg；

[root@nagios ~]#vim /usr/local/nagios/etc/nagios.cfg
	  新建 cfg_file=/usr/local/nagios/etc/objects/hosts.cfg  #存放主机与主机组定义
		   cfg_file=/usr/local/nagios/etc/objects/services.cfg  #存放服务与服务组定义
          修改 #cfg_file=/usr/local/nagios/etc/objects/localhost.cfg  #加”#”注释,在36行

6） 创建hosts.cfg文件；

[root@nagios ~]#vim /usr/local/nagios/etc/objects/hosts.cfg
  define host{
	use		linux-server		#定义使用的模版
	host_name	nagios		#被监控主机名称
	alias			nagios		#别名
	address		127.0.0.1		#被监控主机的IP地址
	icon_image	web.gif
	statusmap_image		web.gd2
				2d_coords	100,300
				3d_coords	100,300,100
				check_command	check-host-alive  #监控命令,来自commands.cfg文件
				max_check_attempts	5	 #检查失败后重试的次数
				check_period		24x7		 #查看的时间段,来自timeperiods.cfg定义
				contact_groups	admins	 #联系人组,在contactgroups.cfg中定义的
				notification_interval	10	 #提醒的间隔，每隔10分钟提醒一次
				notification_period		24x7  #提醒的周期,24x7,来自timeperiods.cfg定义
				notification_options	d,u,r	  #指定什么情况下提醒
}
define hostgroup{
	hostgroup_name		linux-servers
	alias				linux server
	members			*
}

　　

　　

7） 创建services.cfg文件；

[root@nagios ~]#vim /usr/local/nagios/etc/objects/services.cfg
  define service {
use				local-service
host_name		nagios
service_groups	systemcheck
service_description		//主机存活
check_command	check-host-alive
}
define service {
use				local-service
host_name		nagios
service_groups	systemcheck
service_description		//登录用户数
check_command	check_local_users!20!50
//#监测远程主机当前的登录用户数量，如果大于20用户则报warning，如果大于50则报critical
}
define service {
use				local-service
host_name		nagios
service_groups	systemcheck
service_description		//根分区使用率
check_command	check_local_disk!20%!10%!/
//#如果可用空间低于20%会报Warning，如果可用空间低于10%则报Critical
}
define service {
use				local-service
host_name		nagios
service_groups	systemcheck
service_description		//进程总数
check_command	check_local_procs!250!400!RSZDT
//#监测远程主机当前的进程总数，如果大于250进程则报warning，如果大于400进程则报critical，S（休眠）、R(运行)、Z(僵死)、D （不可中断）、T （停止）
}
define service {
use				local-service
host_name		nagios
service_groups	systemcheck
service_description		CPU负载
check_command	check_local_load!5.0,4.0,3.0!10.0,6.0,4.0
//#当1分钟多于5个进程等待,5分钟多于4个,15分钟多于3个则为warning状态
//#当1分钟多于10个进程等待,5分钟多于6个,15分钟多于4个则为critical状态
}
define service {
use				local-service
host_name		nagios
service_groups	systemcheck
service_description		//交换空间利用率
check_command	check_local_swap!20%!10%
//#如果交换空间低于20%会报Warning，如果可用空间低于10%则报Critical
}
		  define servicegroup {
servicegroup_name	systemcheck
alias					systemcheck
}



	[root@nagios ~]#/usr/local/nagios/bin/nagios –v /usr/local/nagios/etc/nagios.cfg
	#校验nagios配置文件的正确性
	[root@nagios ~]#htpasswd –c /usr/local/nagios/etc/htpasswd.users nagiosadmin
	#添加一个访问nagios页面的授权用户，默认用户是nagiosadmin，创建其他用户修改/usr/local/nagios/etc/cgi.cfg文件：
		方法一：修改use_authentication=0 值为0 （在78行）
方法二：authorized_for_system_information=nagiosadmin
authorized_for_configuration_information=nagiosadmin
authorized_for_system_commands=nagiosadmin 
authorized_for_all_services=nagiosadmin
authorized_for_all_hosts=nagiosadmin
authorized_for_all_service_commands=nagiosadmin
authorized_for_all_host_commands=nagiosadmin
（用 :%s/nagiosadmin/新用户名  命令替换所有nagiosadmin字符）

　　

8）启动httpd和nagios服务并设置开机自动启动

[root@nagios ~]#service iptables stop
[root@nagios ~]#service nagios start
[root@nagios ~]#service httpd start
[root@nagios ~]#chkconfig httpd on
[root@nagios ~]#chkconfig nagios on
[root@nagios ~]#chkconfig iptables off
（Ps:如果开启了selinux需要配置如下两步：
chcon -R –t httpd_sys_content_t  /usr/local/nagios/sbin/
chcon -R –t httpd_sys-content_t  /usr/local/nagios/share/  ）

　　

2.被监控端安装

1）安装并启动mysql的服务

[root@mysql ~]#yum –y install mysql-server
[root@mysql ~]#service mysqld start
[root@mysql ~]#service iptables stop
[root@mysql ~]#chkconfig mysqld on
[root@mysql ~]#chkconfig iptables off

　　

2）在mysql服务器上创建监控检测帐户

[root@mysql ~]#mysql
mysql> create database nagdb;
mysql> grant select on nagdb.* to nagdb@’监控主机IP’;
mysql> flush privileges;
mysql>exit

　　

3）在nagis主机上检测是否可以链接mysql主机上的mysql服务

[root@nagios ~]#/usr/local/nagios/libexec/check_mysql –H 被监控端IP –u nagdb –d nagdb

　　

4）在nagios主机上添加对msyql服务监控的定义

[root@nagios ~]#vim /usr/local/nagios/etc/objects/hosts.cfg
	define host{
	use				linux-server
	host_name		mysqlhost
	alias				mysqlserver
	address			被监控端主机IP
	icon_image		server.gif
	statusmap_image	server.gd2
	2d_coords		100,300
	3d_coords		100,300,100
	check_command	check-host-alive
	max_check_attempts	5
	check_period		24x7
	contact_group		admins
	notification_interval	10
	notification_period		24x7
	notification_options	d,u,r


[root@nagios ~]#vim /usr/local/nagios/etc/objects/services.cfg
    define service {
         use                     local-service

         host_name                mysqlhost

         service_groups         mysqlgroup

         service_description           mysqlservice

         check_command      check_mysql

         contact_groups        admins

         notification_interval         10

         notification_period           24x7

         notification_options         w,u,r,c

}

define servicegroup {

         servicegroup_name          mysqlgroup

         alias                                      mysqlservices

}

[root@nagios ~]#vim /usr/local/nagios/etc/objects/commands.cfg

    define command{

command_name check_mysql

command_line $USER1$/check_mysql -H $HOSTADDRESS$ -u nagdb -d nagdb

}

[root@nagios ~]#/usr/local/nagios/bin/nagios –v /usr/local/nagios/etc/nagios.cfg

#检测无误后重新加载nagios服务
[root@nagios ~]#service nagios reload

　　

　　

3.Nagios通过NRPE监控远程主机系统状况（以mysql主机为例）

1）在被监控端安装nagios-plugins和nrpe

[root@mysql ~]#useradd nagios
[root@mysql ~]#tar zxf nagios-plugins-1.4.15.tar.gz
[root@mysql ~]#cd nagios-plugins-1.4.15
[root@mysql nagios-plugins-1.4.15]#./configure --with-nagios-user=nagios 
								--with-nagios-group=nagios
[root@mysql nagios-plugins-1.4.15]#make && make install
[root@mysql nagios-plugins-1.4.15]#cd
[root@mysql ~]#yum –y install xinetd
[root@mysql ~]#tar zxf nrpe-2.12.tar.gz
[root@mysql ~]#cd nrpe-2.12
[root@mysql nrpe-2.12]#./configure
[root@mysql nrpe-2.12]#make all
[root@mysql nrpe-2.12]#make install-plugin
[root@mysql nrpe-2.12]#make install-daemon		#安装守护进程
[root@mysql nrpe-2.12]#make install-daemon-config	#安装配置文件
[root@mysql nrpe-2.12]#make install-xinetd			#安装xinetd脚本

　　

2）配置nrpe，添加nrpe服务

[root@mysql ~]#vim /etc/xinetd.d/nrpe
	修改 only_from	=	127.0.0.1 监控主机IP
	#在后面增加监控主机（即nagios服务器）的地址,以空格间隔
[root@mysql ~]#vim /etc/services
	添加  nrpe	5666/tcp		#nrpe
	#nrpe服务监听端口
[root@mysql ~]#vim /usr/local/nagios/etc/nrpe.cfg
	修改 command[check_disk]=/usr/local/nagios/libexec/check_disk –w 20% -c 10% -p /
	#在234行，将#注释去掉并修改，’/’表示根分区检测
[root@mysql ~]#service xinetd restart
[root@mysql ~]#netstat –at | grep nrpe
[root@mysql ~]#netstat –an | grep 5666
	#重启xinetd服务,并查看NRPE是否已经启动

　　

3）监控主机的设置

[root@nagios ~]#tar zxf nrpe-2.12.tar.gz
	[root@nagios ~]#cd nrpe-2.12
[root@nagios nrpe-2.12]#./configure  
--with-nagios-user=nagios  --with-nagios-group=nagios
	[root@nagios nrpe-2.12]#make all && make install-plugin
	[root@nagios ~]#/usr/local/nagios/libexec/check_nrpe –H 被监控端IP
		#如输出NRPE v2.12说明连接正常
	[root@nagios ~]#vim /usr/local/nagios/etc/objects/command.cfg
		define command{
	command_name	check_nrpe
#定义命令名称为check_nrpe,在services.cfg中要使用这个名称
	command_line	$USER1$/check_nrpe –H $HOSTADDRESS$ -c $ARG1$
#用$USER1$代替/usr/local/nagios/libexec, 后面带的$ARG1$参数是传给nrpe daemon执行的检测命令
}
	[root@mysql ~]#vim /usr/local/nagios/etc/nrpe.cfg	#监控mysql主机的SWAP分区
		command[check_swap]=/usr/local/nagios/libexec/check_swap –w 20% -c 10%
	[root@mysql ~]#service xinetd reload
	[root@nagios ~]#cd /usr/local/nagios/libexec
	[root@nagios libexec]#./check_nrpe –H 被监控端主机IP -c check_swap
	[root@nagios ~]#vim /usr/local/nagios/etc/objects/services.cfg
		define service {
	use				local-service
	host_name		mysqlhost
	service_groups	mysqlgroup
	service_description		SWAP分区
	check_command	check_nrpe!check_swap
	contact_groups	admins
	notification_interval	10
	notification_period		24x7
	notification_options	w,u,r,c
}
define service {
	use				local-service
	host_name		mysqlhost
	service_groups	mysqlgroup
	service_description		CPU负载
	check_command	check_nrpe!check_load
	contact_groups	admins
	notification_interval	10
	notification_period		24x7
	notification_options	w,u,r,c
}
define service {
	use				local-service
	host_name		mysqlhost
	service_groups	mysqlgroup
	service_description		登录用户数
	check_command	check_nrpe!check_users
	contact_groups	admins
	notification_interval	10
	notification_period		24x7
	notification_options	w,u,r,c
}
define service {
	use				local-service
	host_name		mysqlhost
	service_groups	mysqlgroup
	service_description		磁盘剩余空间
	check_command	check_nrpe!check_disk
	contact_groups	admins
	notification_interval	10
	notification_period		24x7
	notification_options	w,u,r,c
}
define service {
	use				local-service
	host_name		mysqlhost
	service_groups	mysqlgroup
	service_description		总进程
	check_command	check_nrpe!check_total_procs
	contact_groups	admins
	notification_interval	10
	notification_period		24x7
	notification_options	w,u,r,c
}
define service {
	use				local-service
	host_name		mysqlhost
	service_groups	mysqlgroup
	service_description		僵尸进程
	check_command	check_nrpe!check_zombie_procs
	contact_groups	admins
	notification_interval	10
	notification_period		24x7
	notification_options	w,u,r,c
}
		define service{
	use				generic-service
	host_name		mysqlhost
	service_description		SWAP
	check_command	check_nrpe!check_swap
}


[root@nagios ~]#/usr/local/nagios/bin/nagios –v /usr/local/nagios/etc/nagios.cfg
[root@nagios ~]#service nagios reload 

　　

4.通过邮件报警！

1）配置nagios邮箱报警功能

[root@nagios ~]#vim /usr/local/nagios/etc/object/contacts.cfg
	define contact{
	contact_name				nagiosadmin
	alias						Nagios Admin
	service_notification_period	24x7
	host_notification_period	24x7
	service_notification_options	w,u,c,r
	host_notification_options	d,u,r
	service_notification_commands	notify-service-by-email
	host_notification_commands		notify-host-by-email
	email				1009864@qq.com
	#多个管理员邮箱地址使用空格或者逗号隔开
}

　　

2）配置邮件服务器（这里以postfix介绍）

[root@nagios ~]#yum –y install postfix*  httpd*  dovecot*
[root@nagios ~]#hostname mail.hello.com
[root@nagios ~]#vim /etc/postfix/main.cf
	修改  myhostname = mail.hello.com		#在75行
	        mydomain = hello.com			#在83行
                myorigin = $myhostname			#在98行
	        myorigin = $mydomain			#在99行
		inet_interfaces = all				#在113行
		mydestination = $myhostname, $mydomain	#在164行
[root@nagios ~]#service sendmail stop
[root@nagios ~]#service postfix start
[root@nagios ~]#netstat –an | grep 25
[root@nagios ~]#service dovecot restart
[root@nagios ~]#postmap /etc/postfix/virtual

　　

另附：自动化监控表锁定问题  http://blog.chinaunix.net/uid-9370128-id-382660.html