一：需求软件
RHEL
5.6
Nagios
Nagios-plugins
Nrpe
下载地址：
二：安装准备工作
1：搭建yum服务器
[root@loc
~]# vim /etc/yum.repos.d/rhel-source.repo
[Server]
name=Server
baseurl=file:///mnt/Server
enabled=1
gpgcheck=0
gpgkey=file:///etc/pki/rpm-gpg/RPM-GPG-KEY-redhat-release
2：安装环境所需要的安装软件包
[root@loc
~]# yum –y install httpd php gcc glibc glibc-common gd gd-devel openssl
openssl-devel
三：开始安装nagios软件
1：解压软件包
[root@loc
~]# tar xf nagios-3.2.3 .tar.gz -C /usr/src/
[root@loc
~]# tar xf nagios-plugins-1.4.10 .tar.gz -C
/usr/src/
[root@loc
~]# tar xf nrpe-1.8.tar.gz -C /usr/src/
2：创建用户
[root@loc
~]# groupadd nagcmd
[root@loc
~]# useradd –G nagcmd nagios
[root@loc
~]# usermod –G nagcmd apache
3：编译安装nagios
[root@loc
~]# cd /usr/src/nagios-3.2.3
[root@loc
nagios-3.2.3 ]# ./configure
--prefix=/usr/local/nagios --with-nagios-user=nagios --with-nagios-group=nagios
--with-command-group=nagcmd
[root@loc
nagios-3.2.3 ]# make all
[root@loc
nagios-3.2.3 ]# make install 编译安装
[root@loc
nagios-3.2.3 ]# make install-init 生成启动脚本
[root@loc
nagios-3.2.3 ]# make install-commandmode 为外部命令文件配置目录权限
[root@loc
nagios-3.2.3 ]# make install-config 生成配置文件
[root@loc
nagios-3.2.3 ]# make install-webconf 生成一个与apache接口的配置文件
4：编译安装nagios-plugins
[root@loc
nagios-3.2.3 ]# cd ../nagios-plugins-1.4.10/
[root@loc
nagios-plugins-1.4.15 ]# ./configure –with-nagios-user=nagios
–with-nagios-group=nagios –prefix=/usr/local/nagios
[root@loc
nagios-plugins-1.4.15 ]# make;make install
5：添加为开机自启动服务
[root@loc
~]# chkconfig --add nagios
[root@loc
~]# chkconfig nagios on
6：添加web用户
[root@loc
~]# htpasswd -c /usr/local/nagios/etc/passwrd.users nagiosadmin
7：启动服务，检查配置
[root@loc
~]# /usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg 检查下nagios 配置文件的正确性
Total
Warnings: 0 查看这两个为“0”，说明配置文件没问题，可以启动服务了。
Total Errors: 0
[root@loc
~]# /etc/init.d/httpd start
[root@loc
~]# /etc/init.d/nagios start
8：登录nagios
Http://127.0.0.1/nagios 出现下面这个登录界面：
登录后的界面：
注意：
如果是开启了selinux服务，就要执行下面两步：
[root@loc
~]# chcon -R -t httpd_sys_content_t /usr/local/nagios/sbin/
[root@loc
~]# chcon -R -t httpd_sys_content_t /usr/local/nagios/share/
到此，安装部分也就完成了！接下来我们就做下添加监控服务器配置。
先观看下监控原理图：
四：配置nagios监控linux主机
1：主配置文件修改（改动部分内容）
[root@loc
~]# vim /usr/local/nagios/etc/nagios.cfg
#
Definitions for monitoring the local (Linux) host
cfg_file=/usr/local/nagios/etc/objects/localhost.cfg 定义监控本机服务（如不需要监控本机，将注释这行）
cfg_file=/usr/local/nagios/etc/objects/hosts.cfg 添加此行，定义被监控的主机名和地址
cfg_file=/usr/local/nagios/etc/objects/hostgroups.cfg 添加此行，定义被监控主机的分组管理
cfg_file=/usr/local/nagios/etc/objects/contactgroups.cfg 添加此行，定义联系人组
cfg_dir/usr/local/nagios/etc/servers 打开此行，定义需要监控的服务项
check_external_commands=1 定义在web界面下重启nagios服务
command_check_interval=10s 定义命令检查服务的间隔时间
[root@loc ~]# vim
/usr/local/nagios/cfi.cfg
authorized_for_system_information=nagiosadmin,test
authorized_for_configuration_information=nagiosadmin,test
authorized_for_system_commands=nagiosadmin,test
authorized_for_all_services=nagiosadmin,test
authorized_for_all_hosts=nagiosadmin,test
authorized_for_all_service_commands=nagiosadmin,test
authorized_for_all_host_commands=nagiosadmin,test
可以定义多个用户，添加到后面用逗号隔开就好。
2：object文件配置（在此目录下添加在四.1中所讲到的文件）
创建联系人和联系人组配置文件
[root@loc
objects]# vi contacts.cfg
define contact {
contact_name admin #联系人名
alias system administrator #别名
service_notification_period 24x7 #服务通知的时间段
host_notification_period 24x7 #主机通知的时间段
service_notification_options w,u,c,r #当服务出现w—报警,u—未知,c—严重,r—从异常恢复到正常，在这四种情况下通知联系人
host_notification_options d,u,r #当主机出现d----—当机,u—返回不可达,r—从异常情况恢复正常,在这3种情况下通知联系人
service_notification_commands notify-service-by-email #服务出问题通知采用的命令
host_notification_commands notify-host-by-email #同上
pager 13800138000 #定义通过手机短信的方式发送警报的手机号码
pager 13810255206
}
[root@loc
objects]# vi contactgroups.cfg
define
contactgroup{
contactgroup_name sagroup #定义组名
alias system administrator group #组别名
members admin #定义联系人名（contacts.cfg中的联系人名）
}
创建被监控的主机和主机组文件
[root@loc
objects]# vi hosts.cfg
define
host {
host_name web #被监控的主机名
alias tomas #别名
address 192.168.2.6 #被监控主机地址
contact_groups sagroup #联系人组
check_command check-host-alive #检查主机状态的名字
check_period 24x7 #提醒周期
max_check_attempts
5 #检查失败后重试的次数
notification_interval 5 #提醒的间隔时间
notification_options d,u,r #在什么情况提醒
}
define
host {
host_name nagios-server
alias tomas1
address 192.168.2.7
contact_groups sagroup
check_command check-host-alive
check_period 24x7
max_check_attempts
5
notification_interval 5
notification_options d,u,r
}
define
host {
host_name linux
alias tomas2
address 192.168.2.8
contact_groups sagroup
check_command check-host-alive
check_period 24x7
max_check_attempts
5
notification_interval 5
notification_options d,u,r
}
[root@loc
objects]# vi hostgroups.cfg
define
hostgroup{
hostgroup_name sa-servers
alias sa servers
members web,nagios-server,linux
}
配置监控主机服务项
/usr/local/nagios/etc/servers/web.cfg #在这下面依次再建nagios-server.cfg和linux.cfg
define
service{
host_name web #必须是hosts.cfg中定义的主机
service_description check-host-alive #
check_command
check-host-alive #在commands.cfg文件中定义或在nrpe.cfg里面定义的命令
max_check_attempts 5 #最大重试次数
normal_check_interval 5 #检查间隔的单位是分钟
retry_check_interval 2 #检查间隔的单位是分钟
check_period 24x7
notification_interval 10 #探测到故障后，每隔多长时间发送一次报警信息，单位是分钟
notification_period 24x7 #通知选项跟联系人配置文件相同
notification_options w,u,c,r
contact_groups sagroup #配置文件contactgroup.cfg定义的组名称
}
define service{
host_name web
service_description check_tcp 80
check_command check_tcp!80
check_period 24x7
max_check_attempts 4
normal_check_interval 3
retry_check_interval 2
contact_groups sagroup
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
}
define service{
host_name web
service_description cpu load
check_period 24x7
max_check_attempts 4
normal_check_interval 3
retry_check_interval 2
contact_groups sagroup
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
}
define service{
host_name web
service_description total-procs
check_command
check_nrpe!check_total_procs
check_period 24x7
max_check_attempts 4
normal_check_interval 3
retry_check_interval 2
contact_groups sagroup
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
}
监控主机文件配置完成了，我们可以重启下服务，查看下nagios的界面。
验证下配置文件：
[root@loc
objects]# /usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg
Nagios Core 3.2.3
Copyright (c)
2009-2010 Nagios Core Development Team and Community Contributors
Copyright (c)
1999-2009 Ethan Galstad
Last Modified: 10-03-2010
License: GPL
Website:
http://www.nagios.org
Reading
configuration data...
Read main config file okay...
Processing
object config file '/usr/local/nagios/etc/objects/commands.cfg'...
Processing
object config file '/usr/local/nagios/etc/objects/contacts.cfg'...
Processing
object config file '/usr/local/nagios/etc/objects/timeperiods.cfg'...
Processing
object config file '/usr/local/nagios/etc/objects/templates.cfg'...
Processing
object config file '/usr/local/nagios/etc/objects/localhost.cfg'...
Processing
object config file '/usr/local/nagios/etc/objects/hosts.cfg'...
Processing
object config file '/usr/local/nagios/etc/objects/hostgroups.cfg'...
Processing
object config file '/usr/local/nagios/etc/objects/contactgroups.cfg'...
Processing
object config directory '/usr/local/nagios/etc/servers'...
Processing
object config file '/usr/local/nagios/etc/servers/linux.cfg'...
Processing
object config file '/usr/local/nagios/etc/servers/web.cfg'...
Processing
object config file '/usr/local/nagios/etc/servers/nagios-server.cfg'....
Read object config files okay...
Running
pre-flight check on configuration data...
Checking
services...
Checked 12 services.
Checking
hosts...
Checked 2 hosts.
Checking host
groups...
Checked 2 host groups.
Checking service
groups...
Checked 0 service groups.
Checking
contacts...
Checked 3 contacts.
Checking contact
groups...
Checked 2 contact groups.
Checking service
escalations...
Checked 0 service escalations.
Checking service
dependencies...
Checked 0 service dependencies.
Checking host
escalations...
Checked 0 host escalations.
Checking host
dependencies...
Checked 0 host dependencies.
Checking
commands...
Checked 24 commands.
Checking time
periods...
Checked 5 time periods.
Checking for
circular paths between hosts...
Checking for
circular host and service dependencies...
Checking global
event handlers...
Checking
obsessive compulsive processor commands...
Checking misc
settings...
Total Warnings:
0 #表示文件没有任何警告
Total
Errors: 0 #表示文件没有任何错误
重新启动服务：
[root@loc
objects]# /etc/init.d/nagios restart
Running
configuration check...done.
Stopping nagios:
done.
Starting nagios:
done.
[root@loc
objects]# /etc/init.d/httpd restart
登录界面：
Http://IP/nagios
可以清晰的看到前面所做的监控配置了。
远程监控插件NRPE的安装就不再记录了，在用NRPE监控的时候记得去修改services.cfg、command.cfg配置文档，网络上文档都很详细。
在被监控的服务器上只要安装以下这两个软件包就好：
Nagios-plugins
Nrpe