nagios 监控笔记(二)

原创

cqfish 2009-04-18 01:42:29 博主文章分类：运维 ©著作权

©著作权归作者所有：来自51CTO博客作者cqfish的原创作品，请联系作者获取转载授权，否则将追究法律责任

四、nagios服务端配置与启动

1）、文件说明

nagios.cfg                    #nagios主配置文件
cgi.cfg                          #cgi配置文件
commands.cfg            #命令配置文件
contacts.cfg               #联系人配置文件
resource.cfg               #定义插件路径文件
templates.cfg、timeperiods.cfg 组，监控时间段等配置文件
linux.cfg                      #用户自定义文件，监控linux主机,定义主机配置文件
windows.cfg              #用户自定义文件，监控windows主机,定义主机配置文件
l-services.cfg             #用户自定义文件，定义linux主机服务配置文件
w-services.cfg          #用户自定义文件，定义windows主机服务配置文件

2)、cgi.cfg文件配置

root@nagios#cd /usr/local/nagios/etc
vi    cgi.cfg                #以下是需要修改的地方
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
use_authentication=0

#修改为0,不然监控访问的时候会出现以下提示

It appears as though you do not have permission to view information for any of the hosts you requested...

If you believe this is an error, check the HTTP server authentication requirements for accessing this CGI
and check the authorization options in your CGI configuration file.

3)、配置nagios.cfg文件

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

# wb config
cfg_dir=/usr/local/nagios/etc/linux #配置linux主机加载自定义文件的目录(下面包括linux.cfg、l-services.cfg文件)
cfg_dir=/usr/local/nagios/etc/windows #配置win主机加载自定义文件的目录(包括windows.cfg、w-services.cfg)

4)、配置commands.cfg命令配置文件

define command{
                command_name check_nrpe
                command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
                }

define command{
        command_name check_mysql_health #定义mysql监控命令        command_line $USER1$/check_mysql_health --hostname $ARG1$ --port $ARG2$ --username $ARG3$ --password $ARG4$ --mode $ARG5$
        }
define command{
        command_name notify-service-by-sms #定义飞信监控命令        command_line /usr/local/tools/install/fetion --mobile=159230***** --pwd=2255*** --to=$CONTACTPAGER$ --msg-gb="$HOSTNAME$ $SERVICEDESC$ is $SERVICESTATE$ on $TIME$ result is $SERVICEOUTPUT$" $CONTACTPAGER$
}
notify-host-by-email、notify-service-by-email这二项是定义mail报警的命令，默认文件有这二项

5)、配置contacts.cfg联系人配置文件

define contact{
contact_name nagiosadmin

use generic-contact

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,notify-service-by-sms
     host_notification_commands            notify-host-by-email
   email                             [email]test@[/email],[email]test@[/email]

pager 1592304****
}

#email 定义联系人报警mail地址

#pager 定义联系人报警手机号码

#notify-service-by-email、notify-service-by-sms、notify-host-by-email、要与commands.cfg命令配置文件里的相对应

6)、linux.cfg主机配置文件

#====================linux server=====================
define host{
                use                        generic-host
                host_name                cvs-1.11
                alias                         cvs-server
                address                     192.168.1.11
                check_command          check-host-alive
                max_check_attempts            10
                check_period                        24x7
                notification_interval               20
                notification_period                24x7
                notification_options                d,r
                contact_groups    admins
                name                         cvs-1.11 #定义名字
                }
define host{
                use                           generic-host

                host_name                   web-1.72
                alias                            web-server
                address                        192.168.1.72
                use                              cvs-1.11 #调用cvs-1.11的配置
                }

7)、windows.cfg配置文件

##############windows host################

define host{
                use                           generic-host
                host_name                 windows-1.8
                alias                          win-server
                address                      192.168.1.8
                check_command          check-host-alive
                max_check_attempts             10
                check_period                        24x7
                notification_interval               20
                notification_period                24x7
                notification_options                d,r
                contact_groups    admins
                name                          windows-1.8 #定义名字
                }
define host{
                use                  generic-host

                host_name        windows-1.71
                alias                 web-server
                address            192.168.1.71
                use                  windows-1.8 #调用windows-1.8配置文件
                }

8)、l-services.cfg定义服务配置文件

define service{
                use                                 generic-service
                host_name                       cvs-1.11 #与l-linux.cfg主机服务的名字相对应
                service_description              HTTP    status
                is_volatile                            0 #类似声音警告功能关闭
                check_period                       24x7 #监控期限为24X7
                max_check_attempts              3 #最大检测3次
                normal_check_interval             1  #每一分钟检测一次
                retry_check_interval               1  #间隔1分钟检测
                contact_groups                       admins #监控组
                notification_options                  w,u,c,r # w,u,c,r 发生这四种情况时，进行通告
                notification_interval                  5 # 通告间隔
                notification_period                    24x7 #检测时间段
                check_command                       check_http
                }

check_command监控命令有

check-host-alive、check_nrpe!check_disk1、check_nrpe!check_load、check_nrpe!check_total_procs、check_nrpe!check_swap等

9)、w-services.cfg配置文件

define service{
                use                                  generic-service
                host_name                        windows-1.8
                service_description         NSClient++ Version
                is_volatile                                 0
                check_period                             24x7
                max_check_attempts                  3
                normal_check_interval                 1
                retry_check_interval                   1
                contact_groups                          admins
                notification_options                     w,u,c,r
                notification_interval                     5
                notification_period                       24x7
                check_command             check_nt!CLIENTVERSION
                }

define service{
        use                       generic-service
        host_name               windows-1.8
        service_description     E:\ Drive Space
        is_volatile                     0
        check_period                 24x7
        max_check_attempts       3
        normal_check_interval      1
        retry_check_interval        1
        contact_groups               admins
        notification_options          w,u,c,r
        notification_interval           5
        notification_period             24x7
        check_command           check_nt!USEDDISKSPACE!-l e -w 80 -c 90
        }

# 如果要监控c 盘，check_nt!USEDDISKSPACE!-l c -w 80 -c 90 这里的c表示是c盘

check_command命令有

check_nt!UPTIME、check_nt!MEMUSE!-w 80 -c 90、(-w 80 -c 90)为当内存使用到80%为warning警告，内存使用到90%为critical紧急，check_nt!USEDDISKSPACE!-l c -w 80 -c 90、check_nt!PROCSTATE!-d SHOWALL -l Explorer.exe等。

10)、linux 客户端的安装配置与启动

    tar zxvf nrpe-2.8.1.tar.gz
    cd nrpe-2.8.1
   ./configure –prefix=/usr/local/nrpe
    make
    make install

10.1)、添加nagios用户组，并设置权限

root@client#useradd nagios -s /sbin/nologin

chown -R nagios.nagios /usr/local/nrpe

10.2）、需要把nagios监控服务器里的/usr/local/nagios/libexec下面的5个文件cp到 /usr/local/nrpe/libexec目录下

cp /usr/local/nrpe/libexec/check_nrpe     /usr/local/nagios/libexec
cp /usr/local/nagios/libexec/check_disk    /usr/local/nrpe/libexec
cp /usr/local/nagios/libexec/check_load    /usr/local/nrpe/libexec
cp /usr/local/nagios/libexec/check_ping    /usr/local/nrpe/libexec
cp /usr/local/nagios/libexec/check_procs   /usr/local/nrpe/libexec

10.3）、配置nrpe.cfg文件

mkdir /usr/local/nrpe/etc 创建目录

复制nrpe解压目录下的nrpe.cfg文件以 /usr/local/nrpe/etc目录下

cp /root/nrpe/nrpe.cfg /usr/local/nrpe/etc

修改nrpe.cfg文件

server_port=5666 #端口
server_address=192.168.1.56 #服务器IP
allowed_hosts=127.0.0.1,192.168.1.56 #充许nagios服务器IP访问

10.4)启动nrpe服务

10.4.1)、以独立守护进程启动nrpe服务

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

10.4.2)、检测nrpe服务是否正常启动

[root@nagios nrpe]# netstat -nltp | grep nrpe
tcp 0 0 192.168.1.56:5666 0.0.0.0:* LISTEN 2233/nrpe

能查看到5666这端口，说明nrpe启动正常