define contact{ name generic-contact ; 联系人名称 service_notification_period 24x7 ; 当服务出现异常时,发送通知的时间段,这个时间段"24x7"在timeperiods.cfg文件中定义 host_notification_period 24x7 ; 当主机出现异常时,发送通知的时间段,这个时间段"24x7"在timeperiods.cfg文件中定义 service_notification_options w,u,c,r ; 这个定义的是“通知可以被发出的情况”。w即warn,表示警告状态,u即unknown,表示不明状态; ; c即criticle,表示紧急状态,r即recover,表示恢复状态; ; 也就是在服务出现警告状态、未知状态、紧急状态和重新恢复状态时都发送通知给使用者。 host_notification_options d,u,r ; 定义主机在什么状态下需要发送通知给使用者,d即down,表示宕机状态; ; u即unreachable,表示不可到达状态,r即recovery,表示重新恢复状态。 service_notification_commands notify-service-by-email ; 服务故障时,发送通知的方式,可以是邮件和短信,这里发送的方式是邮件; ; 其中“notify-service-by-email”在commands.cfg文件中定义。 host_notification_commands notify-host-by-email ; 主机故障时,发送通知的方式,可以是邮件和短信,这里发送的方式是邮件; ; 其中“notify-host-by-email”在commands.cfg文件中定义。 register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL CONTACT, JUST A TEMPLATE! } define host{ name generic-host ; 主机名称,这里的主机名,并不是直接对应到真正机器的主机名; ; 乃是对应到在主机配置文件里所设定的主机名。 notifications_enabled 1 ; Host notifications are enabled event_handler_enabled 1 ; Host event handler is enabled flap_detection_enabled 1 ; Flap detection is enabled failure_prediction_enabled 1 ; Failure prediction is enabled process_perf_data 1 ; 其值可以为0或1,其作用为是否启用Nagios的数据输出功能; ; 如果将此项赋值为1,那么Nagios就会将收集的数据写入某个文件中,以备提取。 retain_status_information 1 ; Retain status information across program restarts retain_nonstatus_information 1 ; Retain non-status information across program restarts notification_period 24x7 ; 指定“发送通知”的时间段,也就是可以在什么时候发送通知给使用者。 register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL HOST, JUST A TEMPLATE! } define host{ name linux-server ; 主机名称 use generic-host ; use表示引用,也就是将主机generic-host的所有属性引用到linux-server中来; ; 在nagios配置中,很多情况下会用到引用。 check_period 24x7 ; 这里的check_period告诉nagios检查主机的时间段 check_interval 5 ; nagios对主机的检查时间间隔,这里是5分钟。 retry_interval 1 ; 重试检查时间间隔,单位是分钟。 max_check_attempts 10 ; nagios对主机的最大检查次数,也就是nagios在检查发现某主机异常时,并不马上判断为异常状况; ; 而是多试几次,因为有可能只是一时网络太拥挤,或是一些其他原因,让主机受到了一点影响; ; 这里的10就是最多试10次的意思。 check_command check-host-alive ; 指定检查主机状态的命令,其中“check-host-alive”在commands.cfg文件中定义。 notification_period 24x7 ; 主机故障时,发送通知的时间范围,其中“workhours”在timeperiods.cfg中进行了定义; ; 下面会陆续讲到。 notification_interval 10 ; 在主机出现异常后,故障一直没有解决,nagios再次对使用者发出通知的时间。单位是分钟; ; 如果你觉得,所有的事件只需要一次通知就够了,可以把这里的选项设为0 notification_options d,u,r ; 定义主机在什么状态下可以发送通知给使用者,d即down,表示宕机状态; ; u即unreachable,表示不可到达状态; ; r即recovery,表示重新恢复状态。 contact_groups ts ; 指定联系人组,这个“admins”在contacts.cfg文件中定义。 register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL HOST, JUST A TEMPLATE! } define host{ name windows-server ; The name of this host template use generic-host ; Inherit default values from the generic-host template check_period 24x7 ; By default, Windows servers are monitored round the clock check_interval 5 ; Actively check the server every 5 minutes retry_interval 1 ; Schedule host check retries at 1 minute intervals max_check_attempts 10 ; Check each server 10 times (max) check_command check-host-alive ; Default command to check if servers are "alive" notification_period 24x7 ; Send notification out at any time - day or night notification_interval 10 ; Resend notifications every 30 minutes notification_options d,r ; Only send notifications for specific host states contact_groups ts ; Notifications get sent to the admins by default hostgroups windows-servers ; Host groups that Windows servers should be a member of register 0 ; DONT REGISTER THIS - ITS JUST A TEMPLATE } define service{ name generic-service ; 定义一个服务名称 active_checks_enabled 1 ; Active service checks are enabled passive_checks_enabled 1 ; Passive service checks are enabled/accepted parallelize_check 1 ; Active service checks should be parallelized; ; (disabling this can lead to major performance problems) obsess_over_service 1 ; We should obsess over this service (if necessary) check_freshness 0 ; Default is to NOT check service 'freshness' notifications_enabled 1 ; Service notifications are enabled event_handler_enabled 1 ; Service event handler is enabled flap_detection_enabled 1 ; Flap detection is enabled failure_prediction_enabled 1 ; Failure prediction is enabled process_perf_data 1 ; Process performance data retain_status_information 1 ; Retain status information across program restarts retain_nonstatus_information 1 ; Retain non-status information across program restarts is_volatile 0 ; The service is not volatile check_period 24x7 ; 这里的check_period告诉nagios检查服务的时间段。 max_check_attempts 3 ; nagios对服务的最大检查次数。 normal_check_interval 5 ; 此选项是用来设置服务检查时间间隔,也就是说,nagios这一次检查和下一次检查之间所隔的时间; ; 这里是5分钟。 retry_check_interval 2 ; 重试检查时间间隔,单位是分钟。 contact_groups ts ; 指定联系人组 notification_options w,u,c,r ; 这个定义的是“通知可以被发出的情况”。w即warn,表示警告状态; ; u即unknown,表示不明状态; ; c即criticle,表示紧急状态,r即recover,表示恢复状态; ; 也就是在服务出现警告状态、未知状态、紧急状态和重新恢复后都发送通知给使用者。 notification_interval 10 ; Re-notify about service problems every hour notification_period 24x7 ; 指定“发送通知”的时间段,也就是可以在什么时候发送通知给使用者。 register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL SERVICE, JUST A TEMPLATE! } define service{ name local-service ; The name of this service template use generic-service ; Inherit default values from the generic-service definition max_check_attempts 4 ; Re-check the service up to 4 times in order to determine its final (hard) state normal_check_interval 5 ; Check the service every 5 minutes under normal conditions retry_check_interval 1 ; Re-check the service every minute until a hard state can be determined register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL SERVICE, JUST A TEMPLATE! }
define hostgroup { hostgroup_name 51_ganglia-servers ; 这个name也是要在hostgroup中全局唯一的,而且也是在下面使用到 alias nagios server members 192.168.1.51 ; 这里的成员名字是上面host里面的host_name字段的值,如果是多个成员,记得使用英文逗号隔开 }
define service { use 51_ganglia-service ; Name of service template to use service_description 当前用户 check_period 24x7 ; 检测的时间段 max_check_attempts 3 ; 最大检测次数 normal_check_interval 3 retry_check_interval 2 contact_groups admins ; 发生故障通知的联系人组 notification_interval 120 notification_period 24x7 ; 通知的时间段 notification_options w,u,c,r
check_command check_local_users!20!50 }
define service { use 51_ganglia-service ; Name of service template to use service_description Total Processes check_period 24x7 ; 检测的时间段 max_check_attempts 3 ; 最大检测次数 normal_check_interval 3 retry_check_interval 2 contact_groups admins ; 发生故障通知的联系人组 notification_interval 30 notification_period 24x7 ; 通知的时间段 notification_options w,u,c,r
check_command check_local_procs!250!400!RSZDT }
define service { use 51_ganglia-service ; Name of service template to use service_description Swap Usage check_period 24x7 ; 检测的时间段 max_check_attempts 3 ; 最大检测次数 normal_check_interval 3 retry_check_interval 2 contact_groups admins ; 发生故障通知的联系人组 notification_interval 30 notification_period 24x7 ; 通知的时间段 notification_options w,u,c,r
check_command check_local_swap!15%!10% }
define service { use 51_ganglia-service ; Name of service template to use service_description HTTP check_period 24x7 ; 检测的时间段 max_check_attempts 3 ; 最大检测次数,达到之后即发送警报 normal_check_interval 3 ; 正常监测时间间隔 retry_check_interval 2 ; 异常重试时间间隔 contact_groups admins ; 发生故障通知的联系人组 notification_interval 0 ; 发送警报时间间隔,单位为分钟 notification_period 24x7 ; 通知的时间段 notification_options w,u,c,r
check_command check_http }
define service { use 51_ganglia-service ; Name of service template to use service_description nginx check_period 24x7 ; 检测的时间段 max_check_attempts 3 ; 最大检测次数,达到之后即发送警报 normal_check_interval 3 ; 正常监测时间间隔 retry_check_interval 2 ; 异常重试时间间隔 contact_groups admins ; 发生故障通知的联系人组 notification_interval 0 ; 发送警报时间间隔,单位为分钟,为0表示仅仅发送一次 notification_period 24x7 ; 通知的时间段 notification_options w,u,c,r
check_command check_procs_nginx }
define service { use 51_ganglia-service ; Name of service template to use service_description mysql check_period 24x7 ; 检测的时间段 max_check_attempts 3 ; 最大检测次数,达到之后即发送警报 normal_check_interval 3 ; 正常监测时间间隔 retry_check_interval 2 ; 异常重试时间间隔 contact_groups admins ; 发生故障通知的联系人组 notification_interval 0 ; 发送警报时间间隔,单位为分钟,为0表示仅仅发送一次 notification_period 24x7 ; 通知的时间段 notification_options w,u,c,r
define host{ 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 } define hostgroup{ hostgroup_name linux-servers ; The name of the hostgroup alias Linux Servers ; Long name of the group members Nagios-Server ; Comma separated list of hosts that belong to this group } define service{ 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% } define service{ use local-service ; Name of service template to use host_name Nagios-Server service_description Root Partition check_command check_local_disk!20%!10%!/ } define service{ use local-service ; Name of service template to use host_name Nagios-Server service_description Current Users check_command check_local_users!20!50 } define service{ 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 } define service{ 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 } define service{ use local-service ; Name of service template to use host_name Nagios-Server service_description Swap Usage check_command check_local_swap!20!10 } define service{ use local-service ; Name of service template to use host_name Nagios-Server service_description SSH check_command check_ssh notifications_enabled 0 } define service{ use local-service ; Name of service template to use host_name Nagios-Server service_description HTTP check_command check_http notifications_enabled 0 }
define host{ 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 } define hostgroup{ hostgroup_name windows-servers ; The name of the hostgroup alias Windows Servers ; Long name of the group } define service{ use generic-service host_name Nagios-Windows service_description NSClient++ Version check_command check_nt!CLIENTVERSION } define service{ use generic-service host_name Nagios-Windows service_description Uptime check_command check_nt!UPTIME } define service{ use generic-service host_name Nagios-Windows service_description CPU Load check_command check_nt!CPULOAD!-l 5,80,90 } define service{ use generic-service host_name Nagios-Windows service_description Memory Usage check_command check_nt!MEMUSE!-w 80 -c 90 } define service{ use generic-service host_name Nagios-Windows service_description C:\ Drive Space check_command check_nt!USEDDISKSPACE!-l c -w 80 -c 90 } define service{ use generic-service host_name Nagios-Windows service_description W3SVC check_command check_nt!SERVICESTATE!-d SHOWALL -l W3SVC } define service{ use generic-service host_name Nagios-Windows service_description Explorer check_command check_nt!PROCSTATE!-d SHOWALL -l Explorer.exe }
Nagios Core 4.4.3 Copyright (c) 2009-present Nagios Core Development Team and Community Contributors Copyright (c) 1999-2009 Ethan Galstad Last Modified: 2019-01-15 License: GPL
Website: https://www.nagios.org Reading configuration data... Read main config file okay... WARNING: The normal_check_interval attribute is deprecated and will be removed in future versions. Please use check_interval instead.