Estou com dificuldades para configurar o nagios3 para fazer o que eu quero. Muitos arquivos de configuração e não sei exatamente onde está o problema, pois tudo parece correto.
Primeiro, as notificações foram enviadas para down hosts e serviços críticos, então eu queria configurá-lo para que ele também enviasse notificações sobre recuperação e agora ele só envia isso, mas não para tudo.
A maneira que eu quero configurá-lo é para usar o serviço genérico como modelo e depois configurar detalhes adicionais se eu precisar, mas não está jogando bola, aqui estão meus arquivos de configuração, veja se você vê algo errado:
O que eu quero é simples. Envie e-mail quando o host estiver inoperante, quando o serviço for crítico e quando ele for recuperado - é isso!
---- Arquivo contacts.cfg ---
define contact{
contact_name admin
alias administrator
service_notification_period 24x7
host_notification_period 24x7
service_notification_options u,c,r
host_notification_options d,u,r
service_notification_commands notify-service-by-email
host_notification_commands notify-host-by-email
email [email protected]
}
define contactgroup{
contactgroup_name admins
alias Nagios Administrators
members admin
}
--------------------- EOF ----------
------ arquivo generic-service.cfg ---------
define service{
name generic-service ; The 'name' of this service template
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
notification_interval 0 ; Only send notifications on status change by default.
is_volatile 0
check_period 24x7
normal_check_interval 1
retry_check_interval 1
max_check_attempts 4
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL SERVICE, JUST A TEMPLATE!
}
--------------- EOF --------
---- arquivo generic-host.cfg ----
define host{
name generic-host ; The name of this host template
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 ; Process performance data
retain_status_information 1 ; Retain status information across program restarts
retain_nonstatus_information 1 ; Retain non-status information across program restarts
# check_command check-host-alive
check_command check_tcp_alive
max_check_attempts 10
notification_interval 0
notification_period 24x7
notification_options d,u,r
contact_groups admins
register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL HOST, JUST A TEMPLATE!
}
---- Excerce de servicegroups.cfg -----
define service {
hostgroup_name Live, inhouse
service_description USERS
check_command check_nrpe_1arg!check_users
use generic-service
normal_check_interval
10
retry_check_interval 10
contact_groups admins
notification_interval 0 ; set > 0 if you want to be renotified
}
# check the LOAD
define service {
hostgroup_name Live, inhouse
service_description LOAD
check_command check_nrpe_1arg!check_load
use generic-service
normal_check_interval 5
retry_check_interval 1
notification_interval 0 ; set > 0 if you want to be renotified
}
# check the HDD
define service {
hostgroup_name Live, inhouse
service_description HDD
check_command check_nrpe_1arg!check_all_disks
use generic-service
normal_check_interval 600
retry_check_interval 30
notification_interval 0 ; set > 0 if you want to be renotified
}
----- EOF -----
--- Trecho de Hostgroups.cfg ----
define hostgroup {
hostgroup_name http-servers
alias HTTP servers
members *
}
---- EOF -----