feat: add postgres/gitea/blackbox alerts and more node alerts
This commit is contained in:
19
environments/dev/adibrov/alerts/blackbox/endpoint_down.yaml
Normal file
19
environments/dev/adibrov/alerts/blackbox/endpoint_down.yaml
Normal file
@ -0,0 +1,19 @@
|
||||
name: "DEV ADIBROV - Endpoint Down (Blackbox)"
|
||||
expression: |
|
||||
probe_success{job="blackbox"}
|
||||
threshold: 1
|
||||
for: "3m"
|
||||
condition_type: "lt"
|
||||
need_reduce: true
|
||||
reducer_type: "min"
|
||||
no_data_state: "Alerting"
|
||||
exec_err_state: "Alerting"
|
||||
labels:
|
||||
service: "blackbox"
|
||||
severity: "critical"
|
||||
team: "infra"
|
||||
summary: |
|
||||
Endpoint недоступен: {{ $labels.instance }}
|
||||
description: |
|
||||
Blackbox exporter не может достучаться до {{ $labels.instance }}.
|
||||
Сервис недоступен снаружи уже более 3 минут.
|
||||
@ -0,0 +1,19 @@
|
||||
name: "DEV ADIBROV - SSL Certificate Expiring Soon"
|
||||
expression: |
|
||||
(probe_ssl_earliest_cert_expiry{job="blackbox"} - time()) / 86400
|
||||
threshold: 14
|
||||
for: "1h"
|
||||
condition_type: "lt"
|
||||
need_reduce: true
|
||||
reducer_type: "min"
|
||||
no_data_state: "OK"
|
||||
exec_err_state: "Error"
|
||||
labels:
|
||||
service: "blackbox"
|
||||
severity: "warning"
|
||||
team: "infra"
|
||||
summary: |
|
||||
SSL сертификат истекает через {{ printf "%.0f" $values.B.Value }} дней: {{ $labels.instance }}
|
||||
description: |
|
||||
SSL сертификат для {{ $labels.instance }} истекает менее чем через 14 дней.
|
||||
Необходимо обновить сертификат до истечения срока действия.
|
||||
Reference in New Issue
Block a user