mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-21 00:47:18 +08:00
Fix from #405
This commit is contained in:
parent
d916b7c6ab
commit
fc6b3faadc
1 changed files with 12 additions and 0 deletions
|
|
@ -331,6 +331,18 @@ groups:
|
|||
description: Device temperature critical on {{ $labels.instance }} drive {{ $labels.device }} over 70°C
|
||||
query: '(max_over_time(smartctl_device_temperature{temperature_type="current"} [5m]) unless on (instance, device) smartctl_device_temperature{temperature_type="drive_trip"}) > 70'
|
||||
severity: critical
|
||||
- name: SMART device temperature over trip value
|
||||
description: Device temperature over trip value on {{ $labels.instance }} drive {{ $labels.device }})
|
||||
query: 'max_over_time(smartctl_device_temperature{temperature_type="current"} [10m]) >= on(device, instance) smartctl_device_temperature{temperature_type="drive_trip"}'
|
||||
severity: critical
|
||||
- name: SMART device temperature nearing trip value
|
||||
description: Device temperature at 80% of trip value on {{ $labels.instance }} drive {{ $labels.device }})
|
||||
query: 'max_over_time(smartctl_device_temperature{temperature_type="current"} [10m]) >= on(device, instance) (smartctl_device_temperature{temperature_type="drive_trip"} * .80)'
|
||||
severity: warning
|
||||
- name: SMART status
|
||||
description: Device has a SMART status failure on {{ $labels.instance }} drive {{ $labels.device }})
|
||||
query: 'smartctl_device_smart_status != 1'
|
||||
severity: critical
|
||||
- name: SMART critical warning
|
||||
description: Disk controller has critical warning on {{ $labels.instance }} drive {{ $labels.device }})
|
||||
query: 'smartctl_device_critical_warning > 0'
|
||||
|
|
|
|||
Loading…
Reference in a new issue