XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-24 02:17:00 +08:00
Code Issues Projects Releases Packages Wiki Activity

Added RAID alerts

Browse source
This commit is contained in:
Samuel Berthe 2020-03-07 17:50:41 +01:00
parent 67b322ae5b
commit ab477bb21e
No known key found for this signature in database
GPG key ID: 9D7813625412A946
1 changed files with 9 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
_data/rules.yml
View file

@ -92,6 +92,15 @@ services:
description: "Physical node temperature alarm triggered" description: "Physical node temperature alarm triggered"
query: "node_hwmon_temp_alarm == 1" query: "node_hwmon_temp_alarm == 1"
severity: critical severity: critical
- name: RAID array got inactive
description: 'RAID array "{{ $labels.device }}" is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.'
query: 'node_md_state{state="inactive"} > 0'
severity: critical
- name: RAID disk failure
description: 'At least one device in RAID array on {{ $labels.instance }} failed. Array "{{ $labels.md_device }}" needs attention and possibly a disk swap'
query: 'node_md_disks{state="fail"} > 0'
severity: warning
- name: Docker containers - name: Docker containers
exporters: exporters: