This commit is contained in:
samber 2026-04-06 19:14:46 +00:00
parent c2615fae52
commit 0d148832d3

View file

@ -6,7 +6,7 @@ groups:
rules:
# ceph_health_status: 0=HEALTH_OK, 1=HEALTH_WARN, 2=HEALTH_ERR.
# This rule fires on any non-OK state. Split into separate warning/critical rules by using ==1 and ==2 thresholds if needed.
# This rule fires on any non-OK state. Split into ==1 (warning) and ==2 (critical) if you want separate severity levels.
- alert: CephState
expr: 'ceph_health_status != 0'
for: 1m
@ -54,7 +54,7 @@ groups:
description: "Ceph Object Storage Daemon latency is high. Please check if it doesn't stuck in weird state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Ceph internally triggers OSD_NEARFULL based on the nearfull_ratio (default 85%).
# ceph_health_detail can also be used for more granular OSD space alerts.
# ceph_health_detail exposes named health checks as individual time series.
- alert: CephOsdNearFull
expr: 'ceph_health_detail{name="OSD_NEARFULL"} == 1'
for: 5m