monitoring: wait before firing osd full alert

Fixes: https://tracker.ceph.com/issues/42862
Signed-off-by: Patrick Seidensal <pseidensal@suse.com>
(cherry picked from commit e923af34309a0c0adbf36e0fcf57fb6aa0240c48)

diff --git a/monitoring/prometheus/alerts/ceph_default_alerts.yml b/monitoring/prometheus/alerts/ceph_default_alerts.yml
index 310be58fa710fbb0a64b1e3b3fa893e3dfaf3f1f..bf547cf008dad4b5397d4ca3ca3f7030e9c7943c 100644 (file)
--- a/monitoring/prometheus/alerts/ceph_default_alerts.yml
+++ b/monitoring/prometheus/alerts/ceph_default_alerts.yml
@@ -45,6 +45,7 @@ groups:
           description: One or more OSDs down for more than 15 minutes.
       - alert: OSDs near full
         expr: ((ceph_osd_stat_bytes_used / ceph_osd_stat_bytes) and on(ceph_daemon) ceph_osd_up == 1) > 0.8
+        for: 5m
         labels:
           severity: critical
           type: ceph_default