Merge pull request #31711 from p-se/wip-pse-fix-osd-full-alert

monitoring: wait before firing osd full alert Reviewed-by: Jan Fajerski <jfajerski@suse.com>
ceph · Nov 24, 2019 · 2add8d1 · 2add8d1
2 parents 3e66ada + d262ade
commit 2add8d1
Showing 1 changed file with 5 additions and 4 deletions.
diff --git a/monitoring/prometheus/alerts/ceph_default_alerts.yml b/monitoring/prometheus/alerts/ceph_default_alerts.yml
@@ -50,6 +50,7 @@ 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
@@ -65,8 +66,8 @@ groups:
           oid: 1.3.6.1.4.1.50495.15.1.2.4.4
         annotations:
           description: >
-              OSD {{ $labels.ceph_daemon }} was marked down and back up at least once a
-              minute for 5 minutes.
+            OSD {{ $labels.ceph_daemon }} was marked down and back up at least once a
+            minute for 5 minutes.
       # alert on high deviation from average PG count
       - alert: high pg count deviation
         expr: abs(((ceph_osd_numpg > 0) - on (job) group_left avg(ceph_osd_numpg > 0) by (job)) / on (job) group_left avg(ceph_osd_numpg > 0) by (job)) > 0.35
@@ -77,8 +78,8 @@ groups:
           oid: 1.3.6.1.4.1.50495.15.1.2.4.5
         annotations:
           description: >
-              OSD {{ $labels.ceph_daemon }} deviates by more than 30% from
-              average PG count.
+            OSD {{ $labels.ceph_daemon }} deviates by more than 30% from
+            average PG count.
       # alert on high commit latency...but how high is too high
   - name: mds
     rules: