monitoring: alert for prediction of disk and pool fill up broken

Fixes: https://tracker.ceph.com/issues/44776
Signed-off-by: Patrick Seidensal <pseidensal@suse.com>
(cherry picked from commit 6935dc55921ef533e939719bad7dc12324450bbb)

Conflicts:
  monitoring/prometheus/alerts/ceph_default_alerts.yml

diff --git a/monitoring/prometheus/alerts/ceph_default_alerts.yml b/monitoring/prometheus/alerts/ceph_default_alerts.yml
index ba7764d32e9c689e03939f2c17bde1be57ec844b..4c37d7f9c9b0a949296c772263edd7b9949509fc 100644 (file)
--- a/monitoring/prometheus/alerts/ceph_default_alerts.yml
+++ b/monitoring/prometheus/alerts/ceph_default_alerts.yml
@@ -186,15 +186,10 @@ groups:
             Node {{ $labels.instance }} experiences packet errors > 1
             packet/s on interface {{ $labels.device }}.
 
-      # predict fs fill-up times
-      - alert: storage filling
+      - alert: storage filling up
         expr: |
-          (
-            (
-              node_filesystem_free_bytes / deriv(node_filesystem_free_bytes[2d])
-              * on(instance) group_left(nodename) node_uname_info
-            ) <= 5
-          ) > 0
+          predict_linear(node_filesystem_free_bytes[2d], 3600 * 24 * 5) *
+          on(instance) group_left(nodename) node_uname_info < 0
         labels:
           severity: warning
           type: ceph_default
@@ -219,10 +214,9 @@ groups:
       - alert: pool filling up
         expr: |
           (
-            (
-              (ceph_pool_max_avail - ceph_pool_stored) / deriv(ceph_pool_max_avail[2d])
-            ) * on(pool_id) group_right ceph_pool_metadata <= 5
-          ) > 0
+            predict_linear(ceph_pool_stored[2d], 3600 * 24 * 5) >=
+            ceph_pool_max_avail
+          ) * on(pool_id) group_right(name) ceph_pool_metadata
         labels:
           severity: warning
           type: ceph_default