mgr/dashboard: trigger alert if some nodes have a MTU different than the median value

This PR intends to alert a user if a specific network is configured with a custom MTU

Fixes: https://tracker.ceph.com/issues/48748
Signed-off-by: Aashish Sharma <aasharma@redhat.com>
(cherry picked from commit 06cc0d8743f288e1ef77e96b817f0f3381ac53d3)

diff --git a/monitoring/prometheus/alerts/ceph_default_alerts.yml b/monitoring/prometheus/alerts/ceph_default_alerts.yml
index 74907fd024e47db549b1d2b69f3c9950f3b0b8bc..5917b80161ada8b941d914743ff8749751a74a68 100644 (file)
--- a/monitoring/prometheus/alerts/ceph_default_alerts.yml
+++ b/monitoring/prometheus/alerts/ceph_default_alerts.yml
@@ -200,6 +200,17 @@ groups:
             will be full in less than 5 days assuming the average fill-up
             rate of the past 48 hours.
 
+      - alert: MTU Mismatch
+        expr: node_network_mtu_bytes{device!="lo"} != on(device) group_left() (quantile(0.5, node_network_mtu_bytes{device!="lo"}) by (device))
+        labels:
+          severity: warning
+          type: ceph_default
+          oid: 1.3.6.1.4.1.50495.15.1.2.8.5
+        annotations:
+          description: >
+            Node {{ $labels.instance }} has a different MTU size ({{ $value }})
+            than the median value on device {{ $labels.device }}.
+
   - name: pools
     rules:
       - alert: pool full