From f3d21320a2c1dc365388b6809085db8f9204b777 Mon Sep 17 00:00:00 2001 From: Aashish Sharma Date: Tue, 5 Jan 2021 14:34:22 +0530 Subject: [PATCH] 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 (cherry picked from commit 06cc0d8743f288e1ef77e96b817f0f3381ac53d3) --- monitoring/prometheus/alerts/ceph_default_alerts.yml | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/monitoring/prometheus/alerts/ceph_default_alerts.yml b/monitoring/prometheus/alerts/ceph_default_alerts.yml index b07ea80ea8ac0..abc6f647142b5 100644 --- a/monitoring/prometheus/alerts/ceph_default_alerts.yml +++ b/monitoring/prometheus/alerts/ceph_default_alerts.yml @@ -214,6 +214,17 @@ 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 -- 2.39.5