From: Vallari Agrawal <val.agl002@gmail.com>
Date: Tue, 8 Oct 2024 21:07:48 +0000 (+0530)
Subject: monitoring: add 2 nvmeof alerts to prometheus_alerts.yaml
X-Git-Tag: testing/wip-vshankar-testing-20241118.055430-debug~11^2~2
X-Git-Url: http://git.apps.os.sepia.ceph.com/?a=commitdiff_plain;h=f02e3128441f5bba95c6173d2acb61baa4111d01;p=ceph-ci.git

monitoring: add 2 nvmeof alerts to prometheus_alerts.yaml

- `NVMeoFMissingListener`: trigger if all listeners
     are not created for each gateway in a subsystem
- `NVMeoFZeroListenerSubsystem`: trigger if a subsystem has no listeners

Signed-off-by: Vallari Agrawal <vallari.agrawal@ibm.com>
---

diff --git a/monitoring/ceph-mixin/prometheus_alerts.yml b/monitoring/ceph-mixin/prometheus_alerts.yml
index ba6a6ded0a3..805ecb1188a 100644
--- a/monitoring/ceph-mixin/prometheus_alerts.yml
+++ b/monitoring/ceph-mixin/prometheus_alerts.yml
@@ -837,6 +837,24 @@ groups:
         labels:
           severity: "warning"
           type: "ceph_default"
+      - alert: "NVMeoFMissingListener"
+        annotations:
+          description: "For every subsystem, each gateway should have a listener to balance traffic between gateways."
+          summary: "No listener added for {{ $labels.instance }} NVMe-oF Gateway to {{ $labels.nqn }} subsystem"
+        expr: "ceph_nvmeof_subsystem_listener_count == 0 and on(nqn) sum(ceph_nvmeof_subsystem_listener_count) by (nqn) > 0"
+        for: "10m"
+        labels:
+          severity: "warning"
+          type: "ceph_default"
+      - alert: "NVMeoFZeroListenerSubsystem"
+        annotations:
+          description: "NVMeoF gateway configuration incomplete; one of the subsystems have zero listeners."
+          summary: "No listeners added to {{ $labels.nqn }} subsystem"
+        expr: "sum(ceph_nvmeof_subsystem_listener_count) by (nqn) == 0"
+        for: "10m"
+        labels:
+          severity: "warning"
+          type: "ceph_default"
       - alert: "NVMeoFHighHostCPU"
         annotations:
           description: "High CPU on a gateway host can lead to CPU contention and performance degradation"