From: Vallari Agrawal <vallari.agrawal@ibm.com>
Date: Wed, 30 Oct 2024 14:02:41 +0000 (+0530)
Subject: monitoring: add 2 new nvmeof alerts
X-Git-Tag: testing/wip-vshankar-testing-20241118.055430-debug~11^2~1
X-Git-Url: http://git-server-git.apps.pok.os.sepia.ceph.com/?a=commitdiff_plain;h=7994fea43630b052fabb79c39241927dc7bb6678;p=ceph-ci.git

monitoring: add 2 new nvmeof alerts

Add NVMeoFMissingListener and NVMeoFZeroListenerSubsystem
alerts to prometheus_alerts.libsonnet.

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

diff --git a/monitoring/ceph-mixin/prometheus_alerts.libsonnet b/monitoring/ceph-mixin/prometheus_alerts.libsonnet
index cde1a736f8c..30b6b07d463 100644
--- a/monitoring/ceph-mixin/prometheus_alerts.libsonnet
+++ b/monitoring/ceph-mixin/prometheus_alerts.libsonnet
@@ -935,6 +935,26 @@
             description: 'The supported limit for clients connecting to a subsystem is %(NVMeoFHighClientCount)d' % $._config,
           },
         },
+        {
+          alert: 'NVMeoFMissingListener',
+          'for': '10m',
+          expr: 'ceph_nvmeof_subsystem_listener_count == 0 and on(nqn) sum(ceph_nvmeof_subsystem_listener_count) by (nqn) > 0',
+          labels: { severity: 'warning', type: 'ceph_default' },
+          annotations: {
+            summary: 'No listener added for {{ $labels.instance }} NVMe-oF Gateway to {{ $labels.nqn }} subsystem',
+            description: 'For every subsystem, each gateway should have a listener to balance traffic between gateways.',
+          },
+        },
+        {
+          alert: 'NVMeoFZeroListenerSubsystem',
+          'for': '10m',
+          expr: 'sum(ceph_nvmeof_subsystem_listener_count) by (nqn) == 0',
+          labels: { severity: 'warning', type: 'ceph_default' },
+          annotations: {
+            summary: 'No listeners added to {{ $labels.nqn }} subsystem',
+            description: 'NVMeoF gateway configuration incomplete; one of the subsystems have zero listeners.',
+          },
+        },
         {
           alert: 'NVMeoFHighHostCPU',
           'for': '10m',