From: Vallari Agrawal <vallari.agrawal@ibm.com>
Date: Wed, 26 Feb 2025 16:01:54 +0000 (+0530)
Subject: monitoring: fix NVMeoFSubsystemNamespaceLimit
X-Git-Tag: testing/wip-vshankar-testing-20250306.055054-debug~2^2
X-Git-Url: http://git.apps.os.sepia.ceph.com/?a=commitdiff_plain;h=4a7866aeccfa29a7f1e46f8ca21a2487345d0d73;p=ceph-ci.git

monitoring: fix NVMeoFSubsystemNamespaceLimit

Alert is not triggered as expected, change the query
to fix that.

BZ: https://bugzilla.redhat.com/show_bug.cgi?id=2282348

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 f3e06a76f1f..2546a676222 100644
--- a/monitoring/ceph-mixin/prometheus_alerts.libsonnet
+++ b/monitoring/ceph-mixin/prometheus_alerts.libsonnet
@@ -848,7 +848,7 @@
         {
           alert: 'NVMeoFSubsystemNamespaceLimit',
           'for': '1m',
-          expr: '(count by(nqn, cluster) (ceph_nvmeof_subsystem_namespace_metadata)) >= ceph_nvmeof_subsystem_namespace_limit',
+          expr: '(count by(nqn, cluster, instance) (ceph_nvmeof_subsystem_namespace_metadata)) >= on(nqn, instance) group_right(cluster) ceph_nvmeof_subsystem_namespace_limit',
           labels: { severity: 'warning', type: 'ceph_default' },
           annotations: {
             summary: '{{ $labels.nqn }} subsystem has reached its maximum number of namespaces%(cluster)s' % $.MultiClusterSummary(),
diff --git a/monitoring/ceph-mixin/prometheus_alerts.yml b/monitoring/ceph-mixin/prometheus_alerts.yml
index f8bcd4ca0e1..33636f4ef41 100644
--- a/monitoring/ceph-mixin/prometheus_alerts.yml
+++ b/monitoring/ceph-mixin/prometheus_alerts.yml
@@ -760,7 +760,7 @@ groups:
         annotations:
           description: "Subsystems have a max namespace limit defined at creation time. This alert means that no more namespaces can be added to {{ $labels.nqn }}"
           summary: "{{ $labels.nqn }} subsystem has reached its maximum number of namespaces on cluster {{ $labels.cluster }}"
-        expr: "(count by(nqn, cluster) (ceph_nvmeof_subsystem_namespace_metadata)) >= ceph_nvmeof_subsystem_namespace_limit"
+        expr: "(count by(nqn, cluster, instance) (ceph_nvmeof_subsystem_namespace_metadata)) >= on(nqn, instance) group_right(cluster) ceph_nvmeof_subsystem_namespace_limit"
         for: "1m"
         labels:
           severity: "warning"