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>
This commit is contained in:
Vallari Agrawal 2025-02-26 21:31:54 +05:30
parent 9fa163df8f
commit 4a7866aecc
No known key found for this signature in database
GPG Key ID: 83EC142692896009
2 changed files with 2 additions and 2 deletions

View File

@ -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(),

View File

@ -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"