monitoring: fix NVMeoFSubsystemNamespaceLimit

VallariAg · VallariAg · commit 4a7866aeccfa · 2025-02-26T21:31:54.000+05:30
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
@@ -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
@@ -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"

Original file line number	Diff line number	Diff line change
`@@ -848,7 +848,7 @@`
`848`	`848`	`{`
`849`	`849`	`alert: 'NVMeoFSubsystemNamespaceLimit',`
`850`	`850`	`'for': '1m',`
`851`		`- expr: '(count by(nqn, cluster) (ceph_nvmeof_subsystem_namespace_metadata)) >= ceph_nvmeof_subsystem_namespace_limit',`
	`851`	`+ expr: '(count by(nqn, cluster, instance) (ceph_nvmeof_subsystem_namespace_metadata)) >= on(nqn, instance) group_right(cluster) ceph_nvmeof_subsystem_namespace_limit',`
`852`	`852`	`labels: { severity: 'warning', type: 'ceph_default' },`
`853`	`853`	`annotations: {`
`854`	`854`	`summary: '{{ $labels.nqn }} subsystem has reached its maximum number of namespaces%(cluster)s' % $.MultiClusterSummary(),`