]> git-server-git.apps.pok.os.sepia.ceph.com Git - ceph.git/commitdiff
monitoring: update NVMeoFTooManyNamespaces to 4096 ns 66988/head
authorVallari Agrawal <vallari.agrawal@ibm.com>
Tue, 20 Jan 2026 08:56:13 +0000 (14:26 +0530)
committerVallari Agrawal <vallari.agrawal@ibm.com>
Tue, 20 Jan 2026 09:13:03 +0000 (14:43 +0530)
Change NVMeoFTooManyNamespaces alert limit from 2048 namespaces
to 4096 namespaces.

Fixes: https://tracker.ceph.com/issues/74464
Signed-off-by: Vallari Agrawal <vallari.agrawal@ibm.com>
monitoring/ceph-mixin/config.libsonnet
monitoring/ceph-mixin/prometheus_alerts.yml
monitoring/ceph-mixin/tests_alerts/test_alerts.yml

index ebe22e425f5b5713e3213fc0cde95fe648eb5603..180ebfa0903c4e8688589d098216092dc1c051bf 100644 (file)
@@ -14,7 +14,7 @@
     NVMeoFMaxGatewaysPerCluster: 32,
     NVMeoFHighGatewayCPU: 80,
     NVMeoFMaxSubsystemsPerGateway: 128,
-    NVMeoFMaxNamespaces: 2048,
+    NVMeoFMaxNamespaces: 4096,
     NVMeoFHighClientCount: 128,
     NVMeoFHostKeepAliveTimeoutTrackDurationHours: 24,
     NVMeoFHighHostCPU: 80,
index 8901a477a2a8efcfade1e628d01a0ff2ccae3275..87631e81296a2ba74da6e73668e372d5847503c9 100644 (file)
@@ -875,9 +875,9 @@ groups:
           type: "ceph_default"
       - alert: "NVMeoFTooManyNamespaces"
         annotations:
-          description: "NVMeoF gateway {{ $labels.gateway_host }} has reached or exceeded the supported maximum of 2048 namespaces. Current count: {{ $value }}."
+          description: "NVMeoF gateway {{ $labels.gateway_host }} has reached or exceeded the supported maximum of 4096 namespaces. Current count: {{ $value }}."
           summary: "The number of namespaces defined to the NVMeoF gateway reached or exceeded supported values on cluster {{ $labels.cluster }}"
-        expr: "sum by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_namespace_count,\"gateway_host\",\"$1\",\"instance\",\"(.*?)(?::.*)?\")) >= 2048.00"
+        expr: "sum by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_namespace_count,\"gateway_host\",\"$1\",\"instance\",\"(.*?)(?::.*)?\")) >= 4096.00"
         for: "1m"
         labels:
           severity: "warning"
index 88caf7a3725eaee67a20e11ca5e2f1a149f9c6fd..131d9811d562fadfc63ebf8e296a86b58dcaf6bc 100644 (file)
@@ -2850,33 +2850,33 @@ tests:
  - interval: 1m
    input_series:
     - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn1",cluster="mycluster"}'
-      values: '200+0x10'
+      values: '400+0x10'
     - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn2",cluster="mycluster"}'
-      values: '200+0x10'
+      values: '400+0x10'
     - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn3",cluster="mycluster"}'
-      values: '200+0x10'
+      values: '400+0x10'
     - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn4",cluster="mycluster"}'
-      values: '200+0x10'
+      values: '400+0x10'
     - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn5",cluster="mycluster"}'
-      values: '200+0x10'
+      values: '400+0x10'
     - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn6",cluster="mycluster"}'
-      values: '200+0x10'
+      values: '400+0x10'
     - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn7",cluster="mycluster"}'
-      values: '200+0x10'
+      values: '400+0x10'
     - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn8",cluster="mycluster"}'
-      values: '200+0x10'
+      values: '400+0x10'
     - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn9",cluster="mycluster"}'
-      values: '200+0x10'
+      values: '400+0x10'
     - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn10",cluster="mycluster"}'
-      values: '200+0x10'
+      values: '400+0x10'
     - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn11",cluster="mycluster"}'
-      values: '200+0x10'
+      values: '400+0x10'
    promql_expr_test:
-     - expr: sum by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_namespace_count,"gateway_host","$1","instance","(.*):.*")) > 2048
+     - expr: sum by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_namespace_count,"gateway_host","$1","instance","(.*):.*")) > 4096
        eval_time: 1m
        exp_samples:
          - labels: '{gateway_host="node-1", cluster="mycluster"}'
-           value: 2200
+           value: 4400
    alert_rule_test:
     - eval_time: 5m
       alertname: NVMeoFTooManyNamespaces
@@ -2888,7 +2888,7 @@ tests:
           type: ceph_default
         exp_annotations:
           summary: "The number of namespaces defined to the NVMeoF gateway reached or exceeded supported values on cluster mycluster"
-          description: "NVMeoF gateway node-1 has reached or exceeded the supported maximum of 2048 namespaces. Current count: 2200."
+          description: "NVMeoF gateway node-1 has reached or exceeded the supported maximum of 4096 namespaces. Current count: 4400."
 
  # NVMeoFVersionMismatch
  - interval: 1m