From ad708f4c6959b5f3e701cd91db792f5e1a17b1c2 Mon Sep 17 00:00:00 2001 From: Vallari Agrawal Date: Tue, 20 Jan 2026 14:26:13 +0530 Subject: [PATCH] monitoring: update NVMeoFTooManyNamespaces to 4096 ns Change NVMeoFTooManyNamespaces alert limit from 2048 namespaces to 4096 namespaces. Fixes: https://tracker.ceph.com/issues/74464 Signed-off-by: Vallari Agrawal --- monitoring/ceph-mixin/config.libsonnet | 2 +- monitoring/ceph-mixin/prometheus_alerts.yml | 4 +-- .../ceph-mixin/tests_alerts/test_alerts.yml | 28 +++++++++---------- 3 files changed, 17 insertions(+), 17 deletions(-) diff --git a/monitoring/ceph-mixin/config.libsonnet b/monitoring/ceph-mixin/config.libsonnet index ebe22e425f5b5..180ebfa0903c4 100644 --- a/monitoring/ceph-mixin/config.libsonnet +++ b/monitoring/ceph-mixin/config.libsonnet @@ -14,7 +14,7 @@ NVMeoFMaxGatewaysPerCluster: 32, NVMeoFHighGatewayCPU: 80, NVMeoFMaxSubsystemsPerGateway: 128, - NVMeoFMaxNamespaces: 2048, + NVMeoFMaxNamespaces: 4096, NVMeoFHighClientCount: 128, NVMeoFHostKeepAliveTimeoutTrackDurationHours: 24, NVMeoFHighHostCPU: 80, diff --git a/monitoring/ceph-mixin/prometheus_alerts.yml b/monitoring/ceph-mixin/prometheus_alerts.yml index 8901a477a2a8e..87631e81296a2 100644 --- a/monitoring/ceph-mixin/prometheus_alerts.yml +++ b/monitoring/ceph-mixin/prometheus_alerts.yml @@ -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" diff --git a/monitoring/ceph-mixin/tests_alerts/test_alerts.yml b/monitoring/ceph-mixin/tests_alerts/test_alerts.yml index 88caf7a3725ea..131d9811d562f 100644 --- a/monitoring/ceph-mixin/tests_alerts/test_alerts.yml +++ b/monitoring/ceph-mixin/tests_alerts/test_alerts.yml @@ -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 -- 2.47.3