gian/ceph-mirror
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2026-08-02 07:03:18 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

monitoring: update NVMeoFTooManyNamespaces to 4096 ns

Browse Source 
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>
This commit is contained in:
Vallari Agrawal 2026-01-20 14:26:13 +05:30
parent 5c94d225b4
commit ad708f4c69
No known key found for this signature in database
GPG Key ID: 83EC142692896009
3 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
monitoring/ceph-mixin/config.libsonnet
View File

@ -14,7 +14,7 @@
NVMeoFMaxGatewaysPerCluster: 32,
NVMeoFHighGatewayCPU: 80,
NVMeoFMaxSubsystemsPerGateway: 128,
NVMeoFMaxNamespaces: 2048,
NVMeoFMaxNamespaces: 4096,
NVMeoFHighClientCount: 128,
NVMeoFHostKeepAliveTimeoutTrackDurationHours: 24,
NVMeoFHighHostCPU: 80,

4
monitoring/ceph-mixin/prometheus_alerts.yml
View 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"

28
monitoring/ceph-mixin/tests_alerts/test_alerts.yml
View 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