Skip to content

Refactor quota overcommit rules #1089

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 11, 2025
Merged

Refactor quota overcommit rules #1089

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
77 changes: 31 additions & 46 deletions alerts/resource_alerts.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,27 @@ local utils = import '../lib/utils.libsonnet';
)
||| % $._config { resource: resource },

local kubeQuotaOvercommitExpression(resource) = if $._config.showMultiCluster then
|||
sum by(%(clusterLabel)s) (
min without(resource) (kube_resourcequota{%(prefixedNamespaceSelector)s%(kubeStateMetricsSelector)s, type="hard", resource=~"(%(resource)s|requests.%(resource)s)"})
)
/
sum by(%(clusterLabel)s) (
kube_node_status_allocatable{resource="%(resource)s", %(kubeStateMetricsSelector)s}
) > %(namespaceOvercommitFactor)s
||| % $._config { resource: resource }
else
|||
sum (
min without(resource) (kube_resourcequota{%(prefixedNamespaceSelector)s%(kubeStateMetricsSelector)s, type="hard", resource=~"(%(resource)s|requests.%(resource)s)"})
)
/
sum (
kube_node_status_allocatable{resource="%(resource)s", %(kubeStateMetricsSelector)s}
) > %(namespaceOvercommitFactor)s
||| % $._config { resource: resource },

_config+:: {
kubeStateMetricsSelector: error 'must provide selector for kube-state-metrics',
nodeExporterSelector: error 'must provide selector for node-exporter',
Expand Down Expand Up @@ -114,63 +135,27 @@ local utils = import '../lib/utils.libsonnet';
},
annotations: {
summary: 'Cluster has overcommitted CPU resource requests.',
description: 'Cluster%s has overcommitted CPU resource requests for Namespaces.' % [
utils.ifShowMultiCluster($._config, ' {{ $labels.%(clusterLabel)s }}' % $._config),
],
},
expr: kubeQuotaOvercommitExpression('cpu'),
'for': '5m',
} +
if $._config.showMultiCluster then {
expr: |||
sum(min without(resource) (kube_resourcequota{%(prefixedNamespaceSelector)s%(kubeStateMetricsSelector)s, type="hard", resource=~"(cpu|requests.cpu)"})) by (%(clusterLabel)s)
/
sum(kube_node_status_allocatable{resource="cpu", %(kubeStateMetricsSelector)s}) by (%(clusterLabel)s)
> %(namespaceOvercommitFactor)s
||| % $._config,
annotations+: {
description: 'Cluster {{ $labels.%(clusterLabel)s }} has overcommitted CPU resource requests for Namespaces.' % $._config,
},
} else
{
expr: |||
sum(min without(resource) (kube_resourcequota{%(prefixedNamespaceSelector)s%(kubeStateMetricsSelector)s, type="hard", resource=~"(cpu|requests.cpu)"}))
/
sum(kube_node_status_allocatable{resource="cpu", %(kubeStateMetricsSelector)s})
> %(namespaceOvercommitFactor)s
||| % $._config,
annotations+: {
description: 'Cluster has overcommitted CPU resource requests for Namespaces.',
},
},
},
{
alert: 'KubeMemoryQuotaOvercommit',
labels: {
severity: 'warning',
},
annotations: {
summary: 'Cluster has overcommitted memory resource requests.',
description: 'Cluster%s has overcommitted memory resource requests for Namespaces.' % [
utils.ifShowMultiCluster($._config, ' {{ $labels.%(clusterLabel)s }}' % $._config),
],
},
expr: kubeQuotaOvercommitExpression('memory'),
'for': '5m',
} +
if $._config.showMultiCluster then {
expr: |||
sum(min without(resource) (kube_resourcequota{%(prefixedNamespaceSelector)s%(kubeStateMetricsSelector)s, type="hard", resource=~"(memory|requests.memory)"})) by (%(clusterLabel)s)
/
sum(kube_node_status_allocatable{resource="memory", %(kubeStateMetricsSelector)s}) by (%(clusterLabel)s)
> %(namespaceOvercommitFactor)s
||| % $._config,
annotations+: {
description: 'Cluster {{ $labels.%(clusterLabel)s }} has overcommitted memory resource requests for Namespaces.' % $._config,
},
} else
{
expr: |||
sum(min without(resource) (kube_resourcequota{%(prefixedNamespaceSelector)s%(kubeStateMetricsSelector)s, type="hard", resource=~"(memory|requests.memory)"}))
/
sum(kube_node_status_allocatable{resource="memory", %(kubeStateMetricsSelector)s})
> %(namespaceOvercommitFactor)s
||| % $._config,
annotations+: {
description: 'Cluster has overcommitted memory resource requests for Namespaces.',
},
},
},
{
alert: 'KubeQuotaAlmostFull',
expr: |||
Expand Down