Files
infrastructure/clusters/cl01tl/manifests/kube-prometheus-stack/PrometheusRule-kube-prometheus-stack-kube-apiserver-slos.yml

77 lines
3.2 KiB
YAML

---
# Source: kube-prometheus-stack/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-slos.yaml
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: kube-prometheus-stack-kube-apiserver-slos
namespace: kube-prometheus-stack
labels:
app: kube-prometheus-stack
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/instance: kube-prometheus-stack
app.kubernetes.io/version: "79.11.0"
app.kubernetes.io/part-of: kube-prometheus-stack
chart: kube-prometheus-stack-79.11.0
release: "kube-prometheus-stack"
heritage: "Helm"
spec:
groups:
- name: kube-apiserver-slos
rules:
- alert: KubeAPIErrorBudgetBurn
annotations:
description: The API server is burning too much error budget on cluster {{ $labels.cluster }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
summary: The API server is burning too much error budget.
expr: |-
sum by (cluster) (apiserver_request:burnrate1h) > (14.40 * 0.01000)
and on (cluster)
sum by (cluster) (apiserver_request:burnrate5m) > (14.40 * 0.01000)
for: 2m
labels:
long: 1h
severity: critical
short: 5m
- alert: KubeAPIErrorBudgetBurn
annotations:
description: The API server is burning too much error budget on cluster {{ $labels.cluster }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
summary: The API server is burning too much error budget.
expr: |-
sum by (cluster) (apiserver_request:burnrate6h) > (6.00 * 0.01000)
and on (cluster)
sum by (cluster) (apiserver_request:burnrate30m) > (6.00 * 0.01000)
for: 15m
labels:
long: 6h
severity: critical
short: 30m
- alert: KubeAPIErrorBudgetBurn
annotations:
description: The API server is burning too much error budget on cluster {{ $labels.cluster }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
summary: The API server is burning too much error budget.
expr: |-
sum by (cluster) (apiserver_request:burnrate1d) > (3.00 * 0.01000)
and on (cluster)
sum by (cluster) (apiserver_request:burnrate2h) > (3.00 * 0.01000)
for: 1h
labels:
long: 1d
severity: warning
short: 2h
- alert: KubeAPIErrorBudgetBurn
annotations:
description: The API server is burning too much error budget on cluster {{ $labels.cluster }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
summary: The API server is burning too much error budget.
expr: |-
sum by (cluster) (apiserver_request:burnrate3d) > (1.00 * 0.01000)
and on (cluster)
sum by (cluster) (apiserver_request:burnrate6h) > (1.00 * 0.01000)
for: 3h
labels:
long: 3d
severity: warning
short: 6h