mrtz
1bb720840d
Move most of helmfiles into temp to test only velero. File structure: ```bash / ├── helmfile.d/ # Helmfiles, *.yaml.gotmpl ├── charts/ # Our own charts, e.g `Atlantis` ├── values # Values for helmfiles │ ├── <chart> │ │ ├── values.yaml.gotmpl # Values to be templated in `values/` │ │ ├── kustomize # Kustomizations per environment │ │ ├── manifests # Raw manifests │ │ │ ├── <chart>.yaml # Argo App for bootstrap │ │ │ ├── dashboards # Grafana dashboards │ │ │ │ └── <chart>-metrics.yaml │ │ │ └── policies # Cilium and Kyverno policies │ │ │ ├── CiliumNetworkPolicy-allow-api-server.yaml │ │ │ └── KyvernoPolicy-regred-secret.yaml │ │ └── values # Values for each environment │ │ ├── <chart>-staging.yaml.gotmpl # Values for staging environment │ │ ├── <chart>-prod.yaml.gotmpl # Values for prod environment │ │ └── <chart>.yaml.gotmpl # Standard values for all environments │ │ │ ├── values.yaml # Standard values for all cluster │ ├── values-oceanbox.yaml # Values overrides for oceanbox │ ├── values-ekman.yaml # Values overrides for ekman ```
49 lines
2.6 KiB
YAML
49 lines
2.6 KiB
YAML
{{- if .Values.x509_exporter.alerts }}
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
labels:
|
|
# Some labels for various prometheus matching
|
|
k8s-app: x509-exporter
|
|
prometheus: k8s
|
|
role: alert-rules
|
|
name: x509-exporter-x509-certificate-exporter
|
|
namespace: x509-exporter
|
|
spec:
|
|
groups:
|
|
- name: x509-certificate-exporter.rules
|
|
rules:
|
|
- alert: X509ExporterReadErrors
|
|
annotations:
|
|
description: Over the last 15 minutes, this x509-certificate-exporter instance has experienced errors reading certificate files or querying the Kubernetes API. This could be caused by a misconfiguration if triggered when the exporter starts.
|
|
summary: Increasing read errors for x509-certificate-exporter
|
|
expr: delta(x509_read_errors[15m]) > 0
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: CertificateError
|
|
annotations:
|
|
description: Certificate could not be decoded {{`{{`}}if $labels.secret_name {{`}}`}} in Kubernetes secret "{{`{{`}} $labels.secret_namespace {{`}}`}}/{{`{{`}} $labels.secret_name {{`}}`}}"{{`{{`}}else{{`}}`}}at location "{{`{{`}} $labels.filepath {{`}}`}}"{{`{{`}}end{{`}}`}}
|
|
summary: Certificate cannot be decoded
|
|
expr: x509_cert_error > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: CertificateRenewal
|
|
annotations:
|
|
description: Certificate for "{{`{{`}} $labels.subject_CN {{`}}`}}" should be renewed {{`{{`}}if $labels.secret_name {{`}}`}}in Kubernetes secret "{{`{{`}} $labels.secret_namespace {{`}}`}}/{{`{{`}} $labels.secret_name {{`}}`}}"{{`{{`}}else{{`}}`}}at location "{{`{{`}} $labels.filepath {{`}}`}}"{{`{{`}}end{{`}}`}}
|
|
summary: Certificate should be renewed
|
|
expr: ((x509_cert_not_after{secret_name!="linkerd-identity-issuer", issuer_O="", issuer_CN!="webhook.linkerd.cluster.local"} - time()) / 86400) < 28
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: CertificateExpiration
|
|
annotations:
|
|
description: Certificate for "{{`{{`}} $labels.subject_CN {{`}}`}}" is about to expire {{`{{`}}if $labels.secret_name {{`}}`}}in Kubernetes secret "{{`{{`}} $labels.secret_namespace {{`}}`}}/{{`{{`}} $labels.secret_name {{`}}`}}"{{`{{`}}else{{`}}`}}at location "{{`{{`}} $labels.filepath {{`}}`}}"{{`{{`}}end{{`}}`}}
|
|
summary: Certificate is about to expire
|
|
expr: ((x509_cert_not_after{secret_name!="linkerd-identity-issuer", issuer_O="", issuer_CN!="webhook.linkerd.cluster.local"} - time()) / 86400) < 14
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
{{- end }}
|