feat!: Refector directories and flux apps (#559)

This commit is contained in:
Devin Buhl authored and GitHub committed 2022-12-21 14:22:18 -05:00
1 parent a43e2325f1
commit 4e6edcc66a
163 files changed
+1194 -1060

No files matched your search

@@ -0,0 +1,43 @@
---
apiVersion: helm.toolkit.fluxcd.io/v2beta1
kind: HelmRelease
metadata:
name: cert-manager
namespace: cert-manager
spec:
interval: 15m
chart:
spec:
chart: cert-manager
version: v1.10.1
sourceRef:
kind: HelmRepository
name: jetstack
namespace: flux-system
install:
createNamespace: true
remediation:
retries: 3
upgrade:
remediation:
retries: 3
values:
installCRDs: true
replicaCount: 3
webhook:
replicaCount: 3
cainjector:
replicaCount: 3
extraArgs:
- --dns01-recursive-nameservers=1.1.1.1:53,9.9.9.9:53
- --dns01-recursive-nameservers-only
podDnsPolicy: None
podDnsConfig:
nameservers:
- "1.1.1.1"
- "9.9.9.9"
prometheus:
enabled: true
servicemonitor:
enabled: true
prometheusInstance: monitoring
@@ -0,0 +1,17 @@
---
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
namespace: cert-manager
resources:
- ./helmrelease.yaml
- ./prometheusrule.yaml
configMapGenerator:
- name: cert-manager-dashboard
files:
- cert-manager-dashboard.json=https://raw.githubusercontent.com/monitoring-mixins/website/master/assets/cert-manager/dashboards/cert-manager.json
generatorOptions:
disableNameSuffixHash: true
annotations:
kustomize.toolkit.fluxcd.io/substitute: disabled
labels:
grafana_dashboard: "true"
@@ -0,0 +1,68 @@
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: cert-manager.rules
namespace: cert-manager
spec:
groups:
- name: cert-manager
rules:
- alert: CertManagerAbsent
expr: |
absent(up{job="cert-manager"})
for: 15m
labels:
severity: critical
annotations:
description:
"New certificates will not be able to be minted, and existing
ones can't be renewed until cert-manager is back."
runbook_url: https://gitlab.com/uneeq-oss/cert-manager-mixin/-/blob/master/RUNBOOK.md#certmanagerabsent
summary: "Cert Manager has dissapeared from Prometheus service discovery."
- name: certificates
rules:
- alert: CertManagerCertExpirySoon
expr: |
avg by (exported_namespace, namespace, name) (
certmanager_certificate_expiration_timestamp_seconds - time())
< (21 * 24 * 3600)
for: 15m
labels:
severity: warning
annotations:
description:
"The domain that this cert covers will be unavailable after
{{ $value | humanizeDuration }}. Clients using endpoints that this cert
protects will start to fail in {{ $value | humanizeDuration }}."
runbook_url: https://gitlab.com/uneeq-oss/cert-manager-mixin/-/blob/master/RUNBOOK.md#certmanagercertexpirysoon
summary:
"The cert {{ $labels.name }} is {{ $value | humanizeDuration }}
from expiry, it should have renewed over a week ago."
- alert: CertManagerCertNotReady
expr: |
max by (name, exported_namespace, namespace, condition) (
certmanager_certificate_ready_status{condition!="True"} == 1)
for: 15m
labels:
severity: critical
annotations:
description:
"This certificate has not been ready to serve traffic for at least
10m. If the cert is being renewed or there is another valid cert, the ingress
controller _may_ be able to serve that instead."
runbook_url: https://gitlab.com/uneeq-oss/cert-manager-mixin/-/blob/master/RUNBOOK.md#certmanagercertnotready
summary: "The cert {{ $labels.name }} is not ready to serve traffic."
- alert: CertManagerHittingRateLimits
expr: |
sum by (host) (rate(certmanager_http_acme_client_request_count{status="429"}[5m]))
> 0
for: 15m
labels:
severity: critical
annotations:
description:
"Depending on the rate limit, cert-manager may be unable to generate
certificates for up to a week."
runbook_url: https://gitlab.com/uneeq-oss/cert-manager-mixin/-/blob/master/RUNBOOK.md#certmanagerhittingratelimits
summary: "Cert manager hitting LetsEncrypt rate limits."
@@ -0,0 +1,41 @@
apiVersion: cert-manager.io/v1
kind: ClusterIssuer
metadata:
name: letsencrypt-production
spec:
acme:
server: https://acme-v02.api.letsencrypt.org/directory
email: "${SECRET_CLOUDFLARE_EMAIL}"
privateKeySecretRef:
name: letsencrypt-production
solvers:
- dns01:
cloudflare:
email: "${SECRET_CLOUDFLARE_EMAIL}"
apiKeySecretRef:
name: cert-manager-secret
key: api-key
selector:
dnsZones:
- "${SECRET_DOMAIN}"
---
apiVersion: cert-manager.io/v1
kind: ClusterIssuer
metadata:
name: letsencrypt-staging
spec:
acme:
server: https://acme-staging-v02.api.letsencrypt.org/directory
email: "${SECRET_CLOUDFLARE_EMAIL}"
privateKeySecretRef:
name: letsencrypt-staging
solvers:
- dns01:
cloudflare:
email: "${SECRET_CLOUDFLARE_EMAIL}"
apiKeySecretRef:
name: cert-manager-secret
key: api-key
selector:
dnsZones:
- "${SECRET_DOMAIN}"
@@ -0,0 +1,6 @@
---
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
resources:
- ./secret.sops.yaml
- ./issuers.yaml
@@ -0,0 +1,41 @@
---
apiVersion: kustomize.toolkit.fluxcd.io/v1beta2
kind: Kustomization
metadata:
name: cluster-apps-cert-manager
namespace: flux-system
labels:
substitution.flux.home.arpa/enabled: "true"
spec:
path: ./kubernetes/apps/cert-manager/cert-manager/app
prune: true
sourceRef:
kind: GitRepository
name: home-kubernetes
healthChecks:
- apiVersion: helm.toolkit.fluxcd.io/v2beta1
kind: HelmRelease
name: cert-manager
namespace: cert-manager
interval: 30m
retryInterval: 1m
timeout: 3m
---
apiVersion: kustomize.toolkit.fluxcd.io/v1beta2
kind: Kustomization
metadata:
name: cluster-apps-cert-manager-issuers
namespace: flux-system
labels:
substitution.flux.home.arpa/enabled: "true"
spec:
dependsOn:
- name: cluster-apps-cert-manager
path: ./kubernetes/apps/cert-manager/cert-manager/issuers
prune: true
sourceRef:
kind: GitRepository
name: home-kubernetes
interval: 30m
retryInterval: 1m
timeout: 3m
@@ -0,0 +1,6 @@
---
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
resources:
- ./namespace.yaml
- ./cert-manager/ks.yaml
@@ -0,0 +1,7 @@
---
apiVersion: v1
kind: Namespace
metadata:
name: cert-manager
labels:
kustomize.toolkit.fluxcd.io/prune: disabled