- Install Prometheus + Grafana via kube-prometheus-stack (ClusterIP only, no public ingress) - Deploy Tailscale Operator for secure VPN access to internal services - Add CNPG/PostgreSQL monitoring dashboards - Add vLLM inference monitoring dashboards (tokens, latency, GPU) - Add Cilium networking dashboards (policy, traffic, drops) - Update infra-controllers staging kustomization to include all controllers - Add monitoring-configs Flux sync for dashboard deployment - Update README with monitoring architecture and access instructions - Remove broken stale monitoring files (Azure Key Vault refs, wrong domains) Access: kubectl port-forward or Tailscale VPN (replace auth key before deploy)
40 lines
1.1 KiB
YAML
40 lines
1.1 KiB
YAML
apiVersion: helm.toolkit.fluxcd.io/v2
|
|
kind: HelmRelease
|
|
metadata:
|
|
name: tailscale-operator
|
|
namespace: tailscale
|
|
spec:
|
|
interval: 1h
|
|
chart:
|
|
spec:
|
|
chart: tailscale-operator
|
|
version: "1.86.x"
|
|
sourceRef:
|
|
kind: HelmRepository
|
|
name: tailscale
|
|
namespace: tailscale
|
|
interval: 12h
|
|
targetNamespace: tailscale
|
|
install:
|
|
createNamespace: true
|
|
crds: Create
|
|
upgrade:
|
|
crds: CreateReplace
|
|
values:
|
|
# Operator configuration
|
|
operator:
|
|
# Tag to use for pods created by the operator (e.g., tailnet)
|
|
tags: []
|
|
# Auth key from secret - PLACEHOLDER, replace with real key
|
|
# Create secret: kubectl create secret generic tailscale-operator-authkey \
|
|
# -n tailscale --from-literal=authkey=tskey-abc123... \
|
|
# --dry-run=client -o yaml | kubectl apply -f -
|
|
operatorSecretRef:
|
|
name: tailscale-operator-authkey
|
|
key: authkey
|
|
logFile: "/var/log/tailscale.log"
|
|
# Don't block pod startup if Tailscale auth fails
|
|
waitForLinkLocal: false
|
|
# Disable webhook (optional)
|
|
webhook:
|
|
enabled: false
|