blumeops/pulumi/policy.hujson
Erich Blume 17023085cb Migrate observability stack to Kubernetes (#42)
Note: the name of this branch was chosen before the scope widened to encompass the entire observability stack.

Summary

  - Fix Grafana data source URLs (docker driver uses host.minikube.internal, not host.containers.internal)
  - Migrate Prometheus and Loki from indri to Kubernetes with Tailscale Ingresses
  - Expose CNPG PostgreSQL metrics via Tailscale and update dashboard to use cnpg_* metrics
  - Update Alloy to push metrics/logs to k8s endpoints (prometheus.tail8d86e.ts.net, loki.tail8d86e.ts.net)
  - Add ACL rule for port 9187 (CNPG metrics)
  - Delete obsolete ansible roles for prometheus and loki

Changes

  - argocd/manifests/prometheus/ - New Prometheus StatefulSet with 20Gi PVC and Tailscale Ingress
  - argocd/manifests/loki/ - New Loki StatefulSet with 20Gi PVC and Tailscale Ingress
  - argocd/apps/prometheus.yaml, argocd/apps/loki.yaml - ArgoCD Applications
  - argocd/manifests/grafana/values.yaml - Data sources now use k8s internal DNS
  - argocd/manifests/databases/service-metrics-tailscale.yaml - CNPG metrics endpoint
  - argocd/manifests/grafana-config/dashboards/configmap-postgresql.yaml - Updated to cnpg_* metrics
  - ansible/roles/alloy/defaults/main.yml - Push to k8s Tailscale endpoints
  - pulumi/policy.hujson - ACL for port 9187
  - Deleted ansible/roles/prometheus/ and ansible/roles/loki/

Deployment and Testing

  - Stop prometheus and loki on indri
  - Sync ArgoCD apps (apps, prometheus, loki, grafana)
  - Run mise run provision-indri -- --tags alloy
  - Verify Grafana dashboards show data

🤖 Generated with https://claude.ai/claude-code

Reviewed-on: https://forge.tail8d86e.ts.net/eblume/blumeops/pulls/42
2026-01-22 12:06:02 -08:00

155 lines
4.2 KiB
Text

// Tailnet ACL policy for tail8d86e.ts.net
// Managed by blumeops-pulumi
{
// ============== Groups ==============
"groups": {
// Placeholder for future Jellyfin media access
"group:allisonflix": [
"blume.erich@gmail.com",
"acmdavis@gmail.com",
],
},
// ============== Access Grants ==============
"grants": [
// --- Admins: full access to all infrastructure ---
{
"src": ["autogroup:admin"],
"dst": ["*"],
"ip": ["*"],
},
// --- Members: user-facing services only ---
// Kiwix, Forge, devpi, Miniflux, PostgreSQL
{
"src": ["autogroup:member"],
"dst": ["tag:kiwix"],
"ip": ["tcp:443"],
},
{
"src": ["autogroup:member"],
"dst": ["tag:forge"],
"ip": ["tcp:443", "tcp:22"],
},
{
"src": ["autogroup:member"],
"dst": ["tag:devpi"],
"ip": ["tcp:443"],
},
{
"src": ["autogroup:member"],
"dst": ["tag:feed"],
"ip": ["tcp:443"],
},
{
"src": ["autogroup:member"],
"dst": ["tag:pg"],
"ip": ["tcp:5432"],
},
// Note: No member access to grafana, loki, or NAS
// --- Infrastructure ---
{
"src": ["tag:homelab"],
"dst": ["tag:homelab"],
"ip": ["*"],
},
{
"src": ["tag:homelab"],
"dst": ["tag:nas"],
"ip": ["*"],
},
// --- Kubernetes workloads ---
// k8s workloads (e.g., Woodpecker CI) can push/pull from registry
{
"src": ["tag:k8s"],
"dst": ["tag:registry"],
"ip": ["tcp:443"],
},
// k8s workloads (e.g., ArgoCD) can access forge on indri for GitOps
// HTTP on 3001, SSH on 2200
{
"src": ["tag:k8s"],
"dst": ["tag:homelab"],
"ip": ["tcp:3001", "tcp:2200"],
},
// Homelab can reach k8s services: PostgreSQL, CNPG metrics, Prometheus/Loki
{
"src": ["tag:homelab"],
"dst": ["tag:k8s"],
"ip": ["tcp:443", "tcp:5432", "tcp:9187"],
},
],
// ============== SSH Access ==============
"ssh": [
// Members can SSH to their own devices
{
"action": "check",
"src": ["autogroup:member"],
"dst": ["autogroup:self"],
"users": ["autogroup:nonroot"],
},
// Admins can SSH to homelab (for ansible)
{
"action": "check",
"src": ["autogroup:admin"],
"dst": ["tag:homelab"],
"users": ["autogroup:nonroot"],
"checkPeriod": "12h0m0s",
},
// Admins can SSH to NAS
{
"action": "check",
"src": ["autogroup:admin"],
"dst": ["tag:nas"],
"users": ["autogroup:nonroot"],
"checkPeriod": "12h0m0s",
},
],
// ============== Tag Owners ==============
"tagOwners": {
"tag:blumeops": ["autogroup:admin", "tag:blumeops"],
"tag:homelab": ["autogroup:admin", "tag:blumeops"],
"tag:workstation": ["autogroup:admin", "tag:blumeops"],
"tag:nas": ["autogroup:admin", "tag:blumeops"],
"tag:grafana": ["autogroup:admin", "tag:blumeops"],
"tag:kiwix": ["autogroup:admin", "tag:blumeops"],
"tag:forge": ["autogroup:admin", "tag:blumeops"],
"tag:devpi": ["autogroup:admin", "tag:blumeops"],
"tag:loki": ["autogroup:admin", "tag:blumeops"],
"tag:pg": ["autogroup:admin", "tag:blumeops"],
"tag:feed": ["autogroup:admin", "tag:blumeops"],
"tag:registry": ["autogroup:admin", "tag:blumeops"],
"tag:k8s-api": ["autogroup:admin", "tag:blumeops"],
"tag:k8s-operator": ["autogroup:admin", "tag:blumeops"],
"tag:k8s": ["autogroup:admin", "tag:blumeops", "tag:k8s-operator"],
},
// ============== ACL Tests ==============
"tests": [
// Erich can access everything
{
"src": "blume.erich@gmail.com",
"accept": ["tag:grafana:443", "tag:kiwix:443", "tag:feed:443", "tag:loki:3100", "tag:pg:5432", "tag:homelab:22", "tag:registry:443", "tag:k8s-api:443"],
},
// Allison can access user services but NOT grafana, loki, or NAS
{
"src": "acmdavis@gmail.com",
"accept": ["tag:kiwix:443", "tag:forge:443", "tag:feed:443", "tag:pg:5432"],
"deny": ["tag:grafana:443", "tag:loki:3100", "tag:nas:445", "tag:registry:443", "tag:k8s-api:443"],
},
// Homelab can reach homelab, NAS, and k8s services (postgres, metrics, prometheus/loki)
{
"src": "tag:homelab",
"accept": ["tag:homelab:22", "tag:nas:445", "tag:k8s:443", "tag:k8s:5432", "tag:k8s:9187"],
},
// K8s workloads can reach registry and forge (on indri:3001 HTTP, :2200 SSH)
{
"src": "tag:k8s",
"accept": ["tag:registry:443", "tag:homelab:3001", "tag:homelab:2200"],
},
],
}