2025-12-28 20:07:00 +00:00
|
|
|
|
[ci skip] Infrastructure hardening: security, monitoring, reliability, maintainability
Phase 1 - Critical Security:
- Netbox: move hardcoded DB/superuser passwords to variables
- MeshCentral: disable public registration, add Authentik auth
- Traefik: disable insecure API dashboard (api.insecure=false)
- Traefik: configure forwarded headers with Cloudflare trusted IPs
Phase 2 - Security Hardening:
- Add security headers middleware (HSTS, X-Frame-Options, nosniff, etc.)
- Add Kyverno pod security policies in audit mode (privileged, host
namespaces, SYS_ADMIN, trusted registries)
- Tighten rate limiting (avg=10, burst=50)
- Add Authentik protection to grampsweb
Phase 3 - Monitoring & Alerting:
- Add critical service alerts (PostgreSQL, MySQL, Redis, Headscale,
Authentik, Loki)
- Increase Loki retention from 7 to 30 days (720h)
- Add predictive PV filling alert (predict_linear)
- Re-enable Hackmd and Privatebin down alerts
Phase 4 - Reliability:
- Add resource requests/limits to Redis, DBaaS, Technitium, Headscale,
Vaultwarden, Uptime Kuma
- Increase Alloy DaemonSet memory to 512Mi/1Gi
Phase 6 - Maintainability:
- Extract duplicated tiers locals to terragrunt.hcl generate block
(removed from 67 stacks)
- Replace hardcoded NFS IP 10.0.10.15 with var.nfs_server (114
instances across 63 files)
- Replace hardcoded Redis/PostgreSQL/MySQL/Ollama/mail host references
with variables across ~35 stacks
- Migrate xray raw ingress resources to ingress_factory modules
2026-02-23 22:05:28 +00:00
|
|
|
|
2025-12-28 20:07:00 +00:00
|
|
|
resource "kubernetes_persistent_volume_claim" "prometheus_server_pvc" {
|
|
|
|
|
metadata {
|
2026-03-06 20:50:55 +00:00
|
|
|
name = "prometheus-data"
|
2025-12-29 10:23:42 +00:00
|
|
|
namespace = kubernetes_namespace.monitoring.metadata[0].name
|
2025-12-28 20:07:00 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
spec {
|
2026-03-06 20:50:55 +00:00
|
|
|
access_modes = ["ReadWriteOnce"]
|
|
|
|
|
storage_class_name = "iscsi-truenas"
|
2025-12-28 20:07:00 +00:00
|
|
|
resources {
|
|
|
|
|
requests = {
|
2026-03-06 23:16:32 +00:00
|
|
|
storage = "200Gi"
|
2025-12-28 20:07:00 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "helm_release" "prometheus" {
|
2025-12-29 10:23:42 +00:00
|
|
|
namespace = kubernetes_namespace.monitoring.metadata[0].name
|
2025-12-28 20:07:00 +00:00
|
|
|
create_namespace = true
|
|
|
|
|
name = "prometheus"
|
|
|
|
|
|
|
|
|
|
repository = "https://prometheus-community.github.io/helm-charts"
|
|
|
|
|
chart = "prometheus"
|
|
|
|
|
# version = "15.0.2"
|
|
|
|
|
version = "25.8.2"
|
|
|
|
|
|
|
|
|
|
values = [templatefile("${path.module}/prometheus_chart_values.tpl", { alertmanager_mail_pass = var.alertmanager_account_password, alertmanager_slack_api_url = var.alertmanager_slack_api_url, tuya_api_key = var.tiny_tuya_service_secret, haos_api_token = var.haos_api_token })]
|
|
|
|
|
}
|