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
70 lines
1.7 KiB
HCL
70 lines
1.7 KiB
HCL
|
|
|
|
# resource "kubernetes_persistent_volume" "prometheus_grafana_pv" {
|
|
# metadata {
|
|
# name = "grafana-pv"
|
|
# }
|
|
# spec {
|
|
# capacity = {
|
|
# "storage" = "2Gi"
|
|
# }
|
|
# access_modes = ["ReadWriteOnce"]
|
|
# persistent_volume_source {
|
|
# nfs {
|
|
# path = "/mnt/main/grafana"
|
|
# server = var.nfs_server
|
|
# }
|
|
# # iscsi {
|
|
# # target_portal = "iscsi.viktorbarzin.lan:3260"
|
|
# # iqn = "iqn.2020-12.lan.viktorbarzin:storage:monitoring:grafana"
|
|
# # lun = 0
|
|
# # fs_type = "ext4"
|
|
# # }
|
|
# }
|
|
# }
|
|
# }
|
|
|
|
resource "kubernetes_persistent_volume" "alertmanager_pv" {
|
|
metadata {
|
|
name = "alertmanager-pv"
|
|
}
|
|
spec {
|
|
capacity = {
|
|
"storage" = "2Gi"
|
|
}
|
|
access_modes = ["ReadWriteOnce"]
|
|
persistent_volume_source {
|
|
nfs {
|
|
path = "/mnt/main/alertmanager"
|
|
server = var.nfs_server
|
|
}
|
|
}
|
|
}
|
|
}
|
|
# resource "kubernetes_persistent_volume_claim" "grafana_pvc" {
|
|
# metadata {
|
|
# name = "grafana-pvc"
|
|
# namespace = kubernetes_namespace.monitoring.metadata[0].name
|
|
# }
|
|
# spec {
|
|
# access_modes = ["ReadWriteOnce"]
|
|
# resources {
|
|
# requests = {
|
|
# "storage" = "2Gi"
|
|
# }
|
|
# }
|
|
# }
|
|
# }
|
|
|
|
resource "helm_release" "grafana" {
|
|
namespace = kubernetes_namespace.monitoring.metadata[0].name
|
|
create_namespace = true
|
|
name = "grafana"
|
|
atomic = true
|
|
timeout = 600
|
|
|
|
repository = "https://grafana.github.io/helm-charts"
|
|
chart = "grafana"
|
|
|
|
values = [templatefile("${path.module}/grafana_chart_values.yaml", { db_password = var.grafana_db_password, grafana_admin_password = var.grafana_admin_password, mysql_host = var.mysql_host })]
|
|
}
|