[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
This commit is contained in:
parent
1b4737c90c
commit
89a6e08245
104 changed files with 773 additions and 920 deletions
|
|
@ -28,13 +28,13 @@ nextcloud:
|
|||
|
||||
externalRedis:
|
||||
enabled: true
|
||||
host: redis.redis.svc.cluster.local
|
||||
host: ${redis_host}
|
||||
|
||||
# Currently not in use; we use the nextcloud.db sqlite3
|
||||
externalDatabase:
|
||||
enabled: false
|
||||
type: mysql
|
||||
host: mysql.dbaas.svc.cluster.local
|
||||
host: ${mysql_host}
|
||||
user: nextcloud
|
||||
password: ${db_password}
|
||||
databse: nextcloud
|
||||
|
|
|
|||
|
|
@ -1,15 +1,9 @@
|
|||
variable "tls_secret_name" { type = string }
|
||||
variable "nextcloud_db_password" { type = string }
|
||||
variable "nfs_server" { type = string }
|
||||
variable "redis_host" { type = string }
|
||||
variable "mysql_host" { type = string }
|
||||
|
||||
locals {
|
||||
tiers = {
|
||||
core = "0-core"
|
||||
cluster = "1-cluster"
|
||||
gpu = "2-gpu"
|
||||
edge = "3-edge"
|
||||
aux = "4-aux"
|
||||
}
|
||||
}
|
||||
|
||||
module "tls_secret" {
|
||||
source = "../../modules/kubernetes/setup_tls_secret"
|
||||
|
|
@ -36,7 +30,7 @@ resource "helm_release" "nextcloud" {
|
|||
atomic = true
|
||||
version = "8.8.1"
|
||||
|
||||
values = [templatefile("${path.module}/chart_values.yaml", { tls_secret_name = var.tls_secret_name, db_password = var.nextcloud_db_password })]
|
||||
values = [templatefile("${path.module}/chart_values.yaml", { tls_secret_name = var.tls_secret_name, db_password = var.nextcloud_db_password, redis_host = var.redis_host, mysql_host = var.mysql_host })]
|
||||
timeout = 6000
|
||||
}
|
||||
|
||||
|
|
@ -136,7 +130,7 @@ resource "kubernetes_persistent_volume" "nextcloud-data-pv" {
|
|||
persistent_volume_source {
|
||||
nfs {
|
||||
path = "/mnt/main/nextcloud"
|
||||
server = "10.0.10.15"
|
||||
server = var.nfs_server
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -298,7 +292,7 @@ resource "kubernetes_cron_job_v1" "nextcloud-backup" {
|
|||
volume {
|
||||
name = "nextcloud-data"
|
||||
nfs {
|
||||
server = "10.0.10.15"
|
||||
server = var.nfs_server
|
||||
path = "/mnt/main/nextcloud"
|
||||
}
|
||||
}
|
||||
|
|
@ -306,7 +300,7 @@ resource "kubernetes_cron_job_v1" "nextcloud-backup" {
|
|||
volume {
|
||||
name = "backup"
|
||||
nfs {
|
||||
server = "10.0.10.15"
|
||||
server = var.nfs_server
|
||||
path = "/mnt/main/nextcloud-backup"
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue