2025-08-22 21:41:51 +00:00
|
|
|
variable "tls_secret_name" {}
|
2026-01-10 16:28:12 +00:00
|
|
|
variable "tier" { type = string }
|
2025-08-22 21:41:51 +00:00
|
|
|
variable "xray_reality_clients" { type = list(map(string)) }
|
2026-03-07 14:30:36 +00:00
|
|
|
variable "xray_reality_private_key" {
|
2026-03-14 08:51:45 +00:00
|
|
|
type = string
|
2026-03-07 14:30:36 +00:00
|
|
|
sensitive = true
|
|
|
|
|
}
|
2025-08-22 21:41:51 +00:00
|
|
|
variable "xray_reality_short_ids" { type = list(string) }
|
|
|
|
|
|
2025-08-23 10:47:11 +00:00
|
|
|
# Github repo - https://github.com/teddysun/across/blob/master/docker/xray/README.md
|
|
|
|
|
# Clients:
|
|
|
|
|
# iOS - OneXRay - https://github.com/OneXray/OneXray
|
|
|
|
|
# MacOS - V2BOX
|
|
|
|
|
|
2025-08-22 21:41:51 +00:00
|
|
|
|
|
|
|
|
module "tls_secret" {
|
2026-02-22 14:38:14 +00:00
|
|
|
source = "../../../../modules/kubernetes/setup_tls_secret"
|
2025-12-29 10:23:42 +00:00
|
|
|
namespace = kubernetes_namespace.xray.metadata[0].name
|
2025-08-22 21:41:51 +00:00
|
|
|
tls_secret_name = var.tls_secret_name
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_namespace" "xray" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "xray"
|
2026-02-21 23:38:05 +00:00
|
|
|
labels = {
|
|
|
|
|
tier = var.tier
|
|
|
|
|
}
|
2025-08-22 21:41:51 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_config_map" "xray_config" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "xray-config"
|
2025-12-29 10:23:42 +00:00
|
|
|
namespace = kubernetes_namespace.xray.metadata[0].name
|
2025-08-22 21:41:51 +00:00
|
|
|
|
|
|
|
|
labels = {
|
|
|
|
|
app = "xray"
|
|
|
|
|
}
|
|
|
|
|
annotations = {
|
|
|
|
|
"reloader.stakater.com/match" = "true"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
data = {
|
|
|
|
|
"config.json" = templatefile("${path.module}/xray_config.json.tpl", {
|
|
|
|
|
clients = jsonencode(var.xray_reality_clients)
|
|
|
|
|
reality_private_key = var.xray_reality_private_key
|
|
|
|
|
reality_short_ids = jsonencode(var.xray_reality_short_ids)
|
|
|
|
|
})
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_deployment" "xray" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "xray"
|
2025-12-29 10:23:42 +00:00
|
|
|
namespace = kubernetes_namespace.xray.metadata[0].name
|
2025-08-22 21:41:51 +00:00
|
|
|
labels = {
|
2026-01-10 16:28:12 +00:00
|
|
|
app = "xray"
|
|
|
|
|
tier = var.tier
|
2025-08-22 21:41:51 +00:00
|
|
|
}
|
|
|
|
|
annotations = {
|
|
|
|
|
"reloader.stakater.com/search" = "true"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
replicas = 1
|
|
|
|
|
strategy {
|
|
|
|
|
rolling_update {
|
|
|
|
|
max_surge = "2"
|
|
|
|
|
max_unavailable = "0"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
selector {
|
|
|
|
|
match_labels = {
|
|
|
|
|
app = "xray"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
template {
|
|
|
|
|
metadata {
|
|
|
|
|
labels = {
|
|
|
|
|
app = "xray"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
container {
|
|
|
|
|
image = "teddysun/xray"
|
|
|
|
|
name = "xray"
|
|
|
|
|
image_pull_policy = "IfNotPresent"
|
|
|
|
|
port {
|
|
|
|
|
container_port = 6443 // vless
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
container_port = 7443 // reality
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
container_port = 8443 // websocket
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
container_port = 9443 // gRPC
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "tls"
|
|
|
|
|
mount_path = "/etc/xray/tls.crt"
|
|
|
|
|
sub_path = "tls.crt"
|
|
|
|
|
}
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "tls"
|
|
|
|
|
mount_path = "/etc/xray/tls.key"
|
|
|
|
|
sub_path = "tls.key"
|
|
|
|
|
}
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "config"
|
|
|
|
|
mount_path = "/etc/xray/config.json"
|
|
|
|
|
sub_path = "config.json"
|
|
|
|
|
}
|
[ci skip] right-size all pod resources based on VPA + live metrics audit
Full cluster resource audit: cross-referenced Goldilocks VPA recommendations,
live kubectl top metrics, and Terraform definitions for 100+ containers.
Critical fixes:
- dashy: CPU throttled at 98% (490m/500m) → 2 CPU limit
- stirling-pdf: CPU throttled at 99.7% (299m/300m) → 2 CPU limit
- traefik auth-proxy/bot-block-proxy: mem limit 32Mi → 128Mi
Added explicit resources to ~40 containers that had none:
- audiobookshelf, changedetection, cyberchef, dawarich, diun, echo,
excalidraw, freshrss, hackmd, isponsorblocktv, linkwarden, n8n,
navidrome, ntfy, owntracks, privatebin, send, shadowsocks, tandoor,
tor-proxy, wealthfolio, networking-toolbox, rybbit, mailserver,
cloudflared, pgadmin, phpmyadmin, crowdsec-web, xray, wireguard,
k8s-portal, tuya-bridge, ollama-ui, whisper, piper, immich-server,
immich-postgresql, osrm-foot
GPU containers: added CPU/mem alongside GPU limits:
- ollama: removed CPU/mem limits (models vary in size), keep GPU only
- frigate: req 500m/2Gi, lim 4/8Gi + GPU
- immich-ml: req 100m/1Gi, lim 2/4Gi + GPU
Right-sized ~25 over-provisioned containers:
- kms-web-page: 500m/512Mi → 50m/64Mi (was using 0m/10Mi)
- onlyoffice: CPU 8 → 2 (VPA upper 45m)
- realestate-crawler-api: CPU 2000m → 250m
- blog/travel-blog/webhook-handler: 500m → 100m
- coturn/health/plotting-book: reduced to match actual usage
Conservative methodology: limits = max(VPA upper * 2, live usage * 2)
2026-03-01 19:18:50 +00:00
|
|
|
resources {
|
|
|
|
|
requests = {
|
|
|
|
|
cpu = "10m"
|
2026-03-14 21:46:49 +00:00
|
|
|
memory = "64Mi"
|
[ci skip] right-size all pod resources based on VPA + live metrics audit
Full cluster resource audit: cross-referenced Goldilocks VPA recommendations,
live kubectl top metrics, and Terraform definitions for 100+ containers.
Critical fixes:
- dashy: CPU throttled at 98% (490m/500m) → 2 CPU limit
- stirling-pdf: CPU throttled at 99.7% (299m/300m) → 2 CPU limit
- traefik auth-proxy/bot-block-proxy: mem limit 32Mi → 128Mi
Added explicit resources to ~40 containers that had none:
- audiobookshelf, changedetection, cyberchef, dawarich, diun, echo,
excalidraw, freshrss, hackmd, isponsorblocktv, linkwarden, n8n,
navidrome, ntfy, owntracks, privatebin, send, shadowsocks, tandoor,
tor-proxy, wealthfolio, networking-toolbox, rybbit, mailserver,
cloudflared, pgadmin, phpmyadmin, crowdsec-web, xray, wireguard,
k8s-portal, tuya-bridge, ollama-ui, whisper, piper, immich-server,
immich-postgresql, osrm-foot
GPU containers: added CPU/mem alongside GPU limits:
- ollama: removed CPU/mem limits (models vary in size), keep GPU only
- frigate: req 500m/2Gi, lim 4/8Gi + GPU
- immich-ml: req 100m/1Gi, lim 2/4Gi + GPU
Right-sized ~25 over-provisioned containers:
- kms-web-page: 500m/512Mi → 50m/64Mi (was using 0m/10Mi)
- onlyoffice: CPU 8 → 2 (VPA upper 45m)
- realestate-crawler-api: CPU 2000m → 250m
- blog/travel-blog/webhook-handler: 500m → 100m
- coturn/health/plotting-book: reduced to match actual usage
Conservative methodology: limits = max(VPA upper * 2, live usage * 2)
2026-03-01 19:18:50 +00:00
|
|
|
}
|
|
|
|
|
limits = {
|
2026-03-14 21:46:49 +00:00
|
|
|
memory = "64Mi"
|
[ci skip] right-size all pod resources based on VPA + live metrics audit
Full cluster resource audit: cross-referenced Goldilocks VPA recommendations,
live kubectl top metrics, and Terraform definitions for 100+ containers.
Critical fixes:
- dashy: CPU throttled at 98% (490m/500m) → 2 CPU limit
- stirling-pdf: CPU throttled at 99.7% (299m/300m) → 2 CPU limit
- traefik auth-proxy/bot-block-proxy: mem limit 32Mi → 128Mi
Added explicit resources to ~40 containers that had none:
- audiobookshelf, changedetection, cyberchef, dawarich, diun, echo,
excalidraw, freshrss, hackmd, isponsorblocktv, linkwarden, n8n,
navidrome, ntfy, owntracks, privatebin, send, shadowsocks, tandoor,
tor-proxy, wealthfolio, networking-toolbox, rybbit, mailserver,
cloudflared, pgadmin, phpmyadmin, crowdsec-web, xray, wireguard,
k8s-portal, tuya-bridge, ollama-ui, whisper, piper, immich-server,
immich-postgresql, osrm-foot
GPU containers: added CPU/mem alongside GPU limits:
- ollama: removed CPU/mem limits (models vary in size), keep GPU only
- frigate: req 500m/2Gi, lim 4/8Gi + GPU
- immich-ml: req 100m/1Gi, lim 2/4Gi + GPU
Right-sized ~25 over-provisioned containers:
- kms-web-page: 500m/512Mi → 50m/64Mi (was using 0m/10Mi)
- onlyoffice: CPU 8 → 2 (VPA upper 45m)
- realestate-crawler-api: CPU 2000m → 250m
- blog/travel-blog/webhook-handler: 500m → 100m
- coturn/health/plotting-book: reduced to match actual usage
Conservative methodology: limits = max(VPA upper * 2, live usage * 2)
2026-03-01 19:18:50 +00:00
|
|
|
}
|
|
|
|
|
}
|
2025-08-22 21:41:51 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
volume {
|
|
|
|
|
name = "tls"
|
|
|
|
|
secret {
|
|
|
|
|
secret_name = var.tls_secret_name
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
volume {
|
|
|
|
|
name = "config"
|
|
|
|
|
config_map {
|
|
|
|
|
name = "xray-config"
|
|
|
|
|
}
|
|
|
|
|
}
|
2026-02-23 22:43:05 +00:00
|
|
|
dns_config {
|
|
|
|
|
option {
|
|
|
|
|
name = "ndots"
|
|
|
|
|
value = "2"
|
|
|
|
|
}
|
|
|
|
|
}
|
2025-08-22 21:41:51 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_service" "xray" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "xray"
|
2025-12-29 10:23:42 +00:00
|
|
|
namespace = kubernetes_namespace.xray.metadata[0].name
|
2025-08-22 21:41:51 +00:00
|
|
|
labels = {
|
|
|
|
|
"app" = "xray"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
spec {
|
|
|
|
|
selector = {
|
|
|
|
|
app = "xray"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
name = "vless"
|
|
|
|
|
port = 6443
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
name = "websocket"
|
|
|
|
|
port = 8443
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
name = "grpc"
|
|
|
|
|
port = 9443
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_service" "xray-reality" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "xray-reality"
|
2025-12-29 10:23:42 +00:00
|
|
|
namespace = kubernetes_namespace.xray.metadata[0].name
|
2025-08-22 21:41:51 +00:00
|
|
|
labels = {
|
|
|
|
|
"app" = "xray"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
spec {
|
|
|
|
|
type = "LoadBalancer"
|
|
|
|
|
selector = {
|
|
|
|
|
app = "xray"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
name = "reality"
|
|
|
|
|
port = 7443
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
[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
|
|
|
module "ingress_ws" {
|
|
|
|
|
source = "../../../../modules/kubernetes/ingress_factory"
|
|
|
|
|
namespace = kubernetes_namespace.xray.metadata[0].name
|
|
|
|
|
name = "xray-ws"
|
|
|
|
|
service_name = "xray"
|
|
|
|
|
host = "xray-ws"
|
|
|
|
|
port = 8443
|
|
|
|
|
tls_secret_name = var.tls_secret_name
|
2025-08-22 21:41:51 +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
|
|
|
module "ingress_grpc" {
|
|
|
|
|
source = "../../../../modules/kubernetes/ingress_factory"
|
|
|
|
|
namespace = kubernetes_namespace.xray.metadata[0].name
|
|
|
|
|
name = "xray-grpc"
|
|
|
|
|
service_name = "xray"
|
|
|
|
|
host = "xray-grpc"
|
|
|
|
|
port = 9443
|
|
|
|
|
tls_secret_name = var.tls_secret_name
|
|
|
|
|
ingress_path = ["/grpc-vpn"]
|
|
|
|
|
extra_annotations = {
|
|
|
|
|
"traefik.ingress.kubernetes.io/service.serversscheme" = "h2c"
|
2025-08-22 21:41:51 +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
|
|
|
module "ingress_vless" {
|
|
|
|
|
source = "../../../../modules/kubernetes/ingress_factory"
|
|
|
|
|
namespace = kubernetes_namespace.xray.metadata[0].name
|
|
|
|
|
name = "xray-vless"
|
|
|
|
|
service_name = "xray"
|
|
|
|
|
host = "xray-vless"
|
|
|
|
|
port = 6443
|
|
|
|
|
tls_secret_name = var.tls_secret_name
|
2025-08-22 21:41:51 +00:00
|
|
|
}
|