2026-02-22 13:56:34 +00:00
|
|
|
variable "tls_secret_name" { type = string }
|
[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
|
|
|
variable "nfs_server" { type = string }
|
2026-02-22 13:56:34 +00:00
|
|
|
|
|
|
|
|
|
2026-02-22 15:13:55 +00:00
|
|
|
resource "kubernetes_namespace" "whisper" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "whisper"
|
|
|
|
|
labels = {
|
|
|
|
|
tier = local.tiers.gpu
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
module "tls_secret" {
|
|
|
|
|
source = "../../modules/kubernetes/setup_tls_secret"
|
|
|
|
|
namespace = kubernetes_namespace.whisper.metadata[0].name
|
|
|
|
|
tls_secret_name = var.tls_secret_name
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_deployment" "whisper" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "whisper"
|
|
|
|
|
namespace = kubernetes_namespace.whisper.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "whisper"
|
|
|
|
|
tier = local.tiers.gpu
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
replicas = 1
|
|
|
|
|
strategy {
|
|
|
|
|
type = "Recreate"
|
|
|
|
|
}
|
|
|
|
|
selector {
|
|
|
|
|
match_labels = {
|
|
|
|
|
app = "whisper"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
template {
|
|
|
|
|
metadata {
|
|
|
|
|
labels = {
|
|
|
|
|
app = "whisper"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
node_selector = {
|
|
|
|
|
"gpu" : "true"
|
|
|
|
|
}
|
|
|
|
|
toleration {
|
|
|
|
|
key = "nvidia.com/gpu"
|
|
|
|
|
operator = "Equal"
|
|
|
|
|
value = "true"
|
|
|
|
|
effect = "NoSchedule"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
container {
|
|
|
|
|
name = "whisper"
|
|
|
|
|
image = "rhasspy/wyoming-whisper:latest"
|
|
|
|
|
args = ["--model", "small-int8", "--language", "en", "--beam-size", "1"]
|
|
|
|
|
|
|
|
|
|
port {
|
|
|
|
|
container_port = 10300
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "data"
|
|
|
|
|
mount_path = "/data"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
volume {
|
|
|
|
|
name = "data"
|
|
|
|
|
nfs {
|
[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
|
|
|
server = var.nfs_server
|
2026-02-22 15:13:55 +00:00
|
|
|
path = "/mnt/main/whisper"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_service" "whisper" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "whisper"
|
|
|
|
|
namespace = kubernetes_namespace.whisper.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "whisper"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
spec {
|
|
|
|
|
selector = {
|
|
|
|
|
app = "whisper"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
name = "wyoming"
|
|
|
|
|
port = 10300
|
|
|
|
|
target_port = 10300
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# TCP passthrough from Traefik to whisper service
|
|
|
|
|
resource "kubernetes_manifest" "whisper_tcp_ingressroute" {
|
|
|
|
|
manifest = {
|
|
|
|
|
apiVersion = "traefik.io/v1alpha1"
|
|
|
|
|
kind = "IngressRouteTCP"
|
|
|
|
|
metadata = {
|
|
|
|
|
name = "whisper-tcp"
|
|
|
|
|
namespace = "traefik"
|
|
|
|
|
}
|
|
|
|
|
spec = {
|
|
|
|
|
entryPoints = ["whisper-tcp"]
|
|
|
|
|
routes = [{
|
|
|
|
|
match = "HostSNI(`*`)"
|
|
|
|
|
services = [{
|
|
|
|
|
name = "whisper"
|
|
|
|
|
namespace = "whisper"
|
|
|
|
|
port = 10300
|
|
|
|
|
}]
|
|
|
|
|
}]
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# Piper TTS
|
|
|
|
|
resource "kubernetes_deployment" "piper" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "piper"
|
|
|
|
|
namespace = kubernetes_namespace.whisper.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "piper"
|
|
|
|
|
tier = local.tiers.gpu
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
replicas = 1
|
|
|
|
|
strategy {
|
|
|
|
|
type = "Recreate"
|
|
|
|
|
}
|
|
|
|
|
selector {
|
|
|
|
|
match_labels = {
|
|
|
|
|
app = "piper"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
template {
|
|
|
|
|
metadata {
|
|
|
|
|
labels = {
|
|
|
|
|
app = "piper"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
node_selector = {
|
|
|
|
|
"gpu" : "true"
|
|
|
|
|
}
|
|
|
|
|
toleration {
|
|
|
|
|
key = "nvidia.com/gpu"
|
|
|
|
|
operator = "Equal"
|
|
|
|
|
value = "true"
|
|
|
|
|
effect = "NoSchedule"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
container {
|
|
|
|
|
name = "piper"
|
|
|
|
|
image = "rhasspy/wyoming-piper:latest"
|
|
|
|
|
args = ["--voice", "en_US-lessac-medium"]
|
|
|
|
|
|
|
|
|
|
port {
|
|
|
|
|
container_port = 10200
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "data"
|
|
|
|
|
mount_path = "/data"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
volume {
|
|
|
|
|
name = "data"
|
|
|
|
|
nfs {
|
[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
|
|
|
server = var.nfs_server
|
2026-02-22 15:13:55 +00:00
|
|
|
path = "/mnt/main/whisper"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_service" "piper" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "piper"
|
|
|
|
|
namespace = kubernetes_namespace.whisper.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "piper"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
spec {
|
|
|
|
|
selector = {
|
|
|
|
|
app = "piper"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
name = "wyoming"
|
|
|
|
|
port = 10200
|
|
|
|
|
target_port = 10200
|
|
|
|
|
protocol = "TCP"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# TCP passthrough from Traefik to piper service
|
|
|
|
|
resource "kubernetes_manifest" "piper_tcp_ingressroute" {
|
|
|
|
|
manifest = {
|
|
|
|
|
apiVersion = "traefik.io/v1alpha1"
|
|
|
|
|
kind = "IngressRouteTCP"
|
|
|
|
|
metadata = {
|
|
|
|
|
name = "piper-tcp"
|
|
|
|
|
namespace = "traefik"
|
|
|
|
|
}
|
|
|
|
|
spec = {
|
|
|
|
|
entryPoints = ["piper-tcp"]
|
|
|
|
|
routes = [{
|
|
|
|
|
match = "HostSNI(`*`)"
|
|
|
|
|
services = [{
|
|
|
|
|
name = "piper"
|
|
|
|
|
namespace = "whisper"
|
|
|
|
|
port = 10200
|
|
|
|
|
}]
|
|
|
|
|
}]
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# TCP passthrough from Traefik to ollama service (for HA voice pipeline)
|
|
|
|
|
resource "kubernetes_manifest" "ollama_tcp_ingressroute" {
|
|
|
|
|
manifest = {
|
|
|
|
|
apiVersion = "traefik.io/v1alpha1"
|
|
|
|
|
kind = "IngressRouteTCP"
|
|
|
|
|
metadata = {
|
|
|
|
|
name = "ollama-tcp"
|
|
|
|
|
namespace = "traefik"
|
|
|
|
|
}
|
|
|
|
|
spec = {
|
|
|
|
|
entryPoints = ["ollama-tcp"]
|
|
|
|
|
routes = [{
|
|
|
|
|
match = "HostSNI(`*`)"
|
|
|
|
|
services = [{
|
|
|
|
|
name = "ollama"
|
|
|
|
|
namespace = "ollama"
|
|
|
|
|
port = 11434
|
|
|
|
|
}]
|
|
|
|
|
}]
|
|
|
|
|
}
|
|
|
|
|
}
|
2026-02-22 13:56:34 +00:00
|
|
|
}
|