## Context Wave 3A (commitc9d221d5) added the `# KYVERNO_LIFECYCLE_V1` marker to the 27 pre-existing `ignore_changes = [...dns_config]` sites so they could be grepped and audited. It did NOT address pod-owning resources that were simply missing the suppression entirely. Post-Wave-3A sampling (2026-04-18) found that navidrome, f1-stream, frigate, servarr, monitoring, crowdsec, and many other stacks showed perpetual `dns_config` drift every plan because their `kubernetes_deployment` / `kubernetes_stateful_set` / `kubernetes_cron_job_v1` resources had no `lifecycle {}` block at all. Root cause (same as Wave 3A): Kyverno's admission webhook stamps `dns_config { option { name = "ndots"; value = "2" } }` on every pod's `spec.template.spec.dns_config` to prevent NxDomain search-domain flooding (see `k8s-ndots-search-domain-nxdomain-flood` skill). Without `ignore_changes` on every Terraform-managed pod-owner, Terraform repeatedly tries to strip the injected field. ## This change Extends the Wave 3A convention by sweeping EVERY `kubernetes_deployment`, `kubernetes_stateful_set`, `kubernetes_daemon_set`, `kubernetes_cron_job_v1`, `kubernetes_job_v1` (+ their `_v1` variants) in the repo and ensuring each carries the right `ignore_changes` path: - **kubernetes_deployment / stateful_set / daemon_set / job_v1**: `spec[0].template[0].spec[0].dns_config` - **kubernetes_cron_job_v1**: `spec[0].job_template[0].spec[0].template[0].spec[0].dns_config` (extra `job_template[0]` nesting — the CronJob's PodTemplateSpec is one level deeper) Each injection / extension is tagged `# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2` inline so the suppression is discoverable via `rg 'KYVERNO_LIFECYCLE_V1' stacks/`. Two insertion paths are handled by a Python pass (`/tmp/add_dns_config_ignore.py`): 1. **No existing `lifecycle {}`**: inject a brand-new block just before the resource's closing `}`. 108 new blocks on 93 files. 2. **Existing `lifecycle {}` (usually for `DRIFT_WORKAROUND: CI owns image tag` from Wave 4, commit a62b43d1)**: extend its `ignore_changes` list with the dns_config path. Handles both inline (`= [x]`) and multiline (`= [\n x,\n]`) forms; ensures the last pre-existing list item carries a trailing comma so the extended list is valid HCL. 34 extensions. The script skips anything already mentioning `dns_config` inside an `ignore_changes`, so re-running is a no-op. ## Scale - 142 total lifecycle injections/extensions - 93 `.tf` files touched - 108 brand-new `lifecycle {}` blocks + 34 extensions of existing ones - Every Tier 0 and Tier 1 stack with a pod-owning resource is covered - Together with Wave 3A's 27 pre-existing markers → **169 greppable `KYVERNO_LIFECYCLE_V1` dns_config sites across the repo** ## What is NOT in this change - `stacks/trading-bot/main.tf` — entirely commented-out block (`/* … */`). Python script touched the file, reverted manually. - `_template/main.tf.example` skeleton — kept minimal on purpose; any future stack created from it should either inherit the Wave 3A one-line form or add its own on first `kubernetes_deployment`. - `terraform fmt` fixes to pre-existing alignment issues in meshcentral, nvidia/modules/nvidia, vault — unrelated to this commit. Left for a separate fmt-only pass. - Non-pod resources (`kubernetes_service`, `kubernetes_secret`, `kubernetes_manifest`, etc.) — they don't own pods so they don't get Kyverno dns_config mutation. ## Verification Random sample post-commit: ``` $ cd stacks/navidrome && ../../scripts/tg plan → No changes. $ cd stacks/f1-stream && ../../scripts/tg plan → No changes. $ cd stacks/frigate && ../../scripts/tg plan → No changes. $ rg -c 'KYVERNO_LIFECYCLE_V1' stacks/ --include='*.tf' --include='*.tf.example' \ | awk -F: '{s+=$2} END {print s}' 169 ``` ## Reproduce locally 1. `git pull` 2. `rg 'KYVERNO_LIFECYCLE_V1' stacks/ | wc -l` → 169+ 3. `cd stacks/navidrome && ../../scripts/tg plan` → expect 0 drift on the deployment's dns_config field. Refs: code-seq (Wave 3B dns_config class closed; kubernetes_manifest annotation class handled separately in8d94688dfor tls_secret) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
291 lines
6.2 KiB
HCL
291 lines
6.2 KiB
HCL
variable "tls_secret_name" {
|
|
type = string
|
|
sensitive = true
|
|
}
|
|
variable "nfs_server" { type = string }
|
|
|
|
|
|
resource "kubernetes_namespace" "whisper" {
|
|
metadata {
|
|
name = "whisper"
|
|
labels = {
|
|
tier = local.tiers.gpu
|
|
}
|
|
}
|
|
lifecycle {
|
|
# KYVERNO_LIFECYCLE_V1: goldilocks-vpa-auto-mode ClusterPolicy stamps this label on every namespace
|
|
ignore_changes = [metadata[0].labels["goldilocks.fairwinds.com/vpa-update-mode"]]
|
|
}
|
|
}
|
|
|
|
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_persistent_volume_claim" "data_proxmox" {
|
|
wait_until_bound = false
|
|
metadata {
|
|
name = "whisper-data-proxmox"
|
|
namespace = kubernetes_namespace.whisper.metadata[0].name
|
|
annotations = {
|
|
"resize.topolvm.io/threshold" = "80%"
|
|
"resize.topolvm.io/increase" = "100%"
|
|
"resize.topolvm.io/storage_limit" = "5Gi"
|
|
}
|
|
}
|
|
spec {
|
|
access_modes = ["ReadWriteOnce"]
|
|
storage_class_name = "proxmox-lvm"
|
|
resources {
|
|
requests = {
|
|
storage = "1Gi"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
resource "kubernetes_deployment" "whisper" {
|
|
metadata {
|
|
name = "whisper"
|
|
namespace = kubernetes_namespace.whisper.metadata[0].name
|
|
labels = {
|
|
app = "whisper"
|
|
tier = local.tiers.gpu
|
|
}
|
|
}
|
|
spec {
|
|
replicas = 0 # Scaled down - GPU node memory pressure
|
|
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"
|
|
}
|
|
resources {
|
|
requests = {
|
|
cpu = "25m"
|
|
memory = "1Gi"
|
|
}
|
|
limits = {
|
|
memory = "1Gi"
|
|
}
|
|
}
|
|
}
|
|
|
|
volume {
|
|
name = "data"
|
|
persistent_volume_claim {
|
|
claim_name = kubernetes_persistent_volume_claim.data_proxmox.metadata[0].name
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
lifecycle {
|
|
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
|
|
ignore_changes = [spec[0].template[0].spec[0].dns_config]
|
|
}
|
|
}
|
|
|
|
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 = 0 # Scaled down - GPU node memory pressure
|
|
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"
|
|
}
|
|
resources {
|
|
requests = {
|
|
cpu = "25m"
|
|
memory = "64Mi"
|
|
}
|
|
limits = {
|
|
memory = "64Mi"
|
|
}
|
|
}
|
|
}
|
|
|
|
volume {
|
|
name = "data"
|
|
persistent_volume_claim {
|
|
claim_name = kubernetes_persistent_volume_claim.data_proxmox.metadata[0].name
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
lifecycle {
|
|
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
|
|
ignore_changes = [spec[0].template[0].spec[0].dns_config]
|
|
}
|
|
}
|
|
|
|
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
|
|
}]
|
|
}]
|
|
}
|
|
}
|
|
}
|
|
|