## 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>
244 lines
5.5 KiB
HCL
244 lines
5.5 KiB
HCL
variable "tls_secret_name" {
|
|
type = string
|
|
sensitive = true
|
|
}
|
|
variable "public_ip" { type = string }
|
|
|
|
resource "kubernetes_manifest" "external_secret" {
|
|
manifest = {
|
|
apiVersion = "external-secrets.io/v1beta1"
|
|
kind = "ExternalSecret"
|
|
metadata = {
|
|
name = "coturn-secrets"
|
|
namespace = "coturn"
|
|
}
|
|
spec = {
|
|
refreshInterval = "15m"
|
|
secretStoreRef = {
|
|
name = "vault-kv"
|
|
kind = "ClusterSecretStore"
|
|
}
|
|
target = {
|
|
name = "coturn-secrets"
|
|
}
|
|
dataFrom = [{
|
|
extract = {
|
|
key = "coturn"
|
|
}
|
|
}]
|
|
}
|
|
}
|
|
depends_on = [kubernetes_namespace.coturn]
|
|
}
|
|
|
|
data "kubernetes_secret" "eso_secrets" {
|
|
metadata {
|
|
name = "coturn-secrets"
|
|
namespace = kubernetes_namespace.coturn.metadata[0].name
|
|
}
|
|
depends_on = [kubernetes_manifest.external_secret]
|
|
}
|
|
|
|
locals {
|
|
turn_realm = "viktorbarzin.me"
|
|
turn_port = 3478
|
|
# Small relay range — 100 ports is plenty for a home lab (~50 concurrent streams)
|
|
min_port = 49152
|
|
max_port = 49252
|
|
}
|
|
|
|
resource "kubernetes_namespace" "coturn" {
|
|
metadata {
|
|
name = "coturn"
|
|
labels = {
|
|
tier = local.tiers.edge
|
|
}
|
|
}
|
|
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.coturn.metadata[0].name
|
|
tls_secret_name = var.tls_secret_name
|
|
}
|
|
|
|
resource "kubernetes_config_map" "coturn_config" {
|
|
metadata {
|
|
name = "coturn-config"
|
|
namespace = kubernetes_namespace.coturn.metadata[0].name
|
|
}
|
|
|
|
data = {
|
|
"turnserver.conf" = <<-EOF
|
|
# TURN server configuration
|
|
listening-port=${local.turn_port}
|
|
fingerprint
|
|
lt-cred-mech
|
|
use-auth-secret
|
|
static-auth-secret=${data.kubernetes_secret.eso_secrets.data["turn_secret"]}
|
|
realm=${local.turn_realm}
|
|
server-name=turn.${local.turn_realm}
|
|
|
|
# Network — use 0.0.0.0, coturn auto-detects pod IP
|
|
listening-ip=0.0.0.0
|
|
external-ip=${var.public_ip}
|
|
|
|
# Media relay port range (narrow — 100 ports)
|
|
min-port=${local.min_port}
|
|
max-port=${local.max_port}
|
|
|
|
# Logging
|
|
verbose
|
|
no-stdout-log
|
|
syslog
|
|
|
|
# Security
|
|
no-multicast-peers
|
|
no-cli
|
|
no-tlsv1
|
|
no-tlsv1_1
|
|
|
|
# Performance
|
|
total-quota=100
|
|
stale-nonce=600
|
|
max-bps=0
|
|
EOF
|
|
}
|
|
}
|
|
|
|
resource "kubernetes_deployment" "coturn" {
|
|
metadata {
|
|
name = "coturn"
|
|
namespace = kubernetes_namespace.coturn.metadata[0].name
|
|
labels = {
|
|
app = "coturn"
|
|
tier = local.tiers.edge
|
|
}
|
|
annotations = {
|
|
"reloader.stakater.com/auto" = "true"
|
|
}
|
|
}
|
|
|
|
spec {
|
|
replicas = 1
|
|
strategy {
|
|
type = "RollingUpdate"
|
|
rolling_update {
|
|
max_unavailable = 0
|
|
max_surge = 1
|
|
}
|
|
}
|
|
selector {
|
|
match_labels = {
|
|
app = "coturn"
|
|
}
|
|
}
|
|
|
|
template {
|
|
metadata {
|
|
labels = {
|
|
app = "coturn"
|
|
}
|
|
annotations = {
|
|
"diun.enable" = "true"
|
|
"diun.include_tags" = "^\\d+\\.\\d+\\.\\d+-r\\d+$"
|
|
}
|
|
}
|
|
|
|
spec {
|
|
container {
|
|
name = "coturn"
|
|
image = "coturn/coturn:4.10.0-r1"
|
|
args = ["-c", "/etc/turnserver/turnserver.conf"]
|
|
|
|
# STUN/TURN signaling port
|
|
port {
|
|
name = "turn-udp"
|
|
container_port = local.turn_port
|
|
protocol = "UDP"
|
|
}
|
|
port {
|
|
name = "turn-tcp"
|
|
container_port = local.turn_port
|
|
protocol = "TCP"
|
|
}
|
|
|
|
volume_mount {
|
|
name = "config"
|
|
mount_path = "/etc/turnserver"
|
|
read_only = true
|
|
}
|
|
|
|
resources {
|
|
requests = {
|
|
cpu = "10m"
|
|
memory = "64Mi"
|
|
}
|
|
limits = {
|
|
memory = "64Mi"
|
|
}
|
|
}
|
|
}
|
|
|
|
volume {
|
|
name = "config"
|
|
config_map {
|
|
name = kubernetes_config_map.coturn_config.metadata[0].name
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
lifecycle {
|
|
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
|
|
ignore_changes = [spec[0].template[0].spec[0].dns_config]
|
|
}
|
|
}
|
|
|
|
# LoadBalancer service with MetalLB — exposes STUN/TURN signaling + relay ports
|
|
resource "kubernetes_service" "coturn" {
|
|
metadata {
|
|
name = "coturn"
|
|
namespace = kubernetes_namespace.coturn.metadata[0].name
|
|
annotations = {
|
|
"metallb.io/loadBalancerIPs" = "10.0.20.200"
|
|
"metallb.io/allow-shared-ip" = "shared"
|
|
}
|
|
}
|
|
|
|
spec {
|
|
type = "LoadBalancer"
|
|
selector = {
|
|
app = "coturn"
|
|
}
|
|
|
|
# STUN/TURN signaling
|
|
port {
|
|
name = "turn-udp"
|
|
port = local.turn_port
|
|
target_port = local.turn_port
|
|
protocol = "UDP"
|
|
}
|
|
port {
|
|
name = "turn-tcp"
|
|
port = local.turn_port
|
|
target_port = local.turn_port
|
|
protocol = "TCP"
|
|
}
|
|
|
|
# Relay port range (49152-49252)
|
|
dynamic "port" {
|
|
for_each = range(local.min_port, local.max_port + 1)
|
|
content {
|
|
name = "relay-${port.value}"
|
|
port = port.value
|
|
target_port = port.value
|
|
protocol = "UDP"
|
|
}
|
|
}
|
|
}
|
|
}
|