## 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>
369 lines
8.6 KiB
HCL
369 lines
8.6 KiB
HCL
variable "tls_secret_name" {
|
|
type = string
|
|
sensitive = true
|
|
}
|
|
variable "resume_database_url" { type = string }
|
|
variable "nfs_server" { type = string }
|
|
variable "mail_host" { type = string }
|
|
|
|
data "vault_kv_secret_v2" "secrets" {
|
|
mount = "secret"
|
|
name = "resume"
|
|
}
|
|
|
|
locals {
|
|
namespace = "resume"
|
|
app_url = "https://resume.viktorbarzin.me"
|
|
mailserver_accounts = jsondecode(data.vault_kv_secret_v2.secrets.data["mailserver_accounts"])
|
|
}
|
|
|
|
resource "kubernetes_namespace" "resume" {
|
|
metadata {
|
|
name = local.namespace
|
|
labels = {
|
|
tier = local.tiers.aux
|
|
}
|
|
}
|
|
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.resume.metadata[0].name
|
|
tls_secret_name = var.tls_secret_name
|
|
}
|
|
|
|
resource "kubernetes_manifest" "external_secret" {
|
|
manifest = {
|
|
apiVersion = "external-secrets.io/v1beta1"
|
|
kind = "ExternalSecret"
|
|
metadata = {
|
|
name = "resume-secrets"
|
|
namespace = "resume"
|
|
}
|
|
spec = {
|
|
refreshInterval = "15m"
|
|
secretStoreRef = {
|
|
name = "vault-kv"
|
|
kind = "ClusterSecretStore"
|
|
}
|
|
target = {
|
|
name = "resume-secrets"
|
|
}
|
|
dataFrom = [{
|
|
extract = {
|
|
key = "resume"
|
|
}
|
|
}]
|
|
}
|
|
}
|
|
depends_on = [kubernetes_namespace.resume]
|
|
}
|
|
|
|
# Printer service (browserless chromium for PDF generation)
|
|
resource "kubernetes_deployment" "printer" {
|
|
metadata {
|
|
name = "printer"
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
labels = {
|
|
app = "printer"
|
|
tier = local.tiers.aux
|
|
}
|
|
}
|
|
spec {
|
|
replicas = 0 # Scaled down — browserless chromium causes node OOM
|
|
selector {
|
|
match_labels = {
|
|
app = "printer"
|
|
}
|
|
}
|
|
template {
|
|
metadata {
|
|
labels = {
|
|
app = "printer"
|
|
}
|
|
}
|
|
spec {
|
|
container {
|
|
name = "printer"
|
|
image = "ghcr.io/browserless/chromium:latest"
|
|
|
|
port {
|
|
container_port = 3000
|
|
}
|
|
|
|
env {
|
|
name = "HEALTH"
|
|
value = "true"
|
|
}
|
|
env {
|
|
name = "CONCURRENT"
|
|
value = "20"
|
|
}
|
|
env {
|
|
name = "QUEUED"
|
|
value = "10"
|
|
}
|
|
|
|
resources {
|
|
requests = {
|
|
memory = "128Mi"
|
|
cpu = "25m"
|
|
}
|
|
limits = {
|
|
memory = "128Mi"
|
|
}
|
|
}
|
|
|
|
liveness_probe {
|
|
http_get {
|
|
path = "/pressure"
|
|
port = 3000
|
|
}
|
|
initial_delay_seconds = 30
|
|
period_seconds = 10
|
|
timeout_seconds = 5
|
|
}
|
|
readiness_probe {
|
|
http_get {
|
|
path = "/pressure"
|
|
port = 3000
|
|
}
|
|
initial_delay_seconds = 10
|
|
period_seconds = 10
|
|
timeout_seconds = 5
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
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" "printer" {
|
|
metadata {
|
|
name = "printer"
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
}
|
|
spec {
|
|
selector = {
|
|
app = "printer"
|
|
}
|
|
port {
|
|
port = 3000
|
|
target_port = 3000
|
|
}
|
|
}
|
|
}
|
|
|
|
resource "kubernetes_persistent_volume_claim" "data_proxmox" {
|
|
wait_until_bound = false
|
|
metadata {
|
|
name = "resume-data-proxmox"
|
|
namespace = kubernetes_namespace.resume.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"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
# Reactive Resume app
|
|
resource "kubernetes_deployment" "resume" {
|
|
metadata {
|
|
name = "resume"
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
labels = {
|
|
app = "resume"
|
|
tier = local.tiers.aux
|
|
}
|
|
}
|
|
spec {
|
|
replicas = 0 # Scaled down with printer — depends on browserless chromium
|
|
strategy {
|
|
type = "Recreate"
|
|
}
|
|
selector {
|
|
match_labels = {
|
|
app = "resume"
|
|
}
|
|
}
|
|
template {
|
|
metadata {
|
|
labels = {
|
|
app = "resume"
|
|
}
|
|
annotations = {
|
|
"reloader.stakater.com/search" = "true"
|
|
}
|
|
}
|
|
spec {
|
|
container {
|
|
name = "resume"
|
|
image = "amruthpillai/reactive-resume:v5.0.3"
|
|
|
|
port {
|
|
container_port = 3000
|
|
}
|
|
|
|
# Required env vars
|
|
env {
|
|
name = "APP_URL"
|
|
value = local.app_url
|
|
}
|
|
env {
|
|
name = "DATABASE_URL"
|
|
value = var.resume_database_url
|
|
}
|
|
env {
|
|
name = "PRINTER_ENDPOINT"
|
|
value = "ws://printer.${local.namespace}.svc.cluster.local:3000"
|
|
}
|
|
env {
|
|
name = "PRINTER_APP_URL"
|
|
value = "http://resume.${local.namespace}.svc.cluster.local"
|
|
}
|
|
env {
|
|
name = "AUTH_SECRET"
|
|
value_from {
|
|
secret_key_ref {
|
|
name = "resume-secrets"
|
|
key = "auth_secret"
|
|
}
|
|
}
|
|
}
|
|
|
|
# Server config
|
|
env {
|
|
name = "TZ"
|
|
value = "Etc/UTC"
|
|
}
|
|
|
|
# SMTP config for password reset emails
|
|
env {
|
|
name = "SMTP_HOST"
|
|
value = var.mail_host
|
|
}
|
|
env {
|
|
name = "SMTP_PORT"
|
|
value = "587"
|
|
}
|
|
env {
|
|
name = "SMTP_USER"
|
|
value = "info@viktorbarzin.me"
|
|
}
|
|
env {
|
|
name = "SMTP_PASS"
|
|
value = local.mailserver_accounts["info@viktorbarzin.me"]
|
|
}
|
|
env {
|
|
name = "SMTP_FROM"
|
|
value = "Reactive Resume <info@viktorbarzin.me>"
|
|
}
|
|
env {
|
|
name = "SMTP_SECURE"
|
|
value = "false"
|
|
}
|
|
|
|
# Feature flags
|
|
env {
|
|
name = "FLAG_DISABLE_SIGNUPS"
|
|
value = "false" # toggle me
|
|
}
|
|
|
|
volume_mount {
|
|
name = "data"
|
|
mount_path = "/app/data"
|
|
}
|
|
|
|
resources {
|
|
requests = {
|
|
memory = "64Mi"
|
|
cpu = "15m"
|
|
}
|
|
limits = {
|
|
memory = "64Mi"
|
|
}
|
|
}
|
|
|
|
liveness_probe {
|
|
http_get {
|
|
path = "/api/health"
|
|
port = 3000
|
|
}
|
|
initial_delay_seconds = 60
|
|
period_seconds = 30
|
|
timeout_seconds = 10
|
|
}
|
|
readiness_probe {
|
|
http_get {
|
|
path = "/api/health"
|
|
port = 3000
|
|
}
|
|
initial_delay_seconds = 30
|
|
period_seconds = 10
|
|
timeout_seconds = 5
|
|
}
|
|
}
|
|
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" "resume" {
|
|
metadata {
|
|
name = "resume"
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
}
|
|
spec {
|
|
selector = {
|
|
app = "resume"
|
|
}
|
|
port {
|
|
port = 80
|
|
target_port = 3000
|
|
}
|
|
}
|
|
}
|
|
|
|
module "ingress" {
|
|
source = "../../modules/kubernetes/ingress_factory"
|
|
dns_type = "proxied"
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
name = "resume"
|
|
tls_secret_name = var.tls_secret_name
|
|
extra_annotations = {
|
|
"gethomepage.dev/enabled" = "true"
|
|
"gethomepage.dev/name" = "Resume"
|
|
"gethomepage.dev/description" = "Online resume"
|
|
"gethomepage.dev/icon" = "mdi-file-account"
|
|
"gethomepage.dev/group" = "Other"
|
|
"gethomepage.dev/pod-selector" = ""
|
|
}
|
|
}
|