infra/stacks/diun/main.tf
Viktor Barzin bf752dffa5 fix: pvc-autoresizer + TF drift safety — bulk add ignore_changes
After fixing the threshold=80% misconfig and seeing two PVCs
(prometheus + technitium primary) get stuck Terminating, a 3rd round
showed four more PVCs (frigate, hackmd, immich-postgresql,
paperless-ngx) in the same state. Same root cause: TF spec'd a
smaller storage size than the autoresizer-grown live value, K8s
rejected the shrink, TF force-replaced the PVC, and the
pvc-protection finalizer held it in Terminating while the pod kept
using the underlying volume.

Bulk-inject lifecycle.ignore_changes = [spec[0].resources[0].requests]
on every kubernetes_persistent_volume_claim block that has
resize.topolvm.io/threshold annotations. The pattern was already
documented in .claude/CLAUDE.md but ~63 stacks were missing it.

Live PVCs are unaffected; this only prevents future TF applies from
attempting the destroy+recreate.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-10 21:57:01 +00:00

242 lines
5.7 KiB
HCL

variable "tls_secret_name" {
type = string
sensitive = true
}
variable "nfs_server" { type = string }
resource "kubernetes_namespace" "diun" {
metadata {
name = "diun"
labels = {
"istio-injection" : "disabled"
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"]]
}
}
resource "kubernetes_manifest" "external_secret" {
manifest = {
apiVersion = "external-secrets.io/v1beta1"
kind = "ExternalSecret"
metadata = {
name = "diun-secrets"
namespace = "diun"
}
spec = {
refreshInterval = "15m"
secretStoreRef = {
name = "vault-kv"
kind = "ClusterSecretStore"
}
target = {
name = "diun-secrets"
}
dataFrom = [{
extract = {
key = "diun"
}
}]
}
}
depends_on = [kubernetes_namespace.diun]
}
module "tls_secret" {
source = "../../modules/kubernetes/setup_tls_secret"
namespace = kubernetes_namespace.diun.metadata[0].name
tls_secret_name = var.tls_secret_name
}
resource "kubernetes_service_account" "diun" {
metadata {
name = "diun"
namespace = kubernetes_namespace.diun.metadata[0].name
}
}
resource "kubernetes_cluster_role" "diun" {
metadata {
name = "diun"
}
rule {
api_groups = [""]
resources = ["pods"]
verbs = ["get", "watch", "list"]
}
}
resource "kubernetes_cluster_role_binding" "diun" {
metadata {
name = "diun"
}
role_ref {
api_group = "rbac.authorization.k8s.io"
kind = "ClusterRole"
name = "diun"
}
subject {
kind = "ServiceAccount"
name = "diun"
namespace = kubernetes_namespace.diun.metadata[0].name
}
}
resource "kubernetes_persistent_volume_claim" "data_proxmox" {
wait_until_bound = false
metadata {
name = "diun-data-proxmox"
namespace = kubernetes_namespace.diun.metadata[0].name
annotations = {
"resize.topolvm.io/threshold" = "10%"
"resize.topolvm.io/increase" = "100%"
"resize.topolvm.io/storage_limit" = "5Gi"
}
}
spec {
access_modes = ["ReadWriteOnce"]
storage_class_name = "proxmox-lvm"
resources {
requests = {
storage = "1Gi"
}
}
}
lifecycle {
# The autoresizer expands requests.storage up to storage_limit and
# PVCs can't shrink. Without this, every TF apply tries to revert
# to the spec value, K8s rejects the shrink, and the PVC ends up
# in Terminating-but-in-use limbo.
ignore_changes = [spec[0].resources[0].requests]
}
}
resource "kubernetes_deployment" "diun" {
metadata {
name = "diun"
namespace = kubernetes_namespace.diun.metadata[0].name
labels = {
app = "diun"
tier = local.tiers.aux
}
annotations = {
"reloader.stakater.com/search" = "true"
"diun.enable" = "true"
}
}
spec {
replicas = 1
strategy {
type = "Recreate"
}
selector {
match_labels = {
app = "diun"
}
}
template {
metadata {
labels = {
app = "diun"
}
}
spec {
service_account_name = "diun"
container {
image = "viktorbarzin/diun:latest"
name = "diun"
args = ["serve"]
env {
name = "TZ"
value = "Europe/Sofia"
}
env {
name = "DIUN_WATCH_WORKERS"
value = "20"
}
env {
name = "DIUN_WATCH_SCHEDULE"
value = "0 */6 * * *"
}
env {
name = "DIUN_WATCH_JITTER"
value = "30s"
}
env {
name = "DIUN_PROVIDERS_KUBERNETES"
value = "true"
}
env {
name = "DIUN_DEFAULTS_WATCHREPO"
value = "true"
}
env {
name = "DIUN_DEFAULTS_MAXTAGS"
value = "3"
}
env {
name = "DIUN_DEFAULTS_SORTTAGS"
value = "reverse"
}
# Webhook notifier for upgrade agent (via n8n)
env {
name = "DIUN_NOTIF_WEBHOOK_ENDPOINT"
value_from {
secret_key_ref {
name = "diun-secrets"
key = "n8n_webhook_url"
}
}
}
env {
name = "DIUN_NOTIF_WEBHOOK_METHOD"
value = "POST"
}
env {
name = "DIUN_NOTIF_WEBHOOK_HEADERS_CONTENT-TYPE"
value = "application/json"
}
# Slack notifier (independent notification channel)
env {
name = "DIUN_NOTIF_SLACK_WEBHOOKURL"
value_from {
secret_key_ref {
name = "diun-secrets"
key = "slack_url"
}
}
}
env {
name = "LOG_LEVEL"
value = "debug"
}
volume_mount {
name = "data"
mount_path = "/data"
}
resources {
requests = {
cpu = "10m"
memory = "128Mi"
}
limits = {
memory = "256Mi"
}
}
}
volume {
name = "data"
persistent_volume_claim {
claim_name = kubernetes_persistent_volume_claim.data_proxmox.metadata[0].name
}
}
}
}
}
lifecycle {
ignore_changes = [spec[0].template[0].spec[0].dns_config] # KYVERNO_LIFECYCLE_V1
}
}