infra/stacks/onlyoffice/main.tf
Viktor Barzin a0b5cbc922 onlyoffice: migrate PVC from proxmox-lvm to NFS
Wave 1 LUN-cap relief. OnlyOffice document server keeps only 2 WOPI
key files + a .private dir on the PVC (~24K) — the real DB lives in
its external Postgres + Redis stack, not on this PVC. Service is at
replicas=0 (IO-storm temp scaledown — TEMP-SCALEDOWN comment
preserved).

Migration trivia: scheduler tried to put the rsync helper on
k8s-node4 (PVC's last-known location) but node4 had just come back
online and its proxmox-csi/nfs-csi node pods were still in
ContainerCreating — failed. Retried pinned to k8s-node2 via
nodeSelector; rsync template updated to take an optional node arg.

Net: -1 SCSI LUN once onlyoffice is brought back up.
2026-05-26 02:43:47 +00:00

273 lines
7.2 KiB
HCL

variable "tls_secret_name" {
type = string
sensitive = true
}
variable "nfs_server" { type = string }
variable "redis_host" { type = string }
variable "mysql_host" { type = string }
resource "kubernetes_namespace" "onlyoffice" {
metadata {
name = "onlyoffice"
labels = {
"istio-injection" : "disabled"
tier = local.tiers.edge
"resource-governance/custom-limitrange" = "true"
"resource-governance/custom-quota" = "true"
"keel.sh/enrolled" = "true"
}
}
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 = "onlyoffice-secrets"
namespace = "onlyoffice"
}
spec = {
refreshInterval = "15m"
secretStoreRef = {
name = "vault-kv"
kind = "ClusterSecretStore"
}
target = {
name = "onlyoffice-secrets"
}
dataFrom = [{
extract = {
key = "onlyoffice"
}
}]
}
}
depends_on = [kubernetes_namespace.onlyoffice]
}
resource "kubernetes_limit_range" "onlyoffice" {
metadata {
name = "onlyoffice-limits"
namespace = kubernetes_namespace.onlyoffice.metadata[0].name
}
spec {
limit {
type = "Container"
default = {
memory = "256Mi"
}
default_request = {
cpu = "25m"
memory = "64Mi"
}
max = {
memory = "8Gi"
}
}
}
}
resource "kubernetes_resource_quota" "onlyoffice" {
metadata {
name = "onlyoffice-quota"
namespace = kubernetes_namespace.onlyoffice.metadata[0].name
}
spec {
hard = {
"requests.cpu" = "4"
"requests.memory" = "4Gi"
"limits.memory" = "16Gi"
pods = "10"
}
}
}
module "tls_secret" {
source = "../../modules/kubernetes/setup_tls_secret"
namespace = kubernetes_namespace.onlyoffice.metadata[0].name
tls_secret_name = var.tls_secret_name
}
module "nfs_data_host" {
source = "../../modules/kubernetes/nfs_volume"
name = "onlyoffice-data-host"
namespace = kubernetes_namespace.onlyoffice.metadata[0].name
nfs_server = var.nfs_server
nfs_path = "/srv/nfs/onlyoffice"
storage = "1Gi"
access_modes = ["ReadWriteOnce"]
}
resource "kubernetes_deployment" "onlyoffice-document-server" {
metadata {
name = "onlyoffice-document-server"
namespace = kubernetes_namespace.onlyoffice.metadata[0].name
labels = {
app = "onlyoffice-document-server"
tier = local.tiers.edge
}
annotations = {
"reloader.stakater.com/auto" = "true"
}
}
spec {
# TEMP-SCALEDOWN-2026-05-25-IO-STORM: scaled to 0 during cluster recovery.
# Restore to 1 when cluster is fully stable. See post-mortem
# docs/post-mortems/2026-05-25-immich-anca-elements-io-storm.md.
replicas = 0
strategy {
type = "Recreate"
}
selector {
match_labels = {
app = "onlyoffice-document-server"
}
}
template {
metadata {
labels = {
app = "onlyoffice-document-server"
}
annotations = {
"dependency.kyverno.io/wait-for" = "mysql.dbaas:3306,redis-master.redis:6379"
}
}
spec {
container {
name = "onlyoffice-document-server"
image = "onlyoffice/documentserver:9.3.1"
resources {
requests = {
cpu = "100m"
memory = "1536Mi"
}
limits = {
memory = "1536Mi"
}
}
port {
name = "http"
container_port = 80
protocol = "TCP"
}
env {
name = "DB_TYPE"
value = "mariadb"
}
env {
name = "DB_HOST"
value = var.mysql_host
}
env {
name = "DB_PORT"
value = 3306
}
env {
name = "DB_NAME"
value = "onlyoffice"
}
env {
name = "DB_USER"
value = "onlyoffice"
}
env {
name = "DB_PWD"
value_from {
secret_key_ref {
name = "onlyoffice-secrets"
key = "db_password"
}
}
}
env {
name = "REDIS_SERVER_HOST"
value = var.redis_host
}
env {
name = "REDIS_SERVER_PORT"
value = 6379
}
env {
name = "JWT_SECRET"
value_from {
secret_key_ref {
name = "onlyoffice-secrets"
key = "jwt_token"
}
}
}
volume_mount {
name = "data"
mount_path = "/var/www/onlyoffice/Data"
}
}
volume {
name = "data"
persistent_volume_claim {
claim_name = module.nfs_data_host.claim_name
}
}
}
}
}
lifecycle {
ignore_changes = [
spec[0].template[0].spec[0].dns_config, # KYVERNO_LIFECYCLE_V1
metadata[0].annotations["keel.sh/policy"],
metadata[0].annotations["keel.sh/trigger"],
metadata[0].annotations["keel.sh/pollSchedule"], # KYVERNO_LIFECYCLE_V2
]
}
}
resource "kubernetes_service" "onlyoffice" {
metadata {
name = "onlyoffice-document-server"
namespace = kubernetes_namespace.onlyoffice.metadata[0].name
labels = {
"app" = "onlyoffice-document-server"
}
}
spec {
selector = {
app = "onlyoffice-document-server"
}
port {
port = "80"
}
}
}
module "ingress" {
source = "../../modules/kubernetes/ingress_factory"
# Iframe-loaded by Nextcloud with JWT-signed session tokens; OnlyOffice
# validates the JWT itself. Authentik forward-auth would 302 the iframe
# load if the browser doesn't already have an Authentik cookie, AND
# OnlyOffice's server-to-server callback URLs (Nextcloud → OnlyOffice
# for save events, etc.) run outside any browser session entirely.
# The JWT is the auth gate.
# auth = "none": Iframe loaded by Nextcloud with JWT-signed tokens; JWT is the auth gate; forward-auth breaks iframe + server-to-server callbacks.
auth = "none"
dns_type = "proxied"
namespace = kubernetes_namespace.onlyoffice.metadata[0].name
name = "onlyoffice"
service_name = "onlyoffice-document-server"
tls_secret_name = var.tls_secret_name
extra_annotations = {
"gethomepage.dev/enabled" = "true"
"gethomepage.dev/name" = "OnlyOffice"
"gethomepage.dev/description" = "Document editor"
"gethomepage.dev/icon" = "onlyoffice.png"
"gethomepage.dev/group" = "Other"
"gethomepage.dev/pod-selector" = ""
}
}
# CI retrigger 2026-05-16T13:42:57+00:00 — bulk enrollment apply (pipeline #689 killed)
# CI retrigger v2 2026-05-16T13:46:35+00:00