infra/stacks/diun/main.tf
Viktor Barzin ca648ff9bb
[ci skip] right-size all pod resources based on VPA + live metrics audit
Full cluster resource audit: cross-referenced Goldilocks VPA recommendations,
live kubectl top metrics, and Terraform definitions for 100+ containers.

Critical fixes:
- dashy: CPU throttled at 98% (490m/500m) → 2 CPU limit
- stirling-pdf: CPU throttled at 99.7% (299m/300m) → 2 CPU limit
- traefik auth-proxy/bot-block-proxy: mem limit 32Mi → 128Mi

Added explicit resources to ~40 containers that had none:
- audiobookshelf, changedetection, cyberchef, dawarich, diun, echo,
  excalidraw, freshrss, hackmd, isponsorblocktv, linkwarden, n8n,
  navidrome, ntfy, owntracks, privatebin, send, shadowsocks, tandoor,
  tor-proxy, wealthfolio, networking-toolbox, rybbit, mailserver,
  cloudflared, pgadmin, phpmyadmin, crowdsec-web, xray, wireguard,
  k8s-portal, tuya-bridge, ollama-ui, whisper, piper, immich-server,
  immich-postgresql, osrm-foot

GPU containers: added CPU/mem alongside GPU limits:
- ollama: removed CPU/mem limits (models vary in size), keep GPU only
- frigate: req 500m/2Gi, lim 4/8Gi + GPU
- immich-ml: req 100m/1Gi, lim 2/4Gi + GPU

Right-sized ~25 over-provisioned containers:
- kms-web-page: 500m/512Mi → 50m/64Mi (was using 0m/10Mi)
- onlyoffice: CPU 8 → 2 (VPA upper 45m)
- realestate-crawler-api: CPU 2000m → 250m
- blog/travel-blog/webhook-handler: 500m → 100m
- coturn/health/plotting-book: reduced to match actual usage

Conservative methodology: limits = max(VPA upper * 2, live usage * 2)
2026-03-01 19:18:50 +00:00

187 lines
4.4 KiB
HCL

variable "tls_secret_name" { type = string }
variable "diun_nfty_token" { type = string }
variable "diun_slack_url" { type = string }
variable "nfs_server" { type = string }
resource "kubernetes_namespace" "diun" {
metadata {
name = "diun"
labels = {
"istio-injection" : "disabled"
tier = local.tiers.aux
}
}
}
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_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
selector {
match_labels = {
app = "diun"
}
}
template {
metadata {
labels = {
app = "diun"
}
}
spec {
service_account_name = "diun"
container {
image = "crazymax/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_EXCLUDETAGS"
# value = "^.*nightly.*$"
# }
# env {
# name = "DIUN_DEFAULTS_INCLUDETAGS"
# value = "^\\d+\\.\\d+\\.\\d+$"
# }
env {
name = "DIUN_DEFAULTS_WATCHREPO"
value = "true"
# value = "false"
}
env {
name = "DIUN_DEFAULTS_MAXTAGS"
value = "3"
}
env {
name = "DIUN_DEFAULTS_SORTTAGS"
value = "reverse"
}
# DIUN_PROVIDERS_KUBERNETES_WATCHBYDEFAULT = "true" ??
// ntfy settings
# env { // disabled as if this fails, no other notifications are sent
# name = "DIUN_NOTIF_NTFY_ENDPOINT"
# value = "https://ntfy.viktorbarzin.me"
# }
# env {
# name = "DIUN_NOTIF_NTFY_TOPIC"
# value = "diun-updates"
# }
# env {
# name = "DIUN_NOTIF_NTFY_TOKEN"
# value = var.diun_nfty_token
# }
env {
name = "DIUN_NOTIF_SLACK_WEBHOOKURL"
value = var.diun_slack_url
}
env {
name = "LOG_LEVEL"
# value = "info"
value = "debug"
}
# env {
# name = "DIUN_WATCH_FIRSTCHECKNOTIF"
# value = "true" # send notfication on start; subsequent checks check for newer versions and is what you need
# }
# env {
# name = "DIUN_NOTIF_NTFY_TIMEOUT"
# value = "10s"
# }
volume_mount {
name = "data"
mount_path = "/data"
}
resources {
requests = {
cpu = "10m"
memory = "32Mi"
}
limits = {
cpu = "100m"
memory = "128Mi"
}
}
}
volume {
name = "data"
nfs {
path = "/mnt/main/diun"
server = var.nfs_server
}
}
}
}
}
}