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)
222 lines
5 KiB
HCL
222 lines
5 KiB
HCL
variable "tls_secret_name" { type = string }
|
|
variable "nfs_server" { type = string }
|
|
|
|
|
|
resource "kubernetes_namespace" "frigate" {
|
|
metadata {
|
|
name = "frigate"
|
|
labels = {
|
|
tier = local.tiers.gpu
|
|
}
|
|
# labels = {
|
|
# "istio-injection" : "enabled"
|
|
# }
|
|
}
|
|
}
|
|
|
|
module "tls_secret" {
|
|
source = "../../modules/kubernetes/setup_tls_secret"
|
|
namespace = kubernetes_namespace.frigate.metadata[0].name
|
|
tls_secret_name = var.tls_secret_name
|
|
}
|
|
|
|
resource "kubernetes_deployment" "frigate" {
|
|
metadata {
|
|
name = "frigate"
|
|
namespace = kubernetes_namespace.frigate.metadata[0].name
|
|
labels = {
|
|
app = "frigate"
|
|
tier = local.tiers.gpu
|
|
}
|
|
annotations = {
|
|
"reloader.stakater.com/search" = "true"
|
|
}
|
|
}
|
|
spec {
|
|
replicas = 1 # Temporarily disabled due to high power consumption
|
|
strategy {
|
|
type = "Recreate"
|
|
}
|
|
selector {
|
|
match_labels = {
|
|
app = "frigate"
|
|
}
|
|
}
|
|
template {
|
|
metadata {
|
|
labels = {
|
|
app = "frigate"
|
|
}
|
|
}
|
|
spec {
|
|
node_selector = {
|
|
"gpu" : true
|
|
}
|
|
toleration {
|
|
key = "nvidia.com/gpu"
|
|
operator = "Equal"
|
|
value = "true"
|
|
effect = "NoSchedule"
|
|
}
|
|
container {
|
|
# image = "ghcr.io/blakeblackshear/frigate:stable"
|
|
# image = "ghcr.io/blakeblackshear/frigate:stable-tensorrt"
|
|
image = "ghcr.io/blakeblackshear/frigate:0.17.0-beta1-tensorrt"
|
|
name = "frigate"
|
|
|
|
resources {
|
|
requests = {
|
|
cpu = "500m"
|
|
memory = "2Gi"
|
|
}
|
|
limits = {
|
|
cpu = "4"
|
|
memory = "8Gi"
|
|
"nvidia.com/gpu" = "1"
|
|
}
|
|
}
|
|
env {
|
|
name = "FRIGATE_RTSP_PASSWORD"
|
|
value = "password"
|
|
}
|
|
port {
|
|
container_port = 5000
|
|
}
|
|
port {
|
|
container_port = 8554
|
|
}
|
|
port {
|
|
container_port = 8555
|
|
protocol = "TCP"
|
|
}
|
|
port {
|
|
container_port = 8555
|
|
protocol = "UDP"
|
|
}
|
|
volume_mount {
|
|
name = "config"
|
|
mount_path = "/config"
|
|
}
|
|
volume_mount {
|
|
name = "dri"
|
|
mount_path = "/dev/dri"
|
|
}
|
|
volume_mount {
|
|
name = "dshm"
|
|
mount_path = "/dev/shm"
|
|
}
|
|
volume_mount {
|
|
name = "media"
|
|
mount_path = "/media/frigate"
|
|
}
|
|
security_context {
|
|
privileged = true
|
|
}
|
|
}
|
|
|
|
volume {
|
|
name = "config"
|
|
nfs {
|
|
path = "/mnt/main/frigate/config"
|
|
server = var.nfs_server
|
|
}
|
|
}
|
|
volume {
|
|
name = "dshm"
|
|
empty_dir {
|
|
medium = "Memory"
|
|
size_limit = "1Gi"
|
|
}
|
|
}
|
|
volume {
|
|
name = "media"
|
|
nfs {
|
|
path = "/mnt/main/frigate/media"
|
|
server = var.nfs_server
|
|
}
|
|
}
|
|
volume {
|
|
name = "dri"
|
|
host_path {
|
|
path = "/dev/dri"
|
|
type = "Directory"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
resource "kubernetes_service" "frigate" {
|
|
metadata {
|
|
name = "frigate"
|
|
namespace = kubernetes_namespace.frigate.metadata[0].name
|
|
labels = {
|
|
"app" = "frigate"
|
|
}
|
|
}
|
|
|
|
spec {
|
|
selector = {
|
|
app = "frigate"
|
|
}
|
|
port {
|
|
name = "http"
|
|
target_port = 5000
|
|
port = 80
|
|
protocol = "TCP"
|
|
}
|
|
}
|
|
}
|
|
|
|
resource "kubernetes_service" "frigate-rtsp" {
|
|
metadata {
|
|
name = "frigate-rtsp"
|
|
namespace = kubernetes_namespace.frigate.metadata[0].name
|
|
labels = {
|
|
"app" = "frigate"
|
|
}
|
|
}
|
|
|
|
spec {
|
|
type = "NodePort" # Should always live on node1 where the gpu is
|
|
selector = {
|
|
app = "frigate"
|
|
}
|
|
port {
|
|
name = "rtsp-tcp"
|
|
target_port = 8554
|
|
port = 8554
|
|
protocol = "TCP"
|
|
node_port = 30554
|
|
}
|
|
port {
|
|
name = "rtsp-udp"
|
|
target_port = 8554
|
|
port = 8554
|
|
protocol = "UDP"
|
|
node_port = 30554
|
|
}
|
|
}
|
|
}
|
|
|
|
module "ingress" {
|
|
source = "../../modules/kubernetes/ingress_factory"
|
|
namespace = kubernetes_namespace.frigate.metadata[0].name
|
|
name = "frigate"
|
|
tls_secret_name = var.tls_secret_name
|
|
protected = true
|
|
rybbit_site_id = "0d4044069ff5"
|
|
}
|
|
|
|
module "ingress-internal" {
|
|
source = "../../modules/kubernetes/ingress_factory"
|
|
namespace = kubernetes_namespace.frigate.metadata[0].name
|
|
name = "frigate-lan"
|
|
host = "frigate-lan"
|
|
root_domain = "viktorbarzin.lan"
|
|
service_name = "frigate"
|
|
tls_secret_name = var.tls_secret_name
|
|
allow_local_access_only = true
|
|
ssl_redirect = false
|
|
}
|