- Set memory requests = limits across 56 stacks to prevent overcommit - Right-sized limits based on actual pod usage (2x actual, rounded up) - Scaled down trading-bot (replicas=0) to free memory - Fixed OOMKilled services: forgejo, dawarich, health, meshcentral, paperless-ngx, vault auto-unseal, rybbit, whisper, openclaw, clickhouse - Added startup+liveness probes to calibre-web - Bumped inotify limits on nodes 2,3 (max_user_instances 128->8192) Post node2 OOM incident (2026-03-14). Previous kubelet config had no kubeReserved/systemReserved set, allowing pods to starve the kernel.
198 lines
4.7 KiB
HCL
198 lines
4.7 KiB
HCL
variable "tls_secret_name" {
|
|
type = string
|
|
sensitive = true
|
|
}
|
|
variable "nfs_server" { type = string }
|
|
|
|
data "vault_kv_secret_v2" "secrets" {
|
|
mount = "secret"
|
|
name = "diun"
|
|
}
|
|
|
|
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
|
|
}
|
|
}
|
|
|
|
module "nfs_data" {
|
|
source = "../../modules/kubernetes/nfs_volume"
|
|
name = "diun-data"
|
|
namespace = kubernetes_namespace.diun.metadata[0].name
|
|
nfs_server = var.nfs_server
|
|
nfs_path = "/mnt/main/diun"
|
|
}
|
|
|
|
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 = data.vault_kv_secret_v2.secrets.data["nfty_token"]
|
|
# }
|
|
env {
|
|
name = "DIUN_NOTIF_SLACK_WEBHOOKURL"
|
|
value = data.vault_kv_secret_v2.secrets.data["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 = "64Mi"
|
|
}
|
|
limits = {
|
|
memory = "64Mi"
|
|
}
|
|
}
|
|
}
|
|
volume {
|
|
name = "data"
|
|
persistent_volume_claim {
|
|
claim_name = module.nfs_data.claim_name
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|