infra/stacks/platform/modules/cloudflared/main.tf
Viktor Barzin 23019da8e5 equalize memory req=lim across 70+ containers using Prometheus 7d max data
After node2 OOM incident, right-size memory across the cluster by setting
requests=limits based on max_over_time(container_memory_working_set_bytes[7d])
with 1.3x headroom. Eliminates ~37Gi overcommit gap.

Categories:
- Safe equalization (50 containers): set req=lim where max7d well within target
- Limit increases (8 containers): raise limits for services spiking above current
- No Prometheus data (12 containers): conservatively set lim=req
- Exception: nextcloud keeps req=256Mi/lim=8Gi due to Apache memory spikes

Also increased dbaas namespace quota from 12Gi to 16Gi to accommodate mysql
4Gi limits across 3 replicas.
2026-03-14 21:46:49 +00:00

130 lines
2.7 KiB
HCL

# Contents for cloudflare tunnel
variable "tls_secret_name" {}
variable "cloudflare_tunnel_token" {}
resource "kubernetes_namespace" "cloudflared" {
metadata {
name = "cloudflared"
labels = {
tier = var.tier
}
}
}
variable "tier" { type = string }
module "tls_secret" {
source = "../../../../modules/kubernetes/setup_tls_secret"
namespace = kubernetes_namespace.cloudflared.metadata[0].name
tls_secret_name = var.tls_secret_name
}
resource "kubernetes_deployment" "cloudflared" {
metadata {
name = "cloudflared"
namespace = kubernetes_namespace.cloudflared.metadata[0].name
labels = {
app = "cloudflared"
tier = var.tier
}
annotations = {
"reloader.stakater.com/search" = "true"
}
}
spec {
replicas = 3
strategy {
type = "RollingUpdate"
}
selector {
match_labels = {
app = "cloudflared"
}
}
template {
metadata {
labels = {
app = "cloudflared"
}
}
spec {
topology_spread_constraint {
max_skew = 1
topology_key = "kubernetes.io/hostname"
when_unsatisfiable = "ScheduleAnyway"
label_selector {
match_labels = {
app = "cloudflared"
}
}
}
container {
# image = "wisdomsky/cloudflared-web:latest"
image = "cloudflare/cloudflared"
name = "cloudflared"
command = ["cloudflared", "tunnel", "run"]
env {
name = "TUNNEL_TOKEN"
value = var.cloudflare_tunnel_token
}
port {
container_port = 14333
}
resources {
requests = {
cpu = "15m"
memory = "128Mi"
}
limits = {
memory = "128Mi"
}
}
}
dns_config {
option {
name = "ndots"
value = "2"
}
}
}
}
}
}
resource "kubernetes_pod_disruption_budget_v1" "cloudflared" {
metadata {
name = "cloudflared"
namespace = kubernetes_namespace.cloudflared.metadata[0].name
}
spec {
max_unavailable = "1"
selector {
match_labels = {
app = "cloudflared"
}
}
}
}
resource "kubernetes_service" "cloudflared" {
metadata {
name = "cloudflared"
namespace = kubernetes_namespace.cloudflared.metadata[0].name
labels = {
"app" = "cloudflared"
}
}
spec {
selector = {
app = "cloudflared"
}
port {
name = "http"
target_port = 14333
port = 80
protocol = "TCP"
}
}
}