89a6e08245
Phase 1 - Critical Security: - Netbox: move hardcoded DB/superuser passwords to variables - MeshCentral: disable public registration, add Authentik auth - Traefik: disable insecure API dashboard (api.insecure=false) - Traefik: configure forwarded headers with Cloudflare trusted IPs Phase 2 - Security Hardening: - Add security headers middleware (HSTS, X-Frame-Options, nosniff, etc.) - Add Kyverno pod security policies in audit mode (privileged, host namespaces, SYS_ADMIN, trusted registries) - Tighten rate limiting (avg=10, burst=50) - Add Authentik protection to grampsweb Phase 3 - Monitoring & Alerting: - Add critical service alerts (PostgreSQL, MySQL, Redis, Headscale, Authentik, Loki) - Increase Loki retention from 7 to 30 days (720h) - Add predictive PV filling alert (predict_linear) - Re-enable Hackmd and Privatebin down alerts Phase 4 - Reliability: - Add resource requests/limits to Redis, DBaaS, Technitium, Headscale, Vaultwarden, Uptime Kuma - Increase Alloy DaemonSet memory to 512Mi/1Gi Phase 6 - Maintainability: - Extract duplicated tiers locals to terragrunt.hcl generate block (removed from 67 stacks) - Replace hardcoded NFS IP 10.0.10.15 with var.nfs_server (114 instances across 63 files) - Replace hardcoded Redis/PostgreSQL/MySQL/Ollama/mail host references with variables across ~35 stacks - Migrate xray raw ingress resources to ingress_factory modules
59 lines
1.6 KiB
HCL
59 lines
1.6 KiB
HCL
|
|
|
|
resource "kubernetes_persistent_volume_claim" "prometheus_server_pvc" {
|
|
metadata {
|
|
name = "prometheus-iscsi-pvc"
|
|
namespace = kubernetes_namespace.monitoring.metadata[0].name
|
|
}
|
|
|
|
spec {
|
|
access_modes = ["ReadWriteOnce"]
|
|
resources {
|
|
requests = {
|
|
storage = "15Gi"
|
|
}
|
|
}
|
|
# storage_class_name = "standard"
|
|
volume_name = "prometheus-iscsi-pv"
|
|
}
|
|
}
|
|
|
|
resource "kubernetes_persistent_volume" "prometheus_server_pvc" {
|
|
metadata {
|
|
name = "prometheus-iscsi-pv"
|
|
}
|
|
spec {
|
|
capacity = {
|
|
storage = "15Gi"
|
|
}
|
|
access_modes = ["ReadWriteOnce"]
|
|
persistent_volume_source {
|
|
nfs {
|
|
path = "/mnt/main/prometheus"
|
|
server = var.nfs_server
|
|
}
|
|
# iscsi {
|
|
# fs_type = "ext4"
|
|
# iqn = "iqn.2020-12.lan.viktorbarzin:storage:monitoring:prometheus"
|
|
# lun = 0
|
|
# target_portal = "iscsi.viktorbarzin.me:3260"
|
|
# }
|
|
|
|
}
|
|
persistent_volume_reclaim_policy = "Retain"
|
|
volume_mode = "Filesystem"
|
|
}
|
|
}
|
|
|
|
resource "helm_release" "prometheus" {
|
|
namespace = kubernetes_namespace.monitoring.metadata[0].name
|
|
create_namespace = true
|
|
name = "prometheus"
|
|
|
|
repository = "https://prometheus-community.github.io/helm-charts"
|
|
chart = "prometheus"
|
|
# version = "15.0.2"
|
|
version = "25.8.2"
|
|
|
|
values = [templatefile("${path.module}/prometheus_chart_values.tpl", { alertmanager_mail_pass = var.alertmanager_account_password, alertmanager_slack_api_url = var.alertmanager_slack_api_url, tuya_api_key = var.tiny_tuya_service_secret, haos_api_token = var.haos_api_token })]
|
|
}
|