infra/stacks/affine/main.tf

361 lines
8.4 KiB
Terraform
Raw Permalink Normal View History

variable "tls_secret_name" {
type = string
sensitive = true
}
2026-02-23 22:05:28 +00:00
variable "nfs_server" { type = string }
resource "kubernetes_manifest" "external_secret" {
manifest = {
apiVersion = "external-secrets.io/v1beta1"
kind = "ExternalSecret"
metadata = {
name = "affine-secrets"
namespace = "affine"
}
spec = {
refreshInterval = "15m"
secretStoreRef = {
name = "vault-kv"
kind = "ClusterSecretStore"
}
target = {
name = "affine-secrets"
}
dataFrom = [{
extract = {
key = "affine"
}
}]
}
}
depends_on = [kubernetes_namespace.affine]
}
data "kubernetes_secret" "eso_secrets" {
metadata {
name = "affine-secrets"
namespace = kubernetes_namespace.affine.metadata[0].name
}
depends_on = [kubernetes_manifest.external_secret]
}
# DB credentials from Vault database engine (rotated automatically)
# Provides DATABASE_URL that auto-updates when password rotates
resource "kubernetes_manifest" "db_external_secret" {
manifest = {
apiVersion = "external-secrets.io/v1beta1"
kind = "ExternalSecret"
metadata = {
name = "affine-db-creds"
namespace = "affine"
}
spec = {
refreshInterval = "15m"
secretStoreRef = {
name = "vault-database"
kind = "ClusterSecretStore"
}
target = {
name = "affine-db-creds"
template = {
data = {
DATABASE_URL = "postgresql://affine:{{ .password }}@${var.postgresql_host}:5432/affine"
}
}
}
data = [{
secretKey = "password"
remoteRef = {
key = "static-creds/pg-affine"
property = "password"
}
}]
}
}
depends_on = [kubernetes_namespace.affine]
}
locals {
mailserver_accounts = jsondecode(data.kubernetes_secret.eso_secrets.data["mailserver_accounts"])
}
2026-02-23 22:05:28 +00:00
variable "redis_host" { type = string }
variable "postgresql_host" { type = string }
variable "mail_host" { type = string }
resource "kubernetes_namespace" "affine" {
metadata {
name = "affine"
labels = {
tier = local.tiers.aux
}
}
}
module "tls_secret" {
source = "../../modules/kubernetes/setup_tls_secret"
namespace = kubernetes_namespace.affine.metadata[0].name
tls_secret_name = var.tls_secret_name
}
locals {
common_env = [
{
name = "REDIS_SERVER_HOST"
2026-02-23 22:05:28 +00:00
value = var.redis_host
},
{
name = "AFFINE_INDEXER_ENABLED"
value = "false"
},
{
name = "NODE_OPTIONS"
value = "--max-old-space-size=4096"
},
# Server URL configuration
{
name = "AFFINE_SERVER_EXTERNAL_URL"
value = "https://affine.viktorbarzin.me"
},
{
name = "AFFINE_SERVER_HTTPS"
value = "true"
},
# Email/SMTP configuration
{
name = "MAILER_HOST"
2026-02-23 22:05:28 +00:00
value = var.mail_host
},
{
name = "MAILER_PORT"
value = "587"
},
{
name = "MAILER_USER"
value = "info@viktorbarzin.me"
},
{
name = "MAILER_PASSWORD"
value = local.mailserver_accounts["info@viktorbarzin.me"]
},
{
name = "MAILER_SENDER"
value = "AFFiNE <info@viktorbarzin.me>"
},
]
}
feat(storage): migrate all sensitive services to proxmox-lvm-encrypted Reconcile Terraform with cluster state after manual encrypted PVC migrations and complete the remaining unfinished migrations. All services storing sensitive data now use LUKS2-encrypted block storage via the Proxmox CSI plugin. ## Context Only Technitium DNS was using encrypted storage in Terraform. Many services had been manually migrated to encrypted PVCs in the cluster, but Terraform was never updated — creating dangerous state drift where a `tg apply` could recreate unencrypted PVCs. ## This change Phase 0 — Infrastructure: - Add `proxmox-lvm-encrypted` StorageClass to Helm values (extraParameters) - Add ExternalSecret for LUKS encryption passphrase to Terraform - Fix CSI node plugin memory: `node.plugin.resources` (not `node.resources`) with 1280Mi limit for LUKS2 Argon2id key derivation Phase 1 — TF state reconciliation (zero downtime): - Health, Matrix, N8N, Forgejo, Vaultwarden, Mailserver: state rm + import - Redis, DBAAS MySQL, DBAAS PostgreSQL: Helm/CNPG value updates Phase 2 — Data migration (encrypted PVCs existed but unused): - Headscale, Frigate, MeshCentral: rsync + switchover - Nextcloud (20Gi): rsync + chart_values update Phase 3 — New encrypted PVCs: - Roundcube HTML, HackMD, Affine, DBAAS pgadmin: create + rsync + switchover Phase 4 — Cleanup: - Deleted 5 orphaned unencrypted PVCs ## Services migrated (18 PVCs across 14 namespaces) ``` vaultwarden → vaultwarden-data-encrypted dbaas → datadir-mysql-cluster-0, pg-cluster-{1,2}, dbaas-pgadmin-encrypted mailserver → mailserver-data-encrypted, roundcubemail-{enigma,html}-encrypted nextcloud → nextcloud-data-encrypted forgejo → forgejo-data-encrypted matrix → matrix-data-encrypted n8n → n8n-data-encrypted affine → affine-data-encrypted health → health-uploads-encrypted hackmd → hackmd-data-encrypted redis → redis-data-redis-node-{0,1} headscale → headscale-data-encrypted frigate → frigate-config-encrypted meshcentral → meshcentral-{data,files}-encrypted ``` Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 20:15:30 +00:00
resource "kubernetes_persistent_volume_claim" "data_encrypted" {
wait_until_bound = false
metadata {
feat(storage): migrate all sensitive services to proxmox-lvm-encrypted Reconcile Terraform with cluster state after manual encrypted PVC migrations and complete the remaining unfinished migrations. All services storing sensitive data now use LUKS2-encrypted block storage via the Proxmox CSI plugin. ## Context Only Technitium DNS was using encrypted storage in Terraform. Many services had been manually migrated to encrypted PVCs in the cluster, but Terraform was never updated — creating dangerous state drift where a `tg apply` could recreate unencrypted PVCs. ## This change Phase 0 — Infrastructure: - Add `proxmox-lvm-encrypted` StorageClass to Helm values (extraParameters) - Add ExternalSecret for LUKS encryption passphrase to Terraform - Fix CSI node plugin memory: `node.plugin.resources` (not `node.resources`) with 1280Mi limit for LUKS2 Argon2id key derivation Phase 1 — TF state reconciliation (zero downtime): - Health, Matrix, N8N, Forgejo, Vaultwarden, Mailserver: state rm + import - Redis, DBAAS MySQL, DBAAS PostgreSQL: Helm/CNPG value updates Phase 2 — Data migration (encrypted PVCs existed but unused): - Headscale, Frigate, MeshCentral: rsync + switchover - Nextcloud (20Gi): rsync + chart_values update Phase 3 — New encrypted PVCs: - Roundcube HTML, HackMD, Affine, DBAAS pgadmin: create + rsync + switchover Phase 4 — Cleanup: - Deleted 5 orphaned unencrypted PVCs ## Services migrated (18 PVCs across 14 namespaces) ``` vaultwarden → vaultwarden-data-encrypted dbaas → datadir-mysql-cluster-0, pg-cluster-{1,2}, dbaas-pgadmin-encrypted mailserver → mailserver-data-encrypted, roundcubemail-{enigma,html}-encrypted nextcloud → nextcloud-data-encrypted forgejo → forgejo-data-encrypted matrix → matrix-data-encrypted n8n → n8n-data-encrypted affine → affine-data-encrypted health → health-uploads-encrypted hackmd → hackmd-data-encrypted redis → redis-data-redis-node-{0,1} headscale → headscale-data-encrypted frigate → frigate-config-encrypted meshcentral → meshcentral-{data,files}-encrypted ``` Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 20:15:30 +00:00
name = "affine-data-encrypted"
namespace = kubernetes_namespace.affine.metadata[0].name
annotations = {
"resize.topolvm.io/threshold" = "80%"
"resize.topolvm.io/increase" = "100%"
"resize.topolvm.io/storage_limit" = "5Gi"
}
}
spec {
access_modes = ["ReadWriteOnce"]
feat(storage): migrate all sensitive services to proxmox-lvm-encrypted Reconcile Terraform with cluster state after manual encrypted PVC migrations and complete the remaining unfinished migrations. All services storing sensitive data now use LUKS2-encrypted block storage via the Proxmox CSI plugin. ## Context Only Technitium DNS was using encrypted storage in Terraform. Many services had been manually migrated to encrypted PVCs in the cluster, but Terraform was never updated — creating dangerous state drift where a `tg apply` could recreate unencrypted PVCs. ## This change Phase 0 — Infrastructure: - Add `proxmox-lvm-encrypted` StorageClass to Helm values (extraParameters) - Add ExternalSecret for LUKS encryption passphrase to Terraform - Fix CSI node plugin memory: `node.plugin.resources` (not `node.resources`) with 1280Mi limit for LUKS2 Argon2id key derivation Phase 1 — TF state reconciliation (zero downtime): - Health, Matrix, N8N, Forgejo, Vaultwarden, Mailserver: state rm + import - Redis, DBAAS MySQL, DBAAS PostgreSQL: Helm/CNPG value updates Phase 2 — Data migration (encrypted PVCs existed but unused): - Headscale, Frigate, MeshCentral: rsync + switchover - Nextcloud (20Gi): rsync + chart_values update Phase 3 — New encrypted PVCs: - Roundcube HTML, HackMD, Affine, DBAAS pgadmin: create + rsync + switchover Phase 4 — Cleanup: - Deleted 5 orphaned unencrypted PVCs ## Services migrated (18 PVCs across 14 namespaces) ``` vaultwarden → vaultwarden-data-encrypted dbaas → datadir-mysql-cluster-0, pg-cluster-{1,2}, dbaas-pgadmin-encrypted mailserver → mailserver-data-encrypted, roundcubemail-{enigma,html}-encrypted nextcloud → nextcloud-data-encrypted forgejo → forgejo-data-encrypted matrix → matrix-data-encrypted n8n → n8n-data-encrypted affine → affine-data-encrypted health → health-uploads-encrypted hackmd → hackmd-data-encrypted redis → redis-data-redis-node-{0,1} headscale → headscale-data-encrypted frigate → frigate-config-encrypted meshcentral → meshcentral-{data,files}-encrypted ``` Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 20:15:30 +00:00
storage_class_name = "proxmox-lvm-encrypted"
resources {
requests = {
storage = "1Gi"
}
}
}
}
resource "kubernetes_deployment" "affine" {
metadata {
name = "affine"
namespace = kubernetes_namespace.affine.metadata[0].name
labels = {
app = "affine"
tier = local.tiers.aux
}
annotations = {
"reloader.stakater.com/auto" = "true"
}
}
spec {
replicas = 1
strategy {
type = "Recreate"
}
selector {
match_labels = {
app = "affine"
}
}
template {
metadata {
labels = {
app = "affine"
}
annotations = {
"diun.enable" = "true"
"diun.include_tags" = "^\\d+\\.\\d+\\.\\d+$"
"dependency.kyverno.io/wait-for" = "postgresql.dbaas:5432,redis.redis:6379"
}
}
spec {
# Init container to run database migrations
init_container {
name = "migration"
image = "ghcr.io/toeverything/affine:0.26.6"
command = ["sh", "-c", "npx prisma migrate deploy && SERVER_FLAVOR=script node ./dist/main.js run"]
dynamic "env" {
for_each = local.common_env
content {
name = env.value.name
value = env.value.value
}
}
env {
name = "DATABASE_URL"
value_from {
secret_key_ref {
name = "affine-db-creds"
key = "DATABASE_URL"
}
}
}
volume_mount {
name = "data"
mount_path = "/root/.affine/storage"
sub_path = "storage"
}
volume_mount {
name = "data"
mount_path = "/root/.affine/config"
sub_path = "config"
}
resources {
requests = {
cpu = "50m"
memory = "128Mi"
}
limits = {
memory = "512Mi"
}
}
}
container {
name = "affine"
image = "ghcr.io/toeverything/affine:0.26.6"
port {
container_port = 3010
}
dynamic "env" {
for_each = local.common_env
content {
name = env.value.name
value = env.value.value
}
}
env {
name = "DATABASE_URL"
value_from {
secret_key_ref {
name = "affine-db-creds"
key = "DATABASE_URL"
}
}
}
volume_mount {
name = "data"
mount_path = "/root/.affine/storage"
sub_path = "storage"
}
volume_mount {
name = "data"
mount_path = "/root/.affine/config"
sub_path = "config"
}
resources {
requests = {
memory = "128Mi"
cpu = "50m"
}
limits = {
memory = "512Mi"
}
}
liveness_probe {
http_get {
path = "/info"
port = 3010
}
initial_delay_seconds = 120
period_seconds = 30
timeout_seconds = 10
}
readiness_probe {
http_get {
path = "/info"
port = 3010
}
initial_delay_seconds = 60
period_seconds = 10
timeout_seconds = 5
}
}
volume {
name = "data"
persistent_volume_claim {
feat(storage): migrate all sensitive services to proxmox-lvm-encrypted Reconcile Terraform with cluster state after manual encrypted PVC migrations and complete the remaining unfinished migrations. All services storing sensitive data now use LUKS2-encrypted block storage via the Proxmox CSI plugin. ## Context Only Technitium DNS was using encrypted storage in Terraform. Many services had been manually migrated to encrypted PVCs in the cluster, but Terraform was never updated — creating dangerous state drift where a `tg apply` could recreate unencrypted PVCs. ## This change Phase 0 — Infrastructure: - Add `proxmox-lvm-encrypted` StorageClass to Helm values (extraParameters) - Add ExternalSecret for LUKS encryption passphrase to Terraform - Fix CSI node plugin memory: `node.plugin.resources` (not `node.resources`) with 1280Mi limit for LUKS2 Argon2id key derivation Phase 1 — TF state reconciliation (zero downtime): - Health, Matrix, N8N, Forgejo, Vaultwarden, Mailserver: state rm + import - Redis, DBAAS MySQL, DBAAS PostgreSQL: Helm/CNPG value updates Phase 2 — Data migration (encrypted PVCs existed but unused): - Headscale, Frigate, MeshCentral: rsync + switchover - Nextcloud (20Gi): rsync + chart_values update Phase 3 — New encrypted PVCs: - Roundcube HTML, HackMD, Affine, DBAAS pgadmin: create + rsync + switchover Phase 4 — Cleanup: - Deleted 5 orphaned unencrypted PVCs ## Services migrated (18 PVCs across 14 namespaces) ``` vaultwarden → vaultwarden-data-encrypted dbaas → datadir-mysql-cluster-0, pg-cluster-{1,2}, dbaas-pgadmin-encrypted mailserver → mailserver-data-encrypted, roundcubemail-{enigma,html}-encrypted nextcloud → nextcloud-data-encrypted forgejo → forgejo-data-encrypted matrix → matrix-data-encrypted n8n → n8n-data-encrypted affine → affine-data-encrypted health → health-uploads-encrypted hackmd → hackmd-data-encrypted redis → redis-data-redis-node-{0,1} headscale → headscale-data-encrypted frigate → frigate-config-encrypted meshcentral → meshcentral-{data,files}-encrypted ``` Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 20:15:30 +00:00
claim_name = kubernetes_persistent_volume_claim.data_encrypted.metadata[0].name
}
}
}
}
}
}
resource "kubernetes_service" "affine" {
metadata {
name = "affine"
namespace = kubernetes_namespace.affine.metadata[0].name
labels = {
app = "affine"
}
}
spec {
selector = {
app = "affine"
}
port {
name = "http"
port = 80
target_port = 3010
}
}
}
module "ingress" {
source = "../../modules/kubernetes/ingress_factory"
[infra] Auto-create Cloudflare DNS records from ingress_factory ## Context Deploying new services required manually adding hostnames to cloudflare_proxied_names/cloudflare_non_proxied_names in config.tfvars — a separate file from the service stack. This was frequently forgotten, leaving services unreachable externally. ## This change: - Add `dns_type` parameter to `ingress_factory` and `reverse_proxy/factory` modules. Setting `dns_type = "proxied"` or `"non-proxied"` auto-creates the Cloudflare DNS record (CNAME to tunnel or A/AAAA to public IP). - Simplify cloudflared tunnel from 100 per-hostname rules to wildcard `*.viktorbarzin.me → Traefik`. Traefik still handles host-based routing. - Add global Cloudflare provider via terragrunt.hcl (separate cloudflare_provider.tf with Vault-sourced API key). - Migrate 118 hostnames from centralized config.tfvars to per-service dns_type. 17 hostnames remain centrally managed (Helm ingresses, special cases). - Update docs, AGENTS.md, CLAUDE.md, dns.md runbook. ``` BEFORE AFTER config.tfvars (manual list) stacks/<svc>/main.tf | module "ingress" { v dns_type = "proxied" stacks/cloudflared/ } for_each = list | cloudflare_record auto-creates tunnel per-hostname cloudflare_record + annotation ``` ## What is NOT in this change: - Uptime Kuma monitor migration (still reads from config.tfvars) - 17 remaining centrally-managed hostnames (Helm, special cases) - Removal of allow_overwrite (keep until migration confirmed stable) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-16 13:45:04 +00:00
dns_type = "non-proxied"
namespace = kubernetes_namespace.affine.metadata[0].name
name = "affine"
tls_secret_name = var.tls_secret_name
max_body_size = "500m"
extra_annotations = {
"gethomepage.dev/enabled" = "true"
"gethomepage.dev/name" = "Affine"
"gethomepage.dev/description" = "Knowledge base"
"gethomepage.dev/icon" = "affine.png"
"gethomepage.dev/group" = "Other"
"gethomepage.dev/pod-selector" = ""
}
}