## Context Wave 3A (commitc9d221d5) added the `# KYVERNO_LIFECYCLE_V1` marker to the 27 pre-existing `ignore_changes = [...dns_config]` sites so they could be grepped and audited. It did NOT address pod-owning resources that were simply missing the suppression entirely. Post-Wave-3A sampling (2026-04-18) found that navidrome, f1-stream, frigate, servarr, monitoring, crowdsec, and many other stacks showed perpetual `dns_config` drift every plan because their `kubernetes_deployment` / `kubernetes_stateful_set` / `kubernetes_cron_job_v1` resources had no `lifecycle {}` block at all. Root cause (same as Wave 3A): Kyverno's admission webhook stamps `dns_config { option { name = "ndots"; value = "2" } }` on every pod's `spec.template.spec.dns_config` to prevent NxDomain search-domain flooding (see `k8s-ndots-search-domain-nxdomain-flood` skill). Without `ignore_changes` on every Terraform-managed pod-owner, Terraform repeatedly tries to strip the injected field. ## This change Extends the Wave 3A convention by sweeping EVERY `kubernetes_deployment`, `kubernetes_stateful_set`, `kubernetes_daemon_set`, `kubernetes_cron_job_v1`, `kubernetes_job_v1` (+ their `_v1` variants) in the repo and ensuring each carries the right `ignore_changes` path: - **kubernetes_deployment / stateful_set / daemon_set / job_v1**: `spec[0].template[0].spec[0].dns_config` - **kubernetes_cron_job_v1**: `spec[0].job_template[0].spec[0].template[0].spec[0].dns_config` (extra `job_template[0]` nesting — the CronJob's PodTemplateSpec is one level deeper) Each injection / extension is tagged `# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2` inline so the suppression is discoverable via `rg 'KYVERNO_LIFECYCLE_V1' stacks/`. Two insertion paths are handled by a Python pass (`/tmp/add_dns_config_ignore.py`): 1. **No existing `lifecycle {}`**: inject a brand-new block just before the resource's closing `}`. 108 new blocks on 93 files. 2. **Existing `lifecycle {}` (usually for `DRIFT_WORKAROUND: CI owns image tag` from Wave 4, commit a62b43d1)**: extend its `ignore_changes` list with the dns_config path. Handles both inline (`= [x]`) and multiline (`= [\n x,\n]`) forms; ensures the last pre-existing list item carries a trailing comma so the extended list is valid HCL. 34 extensions. The script skips anything already mentioning `dns_config` inside an `ignore_changes`, so re-running is a no-op. ## Scale - 142 total lifecycle injections/extensions - 93 `.tf` files touched - 108 brand-new `lifecycle {}` blocks + 34 extensions of existing ones - Every Tier 0 and Tier 1 stack with a pod-owning resource is covered - Together with Wave 3A's 27 pre-existing markers → **169 greppable `KYVERNO_LIFECYCLE_V1` dns_config sites across the repo** ## What is NOT in this change - `stacks/trading-bot/main.tf` — entirely commented-out block (`/* … */`). Python script touched the file, reverted manually. - `_template/main.tf.example` skeleton — kept minimal on purpose; any future stack created from it should either inherit the Wave 3A one-line form or add its own on first `kubernetes_deployment`. - `terraform fmt` fixes to pre-existing alignment issues in meshcentral, nvidia/modules/nvidia, vault — unrelated to this commit. Left for a separate fmt-only pass. - Non-pod resources (`kubernetes_service`, `kubernetes_secret`, `kubernetes_manifest`, etc.) — they don't own pods so they don't get Kyverno dns_config mutation. ## Verification Random sample post-commit: ``` $ cd stacks/navidrome && ../../scripts/tg plan → No changes. $ cd stacks/f1-stream && ../../scripts/tg plan → No changes. $ cd stacks/frigate && ../../scripts/tg plan → No changes. $ rg -c 'KYVERNO_LIFECYCLE_V1' stacks/ --include='*.tf' --include='*.tf.example' \ | awk -F: '{s+=$2} END {print s}' 169 ``` ## Reproduce locally 1. `git pull` 2. `rg 'KYVERNO_LIFECYCLE_V1' stacks/ | wc -l` → 169+ 3. `cd stacks/navidrome && ../../scripts/tg plan` → expect 0 drift on the deployment's dns_config field. Refs: code-seq (Wave 3B dns_config class closed; kubernetes_manifest annotation class handled separately in8d94688dfor tls_secret) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
341 lines
10 KiB
HCL
341 lines
10 KiB
HCL
variable "tls_secret_name" {
|
|
type = string
|
|
sensitive = true
|
|
}
|
|
variable "nfs_server" { type = string }
|
|
variable "postgresql_host" { type = string }
|
|
variable "woodpecker_forgejo_url" { type = string }
|
|
|
|
data "vault_kv_secret_v2" "secrets" {
|
|
mount = "secret"
|
|
name = "woodpecker"
|
|
}
|
|
|
|
data "vault_kv_secret_v2" "platform" {
|
|
mount = "secret"
|
|
name = "platform"
|
|
}
|
|
|
|
locals {
|
|
k8s_users = jsondecode(data.vault_kv_secret_v2.platform.data["k8s_users"])
|
|
|
|
# Build admin list: existing admin + all namespace-owner usernames
|
|
woodpecker_admins = join(",", concat(
|
|
["ViktorBarzin"],
|
|
[for name, user in local.k8s_users : name if user.role == "namespace-owner"]
|
|
))
|
|
}
|
|
|
|
resource "kubernetes_namespace" "woodpecker" {
|
|
metadata {
|
|
name = "woodpecker"
|
|
labels = {
|
|
"resource-governance/custom-quota" = "true"
|
|
tier = local.tiers.edge
|
|
}
|
|
}
|
|
lifecycle {
|
|
# KYVERNO_LIFECYCLE_V1: goldilocks-vpa-auto-mode ClusterPolicy stamps this label on every namespace
|
|
ignore_changes = [metadata[0].labels["goldilocks.fairwinds.com/vpa-update-mode"]]
|
|
}
|
|
}
|
|
|
|
resource "kubernetes_resource_quota" "woodpecker" {
|
|
metadata {
|
|
name = "tier-quota"
|
|
namespace = kubernetes_namespace.woodpecker.metadata[0].name
|
|
}
|
|
spec {
|
|
hard = {
|
|
"requests.cpu" = "16"
|
|
"requests.memory" = "16Gi"
|
|
"limits.memory" = "32Gi"
|
|
pods = "60"
|
|
}
|
|
}
|
|
}
|
|
|
|
module "tls_secret" {
|
|
source = "../../modules/kubernetes/setup_tls_secret"
|
|
namespace = kubernetes_namespace.woodpecker.metadata[0].name
|
|
tls_secret_name = var.tls_secret_name
|
|
}
|
|
|
|
resource "kubernetes_manifest" "external_secret" {
|
|
manifest = {
|
|
apiVersion = "external-secrets.io/v1beta1"
|
|
kind = "ExternalSecret"
|
|
metadata = {
|
|
name = "woodpecker-secrets"
|
|
namespace = "woodpecker"
|
|
}
|
|
spec = {
|
|
refreshInterval = "15m"
|
|
secretStoreRef = {
|
|
name = "vault-kv"
|
|
kind = "ClusterSecretStore"
|
|
}
|
|
target = {
|
|
name = "woodpecker-secrets"
|
|
}
|
|
dataFrom = [{
|
|
extract = {
|
|
key = "woodpecker"
|
|
}
|
|
}]
|
|
}
|
|
}
|
|
depends_on = [kubernetes_namespace.woodpecker]
|
|
}
|
|
|
|
# DB credentials from Vault database engine (rotated every 24h)
|
|
# ExternalSecret provides WOODPECKER_DATABASE_DATASOURCE injected via
|
|
# server.extraSecretNamesForEnvFrom — auto-updates when password rotates
|
|
resource "kubernetes_manifest" "db_external_secret" {
|
|
field_manager {
|
|
force_conflicts = true
|
|
}
|
|
manifest = {
|
|
apiVersion = "external-secrets.io/v1beta1"
|
|
kind = "ExternalSecret"
|
|
metadata = {
|
|
name = "woodpecker-db-creds"
|
|
namespace = "woodpecker"
|
|
}
|
|
spec = {
|
|
refreshInterval = "15m"
|
|
secretStoreRef = {
|
|
name = "vault-database"
|
|
kind = "ClusterSecretStore"
|
|
}
|
|
target = {
|
|
name = "woodpecker-db-creds"
|
|
template = {
|
|
data = {
|
|
WOODPECKER_DATABASE_DATASOURCE = "postgres://woodpecker:{{ .password }}@${var.postgresql_host}:5432/woodpecker?sslmode=disable"
|
|
}
|
|
}
|
|
}
|
|
data = [{
|
|
secretKey = "password"
|
|
remoteRef = {
|
|
key = "static-creds/pg-woodpecker"
|
|
property = "password"
|
|
}
|
|
}]
|
|
}
|
|
}
|
|
depends_on = [kubernetes_namespace.woodpecker]
|
|
}
|
|
|
|
resource "kubernetes_config_map" "git_crypt_key" {
|
|
metadata {
|
|
name = "git-crypt-key"
|
|
namespace = kubernetes_namespace.woodpecker.metadata[0].name
|
|
}
|
|
|
|
data = {
|
|
"key" = filebase64("${path.root}/../../.git/git-crypt/keys/default")
|
|
}
|
|
}
|
|
|
|
# Database init job - REMOVED: database and user already exist.
|
|
# The job used -U root which doesn't work with CNPG (superuser is 'postgres').
|
|
# Vault DB engine manages the woodpecker credentials via rotation.
|
|
|
|
# Woodpecker server data is on local-path (node-local storage), NOT NFS.
|
|
# The old NFS PV was unused — PVC was already bound to local-path PV.
|
|
# No PV management needed here.
|
|
|
|
# Helm release for Woodpecker CI
|
|
# Database datasource is now injected from ExternalSecret via envFrom
|
|
resource "helm_release" "woodpecker" {
|
|
name = "woodpecker"
|
|
namespace = kubernetes_namespace.woodpecker.metadata[0].name
|
|
repository = "oci://ghcr.io/woodpecker-ci/helm"
|
|
chart = "woodpecker"
|
|
version = "3.5.1"
|
|
|
|
values = [
|
|
templatefile("${path.module}/values.yaml", {
|
|
github_client_id = data.vault_kv_secret_v2.secrets.data["github_client_id"]
|
|
github_client_secret = data.vault_kv_secret_v2.secrets.data["github_client_secret"]
|
|
agent_secret = data.vault_kv_secret_v2.secrets.data["agent_secret"]
|
|
forgejo_client_id = data.vault_kv_secret_v2.secrets.data["forgejo_client_id"]
|
|
forgejo_client_secret = data.vault_kv_secret_v2.secrets.data["forgejo_client_secret"]
|
|
forgejo_url = var.woodpecker_forgejo_url
|
|
woodpecker_admins = local.woodpecker_admins
|
|
})
|
|
]
|
|
|
|
timeout = 600
|
|
depends_on = [kubernetes_manifest.db_external_secret]
|
|
}
|
|
|
|
# ClusterRoleBinding - build pods need cluster-admin to PATCH deployments across namespaces
|
|
resource "kubernetes_cluster_role_binding" "woodpecker" {
|
|
metadata {
|
|
name = "woodpecker"
|
|
}
|
|
subject {
|
|
kind = "ServiceAccount"
|
|
name = "woodpecker-agent"
|
|
namespace = kubernetes_namespace.woodpecker.metadata[0].name
|
|
}
|
|
role_ref {
|
|
kind = "ClusterRole"
|
|
name = "cluster-admin"
|
|
api_group = "rbac.authorization.k8s.io"
|
|
}
|
|
}
|
|
|
|
# Also bind the default SA (pipeline pods run as default)
|
|
resource "kubernetes_cluster_role_binding" "woodpecker_default" {
|
|
metadata {
|
|
name = "woodpecker-default"
|
|
}
|
|
subject {
|
|
kind = "ServiceAccount"
|
|
name = "default"
|
|
namespace = kubernetes_namespace.woodpecker.metadata[0].name
|
|
}
|
|
role_ref {
|
|
kind = "ClusterRole"
|
|
name = "cluster-admin"
|
|
api_group = "rbac.authorization.k8s.io"
|
|
}
|
|
}
|
|
|
|
# --- Vault → Woodpecker Secret Sync ---
|
|
# Syncs secrets from Vault KV (secret/ci/global) to Woodpecker global secrets via API.
|
|
# Runs every 6 hours. Secrets are created/updated via Woodpecker REST API.
|
|
|
|
resource "kubernetes_config_map" "vault_woodpecker_sync" {
|
|
metadata {
|
|
name = "vault-woodpecker-sync"
|
|
namespace = kubernetes_namespace.woodpecker.metadata[0].name
|
|
}
|
|
|
|
data = {
|
|
"sync.sh" = <<-SCRIPT
|
|
#!/bin/sh
|
|
set -e
|
|
VAULT_ADDR="http://vault-active.vault.svc.cluster.local:8200"
|
|
WP_API="http://woodpecker-server.woodpecker.svc.cluster.local/api"
|
|
|
|
# Authenticate to Vault via K8s SA
|
|
SA_TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
|
|
VAULT_TOKEN=$(curl -sf -X POST "$VAULT_ADDR/v1/auth/kubernetes/login" \
|
|
-d "{\"role\":\"woodpecker-sync\",\"jwt\":\"$SA_TOKEN\"}" | jq -r .auth.client_token)
|
|
|
|
if [ -z "$VAULT_TOKEN" ] || [ "$VAULT_TOKEN" = "null" ]; then
|
|
echo "ERROR: Failed to authenticate to Vault"
|
|
exit 1
|
|
fi
|
|
|
|
# Get Woodpecker API token from Vault
|
|
WP_TOKEN=$(curl -sf -H "X-Vault-Token: $VAULT_TOKEN" \
|
|
"$VAULT_ADDR/v1/secret/data/ci/global" | jq -r '.data.data.woodpecker_api_token // empty')
|
|
|
|
if [ -z "$WP_TOKEN" ]; then
|
|
echo "ERROR: No woodpecker_api_token in secret/ci/global"
|
|
exit 1
|
|
fi
|
|
|
|
# Sync global secrets
|
|
SECRETS=$(curl -sf -H "X-Vault-Token: $VAULT_TOKEN" \
|
|
"$VAULT_ADDR/v1/secret/data/ci/global" | jq -r '.data.data | to_entries[] | select(.key != "woodpecker_api_token") | @base64')
|
|
|
|
synced=0
|
|
for entry in $SECRETS; do
|
|
NAME=$(echo "$entry" | base64 -d | jq -r .key)
|
|
VALUE=$(echo "$entry" | base64 -d | jq -r .value)
|
|
|
|
# Try PATCH first (update), fall back to POST (create)
|
|
# Include all event types so secrets work for manual/cron-triggered pipelines too
|
|
STATUS=$(curl -sf -o /dev/null -w "%%{http_code}" -X PATCH "$WP_API/secrets/$NAME" \
|
|
-H "Authorization: Bearer $WP_TOKEN" \
|
|
-H "Content-Type: application/json" \
|
|
-d "{\"name\":\"$NAME\",\"value\":\"$VALUE\",\"events\":[\"cron\",\"deployment\",\"manual\",\"push\",\"tag\"]}" 2>/dev/null || echo "000")
|
|
|
|
if [ "$STATUS" != "200" ]; then
|
|
curl -sf -X POST "$WP_API/secrets" \
|
|
-H "Authorization: Bearer $WP_TOKEN" \
|
|
-H "Content-Type: application/json" \
|
|
-d "{\"name\":\"$NAME\",\"value\":\"$VALUE\",\"events\":[\"cron\",\"deployment\",\"manual\",\"push\",\"tag\"]}" > /dev/null
|
|
fi
|
|
synced=$((synced + 1))
|
|
done
|
|
echo "Synced $synced global secrets from Vault to Woodpecker"
|
|
SCRIPT
|
|
}
|
|
}
|
|
|
|
resource "kubernetes_cron_job_v1" "vault_secret_sync" {
|
|
metadata {
|
|
name = "vault-woodpecker-sync"
|
|
namespace = kubernetes_namespace.woodpecker.metadata[0].name
|
|
}
|
|
spec {
|
|
schedule = "0 */6 * * *"
|
|
successful_jobs_history_limit = 3
|
|
failed_jobs_history_limit = 3
|
|
concurrency_policy = "Forbid"
|
|
job_template {
|
|
metadata {}
|
|
spec {
|
|
template {
|
|
metadata {}
|
|
spec {
|
|
container {
|
|
name = "sync"
|
|
image = "alpine"
|
|
command = ["/bin/sh", "-c", "apk add --no-cache curl jq && /bin/sh /scripts/sync.sh"]
|
|
volume_mount {
|
|
name = "sync-script"
|
|
mount_path = "/scripts"
|
|
}
|
|
resources {
|
|
requests = {
|
|
cpu = "10m"
|
|
memory = "32Mi"
|
|
}
|
|
limits = {
|
|
memory = "64Mi"
|
|
}
|
|
}
|
|
}
|
|
volume {
|
|
name = "sync-script"
|
|
config_map {
|
|
name = kubernetes_config_map.vault_woodpecker_sync.metadata[0].name
|
|
}
|
|
}
|
|
restart_policy = "OnFailure"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
lifecycle {
|
|
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
|
|
ignore_changes = [spec[0].job_template[0].spec[0].template[0].spec[0].dns_config]
|
|
}
|
|
}
|
|
|
|
module "ingress" {
|
|
source = "../../modules/kubernetes/ingress_factory"
|
|
dns_type = "non-proxied"
|
|
namespace = kubernetes_namespace.woodpecker.metadata[0].name
|
|
name = "ci"
|
|
service_name = "woodpecker-server"
|
|
tls_secret_name = var.tls_secret_name
|
|
extra_annotations = {
|
|
"gethomepage.dev/enabled" = "true"
|
|
"gethomepage.dev/name" = "Woodpecker CI"
|
|
"gethomepage.dev/description" = "CI/CD pipelines"
|
|
"gethomepage.dev/icon" = "woodpecker-ci.png"
|
|
"gethomepage.dev/group" = "Development & CI"
|
|
"gethomepage.dev/pod-selector" = ""
|
|
}
|
|
}
|