## Context Wave 3B-continued: the Goldilocks VPA dashboard (stacks/vpa) runs a Kyverno ClusterPolicy `goldilocks-vpa-auto-mode` that mutates every namespace with `metadata.labels["goldilocks.fairwinds.com/vpa-update-mode"] = "off"`. This is intentional — Terraform owns container resource limits, and Goldilocks should only provide recommendations, never auto-update. The label is how Goldilocks decides per-namespace whether to run its VPA in `off` mode. Effect on Terraform: every `kubernetes_namespace` resource shows the label as pending-removal (`-> null`) on every `scripts/tg plan`. Dawarich survey 2026-04-18 confirmed the drift. Cluster-side count: 88 namespaces carry the label (`kubectl get ns -o json | jq ... | wc -l`). Every TF-managed namespace is affected. This commit brings the intentional admission drift under the same `# KYVERNO_LIFECYCLE_V1` discoverability marker introduced inc9d221d5for the ndots dns_config pattern. The marker now stands generically for any Kyverno admission-webhook drift suppression; the inline comment records which specific policy stamps which specific field so future grep audits show why each suppression exists. ## This change 107 `.tf` files touched — every stack's `resource "kubernetes_namespace"` resource gets: ```hcl 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"]] } ``` Injection was done with a brace-depth-tracking Python pass (`/tmp/add_goldilocks_ignore.py`): match `^resource "kubernetes_namespace" ` → track `{` / `}` until the outermost closing brace → insert the lifecycle block before the closing brace. The script is idempotent (skips any file that already mentions `goldilocks.fairwinds.com/vpa-update-mode`) so re-running is safe. Vault stack picked up 2 namespaces in the same file (k8s-users produces one, plus a second explicit ns) — confirmed via file diff (+8 lines). ## What is NOT in this change - `stacks/trading-bot/main.tf` — entire file is `/* … */` commented out (paused 2026-04-06 per user decision). Reverted after the script ran. - `stacks/_template/main.tf.example` — per-stack skeleton, intentionally minimal. User keeps it that way. Not touched by the script (file has no real `resource "kubernetes_namespace"` — only a placeholder comment). - `.terraform/` copies (e.g. `stacks/metallb/.terraform/modules/...`) — gitignored, won't commit; the live path was edited. - `terraform fmt` cleanup of adjacent pre-existing alignment issues in authentik, freedify, hermes-agent, nvidia, vault, meshcentral. Reverted to keep the commit scoped to the Goldilocks sweep. Those files will need a separate fmt-only commit or will be cleaned up on next real apply to that stack. ## Verification Dawarich (one of the hundred-plus touched stacks) showed the pattern before and after: ``` $ cd stacks/dawarich && ../../scripts/tg plan Before: Plan: 0 to add, 2 to change, 0 to destroy. # kubernetes_namespace.dawarich will be updated in-place (goldilocks.fairwinds.com/vpa-update-mode -> null) # module.tls_secret.kubernetes_secret.tls_secret will be updated in-place (Kyverno generate.* labels — fixed in8d94688d) After: No changes. Your infrastructure matches the configuration. ``` Injection count check: ``` $ rg -c 'KYVERNO_LIFECYCLE_V1: goldilocks-vpa-auto-mode' stacks/ | awk -F: '{s+=$2} END {print s}' 108 ``` ## Reproduce locally 1. `git pull` 2. Pick any stack: `cd stacks/<name> && ../../scripts/tg plan` 3. Expect: no drift on the namespace's goldilocks.fairwinds.com/vpa-update-mode label. Closes: code-dwx Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
213 lines
6.1 KiB
HCL
213 lines
6.1 KiB
HCL
resource "kubernetes_namespace" "proxmox_csi" {
|
|
metadata {
|
|
name = "proxmox-csi"
|
|
labels = {
|
|
tier = var.tier
|
|
"resource-governance/custom-quota" = "true"
|
|
}
|
|
}
|
|
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 "helm_release" "proxmox_csi" {
|
|
namespace = kubernetes_namespace.proxmox_csi.metadata[0].name
|
|
create_namespace = false
|
|
name = "proxmox-csi-plugin"
|
|
atomic = true
|
|
timeout = 300
|
|
|
|
repository = "oci://ghcr.io/sergelogvinov/charts"
|
|
chart = "proxmox-csi-plugin"
|
|
|
|
values = [yamlencode({
|
|
config = {
|
|
clusters = [{
|
|
url = var.proxmox_url
|
|
insecure = true
|
|
token_id = var.proxmox_token_id
|
|
token_secret = var.proxmox_token_secret
|
|
region = var.proxmox_cluster_name
|
|
}]
|
|
}
|
|
|
|
# StorageClass for block volumes on existing HDD thin pool
|
|
storageClass = [
|
|
{
|
|
name = "proxmox-lvm"
|
|
storage = "local-lvm"
|
|
reclaimPolicy = "Retain"
|
|
fstype = "ext4"
|
|
ssd = false
|
|
cache = "none"
|
|
volumeBindingMode = "WaitForFirstConsumer"
|
|
allowVolumeExpansion = true
|
|
},
|
|
{
|
|
name = "proxmox-lvm-encrypted"
|
|
storage = "local-lvm"
|
|
reclaimPolicy = "Retain"
|
|
fstype = "ext4"
|
|
ssd = false
|
|
cache = "none"
|
|
volumeBindingMode = "WaitForFirstConsumer"
|
|
allowVolumeExpansion = true
|
|
extraParameters = {
|
|
"csi.storage.k8s.io/node-stage-secret-name" = "proxmox-csi-encryption"
|
|
"csi.storage.k8s.io/node-stage-secret-namespace" = "kube-system"
|
|
"csi.storage.k8s.io/node-expand-secret-name" = "proxmox-csi-encryption"
|
|
"csi.storage.k8s.io/node-expand-secret-namespace" = "kube-system"
|
|
}
|
|
},
|
|
]
|
|
|
|
controller = {
|
|
replicas = 2
|
|
resources = {
|
|
requests = { cpu = "10m", memory = "32Mi" }
|
|
limits = { memory = "64Mi" }
|
|
}
|
|
}
|
|
|
|
# LUKS2 Argon2id key derivation needs ~1GiB memory
|
|
node = {
|
|
plugin = {
|
|
resources = {
|
|
requests = { cpu = "10m", memory = "64Mi" }
|
|
limits = { memory = "1280Mi" }
|
|
}
|
|
}
|
|
}
|
|
})]
|
|
}
|
|
|
|
# Topology labels on K8s nodes — required for Proxmox CSI to map nodes to Proxmox VMs.
|
|
# region = Proxmox cluster name, zone = Proxmox node name (where the VM runs).
|
|
# All our VMs run on the single Proxmox node "pve".
|
|
locals {
|
|
k8s_nodes = {
|
|
"k8s-master" = { vmid = 200, proxmox_node = "pve" }
|
|
"k8s-node1" = { vmid = 201, proxmox_node = "pve" }
|
|
"k8s-node2" = { vmid = 202, proxmox_node = "pve" }
|
|
"k8s-node3" = { vmid = 203, proxmox_node = "pve" }
|
|
"k8s-node4" = { vmid = 204, proxmox_node = "pve" }
|
|
}
|
|
}
|
|
|
|
resource "null_resource" "node_labels" {
|
|
for_each = local.k8s_nodes
|
|
|
|
provisioner "local-exec" {
|
|
command = <<-EOT
|
|
kubectl --kubeconfig=${var.kube_config_path} label node ${each.key} \
|
|
topology.kubernetes.io/region=${var.proxmox_cluster_name} \
|
|
topology.kubernetes.io/zone=${each.value.proxmox_node} \
|
|
node.csi.proxmox.sinextra.dev/name=${each.key} \
|
|
--overwrite
|
|
EOT
|
|
}
|
|
|
|
triggers = {
|
|
region = var.proxmox_cluster_name
|
|
zone = each.value.proxmox_node
|
|
}
|
|
}
|
|
|
|
# --- RBAC for PVE host snapshot restore script ---
|
|
# Provides kubectl access from the Proxmox host for the lvm-pvc-snapshot restore subcommand.
|
|
# Minimal permissions: read PVs/PVCs/Pods, scale Deployments/StatefulSets.
|
|
|
|
resource "kubernetes_service_account" "pve_snapshot_admin" {
|
|
metadata {
|
|
name = "pve-snapshot-admin"
|
|
namespace = "kube-system"
|
|
}
|
|
}
|
|
|
|
resource "kubernetes_secret" "pve_snapshot_admin_token" {
|
|
metadata {
|
|
name = "pve-snapshot-admin-token"
|
|
namespace = "kube-system"
|
|
annotations = {
|
|
"kubernetes.io/service-account.name" = kubernetes_service_account.pve_snapshot_admin.metadata[0].name
|
|
}
|
|
}
|
|
type = "kubernetes.io/service-account-token"
|
|
}
|
|
|
|
resource "kubernetes_cluster_role" "pve_snapshot_admin" {
|
|
metadata {
|
|
name = "pve-snapshot-admin"
|
|
}
|
|
|
|
rule {
|
|
api_groups = [""]
|
|
resources = ["persistentvolumes", "persistentvolumeclaims", "pods"]
|
|
verbs = ["get", "list"]
|
|
}
|
|
|
|
rule {
|
|
api_groups = ["apps"]
|
|
resources = ["deployments", "statefulsets", "replicasets"]
|
|
verbs = ["get", "list", "update", "patch"]
|
|
}
|
|
|
|
rule {
|
|
api_groups = ["apps"]
|
|
resources = ["deployments/scale", "statefulsets/scale"]
|
|
verbs = ["get", "update", "patch"]
|
|
}
|
|
}
|
|
|
|
resource "kubernetes_cluster_role_binding" "pve_snapshot_admin" {
|
|
metadata {
|
|
name = "pve-snapshot-admin"
|
|
}
|
|
|
|
role_ref {
|
|
api_group = "rbac.authorization.k8s.io"
|
|
kind = "ClusterRole"
|
|
name = kubernetes_cluster_role.pve_snapshot_admin.metadata[0].name
|
|
}
|
|
|
|
subject {
|
|
kind = "ServiceAccount"
|
|
name = kubernetes_service_account.pve_snapshot_admin.metadata[0].name
|
|
namespace = "kube-system"
|
|
}
|
|
}
|
|
|
|
# --- ExternalSecret for LUKS encryption passphrase ---
|
|
# Creates K8s Secret "proxmox-csi-encryption" in kube-system from Vault KV.
|
|
# Referenced by the proxmox-lvm-encrypted StorageClass for node-stage and node-expand.
|
|
resource "kubernetes_manifest" "external_secret_encryption" {
|
|
manifest = {
|
|
apiVersion = "external-secrets.io/v1beta1"
|
|
kind = "ExternalSecret"
|
|
metadata = {
|
|
name = "proxmox-csi-encryption"
|
|
namespace = "kube-system"
|
|
}
|
|
spec = {
|
|
refreshInterval = "1h"
|
|
secretStoreRef = {
|
|
kind = "ClusterSecretStore"
|
|
name = "vault-kv"
|
|
}
|
|
target = {
|
|
name = "proxmox-csi-encryption"
|
|
creationPolicy = "Owner"
|
|
deletionPolicy = "Retain"
|
|
}
|
|
data = [{
|
|
secretKey = "encryption-passphrase"
|
|
remoteRef = {
|
|
key = "viktor"
|
|
property = "proxmox_csi_encryption_passphrase"
|
|
}
|
|
}]
|
|
}
|
|
}
|
|
}
|