73b9095d83
Switch gcp/ backend from Cloudflare R2 (S3-compatible) to GCS — uses
Application Default Credentials automatically, no extra env vars needed.
State has been migrated to gs://neuron-785695-terraform-state/gcp/.
Remove GCE Vault node resources (vault-node-1/2/3) from vault-nodes.tf
and Terraform state. GKE Vault (Workload Identity + vault-unseal SA) has
been serving traffic since the NEG cutover; GCE nodes are confirmed dead.
Removed from state and config:
- google_compute_instance.vault_node (x3)
- google_compute_disk.vault_data (x3)
- google_compute_instance_group.vault (x3)
- google_compute_firewall.vault_iap_ssh / vault_raft / vault_api (GCE-targeted)
- google_storage_bucket_object.vault_startup
- google_storage_bucket_iam_member.vault_node_bucket_read
- google_project_iam_member.vault_node_{log_writer,metric_writer,compute_viewer}
Kept: KMS, vault-unseal SA, WI binding, NEG data sources, GKE firewall,
global LB (address, cert, backend service, url maps, proxies, fwd rules).
177 lines
6.7 KiB
Terraform
177 lines
6.7 KiB
Terraform
# ── Vault LB — GCP Global HTTPS LB ───────────────────────────────────────────
|
|
#
|
|
# LB frontend is unchanged: forwarding rule → target HTTPS proxy → url map → backend.
|
|
# Backend uses GKE container-native NEGs (cut over from GCE instance groups).
|
|
#
|
|
# Architecture (GKE):
|
|
# - Vault Helm chart runs 3 pods in namespace: vault on GKE neuron-platform cluster
|
|
# - GKE auto-creates zonal container-native NEGs via Service annotation:
|
|
# cloud.google.com/neg: '{"exposed_ports":{"8200":{}}}'
|
|
# - NEG backends replace GCE instance group backends in the Global HTTPS LB
|
|
# - DNS unchanged: vault.neuralplatform.ai → 34.54.164.21 (same GCP Global LB IP)
|
|
#
|
|
# GCE nodes (vault-node-1/2/3) and their instance groups have been removed.
|
|
# GKE Vault (via Workload Identity + vault-unseal SA) is the sole Vault backend.
|
|
|
|
locals {
|
|
# Container-native NEG names created by GKE from the Vault Service annotation:
|
|
# cloud.google.com/neg: '{"exposed_ports":{"8200":{}}}'
|
|
# GKE creates one NEG per zone where Vault pods are scheduled.
|
|
# Confirmed with: gcloud compute network-endpoint-groups list --project neuron-785695
|
|
vault_neg_names = {
|
|
"us-central1-b" = "k8s1-bfbeff02-vault-vault-helm-gke-8200-db1a474f"
|
|
"us-central1-c" = "k8s1-bfbeff02-vault-vault-helm-gke-8200-db1a474f"
|
|
"us-central1-f" = "k8s1-bfbeff02-vault-vault-helm-gke-8200-db1a474f"
|
|
}
|
|
}
|
|
|
|
# ── GKE container-native NEG data sources ────────────────────────────────────
|
|
# GKE auto-creates these when the Vault Service annotation is applied.
|
|
|
|
data "google_compute_network_endpoint_group" "vault_gke" {
|
|
for_each = local.vault_neg_names
|
|
name = each.value
|
|
zone = each.key
|
|
project = var.project_id
|
|
}
|
|
|
|
# ── Firewall — GKE health checks ─────────────────────────────────────────────
|
|
# Allow GCP health check probers to reach pod IPs on port 8200.
|
|
# Container-native NEGs direct health checks to pod IPs (not node IPs).
|
|
# GKE Autopilot pod CIDR: 10.45.128.0/22 (from cluster ip_allocation_policy).
|
|
# Without this rule, GCP LB health checks fail → "no healthy upstream".
|
|
# No target_tags — applies to all instances/pods in the default network.
|
|
# Safe: GCP health check ranges (130.211.0.0/22, 35.191.0.0/16) are GCP-internal only.
|
|
resource "google_compute_firewall" "vault_api_gke" {
|
|
name = "vault-api-from-lb-gke"
|
|
network = "default"
|
|
project = var.project_id
|
|
direction = "INGRESS"
|
|
priority = 1000
|
|
|
|
allow {
|
|
protocol = "tcp"
|
|
ports = ["8200"]
|
|
}
|
|
|
|
# GCP health check source ranges only — restricted port, low risk
|
|
source_ranges = ["130.211.0.0/22", "35.191.0.0/16"]
|
|
}
|
|
|
|
# ── Regional HTTPS LB for vault.neuralplatform.ai ─────────────────────────────
|
|
# Global external HTTPS LB with a Google-managed cert for vault.neuralplatform.ai.
|
|
#
|
|
# TLS is terminated at the LB. Vault listens on plain 8200 internally.
|
|
# Cloudflare DNS A record for vault.neuralplatform.ai → vault_lb_ip output below.
|
|
|
|
resource "google_compute_global_address" "vault" {
|
|
name = "vault-ip"
|
|
project = var.project_id
|
|
}
|
|
|
|
resource "google_compute_managed_ssl_certificate" "vault" {
|
|
name = "vault-cert"
|
|
project = var.project_id
|
|
|
|
managed {
|
|
domains = ["vault.neuralplatform.ai"]
|
|
}
|
|
}
|
|
|
|
resource "google_compute_health_check" "vault" {
|
|
name = "vault-health"
|
|
project = var.project_id
|
|
|
|
# Vault listens on plain HTTP (tls_disable = true) — TLS is terminated at the LB
|
|
http_health_check {
|
|
port = 8200
|
|
request_path = "/v1/sys/health?standbyok=true&sealedok=true&uninitcode=200"
|
|
}
|
|
|
|
check_interval_sec = 15
|
|
timeout_sec = 5
|
|
healthy_threshold = 2
|
|
unhealthy_threshold = 3
|
|
}
|
|
|
|
resource "google_compute_backend_service" "vault" {
|
|
name = "vault-backend"
|
|
project = var.project_id
|
|
load_balancing_scheme = "EXTERNAL_MANAGED"
|
|
protocol = "HTTP" # Vault serves plain HTTP; TLS terminates at the LB
|
|
timeout_sec = 30
|
|
|
|
health_checks = [google_compute_health_check.vault.self_link]
|
|
|
|
# GKE container-native NEG backends — one per zone where Vault pods are scheduled.
|
|
# RATE balancing mode is required for NEGs with EXTERNAL_MANAGED load balancers.
|
|
dynamic "backend" {
|
|
for_each = data.google_compute_network_endpoint_group.vault_gke
|
|
content {
|
|
group = backend.value.self_link
|
|
balancing_mode = "RATE"
|
|
max_rate_per_endpoint = 100
|
|
}
|
|
}
|
|
|
|
log_config {
|
|
enable = true
|
|
sample_rate = 1.0
|
|
}
|
|
}
|
|
|
|
resource "google_compute_url_map" "vault" {
|
|
name = "vault-urlmap"
|
|
project = var.project_id
|
|
default_service = google_compute_backend_service.vault.self_link
|
|
}
|
|
|
|
resource "google_compute_target_https_proxy" "vault" {
|
|
name = "vault-https-proxy"
|
|
project = var.project_id
|
|
url_map = google_compute_url_map.vault.self_link
|
|
ssl_certificates = [google_compute_managed_ssl_certificate.vault.self_link]
|
|
}
|
|
|
|
resource "google_compute_target_http_proxy" "vault_redirect" {
|
|
name = "vault-http-proxy"
|
|
project = var.project_id
|
|
url_map = google_compute_url_map.vault_redirect.self_link
|
|
}
|
|
|
|
resource "google_compute_url_map" "vault_redirect" {
|
|
name = "vault-urlmap-http-redirect"
|
|
project = var.project_id
|
|
|
|
default_url_redirect {
|
|
https_redirect = true
|
|
redirect_response_code = "MOVED_PERMANENTLY_DEFAULT"
|
|
strip_query = false
|
|
}
|
|
}
|
|
|
|
resource "google_compute_global_forwarding_rule" "vault_https" {
|
|
name = "vault-fwd-https"
|
|
project = var.project_id
|
|
target = google_compute_target_https_proxy.vault.self_link
|
|
ip_address = google_compute_global_address.vault.address
|
|
port_range = "443"
|
|
load_balancing_scheme = "EXTERNAL_MANAGED"
|
|
}
|
|
|
|
resource "google_compute_global_forwarding_rule" "vault_http" {
|
|
name = "vault-fwd-http"
|
|
project = var.project_id
|
|
target = google_compute_target_http_proxy.vault_redirect.self_link
|
|
ip_address = google_compute_global_address.vault.address
|
|
port_range = "80"
|
|
load_balancing_scheme = "EXTERNAL_MANAGED"
|
|
}
|
|
|
|
# ── Outputs ───────────────────────────────────────────────────────────────────
|
|
|
|
output "vault_lb_ip" {
|
|
description = "Global IP for vault.neuralplatform.ai — set as DNS A record in Cloudflare (neuralplatform.ai zone)"
|
|
value = google_compute_global_address.vault.address
|
|
}
|