Squashed commit of the following:

commit 20ee715
Merge: 2466a7e a6320bd
Author: Jeff Raubitschek <[email protected]>
Date:   Thu Sep 12 10:52:46 2024 -0700

    Merge remote-tracking branch 'origin/main' into jhr/add-clickhouse-1

commit 2466a7e
Author: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Date:   Wed Sep 11 21:53:59 2024 +0000

    terraform-docs: automated action

commit 8c84c7f
Author: Jeff Raubitschek <[email protected]>
Date:   Wed Sep 11 14:52:03 2024 -0700

    allow clickhouse subnet to be configured and use class c

commit 13d0f4a
Author: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Date:   Wed Sep 11 17:20:37 2024 +0000

    terraform-docs: automated action

commit 2a7cc59
Author: Jeff Raubitschek <[email protected]>
Date:   Wed Sep 11 10:19:08 2024 -0700

    feat: add clickhouse private service connect

README.md

@@ -78,6 +78,7 @@ resources that lack official modules.
 |------|--------|---------|
 | <a name="module_app_gke"></a> [app\_gke](#module\_app\_gke) | ./modules/app_gke | n/a |
 | <a name="module_app_lb"></a> [app\_lb](#module\_app\_lb) | ./modules/app_lb | n/a |
+| <a name="module_clickhouse"></a> [clickhouse](#module\_clickhouse) | ./modules/clickhouse | n/a |
 | <a name="module_database"></a> [database](#module\_database) | ./modules/database | n/a |
 | <a name="module_gke_app"></a> [gke\_app](#module\_gke\_app) | wandb/wandb/kubernetes | 1.14.1 |
 | <a name="module_kms"></a> [kms](#module\_kms) | ./modules/kms | n/a |
@@ -111,6 +112,9 @@ resources that lack official modules.
 | <a name="input_bucket_location"></a> [bucket\_location](#input\_bucket\_location) | Location of the bucket (US, EU, ASIA) | `string` | `"US"` | no |
 | <a name="input_bucket_name"></a> [bucket\_name](#input\_bucket\_name) | Use an existing bucket. | `string` | `""` | no |
 | <a name="input_bucket_path"></a> [bucket\_path](#input\_bucket\_path) | path of where to store data for the instance-level bucket | `string` | `""` | no |
+| <a name="input_clickhouse_private_endpoint_service_name"></a> [clickhouse\_private\_endpoint\_service\_name](#input\_clickhouse\_private\_endpoint\_service\_name) | ClickHouse private endpoint 'Service name' (ends in -clickhouse-cloud). | `string` | `""` | no |
+| <a name="input_clickhouse_region"></a> [clickhouse\_region](#input\_clickhouse\_region) | ClickHouse region (us-east1, us-central1, etc). | `string` | `""` | no |
+| <a name="input_clickhouse_subnetwork_cidr"></a> [clickhouse\_subnetwork\_cidr](#input\_clickhouse\_subnetwork\_cidr) | ClickHouse private service connect subnetwork | `string` | `"10.50.0.0/24"` | no |
 | <a name="input_create_private_link"></a> [create\_private\_link](#input\_create\_private\_link) | Whether to create a private link service. | `bool` | `false` | no |
 | <a name="input_create_redis"></a> [create\_redis](#input\_create\_redis) | Boolean indicating whether to provision an redis instance (true) or not (false). | `bool` | `false` | no |
 | <a name="input_create_workload_identity"></a> [create\_workload\_identity](#input\_create\_workload\_identity) | Flag to indicate whether to create a workload identity for the service account. | `bool` | `false` | no |
@@ -162,6 +166,7 @@ resources that lack official modules.
 | <a name="output_bucket_name"></a> [bucket\_name](#output\_bucket\_name) | Name of google bucket. |
 | <a name="output_bucket_path"></a> [bucket\_path](#output\_bucket\_path) | path of where to store data for the instance-level bucket |
 | <a name="output_bucket_queue_name"></a> [bucket\_queue\_name](#output\_bucket\_queue\_name) | Pubsub queue created for google bucket file upload events. |
+| <a name="output_clickhouse_private_endpoint_id"></a> [clickhouse\_private\_endpoint\_id](#output\_clickhouse\_private\_endpoint\_id) | ClickHouse Private endpoint Endpoint ID to secure access inside VPC |
 | <a name="output_cluster_ca_certificate"></a> [cluster\_ca\_certificate](#output\_cluster\_ca\_certificate) | Certificate of the kubernetes (GKE) cluster. |
 | <a name="output_cluster_client_certificate"></a> [cluster\_client\_certificate](#output\_cluster\_client\_certificate) | n/a |
 | <a name="output_cluster_client_key"></a> [cluster\_client\_key](#output\_cluster\_client\_key) | n/a |

main.tf

@@ -160,6 +160,17 @@ module "redis" {
   depends_on        = [module.project_factory_project_services, module.kms_default_sql]
 }
 
+module "clickhouse" {
+  count      = var.clickhouse_private_endpoint_service_name != "" ? 1 : 0
+  source     = "./modules/clickhouse"
+  network    = local.network.id
+  namespace  = var.namespace
+
+  clickhouse_reserved_ip_range             = var.clickhouse_subnetwork_cidr
+  clickhouse_private_endpoint_service_name = var.clickhouse_private_endpoint_service_name
+  clickhouse_region                        = var.clickhouse_region
+}
+
 locals {
   redis_certificate       = var.create_redis ? module.redis[0].ca_cert : null
   redis_connection_string = var.create_redis ? "redis://:${module.redis[0].auth_string}@${module.redis[0].connection_string}?tls=true&ttlInSeconds=604800&caCertPath=/etc/ssl/certs/server_ca.pem" : null

modules/clickhouse/main.tf

@@ -0,0 +1,50 @@
+resource "google_compute_subnetwork" "psc_network" {
+  name = "${var.namespace}-subnet-clickhouse"
+
+  region                   = var.clickhouse_region
+  ip_cidr_range            = var.clickhouse_reserved_ip_range
+  private_ip_google_access = true
+  network                  = var.network
+}
+
+resource "google_compute_address" "psc_endpoint_ip" {
+  name         = "${var.namespace}-clickhouse-psc-ip"
+  address_type = "INTERNAL"
+  purpose      = "GCE_ENDPOINT"
+  subnetwork   = google_compute_subnetwork.psc_network.self_link
+  region       = var.clickhouse_region
+}
+
+resource "google_compute_forwarding_rule" "psc_forward_rule" {
+  name                    = "${var.namespace}-clickhouse-psc-forward"
+  ip_address              = google_compute_address.psc_endpoint_ip.self_link
+  network                 = var.network
+  region                  = var.clickhouse_region
+  load_balancing_scheme   = ""
+  allow_psc_global_access = true
+
+  target = "https://www.googleapis.com/compute/v1/${var.clickhouse_private_endpoint_service_name}"
+}
+
+resource "google_dns_managed_zone" "psc_dns_zone" {
+  name          = "${var.namespace}-clickhouse-dns-zone"
+  description   = "Private DNS zone for accessing ClickHouse Cloud using Private Service Connect"
+  dns_name      = "${var.clickhouse_region}.p.gcp.clickhouse.cloud."
+  force_destroy = true
+  visibility    = "private"
+
+  // associate private DNS zone with network
+  private_visibility_config {
+    networks {
+      network_url = var.network
+    }
+  }
+}
+
+resource "google_dns_record_set" "psc_dns_record" {
+  name         = "*.${var.clickhouse_region}.p.gcp.clickhouse.cloud."
+  managed_zone = google_dns_managed_zone.psc_dns_zone.name
+  type         = "A"
+  rrdatas      = [ google_compute_address.psc_endpoint_ip.address ]
+  ttl          = 3600
+}

modules/clickhouse/output.tf

@@ -0,0 +1,4 @@
+output "psc_connection_id" {
+  value       = google_compute_forwarding_rule.psc_forward_rule.psc_connection_id
+  description = "Add GCP PSC Connection ID to ClickHouse allow list."
+}

modules/clickhouse/variables.tf

@@ -0,0 +1,37 @@
+variable "namespace" {
+  type        = string
+  description = "The name prefix for all resources created."
+}
+
+variable "network" {
+  type        = string
+  description = "Google Compute Engine network to which the cluster is connected."
+}
+
+variable "clickhouse_reserved_ip_range" {
+  type        = string
+  description = "Reserved IP range for ClickHouse private link"
+  default     = "10.50.0.0/24"
+}
+
+variable "clickhouse_private_endpoint_service_name" {
+  type        = string
+  description = "ClickHouse private endpoint 'Service name' (ends in -clickhouse-cloud)."
+  default     = ""
+
+  validation {
+    condition = can(regex("-clickhouse-cloud$", var.clickhouse_private_endpoint_service_name))
+    error_message = "ClickHouse Service name must end in '-clickhouse-cloud'."
+  }
+}
+
+variable "clickhouse_region" {
+  type        = string
+  description = "ClickHouse region (us-east1, us-central1, etc)."
+  default     = ""
+
+  validation {
+    condition = length(var.clickhouse_region) > 0
+    error_message = "Clickhouse Region should always be set if the private endpoint service name is specified."
+  }
+}

modules/networking/main.tf

@@ -2,6 +2,7 @@ resource "google_compute_network" "vpc" {
   name                    = "${var.namespace}-vpc"
   description             = "Weights & Biases VPC Network"
   auto_create_subnetworks = false
+  # routing_mode            = "GLOBAL"
 }
 
 resource "google_compute_subnetwork" "default" {

outputs.tf

@@ -96,4 +96,9 @@ output "private_attachement_id" {
 output "sa_account_email" {
   description = "This output provides the email address of the service account created for workload identity, if workload identity is enabled. Otherwise, it returns null"
   value       = var.create_workload_identity == true ? module.service_accounts.sa_account_role : null
-}
+}
+
+output "clickhouse_private_endpoint_id" {
+  description = "ClickHouse Private endpoint Endpoint ID to secure access inside VPC"
+  value = var.clickhouse_private_endpoint_service_name != "" ? module.clickhouse[0].psc_connection_id : null
+}

variables.tf

@@ -353,3 +353,24 @@ variable "stackdriver_sa_name" {
   type    = string
   default = "wandb-stackdriver"
 }
+
+###########################################
+# ClickHouse endpoint                     #
+###########################################
+variable "clickhouse_private_endpoint_service_name" {
+  type        = string
+  description = "ClickHouse private endpoint 'Service name' (ends in -clickhouse-cloud)."
+  default     = ""
+}
+
+variable "clickhouse_region" {
+  type        = string
+  description = "ClickHouse region (us-east1, us-central1, etc)."
+  default     = ""
+}
+
+variable "clickhouse_subnetwork_cidr" {
+  default     = "10.50.0.0/24"
+  description = "ClickHouse private service connect subnetwork"
+  type        = string
+}