k8s: Terraform deployment for GKE clusters

This provides a Terraform configuration for deploying our Kubernetes
clusters to GKE. We deploy an identical cluster to each of a list of
regions, with one small node for admin purposes due to a requirement to
not use spot instances for the main node group for the and two
autoscaling groups one with small 8 core nodes for most jobs and one
with bigger nodes for the more resource intensive ones.

This is different to our current scheme where each cluster has a single
node group and we direct jobs in Jenkins. With this scheme we allow the
Kubernetes scheduler to place jobs, or we can still direct them to
specific node sizes using nodeSelector in the jobs and the labels that
are assigned to the nodegroups. This is a more Kubernetes way of doing
things and decouples further from Jenkins.

Signed-off-by: Mark Brown <[email protected]>

k8s/gke/gke.tf

@@ -0,0 +1,127 @@
+# FIXME: For real deployment we should store the terraform state
+# in cloud storage rather than just the current directory, terraform
+# supports Azure blob storage directly. This means configuration
+# doesn't need to be on a single machine somewhere.
+#
+# See https://developer.hashicorp.com/terraform/language/settings/backends/gcs
+#
+#terraform {
+#  backend "gcs" {
+#    resource_group_name  = "kernelci-tf-storage"
+#    storage_account_name = "kernelci-tf"
+#    container_name       = "tfstate"
+#    key                  = "workers.terraform.tfstate"
+#  }
+#}
+
+#variable "gke_username" {
+#  default     = ""
+#  description = "gke username"
+#}
+
+#variable "gke_password" {
+#  default     = ""
+#  description = "gke password"
+#}
+
+locals {
+  regions = toset([
+    "us-central1",
+    "europe-west2",
+  ])
+}
+
+# GKE cluster
+resource "google_container_cluster" "primary" {
+  for_each = local.regions
+
+  name     = "${each.key}-workers"
+  location = each.key
+
+  # We can't create a cluster with no node pool defined, but we want to only use
+  # separately managed node pools. So we create the smallest possible default
+  # node pool and immediately delete it.
+  remove_default_node_pool = true
+  initial_node_count       = 1
+
+  network    = google_compute_network.vpc.name
+  subnetwork = google_compute_subnetwork.subnet.name
+}
+
+# Smaller nodes for most jobs
+resource "google_container_node_pool" "small_nodes" {
+  for_each = local.regions
+
+  name       = "${each.key}-small-node-pool"
+  location   = each.key
+  cluster    = "${each.key}-workers"
+
+  node_config {
+    oauth_scopes = [
+      "https://www.googleapis.com/auth/logging.write",
+      "https://www.googleapis.com/auth/monitoring",
+    ]
+
+    labels = {
+      "kernelci/worker" = "worker"
+      "kernelci/worker-size" = "small"
+    }
+
+    # Standard machine, 8 vCPUs, 30G memory
+    machine_type = "n1-standard-8"
+    preemptible  = true
+    spot = true
+    tags         = [
+       "kernelci/worker",
+       "kernelci/small-worker"
+    ]
+
+    metadata = {
+      disable-legacy-endpoints = "true"
+    }
+  }
+
+  autoscaling {
+    min_node_count = 1
+    max_node_count = 10
+  }
+}
+
+# Bigger nodes for all*config jobs
+resource "google_container_node_pool" "big_nodes" {
+  for_each = local.regions
+
+  name       = "${each.key}-big-node-pool"
+  location   = each.key
+  cluster    = "${each.key}-workers"
+
+  node_config {
+    oauth_scopes = [
+      "https://www.googleapis.com/auth/logging.write",
+      "https://www.googleapis.com/auth/monitoring",
+    ]
+
+    labels = {
+      "kernelci/worker" = "worker"
+      "kernelci/worker-size" = "big"
+    }
+
+    # Standard machine, 32 vCPUs, 128G (?) memory
+    machine_type = "n2-standard-32"
+    preemptible  = true
+    spot = true
+    tags         = [
+       "kernelci/worker",
+       "kernelci/big-worker"
+    ]
+
+    metadata = {
+      disable-legacy-endpoints = "true"
+    }
+  }
+
+  autoscaling {
+    min_node_count = 1
+    max_node_count = 10
+  }
+}

k8s/gke/outputs.tf

@@ -0,0 +1,4 @@
+output "project_id" {
+  value       = var.project_id
+  description = "GCloud Project ID"
+}

k8s/gke/versions.tf

@@ -0,0 +1,11 @@
+terraform {
+  required_providers {
+    google = {
+      source  = "hashicorp/google"
+      version = "4.27.0"
+    }
+  }
+
+  required_version = ">= 0.14"
+}
+

k8s/gke/vpc.tf

@@ -0,0 +1,26 @@
+variable "project_id" {
+  description = "project id"
+}
+
+variable "region" {
+  description = "region"
+}
+
+provider "google" {
+  project = var.project_id
+  region  = var.region
+}
+
+# VPC
+resource "google_compute_network" "vpc" {
+  name                    = "${var.project_id}-vpc"
+  auto_create_subnetworks = "false"
+}
+
+# Subnet
+resource "google_compute_subnetwork" "subnet" {
+  name          = "${var.project_id}-subnet"
+  region        = var.region
+  network       = google_compute_network.vpc.name
+  ip_cidr_range = "10.10.0.0/24"
+}