Create an auto-scaling node pool with Terraform

Add an auto-scaling node pool to an existing cluster

If you already have an ACK cluster, add a node pool with this minimal configuration:

provider "alicloud" {
}

# Add an auto-scaling node pool to an existing ACK cluster.
resource "alicloud_cs_kubernetes_node_pool" "at1" {
  # The ID of the existing ACK cluster.
  cluster_id     = ""
  name           = "np-test"
  # Specify at least one vSwitch for the node pool.
  vswitch_ids    = ["vsw-bp1mdigyhmilu2h4v****"]
  instance_types = ["ecs.e3.medium"]
  password       = "Hello1234"

  scaling_config {
    min_size = 1  # Minimum node count
    max_size = 5  # Maximum node count
  }
}

Create a cluster and an auto-scaling node pool together

Provision a VPC, an ACK Pro cluster, and an auto-scaling node pool in a single terraform apply:

provider "alicloud" {
  region = var.region_id
}

variable "region_id" {
  type    = string
  default = "cn-shenzhen"
}

variable "cluster_spec" {
  type        = string
  description = "The cluster specifications of kubernetes cluster,which can be empty. Valid values:ack.standard : Standard managed clusters; ack.pro.small : Professional managed clusters."
  default     = "ack.pro.small"
}

# Specify the zones of vSwitches.
variable "availability_zone" {
  description = "The availability zones of vswitches."
  default     = ["cn-shenzhen-c", "cn-shenzhen-e", "cn-shenzhen-f"]
}

# The CIDR blocks used to create vSwitches.
variable "node_vswitch_cidrs" {
  type        = list(string)
  default     = ["172.16.0.0/23", "172.16.2.0/23", "172.16.4.0/23"]
}

# This variable specifies the CIDR blocks in which Terway vSwitches are created.
variable "terway_vswitch_cidrs" {
  type        = list(string)
  default     = ["172.16.208.0/20", "172.16.224.0/20", "172.16.240.0/20"]
}

# Specify the ECS instance types of worker nodes.
variable "worker_instance_types" {
  description = "The ecs instance types used to launch worker nodes."
  default     = ["ecs.g6.2xlarge", "ecs.g6.xlarge"]
}

# Specify a password for the worker node.
variable "password" {
  description = "The password of ECS instance."
  default     = "Test123456"
}

# Specify the prefix of the name of the ACK managed cluster.
variable "k8s_name_prefix" {
  description = "The name prefix used to create managed kubernetes cluster."
  default     = "tf-ack-shenzhen"
}

# Specify the components to install in the ACK managed cluster.
# Components: Terway (network), csi-plugin (volume), csi-provisioner (volume),
# logtail-ds (logging), nginx-ingress-controller (Ingress), arms-prometheus (monitoring),
# ack-node-problem-detector (node diagnostics).
variable "cluster_addons" {
  type = list(object({
    name   = string
    config = string
  }))

  default = [
    {
      "name"   = "terway-eniip",
      "config" = "",
    },
    {
      "name"   = "logtail-ds",
      "config" = "{\"IngressDashboardEnabled\":\"true\"}",
    },
    {
      "name"   = "nginx-ingress-controller",
      "config" = "{\"IngressSlbNetworkType\":\"internet\"}",
    },
    {
      "name"   = "arms-prometheus",
      "config" = "",
    },
    {
      "name"   = "ack-node-problem-detector",
      "config" = "{\"sls_project_name\":\"\"}",
    },
    {
      "name"   = "csi-plugin",
      "config" = "",
    },
    {
      "name"   = "csi-provisioner",
      "config" = "",
    }
  ]
}

# The default resource names.
locals {
  k8s_name_terway         = "k8s_name_terway_${random_integer.default.result}"
  vpc_name                = "vpc_name_${random_integer.default.result}"
  autoscale_nodepool_name = "autoscale-node-pool-${random_integer.default.result}"
}

# Query ECS instance types with 8 vCPUs and 32 GiB memory to use as worker nodes.
data "alicloud_instance_types" "default" {
  cpu_core_count       = 8
  memory_size          = 32
  availability_zone    = var.availability_zone[0]
  kubernetes_node_role = "Worker"
}

resource "random_integer" "default" {
  min = 10000
  max = 99999
}

# The VPC.
resource "alicloud_vpc" "default" {
  vpc_name   = local.vpc_name
  cidr_block = "172.16.0.0/12"
}

# The node vSwitch.
resource "alicloud_vswitch" "vswitches" {
  count      = length(var.node_vswitch_cidrs)
  vpc_id     = alicloud_vpc.default.id
  cidr_block = element(var.node_vswitch_cidrs, count.index)
  zone_id    = element(var.availability_zone, count.index)
}

# The Pod vSwitch (used by Terway for Pod IP allocation).
resource "alicloud_vswitch" "terway_vswitches" {
  count      = length(var.terway_vswitch_cidrs)
  vpc_id     = alicloud_vpc.default.id
  cidr_block = element(var.terway_vswitch_cidrs, count.index)
  zone_id    = element(var.availability_zone, count.index)
}

# The ACK managed cluster.
resource "alicloud_cs_managed_kubernetes" "default" {
  name         = local.k8s_name_terway
  cluster_spec = var.cluster_spec  # ack.pro.small creates an ACK Pro cluster.
  # vSwitches must reside in the zones specified by availability_zone.
  worker_vswitch_ids           = split(",", join(",", alicloud_vswitch.vswitches.*.id))
  pod_vswitch_ids              = split(",", join(",", alicloud_vswitch.terway_vswitches.*.id))
  new_nat_gateway              = true   # Create a NAT gateway for the cluster.
  service_cidr                 = "10.11.0.0/16"  # Must not overlap with the VPC CIDR block. Maximum 256 hosts.
  slb_internet_enabled         = true   # Create an Internet-facing SLB instance for the API server.
  enable_rrsa                  = true
  control_plane_log_components = ["apiserver", "kcm", "scheduler", "ccm"]
  dynamic "addons" {
    for_each = var.cluster_addons
    content {
      name   = lookup(addons.value, "name", var.cluster_addons)
      config = lookup(addons.value, "config", var.cluster_addons)
    }
  }
}

# Create a node pool with auto scaling enabled. Scales between 1 and 10 nodes.
resource "alicloud_cs_kubernetes_node_pool" "autoscale_node_pool" {
  cluster_id     = alicloud_cs_managed_kubernetes.default.id
  node_pool_name = local.autoscale_nodepool_name
  vswitch_ids    = split(",", join(",", alicloud_vswitch.vswitches.*.id))

  scaling_config {
    min_size = 1
    max_size = 10
  }

  instance_types        = var.worker_instance_types
  password              = var.password  # SSH login password for worker nodes.
  install_cloud_monitor = true          # Install the CloudMonitor agent on nodes.
  system_disk_category  = "cloud_efficiency"
  system_disk_size      = 100
  image_type            = "AliyunLinux3"

  data_disks {
    category = "cloud_essd"  # Disk category.
    size     = 120            # Disk size in GiB.
  }
}

Step 1: Initialize Terraform

terraform init

A successful initialization returns:

Terraform has been successfully initialized!

You may now begin working with Terraform. Try running "terraform plan" to see
any changes that are required for your infrastructure. All Terraform commands
should now work.

If you ever set or change modules or backend configuration for Terraform,
rerun this command to reinitialize your working directory. If you forget, other
commands will detect it and remind you to do so if necessary.

Step 2: Apply the configuration

terraform apply

Step 3: Verify the result

After apply completes, go to the Node Pools page in the ACK console. The new node pool shows Auto Scaling Enabled below its name.