terraform-aws-eks/examples/self_managed_node_group/main.tf

provider "aws" {
  region = local.region
}

data "aws_caller_identity" "current" {}
data "aws_availability_zones" "available" {}

locals {
  name            = "ex-${replace(basename(path.cwd), "_", "-")}"
  cluster_version = "1.29"
  region          = "eu-west-1"

  vpc_cidr = "10.0.0.0/16"
  azs      = slice(data.aws_availability_zones.available.names, 0, 3)

  tags = {
    Example    = local.name
    GithubRepo = "terraform-aws-eks"
    GithubOrg  = "terraform-aws-modules"
  }
}

################################################################################
# EKS Module
################################################################################

module "eks" {
  source = "../.."

  cluster_name                   = local.name
  cluster_version                = local.cluster_version
  cluster_endpoint_public_access = true

  enable_cluster_creator_admin_permissions = true

  # Enable EFA support by adding necessary security group rules
  # to the shared node security group
  enable_efa_support = true

  cluster_addons = {
    coredns = {
      most_recent = true
    }
    kube-proxy = {
      most_recent = true
    }
    vpc-cni = {
      most_recent = true
    }
  }

  vpc_id                   = module.vpc.vpc_id
  subnet_ids               = module.vpc.private_subnets
  control_plane_subnet_ids = module.vpc.intra_subnets

  # External encryption key
  create_kms_key = false
  cluster_encryption_config = {
    resources        = ["secrets"]
    provider_key_arn = module.kms.key_arn
  }

  self_managed_node_group_defaults = {
    # enable discovery of autoscaling groups by cluster-autoscaler
    autoscaling_group_tags = {
      "k8s.io/cluster-autoscaler/enabled" : true,
      "k8s.io/cluster-autoscaler/${local.name}" : "owned",
    }
  }

  self_managed_node_groups = {
    # Default node group - as provisioned by the module defaults
    default_node_group = {}

    # AL2023 node group utilizing new user data format which utilizes nodeadm
    # to join nodes to the cluster (instead of /etc/eks/bootstrap.sh)
    al2023_nodeadm = {
      platform = "al2023"

      cloudinit_pre_nodeadm = [
        {
          content_type = "application/node.eks.aws"
          content      = <<-EOT
            ---
            apiVersion: node.eks.aws/v1alpha1
            kind: NodeConfig
            spec:
              kubelet:
                config:
                  shutdownGracePeriod: 30s
                  featureGates:
                    DisableKubeletCloudCredentialProviders: true
          EOT
        }
      ]
    }

    # Bottlerocket node group
    bottlerocket = {
      name = "bottlerocket-self-mng"

      platform      = "bottlerocket"
      ami_id        = data.aws_ami.eks_default_bottlerocket.id
      instance_type = "m5.large"
      desired_size  = 2
      key_name      = module.key_pair.key_pair_name

      bootstrap_extra_args = <<-EOT
        # The admin host container provides SSH access and runs with "superpowers".
        # It is disabled by default, but can be disabled explicitly.
        [settings.host-containers.admin]
        enabled = false

        # The control host container provides out-of-band access via SSM.
        # It is enabled by default, and can be disabled if you do not expect to use SSM.
        # This could leave you with no way to access the API and change settings on an existing node!
        [settings.host-containers.control]
        enabled = true

        # extra args added
        [settings.kernel]
        lockdown = "integrity"

        [settings.kubernetes.node-labels]
        label1 = "foo"
        label2 = "bar"

        [settings.kubernetes.node-taints]
        dedicated = "experimental:PreferNoSchedule"
        special = "true:NoSchedule"
      EOT
    }

    mixed = {
      name = "mixed"

      min_size     = 1
      max_size     = 5
      desired_size = 2

      bootstrap_extra_args = "--kubelet-extra-args '--node-labels=node.kubernetes.io/lifecycle=spot'"

      use_mixed_instances_policy = true
      mixed_instances_policy = {
        instances_distribution = {
          on_demand_base_capacity                  = 0
          on_demand_percentage_above_base_capacity = 20
          spot_allocation_strategy                 = "capacity-optimized"
        }

        override = [
          {
            instance_type     = "m5.large"
            weighted_capacity = "1"
          },
          {
            instance_type     = "m6i.large"
            weighted_capacity = "2"
          },
        ]
      }
    }

    # Complete
    complete = {
      name            = "complete-self-mng"
      use_name_prefix = false

      subnet_ids = module.vpc.public_subnets

      min_size     = 1
      max_size     = 7
      desired_size = 1

      ami_id = data.aws_ami.eks_default.id

      pre_bootstrap_user_data = <<-EOT
        export FOO=bar
      EOT

      post_bootstrap_user_data = <<-EOT
        echo "you are free little kubelet!"
      EOT

      instance_type = "m6i.large"

      launch_template_name            = "self-managed-ex"
      launch_template_use_name_prefix = true
      launch_template_description     = "Self managed node group example launch template"

      ebs_optimized     = true
      enable_monitoring = true

      block_device_mappings = {
        xvda = {
          device_name = "/dev/xvda"
          ebs = {
            volume_size           = 75
            volume_type           = "gp3"
            iops                  = 3000
            throughput            = 150
            encrypted             = true
            kms_key_id            = module.ebs_kms_key.key_arn
            delete_on_termination = true
          }
        }
      }

      instance_attributes = {
        name = "instance-attributes"

        min_size     = 1
        max_size     = 2
        desired_size = 1

        bootstrap_extra_args = "--kubelet-extra-args '--node-labels=node.kubernetes.io/lifecycle=spot'"

        instance_type = null

        # launch template configuration
        instance_requirements = {
          cpu_manufacturers                           = ["intel"]
          instance_generations                        = ["current", "previous"]
          spot_max_price_percentage_over_lowest_price = 100

          vcpu_count = {
            min = 1
          }

          allowed_instance_types = ["t*", "m*"]
        }

        use_mixed_instances_policy = true
        mixed_instances_policy = {
          instances_distribution = {
            on_demand_base_capacity                  = 0
            on_demand_percentage_above_base_capacity = 0
            on_demand_allocation_strategy            = "lowest-price"
            spot_allocation_strategy                 = "price-capacity-optimized"
          }

          # ASG configuration
          override = [
            {
              instance_requirements = {
                cpu_manufacturers                           = ["intel"]
                instance_generations                        = ["current", "previous"]
                spot_max_price_percentage_over_lowest_price = 100

                vcpu_count = {
                  min = 1
                }

                allowed_instance_types = ["t*", "m*"]
              }
            }
          ]
        }
      }

      metadata_options = {
        http_endpoint               = "enabled"
        http_tokens                 = "required"
        http_put_response_hop_limit = 2
        instance_metadata_tags      = "disabled"
      }

      create_iam_role          = true
      iam_role_name            = "self-managed-node-group-complete-example"
      iam_role_use_name_prefix = false
      iam_role_description     = "Self managed node group complete example role"
      iam_role_tags = {
        Purpose = "Protector of the kubelet"
      }
      iam_role_additional_policies = {
        AmazonEC2ContainerRegistryReadOnly = "arn:aws:iam::aws:policy/AmazonEC2ContainerRegistryReadOnly"
        additional                         = aws_iam_policy.additional.arn
      }

      tags = {
        ExtraTag = "Self managed node group complete example"
      }
    }

    efa = {
      # Disabling automatic creation due to instance type/quota availability
      # Can be enabled when appropriate for testing/validation
      create = false

      instance_type = "trn1n.32xlarge"

      enable_efa_support      = true
      pre_bootstrap_user_data = <<-EOT
        # Mount NVME instance store volumes since they are typically
        # available on instances that support EFA
        setup-local-disks raid0
      EOT

      min_size     = 2
      max_size     = 2
      desired_size = 2
    }
  }

  tags = local.tags
}

module "disabled_self_managed_node_group" {
  source = "../../modules/self-managed-node-group"

  create = false

  # Hard requirement
  cluster_service_cidr = ""
}

################################################################################
# Supporting Resources
################################################################################

module "vpc" {
  source  = "terraform-aws-modules/vpc/aws"
  version = "~> 5.0"

  name = local.name
  cidr = local.vpc_cidr

  azs             = local.azs
  private_subnets = [for k, v in local.azs : cidrsubnet(local.vpc_cidr, 4, k)]
  public_subnets  = [for k, v in local.azs : cidrsubnet(local.vpc_cidr, 8, k + 48)]
  intra_subnets   = [for k, v in local.azs : cidrsubnet(local.vpc_cidr, 8, k + 52)]

  enable_nat_gateway = true
  single_nat_gateway = true

  public_subnet_tags = {
    "kubernetes.io/role/elb" = 1
  }

  private_subnet_tags = {
    "kubernetes.io/role/internal-elb" = 1
  }

  tags = local.tags
}

data "aws_ami" "eks_default" {
  most_recent = true
  owners      = ["amazon"]

  filter {
    name   = "name"
    values = ["amazon-eks-node-${local.cluster_version}-v*"]
  }
}

data "aws_ami" "eks_default_bottlerocket" {
  most_recent = true
  owners      = ["amazon"]

  filter {
    name   = "name"
    values = ["bottlerocket-aws-k8s-${local.cluster_version}-x86_64-*"]
  }
}

module "key_pair" {
  source  = "terraform-aws-modules/key-pair/aws"
  version = "~> 2.0"

  key_name_prefix    = local.name
  create_private_key = true

  tags = local.tags
}

module "ebs_kms_key" {
  source  = "terraform-aws-modules/kms/aws"
  version = "~> 2.0"

  description = "Customer managed key to encrypt EKS managed node group volumes"

  # Policy
  key_administrators = [
    data.aws_caller_identity.current.arn
  ]

  key_service_roles_for_autoscaling = [
    # required for the ASG to manage encrypted volumes for nodes
    "arn:aws:iam::${data.aws_caller_identity.current.account_id}:role/aws-service-role/autoscaling.amazonaws.com/AWSServiceRoleForAutoScaling",
    # required for the cluster / persistentvolume-controller to create encrypted PVCs
    module.eks.cluster_iam_role_arn,
  ]

  # Aliases
  aliases = ["eks/${local.name}/ebs"]

  tags = local.tags
}

module "kms" {
  source  = "terraform-aws-modules/kms/aws"
  version = "~> 2.1"

  aliases               = ["eks/${local.name}"]
  description           = "${local.name} cluster encryption key"
  enable_default_policy = true
  key_owners            = [data.aws_caller_identity.current.arn]

  tags = local.tags
}

resource "aws_iam_policy" "additional" {
  name        = "${local.name}-additional"
  description = "Example usage of node additional policy"

  policy = jsonencode({
    Version = "2012-10-17"
    Statement = [
      {
        Action = [
          "ec2:Describe*",
        ]
        Effect   = "Allow"
        Resource = "*"
      },
    ]
  })

  tags = local.tags
}