EKS Cluster Setup

This guide walks through provisioning a production-grade EKS cluster using DevOpsGenie's Terraform modules.

Module Structure

terraform/
├── environments/
│   ├── staging/
│   │   ├── main.tf
│   │   ├── variables.tf
│   │   └── terraform.tfvars
│   └── production/
│       ├── main.tf
│       ├── variables.tf
│       └── terraform.tfvars
└── modules/
    ├── vpc/
    ├── eks/
    └── iam/

1. VPC Configuration

terraform/environments/production/vpc.tf

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

  name = "devopsgenie-production"
  cidr = "10.100.0.0/16"

  azs             = ["us-east-1a", "us-east-1b", "us-east-1c"]
  private_subnets = ["10.100.0.0/20", "10.100.16.0/20", "10.100.32.0/20"]
  public_subnets  = ["10.100.48.0/24", "10.100.49.0/24", "10.100.50.0/24"]

  enable_nat_gateway   = true
  single_nat_gateway   = false   # one NAT per AZ for HA
  enable_dns_hostnames = true
  enable_dns_support   = true

  private_subnet_tags = {
    "kubernetes.io/role/internal-elb"              = "1"
    "kubernetes.io/cluster/devopsgenie-production" = "shared"
    "karpenter.sh/discovery"                       = "devopsgenie-production"
  }

  public_subnet_tags = {
    "kubernetes.io/role/elb"                       = "1"
    "kubernetes.io/cluster/devopsgenie-production" = "shared"
  }
}

2. EKS Cluster

terraform/environments/production/eks.tf

module "eks" {
  source  = "terraform-aws-modules/eks/aws"
  version = "~> 20.0"

  cluster_name    = "devopsgenie-production"
  cluster_version = "1.29"

  vpc_id     = module.vpc.vpc_id
  subnet_ids = module.vpc.private_subnets

  cluster_endpoint_public_access       = true
  cluster_endpoint_public_access_cidrs = ["10.0.0.0/8"]

  cluster_enabled_log_types = [
    "api", "audit", "authenticator", "controllerManager", "scheduler"
  ]

  cluster_addons = {
    coredns = {
      most_recent = true
      configuration_values = jsonencode({
        replicaCount = 2
        resources = {
          limits   = { cpu = "200m", memory = "200Mi" }
          requests = { cpu = "100m", memory = "100Mi" }
        }
      })
    }
    kube-proxy          = { most_recent = true }
    vpc-cni             = {
      most_recent = true
      configuration_values = jsonencode({
        env = {
          ENABLE_PREFIX_DELEGATION = "true"
          WARM_PREFIX_TARGET       = "1"
        }
      })
    }
    aws-ebs-csi-driver  = {
      most_recent              = true
      service_account_role_arn = module.ebs_csi_irsa.iam_role_arn
    }
  }

  eks_managed_node_groups = {
    # System nodes — run platform add-ons (ArgoCD, Prometheus, etc.)
    system = {
      name           = "system"
      instance_types = ["m6i.xlarge"]
      min_size       = 2
      max_size       = 5
      desired_size   = 3

      taints = [{
        key    = "CriticalAddonsOnly"
        value  = "true"
        effect = "NO_SCHEDULE"
      }]

      labels = { role = "system" }
    }

    # Workload nodes — managed by Karpenter
    bootstrap = {
      name           = "bootstrap"
      instance_types = ["m6i.large"]
      min_size       = 1
      max_size       = 2
      desired_size   = 1
      labels         = { role = "bootstrap" }
    }
  }

  tags = {
    Environment = "production"
    ManagedBy   = "devopsgenie"
    "karpenter.sh/discovery" = "devopsgenie-production"
  }
}

3. Apply

cd terraform/environments/production

terraform init
terraform plan -out=tfplan
terraform apply tfplan

4. Update kubeconfig

aws eks update-kubeconfig \
  --region us-east-1 \
  --name devopsgenie-production

kubectl get nodes

5. Install Platform Stack

devopsgenie platform install \
  --cluster devopsgenie-production \
  --region us-east-1

Expected output:

✓ ArgoCD deployed and syncing
✓ kube-prometheus-stack deployed
✓ Loki + Promtail deployed
✓ OPA Gatekeeper deployed
✓ External Secrets Operator configured
✓ cert-manager deployed
✓ Karpenter deployed (see: devopsgenie cluster karpenter)

Verification

# All nodes ready
kubectl get nodes -o wide

# Platform pods running
kubectl get pods -n argocd
kubectl get pods -n monitoring
kubectl get pods -n karpenter

# Full health check
devopsgenie cluster health --cluster devopsgenie-production