GKE

# GKE Standard 클러스터 생성
gcloud container clusters create my-cluster \
  --zone=asia-northeast3-a \
  --num-nodes=3 \
  --machine-type=e2-standard-4 \
  --enable-autoscaling \
  --min-nodes=1 \
  --max-nodes=10 \
  --enable-autorepair \
  --enable-autoupgrade \
  --release-channel=regular \
  --workload-pool=my-project.svc.id.goog

# GKE Autopilot 클러스터 생성
gcloud container clusters create-auto my-autopilot-cluster \
  --region=asia-northeast3 \
  --release-channel=regular

# 클러스터 인증 정보 가져오기
gcloud container clusters get-credentials my-cluster \
  --zone=asia-northeast3-a

# 노드 풀 추가 (GPU 지원)
gcloud container node-pools create gpu-pool \
  --cluster=my-cluster \
  --zone=asia-northeast3-a \
  --machine-type=n1-standard-4 \
  --accelerator=type=nvidia-tesla-t4,count=1 \
  --num-nodes=1

# GKE 클러스터 Terraform 구성
resource "google_container_cluster" "primary" {
  name     = "my-gke-cluster"
  location = "asia-northeast3-a"

  # Autopilot 모드로 생성
  enable_autopilot = false

  # VPC Native 클러스터 설정
  networking_mode = "VPC_NATIVE"
  ip_allocation_policy {}

  # 릴리스 채널 설정
  release_channel {
    channel = "REGULAR"
  }

  # Workload Identity 활성화
  workload_identity_config {
    workload_pool = "${var.project_id}.svc.id.goog"
  }

  # 초기 노드 풀 제거 (별도 노드 풀 사용)
  remove_default_node_pool = true
  initial_node_count       = 1
}

# 노드 풀 설정
resource "google_container_node_pool" "primary_nodes" {
  name       = "primary-pool"
  cluster    = google_container_cluster.primary.id
  node_count = 3

  autoscaling {
    min_node_count = 1
    max_node_count = 10
  }

  management {
    auto_repair  = true
    auto_upgrade = true
  }

  node_config {
    machine_type = "e2-standard-4"
    disk_size_gb = 100

    oauth_scopes = [
      "https://www.googleapis.com/auth/cloud-platform"
    ]

    labels = {
      env = "production"
    }
  }
}

# GKE에 애플리케이션 배포 예제
apiVersion: apps/v1
kind: Deployment
metadata:
  name: web-app
  namespace: production
spec:
  replicas: 3
  selector:
    matchLabels:
      app: web-app
  template:
    metadata:
      labels:
        app: web-app
    spec:
      serviceAccountName: web-app-sa
      containers:
      - name: web-app
        image: gcr.io/my-project/web-app:v1
        ports:
        - containerPort: 8080
        resources:
          requests:
            cpu: "250m"
            memory: "256Mi"
          limits:
            cpu: "500m"
            memory: "512Mi"
        readinessProbe:
          httpGet:
            path: /health
            port: 8080
          initialDelaySeconds: 5
          periodSeconds: 10
---
# GKE Ingress (Google Cloud Load Balancer)
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: web-app-ingress
  annotations:
    kubernetes.io/ingress.class: "gce"
    kubernetes.io/ingress.global-static-ip-name: "web-app-ip"
spec:
  rules:
  - host: app.example.com
    http:
      paths:
      - path: /*
        pathType: ImplementationSpecific
        backend:
          service:
            name: web-app-service
            port:
              number: 80