阿里云容器计算服务ACS深度对接与实践指南

{
  "cluster_type": "ManagedKubernetes",
  "profile": "Serverless",
  "name": "my-acs-cluster",
  "region_id": "cn-hangzhou",
  "zone_ids": ["cn-hangzhou-g", "cn-hangzhou-h"],
  "vpc_id": "vpc-xxxxxx",
  "vswitch_ids": ["vsw-xxxxxx1", "vsw-xxxxxx2"],
  "service_cidr": "172.19.0.0/20",
  "snat_entry": true,
  "security_group_id": "sg-xxxxxx"
}

# 通用型实例配置
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx-general-purpose
spec:
  replicas: 2
  selector:
    matchLabels:
      app: nginx
  template:
    metadata:
      labels:
        app: nginx
        alibabacloud.com/compute-class: general-purpose
    spec:
      containers:
      - name: nginx
        image: nginx:latest
        resources:
          requests:
            cpu: "1"
            memory: "2Gi"
          limits:
            cpu: "2"
            memory: "4Gi"

# GPU型实例配置
apiVersion: apps/v1
kind: Deployment
metadata:
  name: gpu-inference
spec:
  replicas: 1
  selector:
    matchLabels:
      app: gpu-app
  template:
    metadata:
      labels:
        app: gpu-app
        alibabacloud.com/compute-class: "gpu"
    spec:
      containers:
      - name: pytorch-inference
        image: pytorch/pytorch:latest
        resources:
          requests:
            cpu: "4"
            memory: "16Gi"
            nvidia.com/gpu: "1"
          limits:
            cpu: "4"
            memory: "16Gi"
            nvidia.com/gpu: "1"

# 高性能网络GPU型（GPU-HPN）配置
apiVersion: apps/v1
kind: Deployment
metadata:
  name: distributed-training
spec:
  replicas: 2
  selector:
    matchLabels:
      app: train-app
  template:
    metadata:
      labels:
        app: train-app
        alibabacloud.com/compute-class: "gpu-hpn"
    spec:
      containers:
      - name: trainer
        image: nvcr.io/nvidia/pytorch:latest
        resources:
          requests:
            cpu: "8"
            memory: "32Gi"
            nvidia.com/gpu: "1"
          limits:
            cpu: "8"
            memory: "32Gi"
            nvidia.com/gpu: "1"

# 步骤一：创建StorageClass
apiVersion: storage.k8s.io/v1
kind: StorageClass
metadata:
  name: nas-performance
mountOptions:
- nolock,tcp,noresvport
- vers=3
parameters:
  volumeAs: filesystem
  fileSystemType: standard
  storageType: Performance
  vpcId: "vpc-xxxxxx"
  vSwitchId: "vsw-xxxxxx"
  accessGroupName: DEFAULT_VPC_GROUP_NAME
  deleteVolume: "false"
provisioner: nasplugin.csi.alibabacloud.com
# 步骤二：创建PVC
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: nas-data-pvc
spec:
  accessModes:
  - ReadWriteMany
  storageClassName: nas-performance
  resources:
    requests:
      storage: 100Gi
# 步骤三：在Pod中挂载PVC
apiVersion: v1
kind: Pod
metadata:
  name: app-with-nas
spec:
  containers:
  - name: app
    image: nginx:latest
    volumeMounts:
    - name: data-volume
      mountPath: /data
  volumes:
  - name: data-volume
    persistentVolumeClaim:
      claimName: nas-data-pvc

name: Build and Deploy to ACS
on:
  push:
    branches: [ main ]
env:
  REGION: cn-hangzhou
  IMAGE_NAME: my-app
  CLUSTER_NAME: my-acs-cluster
  DEPLOYMENT_NAME: my-app-deployment
jobs:
  build-and-deploy:
    runs-on: ubuntu-latest
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
    - name: Configure Alibaba Cloud credentials
      uses: aliyun/aliyun-cli-action@v1
      with:
        access-key-id: ${{ secrets.ALIYUN_ACCESS_KEY_ID }}
        access-key-secret: ${{ secrets.ALIYUN_ACCESS_KEY_SECRET }}
    - name: Login to ACR
      uses: aliyun/acr-login@v1
      with:
        region-id: ${{ env.REGION }}
        username: ${{ secrets.ACR_USERNAME }}
        password: ${{ secrets.ACR_PASSWORD }}
    - name: Build and push Docker image
      run: |
        IMAGE_TAG=$(date +%s)
        docker build -t ${{ env.REGION }}.cr.aliyuncs.com/my-namespace/${{ env.IMAGE_NAME }}:$IMAGE_TAG .
        docker push ${{ env.REGION }}.cr.aliyuncs.com/my-namespace/${{ env.IMAGE_NAME }}:$IMAGE_TAG
        echo "image_tag=$IMAGE_TAG" >> $GITHUB_OUTPUT
    - name: Update ACS deployment
      uses: appleboy/kubectl-action@v0.0.1
      with:
        kube_config: ${{ secrets.KUBE_CONFIG }}
        args: set image deployment/${{ env.DEPLOYMENT_NAME }} ${{ env.DEPLOYMENT_NAME }}=${{ env.REGION }}.cr.aliyuncs.com/my-namespace/${{ env.IMAGE_NAME }}:${{ env.IMAGE_TAG }} -n default
    - name: Rollout status check
      uses: appleboy/kubectl-action@v0.0.1
      with:
        kube_config: ${{ secrets.KUBE_CONFIG }}
        args: rollout status deployment/${{ env.DEPLOYMENT_NAME }} -n default