本地 IDC 中的 K8s 集群如何以 Serverless 方式使用云上计算资源

kubectl get node
NAME                               STATUS   ROLES    AGE    VERSION
iz8vb1xtnuu0ne6b58hvx0z            Ready    master   4d3h   v1.20.9   //IDC集群节点，示例只有1个master节点，同时也是worker节点，可以运行业务容器
virtual-kubelet-cn-zhangjiakou-a   Ready    agent    99s    v1.20.9。//安装ack-virtual-node组件生产的虚拟节点

> cat <<EOF | kubectl apply -f -
apiVersion: v1
kind: Pod
metadata:
  name: gpu-pod
  labels:
    alibabacloud.com/eci: "true"  # 指定Pod使用Serverless ECI运行
  annotations:
    k8s.aliyun.com/eci-use-specs: ecs.gn5-c4g1.xlarge  # 指定支持的GPU规格，该规格具备1个NVIDIA P100 GPU
spec:
  restartPolicy: Never
  containers:
    - name: cuda-container
      image: acr-multiple-clusters-registry.cn-hangzhou.cr.aliyuncs.com/ack-multiple-clusters/cuda10.2-vectoradd
      resources:
        limits:
          nvidia.com/gpu: 1 # 申请1个GPU
EOF

> kubectl get pod -o wide
NAME       READY   STATUS      RESTARTS   AGE     IP              NODE                               NOMINATED NODE   READINESS GATES
gpu-pod    0/1     Completed   0          5m30s   172.16.217.90   virtual-kubelet-cn-zhangjiakou-a   <none>           <none>
> kubectl logs gpu-pod
Using CUDA Device [0]: Tesla P100-PCIE-16GB
GPU Device has SM 6.0 compute capability
[Vector addition of 50000 elements]
Copy input data from the host memory to the CUDA device
CUDA kernel launch with 196 blocks of 256 threads
Copy output data from the CUDA device to the host memory
Test PASSED
Done

kubectl label namespace <namespace-name> alibabacloud.com/eci=true

> cat << EOF | kubectl apply -f -
apiVersion: scheduling.alibabacloud.com/v1alpha1
kind: ResourcePolicy
metadata:
  name: cost-balance-policy
spec:
  selector:
    app: nginx           // 选择应用Pod
  strategy: prefer
  units:
  - resource: idc        //优先使用idc指定使用IDC中节点资源
  - resource: eci        //当idc节点资源不足时，使用Serverless ECI
EOF

> cat << EOF | kubectl apply -f -
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx
  labels:
    app: nginx
spec:
  replicas: 2
  selector:
    matchLabels:
      app: nginx
  template:
    metadata:
      name: nginx
      annotations:
        addannotion: "true"
      labels:
        app: nginx      # 此处要与上一步创建的ResourcePolicy的selector相关联。
    spec:
      schedulerName: ack-co-scheduler
      containers:
      - name: nginx
        image: acr-multiple-clusters-registry.cn-hangzhou.cr.aliyuncs.com/ack-multiple-clusters/nginx
        resources:
          requests:
            cpu: 2
          limits:
            cpu: 2
EOF

kubectl scale deployment nginx --replicas 4

> kubectl get pod -o widek get pod -o wideNAME                     READY   STATUS    RESTARTS   AGE     IP              NODE                      nginx-79cd98b4b5-97s47   1/1     Running   0          84s     10.100.75.22    iz8vb1xtnuu0ne6b58hvx0z   nginx-79cd98b4b5-gxd8z   1/1     Running   0          84s     10.100.75.23    iz8vb1xtnuu0ne6b58hvx0z   nginx-79cd98b4b5-k55rb   1/1     Running   0          58s     10.100.75.24    virtual-kubelet-cn-zhangjiakou-anginx-79cd98b4b5-m9jxm   1/1     Running   0          58s     10.100.75.25    virtual-kubelet-cn-zhangjiakou-a