---
apiVersion: 
apiVersion: v1
kind: ServiceAccount
metadata:
  name: gpu-admission
  namespace: kube-system

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: gpu-admission-as-kube-scheduler
subjects:
- kind: ServiceAccount
  name: gpu-admission
  namespace: kube-system
roleRef:
  kind: ClusterRole
  name: system:kube-scheduler
  apiGroup: rbac.authorization.k8s.io
  
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: gpu-admission-as-volume-scheduler
subjects:
- kind: ServiceAccount
  name: gpu-admission
  namespace: kube-system
roleRef:
  kind: ClusterRole
  name: system:volume-scheduler
  apiGroup: rbac.authorization.k8s.io
  
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: gpu-admission-as-daemon-set-controller
subjects:
- kind: ServiceAccount
  name: gpu-admission
  namespace: kube-system
roleRef:
  kind: ClusterRole
  name: system:controller:daemon-set-controller
  apiGroup: rbac.authorization.k8s.io

---
# 创建控制器
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    k8s-app: gpu-quota-admission
  name: gpu-quota-admission
  namespace: kube-system
spec:
  replicas: 1
  selector:
    matchLabels:
      k8s-app: gpu-quota-admission
  template:
    metadata:
      labels:
        k8s-app: gpu-quota-admission
      namespace: kube-system
    spec:
      affinity:
        nodeAffinity:
          preferredDuringSchedulingIgnoredDuringExecution:
          - preference:
              matchExpressions:
              - key: node-role.kubernetes.io/master
                operator: Exists
            weight: 1
      containers:
      - env:
        - name: LOG_LEVEL
          value: "4"
        - name: EXTRA_FLAGS
          value: --incluster-mode=true
        image: ccr.ccs.tencentyun.com/tkeimages/gpu-quota-admission:latest
        imagePullPolicy: IfNotPresent
        name: gpu-quota-admission
        ports:
        - containerPort: 3456
          protocol: TCP
        resources:
          limits:
            cpu: "2"
            memory: 2Gi
          requests:
            cpu: "1"
            memory: 1Gi
        volumeMounts:
        - mountPath: /root/gpu-quota-admission/
          name: config
      dnsPolicy: ClusterFirstWithHostNet
      initContainers:
      - command:
        - sh
        - -c
        - ' mkdir -p /etc/kubernetes/ && cp /root/gpu-quota-admission/gpu-quota-admission.config
          /etc/kubernetes/'
        image: busybox
        imagePullPolicy: Always
        name: init-kube-config
        securityContext:
          privileged: true
        volumeMounts:
        - mountPath: /root/gpu-quota-admission/
          name: config
      priority: 2000000000
      priorityClassName: system-cluster-critical
      restartPolicy: Always
      serviceAccount: gpu-admission
      terminationGracePeriodSeconds: 30
      tolerations:
      - effect: NoSchedule
        key: node-role.kubernetes.io/master
      volumes:
      - configMap:
          defaultMode: 420
          name: gpu-quota-admission
        name: config

---
# 创建configMap
apiVersion: v1
kind: ConfigMap
metadata:
  name: gpu-quota-admission
  namespace: kube-system
data:
  gpu-quota-admission.config: |
    {
         "QuotaConfigMapName": "gpuquota",
         "QuotaConfigMapNamespace": "kube-system",
         "GPUModelLabel": "gaia.tencent.com/gpu-model",
         "GPUPoolLabel": "gaia.tencent.com/gpu-pool"
     }

---
# 创建service
apiVersion: v1
kind: Service
metadata:
  name: gpu-quota-admission
  namespace: kube-system
spec:
  ports:
  - port: 3456
    protocol: TCP
    targetPort: 3456
  selector:
    k8s-app: gpu-quota-admission
  type: ClusterIP

kubectl apply -f gpu-quota-admission.yaml