9.2. 分布式工作负载的 Kueue 资源配置示例

apiVersion: kueue.x-k8s.io/v1beta1
kind: ResourceFlavor
metadata:
  name: "a400node"
spec:
  nodeLabels:
    instance-type: nvidia-a400-node
  tolerations:
  - key: "HasGPU"
    operator: "Exists"
    effect: "NoSchedule"

apiVersion: kueue.x-k8s.io/v1beta1
kind: ResourceFlavor
metadata:
  name: "a1000node"
spec:
  nodeLabels:
    instance-type: nvidia-a1000-node
  tolerations:
  - key: "HasGPU"
    operator: "Exists"
    effect: "NoSchedule"

apiVersion: kueue.x-k8s.io/v1beta1
kind: ClusterQueue
metadata:
  name: "a400queue"
spec:
  namespaceSelector: {} # match all.
  resourceGroups:
  - coveredResources: ["cpu", "memory", "nvidia.com/gpu"]
    flavors:
    - name: "a400node"
      resources:
      - name: "cpu"
        nominalQuota: 16
      - name: "memory"
        nominalQuota: 64Gi
      - name: "nvidia.com/gpu"
        nominalQuota: 2

apiVersion: kueue.x-k8s.io/v1beta1
kind: ClusterQueue
metadata:
  name: "a1000queue"
spec:
  namespaceSelector: {} # match all.
  resourceGroups:
  - coveredResources: ["cpu", "memory", "nvidia.com/gpu"]
    flavors:
    - name: "a1000node"
      resources:
      - name: "cpu"
        nominalQuota: 16
      - name: "memory"
        nominalQuota: 64Gi
      - name: "nvidia.com/gpu"
        nominalQuota: 2

apiVersion: kueue.x-k8s.io/v1beta1
kind: ResourceFlavor
metadata:
  name: "amd-node"
spec:
  nodeLabels:
    instance-type: amd-node
  tolerations:
  - key: "HasGPU"
    operator: "Exists"
    effect: "NoSchedule"

apiVersion: kueue.x-k8s.io/v1beta1
kind: ResourceFlavor
metadata:
  name: "nvidia-node"
spec:
  nodeLabels:
    instance-type: nvidia-node
  tolerations:
  - key: "HasGPU"
    operator: "Exists"
    effect: "NoSchedule"

apiVersion: kueue.x-k8s.io/v1beta1
kind: ClusterQueue
metadata:
  name: "team-a-amd-queue"
spec:
  namespaceSelector: {} # match all.
  resourceGroups:
  - coveredResources: ["cpu", "memory", "amd.com/gpu"]
    flavors:
    - name: "amd-node"
      resources:
      - name: "cpu"
        nominalQuota: 16
      - name: "memory"
        nominalQuota: 64Gi
      - name: "amd.com/gpu"
        nominalQuota: 2

apiVersion: kueue.x-k8s.io/v1beta1
kind: ClusterQueue
metadata:
  name: "team-a-nvidia-queue"
spec:
  namespaceSelector: {} # match all.
  resourceGroups:
  - coveredResources: ["cpu", "memory", "nvidia.com/gpu"]
    flavors:
    - name: "nvidia-node"
      resources:
      - name: "cpu"
        nominalQuota: 16
      - name: "memory"
        nominalQuota: 64Gi
      - name: "nvidia.com/gpu"
        nominalQuota: 2