使用Kueue调度Jobs #

kubectl apply --server-side -f https://github.com/kubernetes-sigs/kueue/releases/download/v0.6.0/manifests.yaml

[root❄master-node:~]☭ kubectl -n kueue-system get pods
NAME                                        READY   STATUS    RESTARTS   AGE
kueue-controller-manager-85c4bbc999-lk4vv   2/2     Running   0          12m
[root❄master-node:~]☭ 

apiVersion: kueue.x-k8s.io/v1beta1
kind: ResourceFlavor
metadata:
  name: default-flavor # This ResourceFlavor will be used for all the resources

apiVersion: kueue.x-k8s.io/v1beta1
kind: ClusterQueue
metadata:
  name: cluster-queue
spec:
  namespaceSelector: {} # Available to all namespaces
  queueingStrategy: BestEffortFIFO # Default queueing strategy
  resourceGroups:
  - coveredResources: ["cpu", "memory", "nvidia.com/gpu", "ephemeral-storage"]
    flavors:
    - name: "default-flavor"
      resources:
      - name: "cpu"
        nominalQuota: 10
      - name: "memory"
        nominalQuota: 10Gi
      - name: "nvidia.com/gpu"
        nominalQuota: 10
      - name: "ephemeral-storage"
        nominalQuota: 10Gi

---
apiVersion: v1
kind: Namespace
metadata:
  name: "team-a"
---
apiVersion: v1
kind: Namespace
metadata:
  name: "team-b"
---
apiVersion: kueue.x-k8s.io/v1beta1
kind: LocalQueue
metadata:
  namespace: team-a # LocalQueue under team-a namespace
  name: lq-team-a
spec:
  clusterQueue: cluster-queue # Point to the ClusterQueue
---
apiVersion: kueue.x-k8s.io/v1beta1
kind: LocalQueue
metadata:
  namespace: team-b # LocalQueue under team-b namespace
  name: lq-team-b
spec:
  clusterQueue: cluster-queue # Point to the ClusterQueue

apiVersion: batch/v1
kind: Job
metadata:
  namespace: team-a # Job under team-a namespace
  generateName: sample-job-team-a-
  annotations:
    kueue.x-k8s.io/queue-name: lq-team-a # Point to the LocalQueue
spec:
  ttlSecondsAfterFinished: 60 # Job will be deleted after 60 seconds
  parallelism: 3 # This Job will have 3 replicas running at the same time
  completions: 3 # This Job requires 3 completions
  suspend: true # Set to true to allow Kueue to control the Job when it starts
  template:
    spec:
      nodeSelector:
        cloud.google.com/gke-accelerator: "nvidia-tesla-t4" # Specify the GPU hardware
      containers:
      - name: dummy-job
       image: ir0cn/mtool:latest
        args: ["sleep", "10"] # Sleep for 10 seconds
        resources:
          requests:
            cpu: "500m"
            memory: "512Mi"
            ephemeral-storage: "512Mi"
            nvidia.com/gpu: "1"
          limits:
            cpu: "500m"
            memory: "512Mi"
            ephemeral-storage: "512Mi"
            nvidia.com/gpu: "1"
      restartPolicy: Never