buildbot/google/terraform/deployment-mlir-nvidia-production.yaml

---
# deployment for production at http://lab.llvm.org:8011/
# The deployment for staging is in a separate file!
apiVersion: apps/v1
kind: Deployment
metadata:
  name: mlir-nvidia-production
spec:
  # number of instances we want to run
  replicas: 1
  selector:
    matchLabels:
      app: mlir-nvidia-production
  # define strategy for updating the images
  strategy:
    rollingUpdate:
      # do not deploy more replicas, as the buildbot server 
      # can't handle multiple workers with the same credentials
      maxSurge: 0
      # Allow to have 0 replicas during updates. 
      maxUnavailable: 1
    type: RollingUpdate
  template:
    metadata:
      labels:
        app: mlir-nvidia-production
    spec:
      containers:
      # the image and version we want to run   
      - image: gcr.io/sanitizer-bots/buildbot-mlir-nvidia:14
        name: mlir-nvidia-production
        env:
          # connect to production environment, running at port 9990 
          - name: BUILDBOT_PORT
            value: "9990"
        # reserve "<number of cores>-1" for this image, kubernetes also
        # needs <1 core for management tools
        resources:
          limits:
            cpu: "15"
            memory: 10Gi
            # also request to use the GPU
            # Note: this does not work in terraform at the moment
            nvidia.com/gpu: "1"
          requests:
            cpu: "15"
            memory: 10Gi
            nvidia.com/gpu: "1"
        volumeMounts:
        # mount the secrets into a folder  
        - mountPath: /secrets
          mountPropagation: None
          name: buildbot-token
      # specify the nood pool on which to deploy
      nodeSelector:
        pool: nvidia-16core-pool
      restartPolicy: Always
      volumes:
      # declare the secret as a volume so we can mount it
      - name: buildbot-token
        secret:
          optional: false
          secretName: password-mlir-nvidia