mlbatch-subscription.yaml

apiVersion: v1
kind: Namespace
metadata:
  name: redhat-ods-operator
---
apiVersion: v1
kind: Namespace
metadata:
  name: redhat-ods-applications
---
apiVersion: operators.coreos.com/v1
kind: OperatorGroup
metadata:
  name: rhods-operator
  namespace: redhat-ods-operator
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: mlbatch-codeflare
  namespace: redhat-ods-operator
data:
  manager.yaml: |
    apiVersion: apps/v1
    kind: Deployment
    metadata:
      name: manager
      namespace: system
    spec:
      selector:
        matchLabels:
          app.kubernetes.io/name: codeflare-operator
          app.kubernetes.io/part-of: codeflare
      replicas: 1
      template:
        metadata:
          annotations:
            kubectl.kubernetes.io/default-container: manager
          labels:
            app.kubernetes.io/name: codeflare-operator
            app.kubernetes.io/part-of: codeflare
        spec:
          priorityClassName: system-node-critical
          securityContext:
            runAsNonRoot: true
            # TODO(user): For common cases that do not require escalating privileges
            # it is recommended to ensure that all your Pods/Containers are restrictive.
            # More info: https://kubernetes.io/docs/concepts/security/pod-security-standards/#restricted
            # Please uncomment the following code if your project does NOT have to work on old Kubernetes
            # versions < 1.20 or on vendors versions which do NOT support this field by default (i.e. Openshift < 4.11 ).
            # seccompProfile:
            #   type: RuntimeDefault
          containers:
          - command:
            - /manager
            image: $(codeflare_operator_controller_image)
            imagePullPolicy: Always
            name: manager
            securityContext:
              allowPrivilegeEscalation: false
              capabilities:
                drop:
                  - "ALL"
            env:
              - name: NAMESPACE
                valueFrom:
                  fieldRef:
                    fieldPath: metadata.namespace
            ports:
              - containerPort: 8080
                protocol: TCP
                name: metrics
            livenessProbe:
              httpGet:
                path: /healthz
                port: 8081
              initialDelaySeconds: 15
              periodSeconds: 20
            readinessProbe:
              httpGet:
                path: /readyz
                port: 8081
              initialDelaySeconds: 5
              periodSeconds: 10
            resources:
              limits:
                cpu: "1"
                memory: 1Gi
              requests:
                cpu: "1"
                memory: 1Gi
          serviceAccountName: controller-manager
          terminationGracePeriodSeconds: 10
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: codeflare-operator-config
  namespace: redhat-ods-applications
data:
  config.yaml: |
    appwrapper:
      Config:
        manageJobsWithoutQueueName: true
        userRBACAdmissionCheck: false
        schedulerName: scheduler-plugins-scheduler
        queueName: default-queue
      enabled: true
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: mlbatch-kuberay
  namespace: redhat-ods-operator
data:
  kuberay-operator-image-patch.yaml: |
    apiVersion: apps/v1
    kind: Deployment
    metadata:
      name: kuberay-operator
    spec:
      template:
        spec:
          priorityClassName: system-node-critical
          containers:
          - name: kuberay-operator
            image: $(image)
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: mlbatch-kueue
  namespace: redhat-ods-operator
data:
  controller_manager_config.yaml: |
    apiVersion: config.kueue.x-k8s.io/v1beta1
    kind: Configuration
    health:
      healthProbeBindAddress: :8081
    metrics:
      bindAddress: :8080
    # enableClusterQueueResources: true
    webhook:
      port: 9443
    leaderElection:
      leaderElect: true
      resourceName: c1f6bfd2.kueue.x-k8s.io
    controller:
      groupKindConcurrency:
        Job.batch: 5
        Pod: 5
        Workload.kueue.x-k8s.io: 5
        LocalQueue.kueue.x-k8s.io: 1
        ClusterQueue.kueue.x-k8s.io: 1
        ResourceFlavor.kueue.x-k8s.io: 1
    clientConnection:
      qps: 50
      burst: 100
    #pprofBindAddress: :8082
    waitForPodsReady:
      enable: false
      blockAdmission: false
    manageJobsWithoutQueueName: true
    #internalCertManagement:
    #  enable: false
    #  webhookServiceName: ""
    #  webhookSecretName: ""
    integrations:
      frameworks:
    # - "batch/job"
      - "kubeflow.org/mpijob"
      - "ray.io/rayjob"
      - "ray.io/raycluster"
      - "jobset.x-k8s.io/jobset"
      - "kubeflow.org/mxjob"
      - "kubeflow.org/paddlejob"
      - "kubeflow.org/pytorchjob"
      - "kubeflow.org/tfjob"
      - "kubeflow.org/xgboostjob"
    # - "pod"
      externalFrameworks:
      - "AppWrapper.v1beta2.workload.codeflare.dev"
    # podOptions:
    #   namespaceSelector:
    #     matchExpressions:
    #       - key: kubernetes.io/metadata.name
    #         operator: NotIn
    #         values: [ kube-system, kueue-system ]
  manager_config_patch.yaml: |
    apiVersion: apps/v1
    kind: Deployment
    metadata:
      name: controller-manager
      namespace: system
    spec:
      template:
        spec:
          priorityClassName: system-node-critical
          containers:
          - name: manager
            image: $(image)
            args:
            - "--config=/controller_manager_config.yaml"
            - "--zap-log-level=2"
            volumeMounts:
            - name: manager-config
              mountPath: /controller_manager_config.yaml
              subPath: controller_manager_config.yaml
          volumes:
          - name: manager-config
            configMap:
              name: manager-config
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: mlbatch-training-operator
  namespace: redhat-ods-operator
data:
  manager_config_patch.yaml: |
    apiVersion: apps/v1
    kind: Deployment
    metadata:
      name: training-operator
    spec:
      template:
        spec:
          priorityClassName: system-node-critical
          containers:
          - name:  training-operator
            image: $(image)
            args:
            - "--zap-log-level=2"
            - "--gang-scheduler-name=scheduler-plugins-scheduler"
            resources:
              requests:
                cpu: 100m
                memory: 100Mi
              limits:
                cpu: 500m
                memory: 1000Mi
---
apiVersion: operators.coreos.com/v1alpha1
kind: Subscription
metadata:
  name: rhods-operator
  namespace: redhat-ods-operator
spec:
  channel: fast
  installPlanApproval: Manual
  name: rhods-operator
  source: redhat-operators
  sourceNamespace: openshift-marketplace
  startingCSV: rhods-operator.2.11.0
  config:
    env:
    - name: "DISABLE_DSC_CONFIG"
    volumeMounts:
    - name: mlbatch-codeflare
      mountPath: /opt/manifests/codeflare/manager/manager.yaml
      subPath: manager.yaml
    - name: mlbatch-kuberay
      mountPath: /opt/manifests/ray/openshift/kuberay-operator-image-patch.yaml
      subPath: kuberay-operator-image-patch.yaml
    - name: mlbatch-kueue
      mountPath: /opt/manifests/kueue/components/manager/controller_manager_config.yaml
      subPath: controller_manager_config.yaml
    - name: mlbatch-kueue
      mountPath: /opt/manifests/kueue/rhoai/manager_config_patch.yaml
      subPath: manager_config_patch.yaml
    - name: mlbatch-training-operator
      mountPath: /opt/manifests/trainingoperator/rhoai/manager_config_patch.yaml
      subPath: manager_config_patch.yaml
    volumes:
    - name: mlbatch-codeflare
      configMap:
        name: mlbatch-codeflare
    - name: mlbatch-kuberay
      configMap:
        name: mlbatch-kuberay
    - name: mlbatch-kueue
      configMap:
        name: mlbatch-kueue
    - name: mlbatch-training-operator
      configMap:
        name: mlbatch-training-operator