[Feature] RayJob Volcano integration

Signed-off-by: win5923 <[email protected]>

Author: win5923

ray-operator/config/samples/ray-job.volcano-scheduler-queue.yaml

@@ -0,0 +1,143 @@
+apiVersion: scheduling.volcano.sh/v1beta1
+kind: Queue
+metadata:
+  name: kuberay-test-queue
+spec:
+  weight: 1
+  capability:
+    cpu: 4
+    memory: 6Gi
+---
+apiVersion: ray.io/v1
+kind: RayJob
+metadata:
+  name: rayjob-sample-2
+  labels:
+    ray.io/scheduler-name: volcano
+    volcano.sh/queue-name: kuberay-test-queue
+spec:
+  entrypoint: python /home/ray/samples/sample_code.py
+  runtimeEnvYAML: |
+    pip:
+      - requests==2.26.0
+      - pendulum==2.1.2
+    env_vars:
+      counter_name: "test_counter"
+  # rayClusterSpec specifies the RayCluster instance to be created by the RayJob controller.
+  rayClusterSpec:
+    rayVersion: '2.46.0' # should match the Ray version in the image of the containers
+    # Ray head pod template
+    headGroupSpec:
+      # The `rayStartParams` are used to configure the `ray start` command.
+      # See https://github.com/ray-project/kuberay/blob/master/docs/guidance/rayStartParams.md for the default settings of `rayStartParams` in KubeRay.
+      # See https://docs.ray.io/en/latest/cluster/cli.html#ray-start for all available options in `rayStartParams`.
+      rayStartParams: {}
+      #pod template
+      template:
+        spec:
+          containers:
+          - name: ray-head
+            image: rayproject/ray:2.46.0
+            ports:
+            - containerPort: 6379
+              name: gcs-server
+            - containerPort: 8265 # Ray dashboard
+              name: dashboard
+            - containerPort: 10001
+              name: client
+            resources:
+              limits:
+                cpu: "1"
+                memory: "2Gi"
+              requests:
+                cpu: "1"
+                memory: "2Gi"
+            volumeMounts:
+            - mountPath: /home/ray/samples
+              name: code-sample
+          volumes:
+          # You set volumes at the Pod level, then mount them into containers inside that Pod
+          - name: code-sample
+            configMap:
+              # Provide the name of the ConfigMap you want to mount.
+              name: ray-job-code-sample
+              # An array of keys from the ConfigMap to create as files
+              items:
+              - key: sample_code.py
+                path: sample_code.py
+    workerGroupSpecs:
+    # the pod replicas in this group typed worker
+    - replicas: 2
+      minReplicas: 2
+      maxReplicas: 2
+      # logical group name, for this called small-group, also can be functional
+      groupName: small-group
+      # The `rayStartParams` are used to configure the `ray start` command.
+      # See https://github.com/ray-project/kuberay/blob/master/docs/guidance/rayStartParams.md for the default settings of `rayStartParams` in KubeRay.
+      # See https://docs.ray.io/en/latest/cluster/cli.html#ray-start for all available options in `rayStartParams`.
+      rayStartParams: {}
+      #pod template
+      template:
+        spec:
+          containers:
+          - name: ray-worker # must consist of lower case alphanumeric characters or '-', and must start and end with an alphanumeric character (e.g. 'my-name',  or '123-abc'
+            image: rayproject/ray:2.46.0
+            resources:
+              limits:
+                cpu: "1"
+                memory: "1Gi"
+              requests:
+                cpu: "1"
+                memory: "1Gi"
+
+  # SubmitterPodTemplate is the template for the pod that will run the `ray job submit` command against the RayCluster.
+  # If SubmitterPodTemplate is specified, the first container is assumed to be the submitter container.
+  # submitterPodTemplate:
+  #   spec:
+  #     restartPolicy: Never
+  #     containers:
+  #     - name: my-custom-rayjob-submitter-pod
+  #       image: rayproject/ray:2.46.0
+  #       # If Command is not specified, the correct command will be supplied at runtime using the RayJob spec `entrypoint` field.
+  #       # Specifying Command is not recommended.
+  #       # command: ["sh", "-c", "ray job submit --address=http://$RAY_DASHBOARD_ADDRESS --submission-id=$RAY_JOB_SUBMISSION_ID -- echo hello world"]
+
+
+######################Ray code sample#################################
+# this sample is from https://docs.ray.io/en/latest/cluster/job-submission.html#quick-start-example
+# it is mounted into the container and executed to show the Ray job at work
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: ray-job-code-sample
+data:
+  sample_code.py: |
+    import ray
+    import os
+    import requests
+
+    ray.init()
+
+    @ray.remote
+    class Counter:
+        def __init__(self):
+            # Used to verify runtimeEnv
+            self.name = os.getenv("counter_name")
+            assert self.name == "test_counter"
+            self.counter = 0
+
+        def inc(self):
+            self.counter += 1
+
+        def get_counter(self):
+            return "{} got {}".format(self.name, self.counter)
+
+    counter = Counter.remote()
+
+    for _ in range(5):
+        ray.get(counter.inc.remote())
+        print(ray.get(counter.get_counter.remote()))
+
+    # Verify that the correct runtime env was used for the job.
+    assert requests.__version__ == "2.26.0"

ray-operator/controllers/ray/batchscheduler/kai-scheduler/kai_scheduler.go

@@ -33,7 +33,7 @@ func GetPluginName() string { return "kai-scheduler" }
 
 func (k *KaiScheduler) Name() string { return GetPluginName() }
 
-func (k *KaiScheduler) DoBatchSchedulingOnSubmission(_ context.Context, _ *rayv1.RayCluster) error {
+func (k *KaiScheduler) DoBatchSchedulingOnSubmission(_ context.Context, _ client.Object) error {
 	return nil
 }
 
@@ -53,6 +53,9 @@ func (k *KaiScheduler) AddMetadataToPod(ctx context.Context, app *rayv1.RayClust
 	pod.Labels[QueueLabelName] = queue
 }
 
+func (k *KaiScheduler) AddMetadataToChildResource(_ context.Context, _ client.Object, _ string, _ client.Object) {
+}
+
 func (kf *KaiSchedulerFactory) New(_ context.Context, _ *rest.Config, _ client.Client) (schedulerinterface.BatchScheduler, error) {
 	return &KaiScheduler{}, nil
 }

ray-operator/controllers/ray/batchscheduler/schedulermanager.go

@@ -83,7 +83,7 @@ func getSchedulerFactory(rayConfigs configapi.Configuration) (schedulerinterface
 	return factory, nil
 }
 
-func (batch *SchedulerManager) GetSchedulerForCluster() (schedulerinterface.BatchScheduler, error) {
+func (batch *SchedulerManager) GetScheduler() (schedulerinterface.BatchScheduler, error) {
 	return batch.scheduler, nil
 }