ray cluste and test file

docker/runner/README.md

@@ -0,0 +1,31 @@
+
+In a ray or distributed computing cluster, the terms "head node" and "worker nodes" refer to different roles that containers play in the cluster. The head node is the master node in a Ray cluster. You typically have one head node. Worker nodes are the containers that execute the jobs, in parallel. You can have as many worker nodes as you want.
+
+-----------------------------------------------------------
+To install KubeRay:
+curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
+helm repo add kuberay https://ray-project.github.io/kuberay-helm/
+helm repo update
+helm install kuberay-operator kuberay/kuberay-operator --namespace ray-system --create-namespace
+
+https://docs.ray.io/en/latest/cluster/kubernetes/user-guides/config.html
+The above source was used for creating the ray-cluster.yaml
+
+Installing kubernetes and minikubernetes, you can follow this guide to check out how to install and run them: https://medium.com/@areesmoon/installing-minikube-on-ubuntu-20-04-lts-focal-fossa-b10fad9d0511
+
+Use 'pip install ray' and then 'pip show ray' to get your version of ray.
+
+----------------------------------------------------------------------------------
+After you have both kubernetes and ray, use the following command to create a cluster: kubectl apply -f ray-cluster.yaml
+
+'kubectl get pods'-> this is will give you the cluster name
+
+Use to forward the needed port to the ray service: kubectl port-forward svc/<cluster name> 8265:8265
+
+This is the port that will be used inside ray_jobs.py, where we submit the jobs to ray.
+
+
+
+
+
+

docker/runner/ray-cluster.yaml

@@ -0,0 +1,83 @@
+apiVersion: ray.io/v1alpha1
+kind: RayCluster
+metadata:
+  name: roboteam-ray-cluster
+spec:
+  rayVersion: "2.38.0"  
+  # Head node configuration
+  headGroupSpec:
+    rayStartParams:
+      dashboard-host: "0.0.0.0"
+    template:
+      metadata:
+        labels:
+          app: ray-head
+      spec:
+        containers:
+        - name: ray-head
+          image: rayproject/ray:2.38.0  
+          ports:
+          - containerPort: 8265  # dashboard port
+          - containerPort: 6379  # redis port 
+          - containerPort: 10001  # GCS server port
+          - containerPort: 8000   # Serve port
+          resources:
+            requests:
+              cpu: 300m
+              memory: 256Mi
+            limits:
+              cpu: 600
+              memory: 512Mi
+          command: ["/bin/bash", "-c", "--"]
+          args: ["ray start --head --port=6379 --dashboard-host=0.0.0.0 --block"]
+
+          livenessProbe:
+            exec:
+              command:
+              - bash
+              - -c
+              - "wget -T 2 -q -O- http://localhost:52365/api/local_raylet_healthz | grep success"
+            initialDelaySeconds: 90
+            timeoutSeconds: 10
+            periodSeconds: 30
+            failureThreshold: 5
+
+          readinessProbe:
+            exec:
+              command:
+              - bash
+              - -c
+              - "wget -T 10 -q -O- http://localhost:8265/api/gcs_healthz | grep success"
+            initialDelaySeconds: 90
+            timeoutSeconds: 10
+            periodSeconds: 30
+            failureThreshold: 5
+
+
+  # Worker node configuration
+  workerGroupSpecs:
+    - groupName: worker-group
+      replicas: 1  # Number of worker nodes
+      rayStartParams:
+        num-cpus: "1" 
+      template:
+        metadata:
+          labels:
+            app: ray-worker
+        spec:
+          containers:
+          - name: ray-worker
+            image: rayproject/ray:2.38.0  
+            resources:
+              requests:
+                cpu: 500m
+                memory: 1Gi
+              limits:
+                cpu: 1000m
+                memory: 2Gi
+            env:
+            - name: RAY_HEAD_IP
+              value: "roboteam-ray-cluster-head-svc.default.svc.cluster.local"
+            command: ["/bin/bash", "-c", "--"]
+            args: ["ray start --address='roboteam-ray-cluster-head-svc.default.svc.cluster.local:6379' --block"]
+

roboteam_ai/src/RL/example_ray_job.py

@@ -0,0 +1,32 @@
+import ray
+
+#Case 1: the function will be distributed across the ray cluster
+@ray.remote
+def compute_square(x):
+    return x * x
+
+#Case 2: the class will be distributes across th ray cluster
+@ray.remote
+class Counter:
+    def __init__(self):
+        self.count = 0
+
+    def increment(self):
+        self.count += 1
+        return self.count
+
+#Testing case 1:
+future = compute_square.remote(5)
+result = ray.get(future)
+print(f"Result: {result}")
+
+#submiting multiple tasks in parallel
+futures = [compute_square.remote(i) for i in range(10)]
+results = ray.get(futures)
+print(f"Results: {results}")
+
+
+#Testing case 2, using the class:
+counter = Counter.remote()
+future_count = counter.increment.remote()
+print(f"Count: {ray.get(future_count)}")

roboteam_ai/src/RL/ray_jobs.py

@@ -0,0 +1,22 @@
+import ray
+import requests
+
+#connect to the head node, to submit jobs
+#ray.init(address=os.getenv('RAY_ADDRESS'))
+
+#@ray.remote
+#def run_simulation(simulation_name, port):
+#    print(f"Running simulation {simulation_name} on port {port}")
+#    return f"Simulation {simulation_name} completed on port {port}"
+
+#result = ray.get(compute_square.remote(4))
+#print(result)
+
+
+
+job_payload = {
+    "entrypoint": "python3 example_ray_job.py"
+}
+
+response = requests.post("http://localhost:8265/api/jobs/", json=job_payload)
+print(response.json())