From 2d77438d62f5cc2607d4528dfb5e434fd334e182 Mon Sep 17 00:00:00 2001
From: Hansini Karunarathne
 <107214435+hansinikarunarathne@users.noreply.github.com>
Date: Tue, 30 Jul 2024 16:16:56 +0530
Subject: [PATCH] change ray version and enable auto scaling (#2821)

* change ray version and enable auto scaling

Signed-off-by: hansinikarunarathne <107214435+hansinikarunarathne@users.noreply.github.com>

* fix a issue

Signed-off-by: hansinikarunarathne <107214435+hansinikarunarathne@users.noreply.github.com>

* Add autoscaler options to ray

Signed-off-by: hansinikarunarathne <107214435+hansinikarunarathne@users.noreply.github.com>

---------

Signed-off-by: hansinikarunarathne <107214435+hansinikarunarathne@users.noreply.github.com>
---
 contrib/ray/raycluster_example.yaml | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/contrib/ray/raycluster_example.yaml b/contrib/ray/raycluster_example.yaml
index c147a75a69..0de4047263 100644
--- a/contrib/ray/raycluster_example.yaml
+++ b/contrib/ray/raycluster_example.yaml
@@ -1,15 +1,27 @@
-apiVersion: ray.io/v1alpha1
+apiVersion: ray.io/v1
 kind: RayCluster
 metadata:
   name: kubeflow-raycluster
 spec:
   rayVersion: '2.23.0'
+  # If `enableInTreeAutoscaling` is true, the Autoscaler sidecar will be added to the Ray head pod.
+  enableInTreeAutoscaling: true
+  # `autoscalerOptions` is an OPTIONAL field specifying configuration overrides for the Ray Autoscaler.
+  # The example configuration shown below below represents the DEFAULT values.
+  # (You may delete autoscalerOptions if the defaults are suitable.)
+  autoscalerOptions:
+    # Default: Upscaling is not rate-limited. This mode adds new worker pods to handle increased workload as quiclky as possible.
+    upscalingMode: Default 
+    # `idleTimeoutSeconds` is the number of seconds to wait before scaling down a worker pod which is not using Ray resources.
+    idleTimeoutSeconds: 60
   # Ray head pod configuration
   headGroupSpec:
     # Kubernetes Service Type.
     serviceType: ClusterIP
     # The following params are used to complete the ray start: ray start --head --block --dashboard-host: '0.0.0.0' ...
     rayStartParams:
+      # Setting "num-cpus: 0" to avoid any Ray actors or tasks being scheduled on the Ray head Pod.
+      num-cpus: "0"
       dashboard-host: '0.0.0.0'
       block: 'true'
     # pod template