feat: make elasticConfig.maxReplicas to a required parameter (#331)

Author: nayihz

api/inference/v1alpha1/playground_types.go

@@ -44,6 +44,7 @@ type PlaygroundSpec struct {
 	BackendRuntimeConfig *BackendRuntimeConfig `json:"backendRuntimeConfig,omitempty"`
 	// ElasticConfig defines the configuration for elastic usage,
 	// e.g. the max/min replicas.
+	// +optional
 	ElasticConfig *ElasticConfig `json:"elasticConfig,omitempty"`
 }
 
@@ -56,8 +57,9 @@ type ElasticConfig struct {
 	MinReplicas *int32 `json:"minReplicas,omitempty"`
 	// MaxReplicas indicates the maximum number of inference workloads based on the traffic.
 	// Default to nil means there's no limit for the instance number.
-	// +optional
-	MaxReplicas *int32 `json:"maxReplicas,omitempty"`
+	// +kubebuilder:validation:Required
+	// +kubebuilder:validation:Minimum:=1
+	MaxReplicas int32 `json:"maxReplicas,omitempty"`
 	// ScaleTrigger defines the rules to scale the workloads.
 	// Only one trigger cloud work at a time, mostly used in Playground.
 	// ScaleTrigger defined here will "overwrite" the scaleTrigger in the recommendedConfig.

api/inference/v1alpha1/zz_generated.deepcopy.go

@@ -242,6 +242,7 @@ spec:
                       MaxReplicas indicates the maximum number of inference workloads based on the traffic.
                       Default to nil means there's no limit for the instance number.
                     format: int32
+                    minimum: 1
                     type: integer
                   minReplicas:
                     default: 1
@@ -864,6 +865,8 @@ spec:
                             type: array
                         type: object
                     type: object
+                required:
+                - maxReplicas
                 type: object
               modelClaim:
                 description: |-

config/crd/bases/inference.llmaz.io_playgrounds.yaml

@@ -557,12 +557,7 @@ func newHPA(playground *inferenceapi.Playground) *autoscalingv2.HorizontalPodAut
 	}
 
 	hpa.Spec.MinReplicas = playground.Spec.ElasticConfig.MinReplicas
-	if playground.Spec.ElasticConfig.MaxReplicas == nil {
-		// The value is hardcoded, because maxReplicas is required by HPA.
-		hpa.Spec.MaxReplicas = 99999
-	} else {
-		hpa.Spec.MaxReplicas = *playground.Spec.ElasticConfig.MaxReplicas
-	}
+	hpa.Spec.MaxReplicas = playground.Spec.ElasticConfig.MaxReplicas
 
 	return hpa
 }

pkg/controller/inference/playground_controller.go

@@ -145,8 +145,8 @@ func (w *PlaygroundWebhook) generateValidate(obj runtime.Object) field.ErrorList
 			allErrs = append(allErrs, field.Forbidden(specPath.Child("elasticConfig.minReplicas"), "minReplicas couldn't be 0"))
 		}
 
-		if playground.Spec.ElasticConfig.MinReplicas != nil && playground.Spec.ElasticConfig.MaxReplicas != nil {
-			if *playground.Spec.ElasticConfig.MinReplicas >= *playground.Spec.ElasticConfig.MaxReplicas {
+		if playground.Spec.ElasticConfig.MinReplicas != nil {
+			if *playground.Spec.ElasticConfig.MinReplicas >= playground.Spec.ElasticConfig.MaxReplicas {
 				allErrs = append(allErrs, field.Invalid(specPath.Child("elasticConfig.scaleTrigger.hpa"), *playground.Spec.ElasticConfig.MinReplicas, "minReplicas must be less than maxReplicas"))
 			}
 		}

pkg/webhook/playground_webhook.go

@@ -160,7 +160,7 @@ func (w *PlaygroundWrapper) ElasticConfig(minReplicas, maxReplicas int32) *Playg
 	if w.Spec.ElasticConfig == nil {
 		w.Spec.ElasticConfig = &inferenceapi.ElasticConfig{}
 	}
-	w.Spec.ElasticConfig.MaxReplicas = ptr.To[int32](maxReplicas)
+	w.Spec.ElasticConfig.MaxReplicas = maxReplicas
 	w.Spec.ElasticConfig.MinReplicas = ptr.To[int32](minReplicas)
 	return w
 }