feature: hpa for jointinference

Signed-off-by: ming.tang <[email protected]>

go.mod

@@ -7,49 +7,50 @@ require (
 	github.com/gorilla/websocket v1.4.2
 	github.com/microcosm-cc/bluemonday v1.0.18
 	github.com/minio/minio-go/v7 v7.0.10
-	github.com/onsi/ginkgo v1.11.0
-	github.com/onsi/gomega v1.7.0
-	github.com/spf13/cobra v1.1.1
+	github.com/onsi/ginkgo v1.14.0
+	github.com/onsi/gomega v1.10.1
+	github.com/spf13/cobra v1.2.1
 	github.com/spf13/pflag v1.0.5
 	gorm.io/driver/sqlite v1.1.4
 	gorm.io/gorm v1.20.9
-	k8s.io/api v0.21.4
-	k8s.io/apimachinery v0.21.4
-	k8s.io/client-go v0.21.4
-	k8s.io/code-generator v0.21.4
-	k8s.io/component-base v0.21.4
-	k8s.io/klog/v2 v2.8.0
-	k8s.io/kube-openapi v0.0.0-20210305001622-591a79e4bda7
-	k8s.io/kubernetes v1.21.4
+	k8s.io/api v0.23.0
+	k8s.io/apimachinery v0.23.0
+	k8s.io/client-go v0.23.0
+	k8s.io/code-generator v0.23.0
+	k8s.io/component-base v0.23.0
+	k8s.io/klog/v2 v2.30.0
+	k8s.io/kube-openapi v0.0.0-20211115234752-e816edb12b65
+	k8s.io/kubernetes v1.23.0
 	sigs.k8s.io/yaml v1.2.0
 )
 
 replace (
 	// https://github.com/kubernetes/kubernetes/issues/79384
-	k8s.io/api => k8s.io/api v0.21.4
-	k8s.io/apiextensions-apiserver => k8s.io/apiextensions-apiserver v0.21.4
-	k8s.io/apimachinery => k8s.io/apimachinery v0.21.4
-	k8s.io/apiserver => k8s.io/apiserver v0.21.4
-	k8s.io/cli-runtime => k8s.io/cli-runtime v0.21.4
-	k8s.io/client-go => k8s.io/client-go v0.21.4
-	k8s.io/cloud-provider => k8s.io/cloud-provider v0.21.4
-	k8s.io/cluster-bootstrap => k8s.io/cluster-bootstrap v0.21.4
-	k8s.io/code-generator => k8s.io/code-generator v0.21.4
-	k8s.io/component-base => k8s.io/component-base v0.21.4
-	k8s.io/component-helpers => k8s.io/component-helpers v0.21.4
-	k8s.io/controller-manager => k8s.io/controller-manager v0.21.4
-	k8s.io/cri-api => k8s.io/cri-api v0.21.4
-	k8s.io/csi-translation-lib => k8s.io/csi-translation-lib v0.21.4
-	k8s.io/kube-aggregator => k8s.io/kube-aggregator v0.21.4
-	k8s.io/kube-controller-manager => k8s.io/kube-controller-manager v0.21.4
-	k8s.io/kube-proxy => k8s.io/kube-proxy v0.21.4
-	k8s.io/kube-scheduler => k8s.io/kube-scheduler v0.21.4
-	k8s.io/kubectl => k8s.io/kubectl v0.21.4
-	k8s.io/kubelet => k8s.io/kubelet v0.21.4
-	k8s.io/legacy-cloud-providers => k8s.io/legacy-cloud-providers v0.21.4
-	k8s.io/metrics => k8s.io/metrics v0.21.4
-	k8s.io/mount-utils => k8s.io/mount-utils v0.21.4
-	k8s.io/sample-apiserver => k8s.io/sample-apiserver v0.21.4
-	k8s.io/sample-cli-plugin => k8s.io/sample-cli-plugin v0.21.4
-	k8s.io/sample-controller => k8s.io/sample-controller v0.21.4
+	k8s.io/api => k8s.io/api v0.23.0
+	k8s.io/apiextensions-apiserver => k8s.io/apiextensions-apiserver v0.23.0
+	k8s.io/apimachinery => k8s.io/apimachinery v0.23.0
+	k8s.io/apiserver => k8s.io/apiserver v0.23.0
+	k8s.io/cli-runtime => k8s.io/cli-runtime v0.23.0
+	k8s.io/client-go => k8s.io/client-go v0.23.0
+	k8s.io/cloud-provider => k8s.io/cloud-provider v0.23.0
+	k8s.io/cluster-bootstrap => k8s.io/cluster-bootstrap v0.23.0
+	k8s.io/code-generator => k8s.io/code-generator v0.23.0
+	k8s.io/component-base => k8s.io/component-base v0.23.0
+	k8s.io/component-helpers => k8s.io/component-helpers v0.23.0
+	k8s.io/controller-manager => k8s.io/controller-manager v0.23.0
+	k8s.io/cri-api => k8s.io/cri-api v0.23.0
+	k8s.io/csi-translation-lib => k8s.io/csi-translation-lib v0.23.0
+	k8s.io/kube-aggregator => k8s.io/kube-aggregator v0.23.0
+	k8s.io/kube-controller-manager => k8s.io/kube-controller-manager v0.23.0
+	k8s.io/kube-proxy => k8s.io/kube-proxy v0.23.0
+	k8s.io/kube-scheduler => k8s.io/kube-scheduler v0.23.0
+	k8s.io/kubectl => k8s.io/kubectl v0.23.0
+	k8s.io/kubelet => k8s.io/kubelet v0.23.0
+	k8s.io/legacy-cloud-providers => k8s.io/legacy-cloud-providers v0.23.0
+	k8s.io/metrics => k8s.io/metrics v0.23.0
+	k8s.io/mount-utils => k8s.io/mount-utils v0.23.0
+	k8s.io/pod-security-admission => k8s.io/pod-security-admission v0.23.0
+	k8s.io/sample-apiserver => k8s.io/sample-apiserver v0.23.0
+	k8s.io/sample-cli-plugin => k8s.io/sample-cli-plugin v0.23.0
+	k8s.io/sample-controller => k8s.io/sample-controller v0.23.0
 )

pkg/apis/sedna/v1alpha1/jointinferenceservice_types.go

@@ -17,6 +17,7 @@ limitations under the License.
 package v1alpha1
 
 import (
+	autoscalingv2 "k8s.io/api/autoscaling/v2"
 	v1 "k8s.io/api/core/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 )
@@ -42,17 +43,56 @@ type JointInferenceServiceSpec struct {
 	CloudWorker CloudWorker `json:"cloudWorker"`
 }
 
+// HPA describes the desired functionality of the HorizontalPodAutoscaler.
+type HPA struct {
+	// minReplicas is the lower limit for the number of replicas to which the autoscaler
+	// can scale down.  It defaults to 1 pod.  minReplicas is allowed to be 0 if the
+	// alpha feature gate HPAScaleToZero is enabled and at least one Object or External
+	// metric is configured.  Scaling is active as long as at least one metric value is
+	// available.
+	// +optional
+	MinReplicas *int32 `json:"minReplicas,omitempty"`
+
+	// maxReplicas is the upper limit for the number of replicas to which the autoscaler can scale up.
+	// It cannot be less that minReplicas.
+	MaxReplicas int32 `json:"maxReplicas"`
+
+	// metrics contains the specifications for which to use to calculate the
+	// desired replica count (the maximum replica count across all metrics will
+	// be used).  The desired replica count is calculated multiplying the
+	// ratio between the target value and the current value by the current
+	// number of pods.  Ergo, metrics used must decrease as the pod count is
+	// increased, and vice-versa.  See the individual metric source types for
+	// more information about how each type of metric must respond.
+	// +optional
+	Metrics []autoscalingv2.MetricSpec `json:"metrics,omitempty"`
+
+	// behavior configures the scaling behavior of the target
+	// in both Up and Down directions (scaleUp and scaleDown fields respectively).
+	// If not set, the default HPAScalingRules for scale up and scale down are used.
+	// +optional
+	Behavior *autoscalingv2.HorizontalPodAutoscalerBehavior `json:"behavior,omitempty"`
+}
+
 // EdgeWorker describes the data a edge worker should have
 type EdgeWorker struct {
 	Model             SmallModel         `json:"model"`
 	HardExampleMining HardExampleMining  `json:"hardExampleMining"`
 	Template          v1.PodTemplateSpec `json:"template"`
+
+	// HPA describes the desired functionality of the HorizontalPodAutoscaler.
+	// +optional
+	HPA *HPA `json:"hpa"`
 }
 
 // CloudWorker describes the data a cloud worker should have
 type CloudWorker struct {
 	Model    BigModel           `json:"model"`
 	Template v1.PodTemplateSpec `json:"template"`
+
+	// HPA describes the desired functionality of the HorizontalPodAutoscaler.
+	// +optional
+	HPA *HPA `json:"hpa"`
 }
 
 // SmallModel describes the small model