// Package-wide variables from generator "generated".
option go_package = "k8s.io/api/autoscaling/v2beta2";

// ContainerResourceMetricSource indicates how to scale on a resource metric known to
// Kubernetes, as specified in requests and limits, describing each pod in the
// current scale target (e.g. CPU or memory).  The values will be averaged
// together before being compared to the target.  Such metrics are built in to

// Package-wide variables from generator "generated".
option go_package = "k8s.io/api/autoscaling/v2beta1";

// ContainerResourceMetricSource indicates how to scale on a resource metric known to
// Kubernetes, as specified in requests and limits, describing each pod in the
// current scale target (e.g. CPU or memory).  The values will be averaged
// together before being compared to the target.  Such metrics are built in to

  optional ScaleSpec spec = 2;

  // current status of the scale. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#spec-and-status. Read-only.
  // +optional
  optional ScaleStatus status = 3;
}

// ScaleSpec describes the attributes of a scale subresource
message ScaleSpec {
  // desired number of instances for the scaled object.
  // +optional
  optional int32 replicas = 1;
}

message HorizontalPodAutoscalerSpec {
  // reference to scaled resource; horizontal pod autoscaler will learn the current resource consumption
  // and will set the desired number of pods by using its Scale subresource.
  optional CrossVersionObjectReference scaleTargetRef = 1;

  // 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

  // status defines current status of the scale. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#spec-and-status. Read-only.
  // +optional
  optional ScaleStatus status = 3;
}

// ScaleSpec describes the attributes of a scale subresource
message ScaleSpec {
  // replicas is the number of observed instances of the scaled object.
  // +optional
  optional int32 replicas = 1;

  * Specifically, ztunnel should be able to send a request to the control plane to answer "I got a request to send traffic to 1.1.1.1, what is 1.1.1.1?"
  * While this is not needed for small scales, this is important for the long tail of massive clusters (think 1 million endpoints), where the entire set of endpoints cannot reasonably be replicated to each ztunnel.
* It should not be client-specific.

// Package-wide variables from generator "generated".
option go_package = "k8s.io/api/autoscaling/v2";

// ContainerResourceMetricSource indicates how to scale on a resource metric known to
// Kubernetes, as specified in requests and limits, describing each pod in the
// current scale target (e.g. CPU or memory).  The values will be averaged
// together before being compared to the target.  Such metrics are built in to

  // This can not be 0 if MaxSurge is 0.
  // Defaults to 25%.
  // Example: when this is set to 30%, the old ReplicaSet can be scaled down to 70% of desired pods
  // immediately when the rolling update starts. Once new pods are ready, old ReplicaSet
  // can be scaled down further, followed by scaling up the new ReplicaSet, ensuring
  // that the total number of pods available at all times during the update is at

  optional ScaleSpec spec = 2;

  // current status of the scale. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#spec-and-status. Read-only.
  // +optional
  optional ScaleStatus status = 3;
}

// describes the attributes of a scale subresource
message ScaleSpec {
  // desired number of instances for the scaled object.
  // +optional
  optional int32 replicas = 1;
}

#### Optimizations

A naive implementation would simply regenerate all resources, of all subscribed types, for each client, on any configuration change. However, this scales poorly. As a result, we have many levels of optimizations to avoid doing this work.