Feature Proposal: Scale Buffer

[elijah-rou]

Proposal: Introduce a "Scale Buffer", which ensures that n extra service instances are always running.

We have had a number of customers which desire control over the number of instances that are available to serve requests. This is particularly important with GPU instances, which typically can only process a single request at a time. Specifically, they have voiced need for a feature that is able to ensure that n instances are always available to serve requests, above what the autoscale suggests. This ensures that even at low volumes, there is enough capacity.

This proposal introduces a scale-buffer annotation on the service manifest, which statically adds n to the desired pod count above the autoscaler suggestion for a KPA. Even though logic is pretty simple, we currently have this running in our KNative fork and it is working well. I figured it could be useful to others that are also running low-concurrency/no-concurrency workloads in the KNative community. Happy to amend it as needed if the maintainers wish to accept it as a proposal.

[knative-prow]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: elijah-rou
Once this PR has been reviewed and has the lgtm label, please assign dprotaso for approval. For more information see the Code Review Process.

The full list of commands accepted by this bot can be found here.

Needs approval from an approver in each of these files:

• OWNERS
• pkg/apis/OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[knative-prow]

Hi @elijah-rou. Thanks for your PR.

I'm waiting for a knative member to verify that this patch is reasonable to test. If it is, they should reply with /ok-to-test on its own line. Until that is done, I will not automatically test new commits in this PR, but the usual testing commands by org members will still work. Regular contributors should join the org to skip this step.

Once the patch is verified, the new status will be reflected by the ok-to-test label.

I understand the commands that are listed here.

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository.