Add Prefill Heavy E2E Test to Github Actions

[rlakhtakia]

What type of PR is this?
/kind feature
/area conformance-test

What this PR does / why we need it:
Add new github actions e2e test to validate and benchmark anything requiring the use of prefill heavy workloads.

Does this PR introduce a user-facing change?:

NONE

[k8s-ci-robot]

Hi @rlakhtakia. Thanks for your PR.

I'm waiting for a github.com 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.

Details

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.

[netlify]

✅ Deploy Preview for gateway-api-inference-extension ready!

Name	Link
🔨 Latest commit	ece581f
🔍 Latest deploy log	https://app.netlify.com/projects/gateway-api-inference-extension/deploys/6937d8028edc62000891e068
😎 Deploy Preview	https://deploy-preview-1894--gateway-api-inference-extension.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[liu-cong]

/ok-to-test

[shmuelk]

@rlakhtakia How is this workflow launched? I hope it isn't launched on every PR, I saw a timeout of 7200 (seconds I assume).

[rlakhtakia]

@rlakhtakia How is this workflow launched? I hope it isn't launched on every PR, I saw a timeout of 7200 (seconds I assume).

It won't be auto triggered on every PR, but will require a comment /run-gke-prefill-heavy. We can make it more strict so that only owners and members can trigger the command to ensure its not overused.

[liu-cong]

We can make it more strict so that only owners and members can trigger the command to ensure its not overused.

@rlakhtakia

Given this is currently running on a GCP project, can we limit the access to people who have access to that project. This is just to make sure whoever triggers the workflow can coordinate the resources in the project given the resource scarcity.

Can we also update the benchmark public doc on who and how to trigger these tests?

[rlakhtakia]

@liu-cong Updated to only allow maintainers, owners and anyone authorized from the workflow file to trigger the command from a PR comment or manually through the github actions tab. Docs have also been updated to reflect how to trigger these tests.

Note: Even if a collaborator were to create a branch and add their name to the list, when setting up these workflows, those users will still have to pass in the correct secrets to use the GCP project.

[ahg-g]

/lgtm
/approve

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: ahg-g, rlakhtakia

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

The pull request process is described here

Details

Needs approval from an approver in each of these files:

• OWNERS [ahg-g]

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