Adding metrics for request total, latency and size

[courageJ]

The PR adds the metrics handler and basic metrics for requests.

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: courageJ
Once this PR has been reviewed and has the lgtm label, please assign terrytangyuan 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

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

[linux-foundation-easycla]

The committers listed above are authorized under a signed CLA.

• ✅ login: courageJ (d4bddf5, 89b047c, cdfc26d, 0fe8f62, cd8d579, 8fd5a06, a5239a4, 3c3a9d3, fe38732)

[k8s-ci-robot]

Hi @courageJ. Thanks for your PR.

I'm waiting for a kubernetes-sigs 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.

[courageJ]

cc @liu-cong @ahg-g

[liu-cong]

I haven't read through the PR but sharing this early feedback.

request start time: to be precise, this should be the first time when the Process function is called, perhaps here

gateway-api-inference-extension/pkg/ext-proc/handlers/server.go

Line 55 in 1ad93e4

reqCtx := &RequestContext{}

. You can use the RequestContext to store states for a request.

request end time: This needs to be the time after we finish processing the response body, potentially here:

gateway-api-inference-extension/pkg/ext-proc/handlers/server.go

Line 87 in 1ad93e4

resp, err = s.HandleResponseBody(reqCtx, req)

[liu-cong]

I think we can have request_bytes and request_tokens to be clear about what size means. In inference, number of tokens is an important metric we should have. It's OK to add as a follow up though. Just to make sure this is captured.

[k8s-ci-robot]

PR needs rebase.

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.