Skip to content

docs(metrics): document all flow control metrics#1679

Open
RishabhSaini wants to merge 1 commit into
llm-d:mainfrom
RishabhSaini:fc-metrics-docs
Open

docs(metrics): document all flow control metrics#1679
RishabhSaini wants to merge 1 commit into
llm-d:mainfrom
RishabhSaini:fc-metrics-docs

Conversation

@RishabhSaini

@RishabhSaini RishabhSaini commented Jun 17, 2026

Copy link
Copy Markdown
Contributor

Summary

  • Document all 6 flow control metrics in docs/metrics.md
  • Covers: queue duration, dispatch cycle duration, enqueue duration, queue size, queue bytes, and pool saturation
  • Each metric includes type, labels with descriptions, release stage, description, and usage guidance

Context

Flow control metrics exist in code (pkg/epp/metrics/llm_d_router_metrics.go) but were not documented in docs/metrics.md. This adds a "Flow Control Metrics" section following the existing format used by disagg and ext_proc metrics.

Relates to #1270 (graduate flow control feature gate)

Test plan

  • Verified all metric names, labels, and descriptions match the code
  • Follows existing metrics.md formatting conventions

@RishabhSaini RishabhSaini requested a review from a team as a code owner June 17, 2026 13:47
@RishabhSaini RishabhSaini requested review from ahg-g and elevran June 17, 2026 13:47
@github-actions github-actions Bot added the size/M Denotes a PR that changes 30-99 lines, ignoring generated files. label Jun 17, 2026
@RishabhSaini

Copy link
Copy Markdown
Contributor Author

@gyliu513 For FlowControl metrics documentation

@gyliu513 gyliu513 left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think there are only 6 metrics but not 7, and there is no request total.

Comment thread docs/metrics.md Outdated
Add documentation for the seven flow control metrics exposed when the
flowControl feature gate is enabled: queue duration, dispatch cycle
duration, enqueue duration, queue size, queue bytes, pool saturation,
and requests total.

Signed-off-by: RishabhSaini <rishabhsaini01@gmail.com>
@gyliu513

Copy link
Copy Markdown
Member

lgtm, thanks @RishabhSaini

@ahg-g

ahg-g commented Jun 17, 2026

Copy link
Copy Markdown
Collaborator

/approve
/lgtm

@RishabhSaini

RishabhSaini commented Jun 18, 2026

Copy link
Copy Markdown
Contributor Author

has the action bot not picked up the approve labels
Might require a github review approval

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size/M Denotes a PR that changes 30-99 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants