Emit Prometheus merics for runtime observability#501
Open
Bslabe123 wants to merge 2 commits into
Open
Conversation
Adds a minimal HTTP /metrics endpoint exposing a single gauge, inference_perf_run_elapsed_seconds, as the first step toward kubernetes-sigs#489. Default port 9464 (OTel Collector convention), fresh CollectorRegistry per instance, no wiring into run lifecycle yet (intentional, to keep this reviewable). Metric name and naming conventions are placeholder pending the design sync; this PR is structural only.
k8s-ci-robot
added
the
do-not-merge/work-in-progress
Contributor
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: Bslabe123 The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
k8s-ci-robot
added
cncf-cla: yes
Bslabe123
changed the title
k8s-ci-robot
removed
the
do-not-merge/work-in-progress
- Add Iterator[PrometheusMetricsServer] return type to the fixture - Annotate _scrape's read() locally to satisfy --strict - Apply ruff format to tests/required/apis/test_chat.py (pre-existing drift from kubernetes-sigs#496 that was blocking CI on this PR)
Bslabe123
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Partially Adresses: #489
Summary
Adds a Prometheus HTTP exposition surface under a new
inference_perf/observability/package and emits one metric:inference_perf_run_elapsed_seconds, wall-clock seconds since the metrics server started.No wiring into the run lifecycle, no CLI flag, no pushgateway, no additional metrics. Those are deliberate follow-ups so this PR stays trivially reviewable and so the metric-naming decisions in #489 don't block landing the plumbing.
Intentionally deferred