Drop deprecated dstack_server_request* Prometheus metrics - #4130
Merged
Conversation
Superseded by the OpenTelemetry http_server_* metrics, which are correct under multiple replicas. Scraping /metrics through a load balancer interleaved the replicas' counters into the same series.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Part of #4129
Removes
dstack_server_requests_totalanddstack_server_request_duration_seconds, along with thelog_http_metricsmiddleware that populated them.They were already marked deprecated in favour of the OpenTelemetry
http_server_*metrics (DSTACK_OTEL_METRICS_ENABLED), and they are incorrect under multiple replicas: scraping/metricsthrough a load balancer interleaves the replicas' counters into the same series. They also made up >50% of the/metricspayload.This PR was written primarily by Claude Code.