Measure million-document search under memory pressure - #31
Merged
Merged
Conversation
bweis
added this pull request to stack #33
September 19, 2026 20:34
bweis
marked this pull request as ready for review
September 19, 2026 22:38
…-pressure # Conflicts: # source-provenance.json
This was referenced Sep 19, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The published-trace runner now retains resource samples across index construction and timed traffic, even when the upstream driver stops PostgreSQL. Reports derive counter deltas only from samples wholly inside the measured interval and explicitly retain boundary gaps, unsupported metrics, and missing samples.
A million-document ranked run with an 8 GiB cap covered all 906 query forms at 314.1 QPS (12.840 ms p95), with all same-engine exhaustive ranked checks passing. The 2 GiB attempt was OOM-killed during index construction; it provides no query-phase result. The report retains both outcomes and distinguishes sampled peaks from container-lifetime high-water marks. These are diagnostic observations, not paired speedups or capacity claims.
Validation: 115 Python harness tests and 167 source-header checks pass. The completed million-row run was reprocessed successfully through the new resource summarizer. Linux pressure-stall metrics are unavailable on this Docker VM and remain null.