bench(pk): report median of 3 runs per phase in the fair-PK harness (D1) - #381
Merged
Conversation
Single-shot fair-PK arms fluctuated by roughly +-30% between runs, which made before/after attribution unreliable. RunPkComparison now runs every arm three times and reports the per-phase median time (ops/s recomputed from the median time), so each UPDATE/DELETE optimization can be judged on stable numbers.
MPCoreDeveloper
force-pushed
the
perf/d1-median-pk-harness
branch
from
September 4, 2026 09:37
f118dcd to
950c04d
Compare
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Samenvatting
D1: de fair-PK harness rapporteert nu de median van 3 runs per fase.
Single-shot fair-PK runs fluctueerden met ruwweg ±30% tussen runs, waardoor before/after-attributie
onbetrouwbaar was (dat is zichtbaar in alle eerdere UPDATE/DELETE-A/B-metingen).
RunPkComparisondraait nu elke arm (legacy, fixed-width, SQLite) drie keer en rapporteert per fase de mediane
tijd; ops/s wordt herberekend uit de mediane tijd. Dit maakt elke volgende
UPDATE/DELETE-optimalisatie (zoals de FW-DELETE core stap) op stabiele cijfers beoordeelbaar.
Harness-only wijziging (geen productcode, geen gedragswijziging).