Skip to content

Add rayforce 10M-row scaled harness and queries - #940

Closed
singaraiona wants to merge 2 commits into
ClickHouse:mainfrom
RayforceDB:perf/rayforce-bench10m
Closed

Add rayforce 10M-row scaled harness and queries#940
singaraiona wants to merge 2 commits into
ClickHouse:mainfrom
RayforceDB:perf/rayforce-bench10m

Conversation

@singaraiona

Copy link
Copy Markdown

Iteration-fast subset of the full ClickBench load: 10M rows of hits (~8 GB CSV) loaded in-memory via .csv.read, all 43 queries ported to rayforce expressions under q/, and harness scripts:

bench_rf_mine.sh full 43 queries × 3 reps, min-of-3
benchq.sh load once, run a listed subset of queries
perfq.sh perf record one query, skips ~30s load via -D
capture_rf.sh full REPL output dump for correctness inspection
corr.sh fast 100k-row correctness pass
cmpq.sh side-by-side result diff against the reference run
bench_duck.sh reference engine timings on the same hits.db

hits_h.csv / hits.db are not checked in — gitignored. rf_min.txt / duck_min.txt are the latest min-of-3 timings.

Thank You for Your Contribution!

We appreciate your effort and contribution to the project. To ensure that your Pull Request (PR) adheres to our guidelines, please ensure to review the rules mentioned in our contribution guidelines:

ClickHouse/ClickBench Contribution Rules

Thank you for your attention to these details and for helping us maintain the quality and integrity of the project.

Iteration-fast subset of the full ClickBench load: 10M rows of `hits`
(~8 GB CSV) loaded in-memory via `.csv.read`, all 43 queries ported
to rayforce expressions under `q/`, and harness scripts:

  bench_rf_mine.sh  full 43 queries × 3 reps, min-of-3
  benchq.sh         load once, run a listed subset of queries
  perfq.sh          perf record one query, skips ~30s load via -D
  capture_rf.sh     full REPL output dump for correctness inspection
  corr.sh           fast 100k-row correctness pass
  cmpq.sh           side-by-side result diff against the reference run
  bench_duck.sh     reference engine timings on the same hits.db

`hits_h.csv` / `hits.db` are not checked in — gitignored.
`rf_min.txt` / `duck_min.txt` are the latest min-of-3 timings.
@CLAassistant

CLAassistant commented May 26, 2026

Copy link
Copy Markdown

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

✅ singaraiona
❌ hetoku
You have signed the CLA already but the status is still pending? Let us recheck it.

@singaraiona
singaraiona deleted the perf/rayforce-bench10m branch May 26, 2026 09:56
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants