hhhizzz commented on PR #10852:
URL: https://github.com/apache/arrow-rs/pull/10852#issuecomment-5441557715
> Thanks @hhhizzz, look good to me. This is a good improvement for the
first-predicate path. One remaining limitation is that when the selection stays
selector-backed, later predicates still fully materialize selectors via
`from_filters`. A follow-up can extend capped construction to those
predicates(becuase when page index are available and page pruning is effective,
datafusion usually provides an existing `RowSelection`).
>
> for the regression in TPC-DS Q14/Q50, maybe we can run the benchmark once
again to check if this a noisy, because both Q14/Q50 are join-dominated, the pr
should not affect so much. also i can help test, if you can share how to run
the test .
Thanks for pointing this out. I investigated the apparent regressions
further.
In a new four focused 10-iteration rounds, neither regression reproduced:
- Q14: -3.7% (noisy/overlapping)
- Q50: -0.5%
- Arrow async Q21: -1.0%
Profiles showed no new candidate hotspot, and the Q14/Q50 direct-output
counters were zero. **The earlier regressions were most likely caused by
insufficient iterations** and benchmark noise. I’ll treat that table as
experimental context rather than PR-only evidence.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
