-
Notifications
You must be signed in to change notification settings - Fork 210
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
perf: coalesce ids before executing take (#2680)
Late materialization is a great benefit when executing a highly selective filter. However, if a filter is highly selective it means that each input batch will probably only have a few matching rows. The current implementation executes take for each filtered batch. E.g. instead of a single call of `take(500, 10000, 300000)` we get three calls `take(500)`, `take(10000)`, and `take(300000)`. This means: * We can't coalesce * More CPU overhead (many calls to take_ranges) * Very small output batches (user's batch size is not respected) On cloud storage I see a 10x plus benefit in scan performance. We have a benchmark for this (EDA search plot 4) which should assist with preventing regression in the future: https://bencher.dev/console/projects/weston-lancedb/plots
- Loading branch information
1 parent
8cfb6a5
commit 711bad7
Showing
4 changed files
with
204 additions
and
125 deletions.
There are no files selected for viewing
This file contains 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
This file contains 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
This file contains 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
Oops, something went wrong.