Filter pushdown selectivity threshold
Open
parquet
performance
- Dominant language
- Rust
- Stars
- 3.6k
- Forks
- 1.3k
- Avg merge
- 2d 18h
- Merged PRs (30d)
- 169
Description
## Summary
Skip pushing down row selection filters when the selection has low effectivity (selects nearly all rows), as the overhead of individual small skip/read calls during Parquet decoding can outweigh the benefit.
Related PR: #9414
Contributor guide
Research direction
Start by reviewing related PR #9414 and tracing the Parquet filter pushdown and decoding path. Identify how selection effectivity is measured and where a selectivity threshold can be applied; done means highly inclusive selections avoid costly individual skip/read calls without losing filtering benefits.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- data, performance
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100