2010YOUY01 commented on issue #10140: URL: https://github.com/apache/arrow-rs/issues/10140#issuecomment-4715430639
I suspect the underlying Parquet decoder is only optimized for patterns with long contiguous runs. If we try to decode a pattern like `skip 1, read 1, skip 1, read 1, ...`, we may see a significant slowdown. This code snippet seems to show a large per-run overhead: https://github.com/apache/arrow-rs/blob/25114c5caaa9e767050b366e57c20eca54aca987/parquet/src/arrow/arrow_reader/mod.rs#L853 -- 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]
