yihua opened a new issue, #893: URL: https://github.com/apache/hudi-rs/issues/893
### Feature Description `HFileWriter::write` copies its whole input (`entries.to_vec()`, a `String` and a `Vec<u8>` per entry) only to sort it, and grows its data buffer one entry at a time. Every record-level index update goes through it, so a write that indexes millions of keys spends most of its index-building time allocating, copying and freeing those entries. Proposed: sort references to the entries instead of copies, and size the data buffer once from the entries' lengths. -- 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]
