luoyuxia opened a new issue, #3416: URL: https://github.com/apache/fluss/issues/3416
## Summary In `UnshadedArrowReadUtils.projectVectorSchemaRoot`, the current implementation copies data row-by-row via `copyFromSafe` when projecting columns. This could be optimized to use Arrow's vector transfer/copy utilities (e.g., `TransferPair`) when we only need to reuse or reorder existing columns. ## Context The current row-by-row approach is acceptable because this path is not a hot path — it is mainly used by the tiering service, which recreates scanners instead of scanning in a tight loop. But it would be worth optimizing for future use cases. ## References See the TODO in `UnshadedArrowReadUtils.projectVectorSchemaRoot`. -- 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]
