andygrove opened a new issue, #3431: URL: https://github.com/apache/datafusion-comet/issues/3431
### What is the problem the feature request solves? Due to the hybrid JVM/Rust nature of the `native_iceberg_scan`, there is a lot of overhead in transferring the batches from Rust to JVM and then back to Rust. This involved serde overhead for the schema with each batch. I am wondering if this round-trip can be avoided in some cases The following profiling information is from running async-profiler. <img width="622" height="217" alt="Image" src="https://github.com/user-attachments/assets/e618fae1-e805-45e0-bf51-1977d57e4684"; /> ### Describe the potential solution _No response_ ### Additional context _No response_ -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
