yihua opened a new issue, #1000: URL: https://github.com/apache/hudi-rs/issues/1000
### Feature Description A large base-file read, such as a big column chunk, goes to the object store as one GET on one connection, so it is capped at that single connection's throughput however much bandwidth is available. Proposal: split reads above a size threshold into parts fetched concurrently, with a bound on the parts in flight, and assemble them into the requested buffers. Small reads stay as they are. ### Additional context A per-call bound is enough to start. A connection cap shared across readers can follow. -- 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]
