lidavidm commented on PR #35603: URL: https://github.com/apache/arrow/pull/35603#issuecomment-1549534625
So gRPC should already be buffering data, meaning that this change is mostly about pipelining the IPC work - except IPC deserialization should be very cheap. That could explain why the benefits are small. 4% is something, but the effects still seem very small. If performance with millions of rows is a concern, has there been any profiling or tracing to identify the bottlenecks? -- 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]
