mapleFU commented on issue #38389: URL: https://github.com/apache/arrow/issues/38389#issuecomment-1779160429
Reading from S3 might better enable PreBuffer, and making some Cache input, it would do some: 1. Merging adjacent S3 IO request with some condition. 2. PreBuffer some column-chunk Generally, I think S3 has higher latency, but might has high bindwidth. So if memory is enough, PreBuffer would help -- 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]
