adriangb commented on PR #24086: URL: https://github.com/apache/datafusion/pull/24086#issuecomment-6067040808
Possible follow-ups (prototypes, not ready for review): - **Eager first fetch.** A file starts its first read-ahead fetch when its stream is built. Thus, read-ahead continues across file boundaries when files are smaller than the window. https://github.com/adriangb/datafusion/commit/88c6304fb967f357a9d1e86d6468db5dc31064f6 - **Prefetch budget.** One byte budget for each scan partition limits the data that queued files fetch early. https://github.com/adriangb/datafusion/commit/64e67f571d2293297504ef654bf2ac4f888d7ca8 -- 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]
