2010YOUY01 commented on issue #15321: URL: https://github.com/apache/datafusion/issues/15321#issuecomment-2786229514
> Thanks for your reply [@2010YOUY01](https://github.com/2010YOUY01) , and the benchmark shows that StreamReader with mmap has no performance improvement compared to current implementation: > > ``` > spill_io/StreamReader/read_100/ > time: [7.1020 ms 7.2847 ms 7.4983 ms] > change: [-2.7305% +1.2574% +5.1899%] (p = 0.55 > 0.05) > No change in performance detected. > ``` > > So there is no need to enable mmap now, as we need stream format here. Maybe it's already using `mmap` 🤔 I'll double-check it when I start to look into the performance, thank you for the experiments. -- 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: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
