cyb70289 edited a comment on pull request #7603: URL: https://github.com/apache/arrow/pull/7603#issuecomment-652289408
> You can't compute latency like that if the test is multithreaded. Assume two threads, one finishes `n1` IO in `t1` time, another finishes `n2` IO in `t2` time. So the average latency should be `(t1/n1 + t2/n2) / 2`, not `(t1+t2) / (n1+n2)`? Or something else? ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
