liupc commented on issue #23672: [SPARK-26750]Estimate memory overhead with multi-cores URL: https://github.com/apache/spark/pull/23672#issuecomment-459602706 I agree that we may can improve this default overhead, but I was curious about how this default 0.1 is generated, by experimatal tests? is there any docs about how the experiment is done? does it taking the number of cores into account when do these tests?
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
