News for hackers. Stuff that matters.

A comment on Hello Heroku World - Autobenching Heroku.

Re:Hello Heroku World - Autobenching Heroku by azov on Thursday March 01, 2012 @12:34AM (#3651065)
Hm... I briefly glanced over the graphs, and the results don't make sense to me. Every single server he tested must do a C accept call at some point, plus some (a lot of) extra stuff. If those servers take less time then plain accept call, doesn't it just indicate that the benchmark is flawed? Am I missing something?
[ Parent | on HN ]
Re:Hello Heroku World - Autobenching Heroku by whargarbl on Thursday March 01, 2012 @01:09AM (#3651137)
AFAIK the issue is the way they listen() to the socket, as well as whether the accept is concurrent in some way.
[ Parent | on HN ]