It would be *really* nice to see latencies as well. Some webservers trade latency to throughput, and there is no point in throughput if your service is hardly usable due to 100ms+ responses.
On Wednesday, January 16, 2013 10:56:23 AM UTC+4, Peter Taoussanis wrote: > > > This is very interesting. Have you tried running the Ring Jetty adapter >> with a larger thread pool? It's set lower than the default so as not to >> overload cloud hosts like Heroku. >> > > Okay, bumped the :max-threads from 50 to 100 without seeing much change to > the results at these relatively low concurrency levels. May well make a > difference at higher concurrency &/or with better hardware (both on the > cards for later). > > Anecdotally, I've seen http-kit happily running dozens of thousands of > concurrent connections in a high-load testing environment. Would like to > see how far I can push it on a 16 logical core box. > -- -- You received this message because you are subscribed to the Google Groups "Clojure" group. To post to this group, send email to clojure@googlegroups.com Note that posts from new members are moderated - please be patient with your first post. To unsubscribe from this group, send email to clojure+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/clojure?hl=en
