https://bz.apache.org/bugzilla/show_bug.cgi?id=63916
--- Comment #35 from Christopher Schultz <ch...@christopherschultz.net> --- (In reply to Michael Osipov from comment #34) > Awesome, can you retry with Java 8? This is Oracle 1.8.0_181. Selector Provider: sun.nio.ch.KQueueSelectorProvider@16e15b65 16,10461 32,5245 64,2696 128,1403 256,728 512,400 1024,223 2048,131 4096,71 8192,50 16384,28 146988,27 Curve is the same: https://jsfiddle.net/mrw3o96t/ > But the results are quite surprising because I have expected similar results > as with FreeBSD due to the BSD userland and kernel parts in macOS. The Macos kernel is quite a bit different than the BSD kernel(s). It's really a mach kernel with a BSD interface slapped on top so they didn't have to write all their own custom userland. Note that this is running the code from Mark's test source from github. All I did was replace the logging and add an optional command-line argument to make it easier to run repeatedly. In light of Mark's comment #27, I'd like to confirm that this is the correct code to run. It's setting the socket's send buffer size and not the appWriteBufSize. -- You are receiving this mail because: You are the assignee for the bug. --------------------------------------------------------------------- To unsubscribe, e-mail: dev-unsubscr...@tomcat.apache.org For additional commands, e-mail: dev-h...@tomcat.apache.org