On 8/3/15, Yawning Angel <yawn...@schwanenlied.me> wrote: > ... > Hm, doesn't running good relays on Windows (especially high capacity > ones) require that we finish off the IOCP related work?
yes. this makes high performing Windows relays much more difficult in practice. there are pages written years back in tor-talk, tor-dev, and tor-relays lists regarding the non paged pool, event handling, and other resources limits on Windows, which are still true today more or less. > IIRC that's > what the bufferevent code was supposed to be for, but it hasn't been > maintained in a while, and is known to be buggy. speaking of buffer events and higher performance ... [ bump for threading thread ] *grin* best regards, _______________________________________________ tor-relays mailing list tor-relays@lists.torproject.org https://lists.torproject.org/cgi-bin/mailman/listinfo/tor-relays
