Thus spake Olaf Selke (olaf.selke@xxxxxxxxxxxx): > in week 14 my exit nodes' bandwidth dropped to less than 400 MBit/s. It > doesn't look like a technical problem. Might it be related to the four > new torservers.net routers providing plenty of new exit bandwidth? We are also experimenting with throttling high-volume flows at entry guards through consensus parameters for the followup work to this blog post: https://blog.torproject.org/blog/research-problem-adaptive-throttling-tor-clients-entry-guards I'd guess that because of your default exit policy, you are seeing the decrease due to throttling of bittorrent traffic. Here is the experiment log if you'd like to check for correlation. I'd be interested to hear if all of these correlate to decrease volume, or just some of them: perconnbwrate=40960 perconnbwburst=10485760 bwconn start: Fri Apr 22 09:57:34 UTC 2011 bwconn end: Sun Apr 24 01:57:57 UTC 2011 perconnbwrate=40960 perconnbwburst=104857600 bwconn start: Tue Apr 26 11:32:40 UTC 2011 bwconn end: Fri Apr 29 05:26:20 UTC 2011 perconnbwrate=20480 perconnbwburst=104857600 bwconn start: Fri Apr 29 05:26:20 UTC 2011 bwconn end: Sun May 1 21:23:18 UTC 2011 I've been meaning to create a public "experiment board" wiki page somewhere with this and other experiment info, but I've been meaning to do a lot of things these days. -- Mike Perry Mad Computer Scientist fscked.org evil labs
Attachment:
pgp4JxJieJRpT.pgp
Description: PGP signature
_______________________________________________ tor-talk mailing list tor-talk@xxxxxxxxxxxxxxxxxxxx https://lists.torproject.org/cgi-bin/mailman/listinfo/tor-talk