News for hackers. Stuff that matters.
Re:BitTorrent Open Sources ‘Improved’ BitTorrent Protocol by Locke1689 on Monday May 24, 2010 @07:49PM (#1376004)
If the current BT protocol is TCP, what makes TCP congestion control ineffective?
Re:BitTorrent Open Sources ‘Improved’ BitTorrent Protocol by 146 on Monday May 24, 2010 @07:57PM (#1376023)
TCP's congestion control algorithm is mostly reactive, while UTP aims to be predictive. What this basically means is that all the TCP connections that Bittorrent opens up are all pushing the network to failure before backing off, and given how many connections Bittorrent makes, wreaks havoc on your quality of service. UTP on the other hand will attempt to predict the congestion control limits, and (I'm guessing) play nicely and slowly reach up to that limit.
Re:BitTorrent Open Sources ‘Improved’ BitTorrent Protocol by Locke1689 on Monday May 24, 2010 @11:23PM (#1376380)
Very interesting, thanks for taking the time to respond. The first time through I read about congestion control addition and thought that BT used UDP.
Re:BitTorrent Open Sources ‘Improved’ BitTorrent Protocol by dedward on Monday May 24, 2010 @09:36PM (#1376185)
I don't think that's the issue.... it's just that when you have. A massive number of sumultaneous tcp sessions, lots of home routers choke up tracking all that state in their nat tables. A custom protocol could do a better job.
Re:BitTorrent Open Sources ‘Improved’ BitTorrent Protocol by Locke1689 on Monday May 24, 2010 @11:27PM (#1376387)
The article specifically mentions additional congestion control as a significant part of the protocol. For the routers themselves, UTP is also an IP protocol so it should have most of the same state requirements (routing tables) as the same number of TCP connections.
Re:BitTorrent Open Sources ‘Improved’ BitTorrent Protocol by dedward on Tuesday May 25, 2010 @12:30AM (#1376507)
True enough... Time to dig into the details I guess.