Researchers Create Selfish BitTorrent Client

An anonymous reader writes "Researchers from the computer science department at the University of Washington have released BitTyrant, a new BitTorrent client that is designed to improve download performance via strategic selection of peers and upload rates. Their results call into question the effectiveness of BitTorrent's tit-for-tat reciprocation strategy which was designed to discourage selfish users. Clients are available for Windows, OS X, and Linux."

Re:Not really selfish

[jackharrer]

But it prioritizes users with high upload/download speeds. It's better the way it's now - everybody gets their files. Maybe later but it's equal. At least people seed for longer.

If you're after communities and sharing current model is better. If you're after fast download but shorter torrent lives - go for new one.

Not necessarily good

[grimsweep]

Selfish selection of peers can lead to cliques of clients on the same network. Tit-for-tat has been proven as a highly effective strategy in games resembling the iterated prisoner's dilemna, but it can be defeated when a large enough group of of agents cooperate. This link [discourse.net] has more.

Re:Not really selfish

[Kjella]

If you're after communities and sharing current model is better. If you're after fast download but shorter torrent lives - go for new one.

If you're after communities and sharing then you're already part of a private tracker, which keeps a tab on your ratio no matter what client you use. Public trackers are a free-for-all grab. I often grab torrents when the seeds are many and peers few, and don't feel bad about that at all.

Even better...downloading without ever uploading

[meese]

Some folks at ETH Zurich took it one step further, and wrote a client - BitThief [dcg.ethz.ch] - that doesn't upload and yet still can download as fast as a regular client. This is especially valuable in countries that define copyright violation to be the uploading of content.

Re:Not really selfish

[hal2814]

"But it prioritizes users with high upload/download speeds. It's better the way it's now - everybody gets their files."

I disagree to an extent. What is high upload/download speed to one node is not neccessarily high upload/download speed to another node. It just depends on the network topography. It's possible for a DSL-connected node to have a faster upload/download connection to a node on a dial-up line than a T3 if the dial-up connection is significantly closer from a network standpoint. If done properly, prioritizing based on uploads could lead to more regionalized torrent relationships. Such a setup still has its downsides but I'm not convinced it's worse or even unfair.

Re:Not necessarily good

[ratboy666]

But the ISP wants to encourage the development of such cliques. It can be directed to keep traffic inside the ISPs bounds.

Interestingly, if bittorrent clients start "cheating", ISPs will be happier, and you will see less throttling.

Ratboy

Re:leechers

[Nasarius]

Not rare, it's extremely common on private sites with specialized material [dimeadozen.org]. I've had trouble raising my ratio above 0.85 on DIME, in spite of having 250KB/s upload. It's annoying, but there's not much you can do about it.

Re:leechers

[smellsofbikes]

Ditto that. I only torrent stuff that is completely unavailable commercially: so-called "out-of-print" material. (What the hell: it's a bunch of zeros and ones, just like all the other zeros and ones. How can it be out of print?) If you're trying to get soundtracks from obscure 1980's movies or ripped '50's jazz LP's, it's pretty frequent that the number of seeders vastly outnumbers the number of people who are still trying to find it.

Re:not so selfish

[CSEMike]

Hi,

Indeed, it's true that BitTyrant will not always improve performance, even when directly compared to other clients on the same torrent at the same time! There are several reasons for this:

• Data availability: Suppose seeders are sending out data at 20 k/sec, and a complete copy does not yet exist in the swarm. Then, even if you start downloading quickly, eventually you will catch up to the data production point and download at no faster than 20 k/sec.
• Luck of the draw: sometimes, you'll get a lucky peer (or seed) from the tracker. Because most trackers only return a subset of the peers available, BitTyrant can't make its peering selections with global information. If one client happens to get several high capacity peers that BitTyrant never sees, relative performance may be worse.
• Seed dominated performance: if there are a lot of seeds for a file, their altruistic contribution might dominate performance. BitTyrant is designed to improve download performance when tit-for-tat controls download speeds. This is typically the case when there are few seeds for a file, but many leechers.

These provide just a glimpse at the many factors that drive BitTorrent download performance. For a more thorough treatment, check out the paper:
http://www.cs.washington.edu/homes/piatek/papers/B itTyrant.pdf [washington.edu]

This is why we conducted an evaluation on not just one torrent, but more than 100, drawn from popular aggregation sites like mininova and piratebay. Aggregate statistics are necessary to have an idea of performance in general, as opposed to special cases that can arise.

Emule / Edonkey has this

[Deathlizard]

Emule has a system like this, and it basically slows everything down in the name of fair sharing. It takes absolutely forever to start downloads, since you're stuck in a vicious "chicken and egg" circle of "I can't upload anything to download" and "I can't download anything to upload".

As it stands, Bittorrent is how the Edonkey protocol used to be before ratio systems were added to the clients; Fast. After Edonkey started adding anti-leech systems to the clients, the speed went into the toilet, and the queues started skyrocketing.

I suspect that if this catches on, you can kiss 300kb's downloads goodbye.

Re:Well, uhm. Ban the client?

[jetmarc]

> Clients should send their rarest packets first, to keep the swarm happy.
> So if the packet doesn't show up, you've got a leech and your drop him in the Queue.

This technique can easily be circumvented. A leech client can co-operate with another leech client. As soon as he receives your rare packet, he can tell the other client to pretend to have it, too (without actually sending it).

It makes sense when he does the same for the other client, so both can leech from the swarm.

The only difficulty is how the leech clients find each other, while staying undetected by the rest. This, while solvable too, is not a problem initially, because the other clients must catch up first.

Regards,
Marc

Re:Well, uhm. Ban the client?

[drsquare]

I have a question: Why the hell is bittorrent so slow? I have a 8MB connection and it downloads slower than I used to get on 56k over non-bittorrent.

Rather than worrying about leeches, why not concentrate on speed?

Re:Well, uhm. Ban the client?

[SpectralDesign]

"why is BT so slow?"

It may be that your ISP is attempting to detect the BT streams, and if it decides you're "BTing" throttles you... It would seem Rogers here in Canada is doing just that.... I can typically get capped downloads via http or ftp, but minutes after launching a BT session I'm throttled to around 1/3rd my subscribed downstream rate. (Bastards!) I can't say when they started doing this -- A couple years ago I got torrents at full speed.