[p2p-hackers] paper "rarest first and choke algorithms are enough"

Michael Rogers m.rogers at cs.ucl.ac.uk
Fri May 5 15:46:16 UTC 2006


Arnaud Legout wrote:
> Byte-for-byte (BFB) algorithm and choke algorithm (CA) are far from 
> being equivalent.
> In all the studies that mention BFB I am aware of, they never mention 
> the case of seeds. They simply say that peers must not receive more than 
> they give.
> This is the definition of BFB. You can introduce a threshold, but it 
> does not change the main idea and there is no proposed solution
> to define a dynamic threshold.

It seems to me that you're comparing apples to oranges if you assume 
that byte-for-byte fairness between downloaders means there can't be any 
seeds. Specifying different behaviours for downloaders and seeds - as 
the choke algorithm does - wouldn't require a dynamic threshold.

SWIFT is a mechanism that uses approximate byte-for-byte fairness 
between downloaders while assuming that seeds will upload to anyone:

http://mnl.cs.stonybrook.edu/home/vinay/papers/swift-p2pecon.pdf

Cheers,
Michael



More information about the P2p-hackers mailing list