Fair and distributed peer-to-peer allocation of a common, refillable resource

We consider the general problem of distributed and fair peer-to-peer (p2p) allocation of a common, refillable resource. This problem recurrs in a number of scenarios, for example grid computing, content distribution, Internet Service Provider service sharing, and file sharing over asymmetric channels. We present several distributed schemes for this allocation problem, and show that these schemes guarantee two key properties: (i) asymptotic fairness, in that (even maliciously colluding) users are proportionally assigned resources corresponding to what they contribute; (ii) natural incentive to join and cooperate fairly in the system. We demonstrate the practicability of our approaches on a prototype p2p file sharing system designed for typical residential internet connections, in which download capacities often significantly exceed upload capacities. Our implementation shares file data when communications are idle using random linear codes, so that, when needed, an end-user can download a file from several sources at a higher data rate than his home computer’s upload capacity. We present experimental results that support our analytical guarantees. A version of this article appeared as: • S. Agarwal, M. Laifenfeld, A. Hagedorn, A. Trachtenberg and M. Alanyali, “Fair and distributed peer-to-peer allocation of a common, refillable resource”, ACM Journal on Parallel and Distributed Computation, 69:12, pp. 974-988