In this paper we present findings from our windowing BitTorrent simulations and show that by carefully optimizing other factors a reasonable level of performance can be achieved while leaving the original BitTorrent tit-for-tat mechanism intact. We compare the previously proposed windowing piece selection algorithms for BitTorrent and propose a new one, called the stretching window algorithm. We also propose a new method for reducing buffering times, adjusting the window size as the download progresses, and we show its effectiveness. We also observe that windowing BitTorrent algorithms exhibit steady state behavior, and that even a small level of altruism leads to significantly improved system performance.
Abstract-The fundamental P2P principle that downloading peers help other peers can be applied in the context of videoon-demand. This represents a demanding application combining aspects of other well-known P2P applications, i.e., live streaming and traditional file sharing. We seek to provide insight on fundamental questions about the performance and scalability of the system. A deterministic fluid model is derived that explicitly takes into account the video transfer and playback phases. The analytical results are complemented with extensive simulations from the corresponding stochastic model, as well as traces from a more realistic BitTorrent simulator.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.