Windowing BitTorrent for Video-on-Demand: Not All is Lost with Tit-for-Tat

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.