Presto: Towards fair and efficient HTTP adaptive streaming from multiple servers

Abstract

Though HTTP adaptive video streaming has been widely adopted in the industry, it has been shown that it suffers from lackluster performance with respect to a number of desirable properties: fairness, efficiency, and stability, especially when multiple players compete for a bottleneck link. Effective algorithms have been proposed for single-server HTTP adaptive streaming to mitigate these problems. In this paper, we present an in-depth analysis on these desirable properties in the context of using HTTP adaptive streaming from multiple servers, which demonstrate that these properties will no longer hold with the existing algorithms. To address this challenge, we present Presto, a new protocol designed to improve the user experience by providing better fairness, efficiency and stability in the context of multi-server HTTP adaptive streaming. Our real-world experimental results indicate that Presto substantially outperforms existing protocols in the multiple server scenario.