Performance study of fluid content distribution model for peer-to-peer overlay networks

Abstract

Recently overlay networks are used to serve high-concurrency applications ranging from live streaming to reliable delivery of popular content. Comparing to traditional communication mechanism overlay networks offer an enhanced alternative for content delivery in terms of flexibility, scalability, and ease of deployment. Content distribution process in overlay networks is facilitated by leveraging the uploading capacity of the receiving nodes. Content distribution in overlay networks is generally based on Chunk and Fluid model. Fluid model provides continuous transfer of the content from the source to multiple receivers. However, deploying Fluid model in heterogeneous peer-topeer overlay networks requires special consideration due to the incorporation of tightly coupled connections between adjacent peers. The aim of this paper is to study the performance of different Fluid content distribution models for peer-topeer overlay networks. In this paper, investigates three different classes of Fluid content distribution models including: Fluid model with scheduling, backpressure and encoding. Moreover, the performance of Fluid model with backpressure, and encoding, have been evaluated and compared based on download time as a critical performance metric in peer-to-peer overlay networks. The performance tests have been carried out by real implementation tests over "PlanetLab". © 2011 Springer-Verlag Berlin Heidelberg.