Improving Peer-to-Peer Performance Through Server-Side Scheduling

The authors show how to significantly improve the mean response time seen by both uploaders and downloaders in peer-to-peer data-sharing systems. The work is motivated by the observation that response times are largely determined by the performance of the peers serving the requested objects, that is, by the peers in their capacity as servers. With this in mind, the authors take a close look at this server side of peers, characterizing its workload by collecting and examining an extensive set of traces. Using trace-driven simulation, they demonstrate the promise and potential problems with scheduling policies based on Shortest-Remaining-Processing-Time (SRPT), the algorithm known to be optimal for minimizing mean response time.