Analysis of Minimum Distribution Time of Two-Class Tit-for-Tat-Based P2P File Distribution

Masahiro Sasabe Masaki Kiyomitsu

In Computer Networks, 2022

Abstract

The demand for large-scale file distribution over the Internet has been increasing, such as software and its update data distribution. When a new and/or popular file is released, many users tend to simultaneously access distribution server(s), making them bottleneck. Several systems (e.g., Ubuntu and Windows Update) have started applying the peer-to-peer (P2P) file distribution paradigm where users' devices (i.e., peers) assist the file distribution. Since peers will consume their access link capacities to upload fragments of the file (i.e., pieces) to others, an appropriate incentive mechanism should be designed to motivate peers to behave cooperatively. In this paper, we focus on the tit-for-tat (TFT) based P2P file distribution with two-class peers where equivalent amount of piece exchange between each pair of peers is guaranteed and peers are classified into two classes: peers with high upload capacity or those with low one. In particular, given the system parameters (e.g., the number of peers and the upload capacity distribution), we specify the bottleneck of the system and derive the corresponding minimum file distribution time, with the help of fluid model. Through numerical results, we verify the validity of analytical results and compare the system performance of TFT based P2P file distribution with that of existing architectures: client-server file distribution and cooperative P2P file distribution.

Downloads

Text Reference

Masahiro Sasabe, Masaki Kiyomitsu, Analysis of Minimum Distribution Time of Two-Class Tit-for-Tat-Based P2P File Distribution, Computer Networks, 214, pp.109142: 1-16, September 2022.

BibTex Reference

@article{sasabe22AnalysisMinimumDistribution,
    author = "Sasabe, Masahiro and Kiyomitsu, Masaki",
    title = "Analysis of {{Minimum Distribution Time}} of {{Two-Class Tit-for-Tat-Based P2P File Distribution}}",
    year = "2022",
    month = "September",
    journal = "Computer Networks",
    volume = "214",
    pages = "109142: 1-16",
    doi = "10.1016/j.comnet.2022.109142"
}