Modeling and performance analysis of BitTorrent-like peer-to-peer networks

By Dongyu Qiu. Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication, 2004

1,313 citations recorded by the source corpus.

In this paper, we develop simple models to study the performance of BitTorrent, a second generation peer-to-peer (P2P) application. We first present a simple fluid model and study the scalability, performance and efficiency of such a file-sharing mechanism. We then consider the built-in incentive mechanism of BitTorrent and study its effect on network performance. We also provide numerical results based on both simulations and real traces obtained from the Internet.

Subfields: Clinical Psychology, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/74bd4ebfa10e2e906b1f014bba0f83df3d09337e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Clinical Psychology

In Computer Networks and Communications

Citations in the corpus

Analyzing and Improving a BitTorrent Networks Performance Mechanisms (2006, methodology): “Our study differs from previous studies of BitTorrent in the following important ways: ﬁrst, while the analytical study reported in [5] presents the steady state scalability properties of BitTorrent, it ignores a number of important BitTorrent parameters (e.g., node degree ( d ), maximum concurrent…”
BiToS: Enhancing BitTorrent for Supporting Streaming Applications (2006, background): “A Free-Rider participating in the distribution of time insensitive data, who contributes none or only a small portion of its upload capacity, would receive a small fraction of download capacity, due to the Tit-for-Tat policy [ 17 ].”
Co-operative downloading in vehicular ad-hoc wireless networks (2005, methodology): “We develop an analytical model to characterize the performance of SPAWN.”
A survey of autonomic communications (2006, background): “Interestingly, BitTorrent can still suffer from free riding [Qiu and Srikant 2004], which attests to the dif.culty of designing sel.shness-proof ACM Transactions on Autonomous and Adaptive Systems, Vol. 1, No. 2, December 2006.”
Can internet video-on-demand be profitable? (2007, background): “Qiu and Srikant [14] developed a .uid model to obtain analytical insights.”
P4p: provider portal for applications (2008, methodology): “Application with Upload/Download Matching Some applications may want to maximize the matching of peer download and upload (see, e.g., [ 23 ]).”
Should internet service providers fear peer-assisted content distribution? (2005, methodology): “Previous work on BitTorrent has focused on measurements [4, 9], theoretical analysis [ 22 ], and improvements [27].”
Gossip Algorithms (2009, methodology): “Historically, the analysis of multi-piece information spreading for BitTorrent like systems was studied using a ‘mean-field’ approximation by Qiu and Srikant [59] as well as Massoulie and Vojnovic [47].”
Network coding for large scale content distribution (2005, methodology): “A detailed analysis of BitTorrent’s performance can be found in [12], [13].”
Stochastic Fluid Theory for P2P Streaming Systems (2007, background): “The fluid models in [ 15 ] and [4] are not applicable to streamin g systems with heterogeneous upload rates, since there is no notion of leechers transitioning to seeds.”
Do incentives build robustness in bit torrent (2007, background): “Qiu and Srikant [17] specifically study BitTorrent’s rate-based TFT strategy.”
Improving Traffic Locality in BitTorrent via Biased Neighbor Selection (2006, background): “Many analytical and simulation studies [16, 1, 25, 22] have shown that the existing BitTorrent algorithm is nearly optimal in terms of user experienced download time.”
Measurements, analysis, and modeling of BitTorrent-like systems (2005, methodology): “Previous research has studied BitTorrent-like systems through trace analysis and modeling, and verified its effectiveness during flash crowds, which normally happen soon upon the debut of a new file [18].”
Game Theory in Wireless and Communication Networks (2008, background): “Consequently, numerous research activities [304, 394, 385, 112, 80, 36, 426, 311, 408] have focused on studying and analyzing peerto-peer systems from various perspectives, ranging from data exchange [394], resource reciprocation [385], and cooperative download [36] to legal issues [408].”
Rarest first and choke algorithms are enough (2006, background): “[22] D. Qiu and R. Srikant.”
An architecture for exploiting multi-core processors to parallelize network intrusion prevention (2007, neutral): “It has already been largely evaluated through analysis of large scale utilization [13, 11], analytical modeling [15] or simulation [2].”
Inside the New Coolstreaming: Principles, Measurements and Performance Implications (2008, result): “This subsequently reduces the impact due to a parent departure or failure, and further helps to achieve better transmission efficiency similar to the P2P file transfer protocols [26].”