Abstract
With the growing popularity of peer-assisted file distribution in commercial applications, flash crowds have a significant impact on download performance. A file distribution system has to cope with extreme flash crowd conditions that correspond with a sudden surge in peer arrivals. In such systems, service providers have to ensure that the system has sufficient capacity to maintain the agreed quality of service at minimum costs. Using our measurement-driven analytic model, we investigate four different server distribution policies for peer-assisted file distributions with heterogeneous peers bandwidth. Our policies are designed to reduce the server data usage without increasing expected peer download time. We observed that increasing the server bandwidth allocated for slow peers and decreasing that for fast peers can be effective in reducing the average download time by 5% and server provisioning data usage by 10%, without affecting the fairness of the system. Secondly, when server bandwidth is reduced by 70% during maximum utilization and increased during the end-game phase, the total server data decreases by 12% with 4.3% improvement in peer download performance.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Cisco Visual Networking Index: Forecast and Methodology, 2012-2017, http://www.cisco.com/en/US/solutions/collateral/ns341/ns525/ns537/ns705/ns827/white_paper_c11-481360.pdf (retrieved 2013)
Carbunaru, C., Teo, Y.M., Leong, B.: A Performance Study of Peer-assisted File Distribution with Heterogeneous Swarms. In: Proc. of IEEE Conference on Local Computer Networks, Germany, pp. 341–349 (2011)
Carbunaru, C., Teo, Y.M., Leong, B., Ho, T.: Modeling Flash Crowd Performance in Peer-to-peer File Distribution. IEEE Transactions on Parallel and Distributed Systems (accepted 2013)
Carlsson, N., Eager, D.L., Mahanti, A.: Using Torrent Inflation to Efficiently Serve the Long Tail in Peer-Assisted Content Delivery Systems. In: Proc. of IFIP Networking, India, pp. 1–14 (2010)
Chun, B., Culler, D., Roscoe, T., Bavier, A., Peterson, L., Wawrzoniak, M., Bowman, M.: PlanetLab: An Overlay Testbed for Broad-Coverage Services. Computer Communication Review 33, 3–12 (2003)
Cohen, B.: Incentives Build Robustness in BitTorrent. In: Workshop on Economics of Peer-to-Peer Systems, USA, pp. 1–5 (2003)
Dán, G., Carlsson, N.: Dynamic Swarm Management for Improved BitTorrent Performance. In: Proc. of International Conference on Peer-to-Peer Systems, USA, pp. 10–15 (2009)
Fan, B., Lui, J.C.S., Chiu, D.M.: The Design Trade-offs of BitTorrent-like File Sharing Protocols. IEEE/ACM Transactions on Networking 17, 365–376 (2009)
Ge, Z., Figueiredo, D.R., Jaiswal, S., Kurose, J., Towsley, D.: Modeling Peer-peer File Sharing Systems. In: Proc. of IEEE INFOCOM, USA, pp. 2188–2198 (2003)
Li, M., Yu, J., Wu, J.: Free-riding on BitTorrent-like Peer-to-peer File Sharing Systems: Modeling Analysis and Improvement. IEEE Transactions on Parallel and Distributed Systems 19, 954–966 (2008)
Liu, F., Li, B., Zhong, L., Li, B., Jin, H., Liao, X.: Flash Crowd in P2P Live Streaming Systems: Fundamental Characteristics and Design Implications. IEEE Transactions on Parallel and Distributed Systems 23(7), 1227–1239 (2012)
Menasche, D., de A Rocha, A., Li, B., Towsley, D., Venkataramani, A.: Content Availability and Bundling in Swarming Systems. IEEE/ACM Transactions on Networking 21(2), 580–593 (2013)
Peterson, R.S., Sirer, E.G.: Antfarm: Efficient Content Distribution with Managed Swarms. In: Proc. of USENIX Symposium on Networked Systems Design and Implementation, USA, pp. 107–122 (2009)
Pouwelse, J.A., Garbacki, P., Epema, D.H.J., Sips, H.J.: The Bittorrent P2P File-Sharing System: Measurements And Analysis. In: The International Workshop on Peer-to-Peer Systems, USA, pp. 205–216 (2005)
Pruteanu, A., D’Acunto, L., Dulman, S.: Distributed Online Flash-crowd Detection in P2P Swarming Systems. Computer Communications 36(5), 533–541 (2013)
Qiu, D., Srikant, R.: Modeling and Performance Analysis of BitTorrent-like Peer-to-Peer Networks. In: Proc. of ACM SIGCOMM, USA, pp. 367–378 (2004)
Sun, Y., Liu, F., Li, B., Li, B.: Peer-assisted Online Storage and Distribution: Modeling and Server Strategies. In: Proc. of NOSSDAV, USA, pp. 13–18 (2009)
Wu, C., Li, B., Zhao, S.: Multi-Channel Live P2P Streaming: Refocusing on Servers. In: Proc. of IEEE INFOCOM, USA, pp. 1–9 (2008)
Yang, X., Veciana, G.: Performance of Peer-to-peer Networks: Service Capacity and Role of Resource Sharing Policies. Performance Evaluation, P2P Computing Systems 63, 175–194 (2006)
Zhang, B., Iosup, A., Pouwelse, J., Epema, D.: Identifying, Analyzing, and Modeling Flashcrowds in BitTorrent. In: Proc. of IEEE International Conference on Peer-to-Peer Computing, Japan, pp. 240–249 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Carbunaru, C., Teo, Y.M. (2014). Analysis of Server Distribution Policies in Peer-Assisted File Distribution with Flash Crowds. In: Tanaka, S., Hasegawa, K., Xu, R., Sakamoto, N., Turner, S.J. (eds) AsiaSim 2014. AsiaSim 2014. Communications in Computer and Information Science, vol 474. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45289-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-662-45289-9_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-45288-2
Online ISBN: 978-3-662-45289-9
eBook Packages: Computer ScienceComputer Science (R0)