Abstract
In a decentralized storage system, agents replicate each other’s data to increase availability. Compared to organizationally centralized solutions, such as cloud storage, a decentralized storage system requires less trust in the provider and may result in smaller monetary costs. Our system is based on reciprocal storage contracts that allow the agents to adopt to changes in their replication partners’ availability (by dropping inefficient contracts and forming new contracts with other partners). The data availability provided by the system is a function of the participating agents’ availability. However, a straightforward system in which agents’ matching is decentralized uses the given agent availability inefficiently. As agents are autonomous, the highly available agents form cliques replicating data between each other, which makes the system too hostile for the weakly available newcomers. In contrast, a centralized, equitable matching is not incentive compatible: it does not reward users for keeping their software running.
We solve this dilemma by a mixed solution: an “adoption” mechanism in which highly available agents donate some replication space, which in turn is used to help the worst-off agents. We show that the adoption motivates agents to increase their availability (is incentive-compatible), but also that it is sufficient for acceptable data availability for weakly-available agents.
Supplemental Material
Available for Download
Supplemental movie, appendix, image and software files for, Game-Theoretic Mechanisms to Increase Data Availability in Decentralized Storage Systems
- B. Amann, B. Elser, Y. Houri, and T. Fuhrmann. 2008. IgorFs: A distributed P2P file system. In Proceedings of P2P. 77--78. Google Scholar
Digital Library
- Amazon S3. 2013. Amazon S3, cloud computing storage for files, images, videos. Retrieved August 1, 2015, from http://aws.amazon.com/s3/.Google Scholar
- S. F. Assmann, D. S. Johnson, D. J. Kleitman, and J. Y. T. Leung. 1984. On a dual version of the one-dimensional bin packing problem. Journal of Algorithms 5, 4, 502--525.Google Scholar
Cross Ref
- G. Ausiello, P. Crescenzi, G. Gambosi, V. Kann, A. Marchetti-Spaccamela, and M. Protasi. 1999. Complexity and Approximation. Springer. Google Scholar
Digital Library
- M. Babaioff, J. Chuang, and M. Feldman. 2007. Incentives in peer-to-peer systems. In Algorithmic Game Theory, N. Nisan, T. Roughgarden, E. Tardos, and V. Vazirani (Eds.). Cambridge University Press, 593--611.Google Scholar
- S. Bernard and F. Le Fessant. 2009. Optimizing peer-to-peer backup using lifetime estimations. In Proceedings of EDBT/ICDT’09. 26--33. Google Scholar
Digital Library
- R. Bhagwan, S. Savage, and G. Voelker. 2002. Replication strategies for highly available peer-to-peer storage systems. In Future Directions in Distributed Computing. Lecture Notes in Computer Science, Vol. 2584. Springer, 153--158. Google Scholar
Digital Library
- R. Bhagwan, S. Savage, and G. M. Voelker. 2003. Understanding availability. In Peer-to-Peer Systems II. Lecture Notes in Computer Science, Vol. 2735. Springer, 256--267.Google Scholar
- R. Bhagwan, K. Tati, Y. C. Cheng, S. Savage, and G. M. Voelker. 2004. Total recall: System support for automated availability management. In Proceedings of NSDI. Google Scholar
Digital Library
- BitTorrentSync 2013. Sync Home Page. Retrieved August 2, 2015, from http://labs.bittorrent.com/experiments/sync.html.Google Scholar
- S. Le Blond, F. Le Fessant, and E. Le Merrer. 2012. Choosing partners based on availability in P2P networks. ACM Transactions on Autonomous and Adaptive Systems 7, 2, 25. Google Scholar
Digital Library
- A. Bogomolnaia and M. O. Jackson. 2002. The stability of hedonic coalition structures. Games and Economic Behavior 38, 2, 201--230.Google Scholar
Cross Ref
- W. J. Bolosky, J. R. Douceur, D. Ely, and M. Theimer. 2000. Feasibility of a serverless distributed file system deployed on an existing set of desktop PCs. In ACM SIGMETRICS Performance Evaluation Review 28, 34--43. Google Scholar
Digital Library
- W. J. Bolosky, J. R. Douceur, and J. Howell. 2007. The Farsite project: A retrospective. ACM SIGOPS Operating Systems Review, 17--26. Google Scholar
Digital Library
- S. Buchegger, D. Schiöberg, L. H. Vu, and A. Datta. 2009. PeerSoN: P2P social networking: Early experiences and insights. In Proceedings of ACM SNS. Google Scholar
Digital Library
- J. Busca, F. Picconi, and P. Sens. 2005. Pastis: A highly-scalable multi-user peer-to-peer file system. In Euro-Par 2005 Parallel Processing. Lecture Notes in Computer Science, Vol. 3648. Springer, 1173--1182. Google Scholar
Digital Library
- F. Chang, J. Dean, S. Ghemawat, W. C. Hsieh, D. A. Wallach, M. Burrows, T. Chandra, A. Fikes, and R. E. Gruber. 2008. Bigtable: A distributed storage system for structured data. ACM Transactions on Computer Systems 26, 4:1--4:26. Google Scholar
Digital Library
- B. G. Chun, F. Dabek, A. Haeberlen, E. Sit, H. Weatherspoon, M. F. Kaashoek, J. Kubiatowicz, and R. Morris. 2006. Efficient replica maintenance for distributed storage systems. In Proceedings of NSDI, Vol. 6. Google Scholar
Digital Library
- I. Clarke, O. Sandberg, B. Wiley, and T. W. Hong. 2001. Freenet: A distributed anonymous information storage and retrieval system. In Designing Privacy Enhancing Technologies. Lecture Notes in Computer Science, Vol. 2009. Springer, 46--66. Google Scholar
Digital Library
- L. P. Cox, C. D. Murray, and B. D. Noble. 2002. Pastiche: Making backup cheap and easy. ACM Operating Systems Review 36, 285--298. Google Scholar
Digital Library
- J. R. Douceur and R. P. Wattenhofer. 2001a. Competitive hill-climbing strategies for replica placement in a distributed file system. In Distributed Computing. Lecture Notes in Computer Science, Vol. 2180. Springer, 48--62. Google Scholar
Digital Library
- J. R. Douceur and R. P. Wattenhofer. 2001b. Optimizing file availability in a secure serverless distributed file system. In Proceedings of RDS.Google Scholar
- J. H. Drèze and J. Greenberg. 1980. Hedonic coalitions: Optimality and stability. Econometrica: Journal of the Econometric Society 48, 4, 987--1003.Google Scholar
Cross Ref
- A. Fabrikant, A. Luthra, E. Maneva, C. H. Papadimitriou, and S. Shenker. 2003. On a network creation game. In Proceedings of PODC. Google Scholar
Digital Library
- M. Feldman, K. Lai, J. Chuang, and I. Stoica. 2003. Quantifying disincentives in peer-to-peer networks. In Proceedings of P2P Econ.Google Scholar
- J. Fingas. 2013. Strategy Analytics: iCloud, Dropbox and Amazon Top Cloud Media in the US. Retrieved August 2, 2015, from http://www.engadget.com/2013/03/21/strategy-analytics-cloud-media-market-share/.Google Scholar
- F. Giroire, J. Monteiro, and S. Pérennes. 2009. P2P storage systems: How much locality can they tolerate? In Proceedings of LCN.Google Scholar
- S. Guha, N. Daswani, and R. Jain. 2006. An experimental study of the Skype peer-to-peer VOIP system. In Proceedings of IPTPS.Google Scholar
- M. Hefeeda, C. Hsu, and K. Mokhtarian. 2008. pCache: A proxy cache for peer-to-peer traffic. In Proceedings of SIGCOMM.Google Scholar
- S. Iyer, A. Rowstron, and P. Druschel. 2002. Squirrel: A decentralized peer-to-peer Web cache. In Proceedings of PODC. Google Scholar
Digital Library
- M. Jelasity and O. Babaoglu. 2006. T-Man: Gossip-based overlay topology management. In Engineering Self-Organising Systems. Lecture Notes in Artificial Intelligence, Vol. 3910. Springer, 1--15. Google Scholar
Digital Library
- E. Koutsoupias and C. Papadimitriou. 1999. Worst-case equilibria. Computer Science Review 1563, 404--413. Google Scholar
Digital Library
- F. Le Fessant, C. Sengul, and A. M. Kermarrec. 2008. Pace-Maker: Tracking Peer Availability in Large Networks. Technical Report RR-6594. INRIA.Google Scholar
- Z. Li, J. Wu, J. Xie, T. Zhang, G. Chen, and Y. Dai. 2011. Stability-optimal grouping strategy of peer-to-peer systems. IEEE Transactions on Parallel and Distributed Systems 22, 12, 2079--2087. Google Scholar
Digital Library
- P. Linga, I. Gupta, and K. Birman. 2003. A churn-resistant peer-to-peer Web caching system. In Proceedings of SSRS. Google Scholar
Digital Library
- X. Liu and A. Datta. 2012. Contextual trust aided enhancement of data availability in peer-to-peer backup storage systems. Journal of Network and Systems Management 20, 2, 200--225. Google Scholar
Digital Library
- P. Michiardi and L. Toka. 2009. Selfish neighbor selection in peer-to-peer backup and storage applications. In Euro-Par 2009 Parallel Processing. Lecture Notes in Computer Science, Vol. 5704. Springer, 548--560. Google Scholar
Digital Library
- J. W. Mickens and B. D. Noble. 2006. Exploiting availability prediction in distributed systems. In Proceedings of NSDI. Google Scholar
Digital Library
- T. Moscibroda, S. Schmid, and R. Wattenhofer. 2006. On the topologies formed by selfish peers. In Proceedings of PODCS. Google Scholar
Digital Library
- A. Muthitacharoen, R. Morris, T. M. Gil, and B. Chen. 2002. Ivy: A read/write peer-to-peer file system. ACM SIGOPS Operating Systems Review 36, 31--44. Google Scholar
Digital Library
- M. J. Osborne. 2004. An Introduction to Game Theory. Oxford University Press.Google Scholar
- L. Pamies-Juarez, P. Garcia-Lopez, and M. Sanchez-Artigas. 2011. Enforcing fairness in P2P storage systems using asymmetric reciprocal exchanges. In Proceedings of P2P.Google Scholar
- R. Rahman, T. Vinkó, D. Hales, J. Pouwelse, and H. Sips. 2011. Design space analysis for modeling incentives in distributed systems. In Proceedings of ACM SIGCOMM. Google Scholar
Digital Library
- S. Raz, R. Lin, and O. Shehory. 2008. Collaborative load-balancing in storage networks using agent negotiation. In Cooperative Information Agents XII. Springer, 306--320. Google Scholar
Digital Library
- R. Rodrigues and B. Liskov. 2005. High availability in DHTs: Erasure coding vs. replication. In Peer-to-Peer Systems IV. Lecture Notes in Computer Science, Vol. 3640. Springer, 226--239. Google Scholar
Digital Library
- A. Rowstron and P. Druschel. 2001. Pastry: Scalable, decentralized object location, and routing for large-scale peer-to-peer systems. In Middleware 2001. Lecture Notes in Computer Science, Vol. 2218. Springer, 329--350. Google Scholar
Digital Library
- K. Rzadca, A. Datta, and S. Buchegger. 2010. Replica placement in P2P storage: Complexity and game theoretic analyses. In Proceedings of ICDCS. Google Scholar
Digital Library
- Y. Saito, C. Karamanolis, M. Karlsson, and M. Mahalingam. 2002. Taming aggressive replication in the Pangaea wide-area file system. ACM SIGOPS Operating Systems Review 36, 15--30. Google Scholar
Digital Library
- R. Sharma, A. Datta, M. DeH’Amico, and P. Michiardi. 2011. An empirical study of availability in friend-to-friend storage systems. In Proceedings of P2P.Google Scholar
- W. Shi and Y. Mao. 2006. Performance evaluation of peer-to-peer Web caching systems. Journal of Systems and Software 79, 5, 714--726. Google Scholar
Digital Library
- P. Skowron and K. Rzadca. 2013. Exploring heterogeneity of unreliable machines for p2p backup. In Proceedings of HPCS.Google Scholar
- R. G. Tinedo, M. S. Artigas, and P. G. Lopez. 2012. Analysis of data availability in F2F storage systems: When correlations matter. In Proceedings of P2P.Google Scholar
- L. Toka and P. Michiardi. 2011. Analysis of user-driven peer selection in peer-to-peer backup and storage systems. Telecommunication Systems 47, 1, 49--63. Google Scholar
Digital Library
- K. D. Vohs, N. L. Mead, and M. R. Goode. 2006. The psychological consequences of money. Science 314, 5802, 1154--1156.Google Scholar
- Z. Yang, J. Tian, B. Y. Zhao, W. Chen, and Y. Dai. 2011. Protector: A probabilistic failure detector for cost-effective peer-to-peer storage. IEEE Transactions on Parallel and Distributed Systems 22, 9, 1514--1527. Google Scholar
Digital Library
- Z. Zhang, Q. Lian, S. Lin, W. Chen, Y. Chen, and C. Jin. 2007. BitVault: A highly reliable distributed data retention platform. ACM SIGOPS Operating Systems Review 41, 27--36. Google Scholar
Digital Library
Index Terms
Game-Theoretic Mechanisms to Increase Data Availability in Decentralized Storage Systems
Recommendations
Bayesian Combinatorial Auctions
We study the following simple Bayesian auction setting: m items are sold to n selfish bidders in m independent second-price auctions. Each bidder has a private valuation function that specifies his or her complex preferences over all subsets of items. ...
Robust combinatorial auction protocol against false-name bids.
This paper presents a new combinatorial auction protocol that is robust against false-name bids. Internet auctions have become an integral part of Electronic Commerce (EC) and a promising field for applying agent and Artificial Intelligence ...
An efficient Nash-implementation mechanism for network resource allocation
We propose a mechanism for auctioning bundles of multiple divisible goods in a network where buyers want the same amount of bandwidth on each link in their route. Buyers can specify multiple routes (corresponding to a source-destination pair). The total ...






Comments