원문정보
초록
영어
With the development of P2P technology, more and more distributed systems are applying it for deploying large-scale storage infrastructure. However, maintaining desirable data availability in P2P environments is still an opening issue because of the vulnerability of participated peers. In this paper, a novel replication model is proposed to improving the data availability of P2P storage platforms. In the proposed replication model, the probability of peer’s failure is estimated by semi-Markov chain, which enables us to significantly improving the prediction accuracy of peer’s failure in a given period. Massive experiments are conducted in a real-world P2P platform to examining the performance of the proposed replication model, and the results indicate that it can achieve better tradeoffs between performance and data availability comparing with other replication schemes.
목차
1. Introduction
2. Related Work
3. Data Replication Model
3.1 Theoretical Analysis on Replication Schemes
3.2 Markov-Chain based Failure Model for Peers
3.3 Data Replication Model
4. Experiments and Performance Evaluation
4.1 Experiment Settings
4.2 Comparison on Data Availability
4.3 Comparison on Replication Performance
6. Conclusion
References