Distler T, Kapitza R (2011)
Publication Type: Conference contribution
Publication year: 2011
Edited Volumes: EuroSys'11 - Proceedings of the EuroSys 2011 Conference
Pages Range: 91-105
Conference Proceedings Title: Proceedings of the EuroSys 2011 Conference (EuroSys '11)
Event location: Salzburg
URI: http://eurosys2011.cs.uni-salzburg.at/pdf/eurosys2011-distler.pdf
Traditional agreement-based Byzantine fault-tolerant (BFT) systems process all requests on all replicas to ensure consistency. In addition to the overhead for BFT protocol and state-machine replication, this practice degrades performance and prevents throughput scalability. In this paper, we propose an extension to existing BFT architectures that increases performance for the default number of replicas by optimizing the resource utilization of their execution stages. Our approach executes a request on only a selected subset of replicas, using a selector component co-located with each replica. As this leads to divergent replica states, a selector on-demand updates outdated objects on the local replica prior to processing a request. Our evaluation shows that with each replica executing only a part of all requests, the overall performance of a Byzantine fault-tolerant NFS can be almost doubled; our prototype even outperforms unreplicated NFS. Copyright © 2011 ACM.
APA:
Distler, T., & Kapitza, R. (2011). Increasing Performance in Byzantine Fault-Tolerant Systems with On-Demand Replica Consistency. In Proceedings of the EuroSys 2011 Conference (EuroSys '11) (pp. 91-105). Salzburg.
MLA:
Distler, Tobias, and Rüdiger Kapitza. "Increasing Performance in Byzantine Fault-Tolerant Systems with On-Demand Replica Consistency." Proceedings of the EuroSys 2011, Salzburg 2011. 91-105.
BibTeX: Download