Computer Science
Rabia: Simplifying State-Machine Replication through Randomization
Document Type
Conference Paper
Abstract
We introduce Rabia, a simple and high performance framework for implementing state-machine replication (SMR) within a datacenter. The main innovation of Rabia is in using randomization to simplify the design. Rabia provides the following two features: (i) It does not need any fail-over protocol and supports trivial auxiliary protocols like log compaction, snapshotting, and reconfiguration, components that are often considered the most challenging when developing SMR systems; and (ii) It provides high performance, up to 1.5x higher throughput than the closest competitor (i.e., EPaxos) in a favorable setup (same availability zone with three replicas) and is comparable with a larger number of replicas or when deployed in multiple availability zones.
Publication Title
SOSP 2021 - Proceedings of the 28th ACM Symposium on Operating Systems Principles
Publication Date
2021
First Page
472
Last Page
487
ISBN
9781450387095
DOI
10.1145/3477132.3483582
Keywords
consensus, formal verification, SMR
Repository Citation
Pan, Haochen; Tuglu, Jesse; Zhou, Neo; Wang, Tianshu; Shen, Yicheng; Zheng, Xiong; Tassarotti, Joseph; Tseng, Lewis; and Palmieri, Roberto, "Rabia: Simplifying State-Machine Replication through Randomization" (2021). Computer Science. 107.
https://commons.clarku.edu/faculty_computer_sciences/107
APA Citation
Pan, H., Tuglu, J., Zhou, N., Wang, T., Shen, Y., Zheng, X., ... & Palmieri, R. (2021, October). Rabia: Simplifying state-machine replication through randomization. In Proceedings of the ACM SIGOPS 28th Symposium on Operating Systems Principles (pp. 472-487).