Rafting multiplayer video games. (26th October 2021)

• Record Type: Journal Article
• Authors: Pozzan, Gabriele; Vardanega, Tullio
• Other Names: Gill Sukhpal Singh guestEditor.; Vinuesa Ricardo guestEditor.; Balasubramanian Venki guestEditor.; Ghosh Soumya K. guestEditor.
• Is Part Of: Software, practice & experience. Volume 52:Number 4(2022)
• Page Start: 1065
• Page End: 1091
• Publication Date: 2021-10-26
• Subjects: distributed consensus -- fault tolerance -- Raft -- reference implementation -- scalability evaluation; Computer software -- Periodicals; Computer programming -- Periodicals; Computer programs -- Periodicals; 005.3
• DOI: 10.1002/spe.3048
• Languages: English
• ISSNs: 0038-0644

Abstract

Abstract: Consensus is a central concern for distributed systems, paramount for fault‐tolerant applications. Online multiplayer (video) games are an attractive instance of highly distributed application, where user experience requires resilience provisioning that includes distributed consensus. In this work, we report on experiments we performed on the use of the Raft consensus algorithm in two Proof‐of‐Concept instances of famous video games. Our experiments aim to show the feasibility of such a novel architectural approach, and to assess the ensuing scalability quantitatively against game‐specific performance metrics. To enable the transferability of this effort, we discuss our implementation choices and testing method, as well as the findings from said empirical evaluation.