Toward a Faster Fault Tolerant Consensus to Maintain Data Consistency in Collaborative Environments

The consensus problem has become a key issue in the field of collaborative telemedicine systems because of the need to guarantee the consistency of shared data. In this paper, we focus on the performance of consensus algorithms. First, we studied, in the literature, the most well-known algorithms in the domain. Experiments on these algorithms allowed us to propose a new algorithm that enhances the performance of consensus in different situations. During 2014, we presented our very first initial thoughts to enhance the performance of the consensus algorithms, but the proposed solution gave very moderate results. The goal of this paper is to present a new enhanced consensus algorithm, named Fouad, Lionel and J.-Christophe (FLC). This new algorithm was built on the architecture of the Mostefaoui-Raynal (MR) consensus algorithm and integrates new features and some known techniques in order to enhance the performance of consensus in situations where process crashes are present in the system. The results from our experiments running on the simulation platform Neko show that the FLC algorithm gives the best performance when using a multicast network model on different scenarios: in the first scenario, where there are no process crashes nor wrong suspicion, and even in the second one, where multiple simultaneous process crashes take place in the system.