Supr: Adaptive Byzantine Fault-Tolerant Replication

Abstract

In the last decade, numerous Byzantine fault-tolerant (BFT) replication protocols have been proposed in the literature. However, practically all of these solutions were designed and optimized only for certain, typically very limited set of environment conditions. Despite previous efforts, no existing BFT replication protocol can guarantee stable and reasonable performance in both correct and faulty environments. In this article we attempt to address this problem by introducing Supr, a novel method for effortlessly combining multiple replication protocols into adaptive BFT solutions, which accommodate to a much wider spectrum of environment conditions than the existing BFT systems. Unlike previous approaches, Supr uses a fine-grained mechanism to monitor the parameters of the execution environment, which enables detecting and counteracting arbitrary faults exhibited in the system. To demonstrate its potential, we use Supr to create a sample BFT solution combining three existing replication protocols, each optimized for different conditions. The performed experiments demonstrate that our approach not only significantly outperforms existing solutions in varying environment conditions, but also does not introduce an observable overhead in stable environments.