This paper presents the first rotating leader state machine replication (SMR) protocol that allows transactions to be confirmed in just a single round-trip time in the Byzantine fault tolerance (BFT) setting. Based on minimal alterations to the Internet Computer Consensus (ICC) protocol and with negligible communication overhead, we introduce a novel dual mode mechanism that enables optimal block finalization latency in the fast path. Crucially, the modes of operation are integrated, such that even if the fast path is not effective, no penalties are incurred. Moreover, our algorithm maintains the core attributes of the original ICC protocol, including optimistic responsiveness and rotating leaders without the necessity for a view-change protocol. We prove the correctness of our Fast Internet Computer Consensus (FICC) protocol and provide an open-source implementation of it. Both the FICC and original ICC protocol are compared in a globally distributed wide-area network. Our evaluation reveals that the FICC protocol achieves reduced latency compared to the ICC protocol, without requiring additional security assumptions. Furthermore, by increasing the number of replicas to $n = 5f + 1$, we exhibit that latency improvements close to the theoretical maximum of 33% are attainable. We conclude by highlighting the network topology as a significant factor in evaluating and comparing the latency of consensus algorithms.

翻译：本文提出首个旋转领导者状态机复制（SMR）协议，该协议在拜占庭容错（BFT）场景下允许交易仅通过单次往返时间即可确认。基于对互联网计算共识（ICC）协议的最小化修改，并借助可忽略的通信开销，我们引入了一种新颖的双模式机制，可在快速路径中实现最优区块确认延迟。关键在于，操作模式是集成的，因此即使快速路径无效，也不会产生性能损失。此外，我们的算法保留了原始ICC协议的核心特性，包括乐观响应性和无需视图更换协议的旋转领导者。我们证明了快速互联网计算机共识（FICC）协议的正确性，并提供了其开源实现。通过在全球分布的广域网中比较FICC与原始ICC协议，评估显示FICC协议在无需额外安全假设的前提下实现了更低的延迟。进一步地，通过将副本数量增加至$n = 5f + 1$，我们证明了接近33%理论最大值的延迟改进是可行的。最后，我们强调网络拓扑是评估和比较共识算法延迟的关键因素。