This paper presents Flutter, the first Byzantine Total Order Broadcast implementation with a broadcast-to-delivery latency of $2Δ+ ε$ time units, $Δ$ being the message delay and $ε$ an arbitrarily small constant margin, when all processes are correct, the network is synchronous, hence local clocks are well-synchronized. Under the same conditions, state-of-the-art protocols require at least $3Δ$ time units in practical deployments where clients differ from servers. We prove Flutter's good-case latency is quasi-optimal, meaning it cannot be improved upon by any finite amount. Flutter is deterministic, leaderless, and signature-free hence quantum-resilient; it assumes partial synchrony and at least $5f + 1$ servers, where $f$ bounds the number of faults. Under the hood, Flutter builds upon Blink, a novel Binary Consensus implementation with Representative Validity, whose fast path enables decisions in $Δ$ time units when all correct servers propose the same value.

翻译：本文提出了Flutter，这是首个广播到交付延迟为$2Δ+ ε$时间单位的拜占庭全序广播实现，其中$Δ$为消息延迟，$ε$为任意小的常数余量——该延迟在假设所有进程正确、网络同步（因此本地时钟高度同步）的条件下成立。在相同条件下，现有最优协议在客户端与服务器分离的实际部署中至少需要$3Δ$个时间单位。我们证明Flutter的最优情况延迟是准最优的，这意味着任何有限量都无法对其加以改进。Flutter是确定性的、无领导者的且免签名（因此具有量子韧性）；它假设部分同步性及至少$5f + 1$台服务器，其中$f$为故障数上限。在实现层面，Flutter基于Blink——一种具有代表性有效性的新型二进制共识实现，其快速路径可在所有正确服务器提议相同值时于$Δ$个时间单位内做出决策。