Moonshot: Optimizing Chain-Based Rotating Leader BFT via Optimistic Proposals

AI Systems and Hardware ZeRO DPS
现有的基于链式轮流领导者的部分同步网络模型的BFT SMR协议,其恒定提交延迟会产生至少$2\delta$的块周期(其中$\delta$是消息传输延迟)。虽然在同步模型下存在一个块周期为$\delta$的协议,但其提交延迟与系统规模成线性关系。为了弥补这一差距,我们提出了第一个基于链式BFT SMR协议,其中诚实领导者的提案之间具有$\delta$的延迟,并且提交延迟为$3\delta$。我们提出了三种协议,针对不同的乐观响应概念,在部分同步模型下实现了流水线处理。我们所有的协议都实现了重组弹性,并且其中两个协议具有短视图长度;这些都是许多现有基于链式BFT SMR协议所缺乏的特性。我们在广域网络中对我们的协议进行了评估,结果显示它们相对于最先进的Jolteon来说,在吞吐量方面有显著提高,在延迟方面有所降低。我们的结果还表明,通常用于减少通信复杂性的技术,如投票流水线处理和指定投票聚合器的使用,实际上会在许多情况下降低实际性能。
Existing chain-based rotating-leader BFT SMR protocols for the partially synchronous network model with constant commit latencies incur block periods of at least $2\delta$ (where $\delta$ is the message transmission latency). While a protocol with a block period of $\delta$ exists under the synchronous model, its commit latency is linear in the size of the system. To close this gap, we present the first chain-based BFT SMR protocols with $\delta$ delay between the proposals of consecutive honest leaders and commit latencies of $3\delta$. We present three protocols for the partially synchronous model under different notions of optimistic responsiveness, two of which implement pipelining. All of our protocols achieve reorg resilience and two have short view lengths; properties that many existing chain-based BFT SMR protocols lack. We present an evaluation of our protocols in a wide-area network wherein they demonstrate significant increases in throughput and reductions in latency compared to the state-of-the-art, Jolteon. Our results also demonstrate that techniques commonly employed to reduce communication complexity$\unicode{x2014}$such as vote-pipelining and the use of designated vote-aggregators$\unicode{x2014}$actually reduce practical performance in many settings.
许愿