论文标题
Phalanx：实用的拜占庭有序共识方案
Phalanx: A Practical Byzantine Ordered Consensus Protocol
论文作者
论文摘要
拜占庭式容错（BFT）共识是分布式计算的基本原始性。但是，BFT协议遭受了订购操作的困扰，在该操作中，对手可以使前进。提出了几种协议来解决操纵问题，但是它们有一些局限性。基于批处理的协议（例如Themis）由于使用复杂算法来找到强烈连接的组件（SCC）而具有重大的性能损失。基于时间戳的协议（例如POMPE）简化了排序阶段，但是它们在对手可以通过交易时间戳操纵订购的公平性限制。在本文中，我们提出了一种拜占庭有序的共识协议，称为phalanx，其中通过基于锚的订购策略进行交易。基于锚的策略使每个参与者的Lamport逻辑时钟汇总，并生成最终排序，而无需对SCC进行复杂的检测。因此，与基于时间戳的策略相比，Phalanx的性能令人满意，并且在抵抗订购操作方面的表现更好。
Byzantine fault tolerance (BFT) consensus is a fundamental primitive for distributed computation. However, BFT protocols suffer from the ordering manipulation, in which an adversary can make front-running. Several protocols are proposed to resolve the manipulation problem, but there are some limitations for them. The batch-based protocols such as Themis has significant performance loss because of the use of complex algorithms to find strongly connected components (SCCs). The timestamp-based protocols such as Pompe have simplified the ordering phase, but they are limited on fairness that the adversary can manipulate the ordering via timestamps of transactions. In this paper, we propose a Byzantine ordered consensus protocol called Phalanx, in which transactions are committed by anchor-based ordering strategy. The anchor-based strategy makes aggregation of the Lamport logical clock of transactions on each participant and generates the final ordering without complex detection for SCCs. Therefore, Phalanx has achieved satisfying performance and performs better in resisting ordering manipulation than timestamp-based strategy.
