Gossiping in Message-Passing Systems

Abstract: We study the gossip problem in a message-passing environment: When a process receives a message, it has to decide whether the sender has more recent information on other processes than itself. This problem is at the heart of many distributed algorithms, and it is tightly related to questions from formal methods concerning the expressive power of distributed automata. We provide a non-deterministic gossip protocol for message-passing systems with unbounded FIFO channels, using only finitely many local states and a finite message alphabet. We show that this is optimal in the sense that there is no deterministic counterpart. As an application, the gossip protocol allows us to show that message-passing systems capture well-known extensions of linear-time temporal logics to a concurrent setting.