An Analysis of the Impact of Network Delay and Churn on Broadcast Efficiency in GossipSub-based P2P Networks

Broadcast efficiency in peer-to-peer (P2P) networks plays a critical role in enhancing blockchain scalability, especially under protocols such as GossipSub. While GossipSub has been widely adopted for its fault-tolerant and bandwidth- efficient message dissemination capabilities, limited attention has been paid to how physical-layer conditions-specifically network delay and churn-impact its broadcast performance. This paper presents an empirical study on the effects of node communication delay and churn dynamics on three key performance indicators: first message reception time, duplicate message count, and Eager Push degree. We utilize a custombuilt testbed, K-P2PLab, to simulate controlled P2P environments based on real GossipSub implementations. The results reveal trade-offs and nonlinear behaviors in protocol performance, including misleading efficiency metrics under excessive churn due to fragmented connectivity. Our findings provide practical insights into how system designers should tune GossipSub parameters to maintain propagation efficiency under diverse network conditions.