Clownfish: Scaling DAG-based BFT Consensus via Sparse Edges

2026-06-03

AI Summary

Existing DAG-based BFT consensus protocols suffer from high communication complexity and limited scalability due to each vertex requiring a linear number of edges. This work proposes Clownfish, a DAG-based BFT protocol for the partial synchrony model that achieves optimal communication efficiency by constructing a sparse DAG structure, incorporating a communication-optimal consistent broadcast primitive, refining round advancement rules, and—uniquely among low-communication protocols—supporting a multi-leader mechanism per round. These innovations collectively reduce the total per-round communication complexity to O(n²). Experimental evaluation demonstrates that Clownfish substantially enhances system scalability while effectively bounding additional latency even in the presence of failures.

Abstract

Directed Acyclic Graph (DAG) based BFT protocols have demonstrated the capability to achieve significantly high throughput in practice. Recent advancements focused on minimizing the good-case latency of these protocols, approaching the theoretical lower bound. However, the high communication complexity inherent in existing DAG-based protocols limits their scalability. This primarily arises because each vertex in the DAG must include a linear number of edges (references) to vertices from previous rounds. We present Clownfish, a partially synchronous DAG-based BFT protocol designed to address the scalability bottleneck. Clownfish achieves lower communication complexity by selectively reducing the number of edges in DAG vertices. When using a communication-optimal consistent broadcast, Clownfish attains quadratic total communication complexity per round, outperforming prior DAG-based protocols. Clownfish also reduces the additional latency in failure cases by optimizing the round advancement rule. Additionally, Clownfish supports multiple leaders per round to reduce average latency while maintaining its lower communication complexity. Our experimental evaluation demonstrates that Clownfish provides significantly better scalability than existing DAG-based protocols.

Problem

• DAG-based BFT
• scalability
• communication complexity
• Byzantine Fault Tolerance
• consensus protocol

Innovation

• DAG-based BFT
• communication complexity
• sparse edges
• scalability
• multi-leader