Shoal: Improving DAG-BFT Latency And Robustness

The Narwhal system is a state-of-the-art Byzantine fault-tolerant scalable architecture that involves constructing a directed acyclic graph (DAG) of messages among a set of validators in a Blockchain network. Bullshark is a zero-overhead consensus protocol on top of the Narwhal's DAG that can order over 100k transactions per second. Unfortunately, the high throughput of Bullshark comes with a latency price due to the DAG construction, increasing the latency compared to the state-of-the-art leader-based BFT consensus protocols. We introduce Shoal, a protocol-agnostic framework for enhancing Narwhal-based consensus. By incorporating leader reputation and pipelining support for the first time, Shoal significantly reduces latency. Moreover, the combination of properties of the DAG construction and the leader reputation mechanism enables the elimination of timeouts in all but extremely uncommon scenarios in practice, a property we name Prevalent Responsiveness" (it strictly subsumes the established and often desired Optimistic Responsiveness property for BFT protocols). We integrated Shoal instantiated with Bullshark, the fastest existing Narwhal-based consensus protocol, in an open-source Blockchain project and provide experimental evaluations demonstrating up to 40% latency reduction in the failure-free executions, and up-to 80% reduction in executions with failures against the vanilla Bullshark implementation