Building State Machine Replication Using Practical Network Synchrony

2025-07-17

AI Summary

Traditional state machine replication (SMR) suffers from performance limitations in partially or fully asynchronous networks. This paper proposes Chora, an SMR protocol designed to exploit the strong synchronization characteristics of modern datacenter networks, enabling low-overhead, highly parallel replication. Chora employs kernel-bypass networking, a multi-threaded architecture, and relaxed round boundary control—achieving tightly bounded 2-μs rounds—to realize pipelined, multi-instance parallel replication. Crucially, it permits concurrent, coordination-free proposal generation across replicas. Its core innovation lies in directly translating network-level synchronization into protocol-level efficiency gains, thereby eliminating the serialization and coordination overhead inherent in conventional consensus protocols. Experimental results demonstrate that Chora achieves 255% and 109% higher throughput than the best-performing single-leader and multi-leader SMR protocols, respectively, significantly surpassing existing SMR performance bottlenecks.

Technology Category

• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems
• Machine Learning: Hardware-aware ML
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Security and Privacy: Large-scale security measurements

Abstract

Distributed systems, such as state machine replication, are critical infrastructures for modern applications. Practical distributed protocols make minimum assumptions about the underlying network: They typically assume a partially synchronous or fully asynchronous network model. In this work, we argue that modern data center systems can be designed to provide strong synchrony properties in the common case, where servers move in synchronous lock-step rounds. We prove this hypothesis by engineering a practical design that uses a combination of kernel-bypass network, multithreaded architecture, and loosened round length, achieving a tight round bound under 2us. Leveraging our engineered networks with strong synchrony, we co-design a new replication protocol, Chora. Chora exploits the network synchrony property to efficiently pipeline multiple replication instances, while allowing all replicas to propose in parallel without extra coordination. Through experiments, we show that Chora achieves 255% and 109% improvement in throughput over state-of-the-art single-leader and multi-leader protocols, respectively.

Problem

• Designing state machine replication with strong network synchrony
• Leveraging modern data centers for synchronous distributed protocols
• Improving throughput via parallel replication without extra coordination

Innovation

• Uses kernel-bypass network for strong synchrony
• Multithreaded architecture with loosened round length
• Chora protocol exploits network synchrony efficiently