CausalMesh: A Formally Verified Causal Cache for Stateful Serverless Computing

2025-08-21

AI Summary

To address the causal consistency challenge in stateful serverless computing—specifically, cache inconsistency across nodes induced by function migration—the paper introduces CausalMesh: the first causally consistent distributed caching system enabling coordination-free, interruption-free read/write operations and read-only transactions under client mobility. Its core innovation lies in embedding causal dependency modeling into a lightweight distributed protocol, rigorously verified end-to-end using Dafny to guarantee correctness under dynamic function migration. Experimental evaluation demonstrates that CausalMesh reduces average latency by up to 32% and improves throughput by 1.8× compared to state-of-the-art approaches across diverse workloads, while exhibiting superior performance stability.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• Security and Privacy: Large-scale security measurements
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Stateful serverless workflows consist of multiple serverless functions that access state on a remote database. Developers sometimes add a cache layer between the serverless runtime and the database to improve I/O latency. However, in a serverless environment, functions in the same workflow may be scheduled to different nodes with different caches, which can cause non-intuitive anomalies. This paper presents CausalMesh, a novel approach to causally consistent caching in environments where a computation may migrate from one machine to another, such as in serverless computing. CausalMesh is the first cache system that supports coordination-free and abort-free read/write operations and read transactions when clients roam among multiple servers. CausalMesh also supports read-write transactional causal consistency in the presence of client roaming, but at the cost of abort-freedom. We have formally verified CausalMesh's protocol in Dafny, and our experimental evaluation shows that CausalMesh has lower latency and higher throughput than existing proposals

Problem

• Ensuring causal consistency in serverless caching systems
• Preventing anomalies when functions migrate across nodes
• Enabling coordination-free operations with client roaming

Innovation

• Causally consistent caching for serverless computing
• Coordination-free read/write operations with client roaming
• Formally verified protocol with improved performance metrics