DR.FIX: Automatically Fixing Data Races at Industry Scale

2025-04-22

AI Summary

Automatically repairing data races in industrial-scale shared-memory concurrent programs—particularly Go-based microservices—remains highly challenging due to complex concurrency semantics and context-sensitive interference patterns. Method: This paper introduces the first end-to-end repair framework that tightly integrates large language models (LLMs) with precise program analysis. It combines static analysis, interprocedural data-flow tracking, concurrency-aware LLM prompting, and domain-informed code generation to accurately identify and safely fix intricate data race patterns. Contribution/Results: Deployed at Uber for 18 months, the framework automatically generated 224 patches addressing 55% of known data races; 86% were approved by developers and merged into the mainline. This significantly improves reliability and repair efficiency in high-concurrency production systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Natural Language Processing: (Large) Language Models

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Data races are a prevalent class of concurrency bugs in shared-memory parallel programs, posing significant challenges to software reliability and reproducibility. While there is an extensive body of research on detecting data races and a wealth of practical detection tools across various programming languages, considerably less effort has been directed toward automatically fixing data races at an industrial scale. In large codebases, data races are continuously introduced and exhibit myriad patterns, making automated fixing particularly challenging. In this paper, we tackle the problem of automatically fixing data races at an industrial scale. We present Dr.Fix, a tool that combines large language models (LLMs) with program analysis to generate fixes for data races in real-world settings, effectively addressing a broad spectrum of racy patterns in complex code contexts. Implemented for Go--the programming language widely used in modern microservice architectures where concurrency is pervasive and data races are common--Dr.Fix seamlessly integrates into existing development workflows. We detail the design of Dr.Fix and examine how individual design choices influence the quality of the fixes produced. Over the past 18 months, Dr.Fix has been integrated into developer workflows at Uber demonstrating its practical utility. During this period, Dr.Fix produced patches for 224 (55%) from a corpus of 404 data races spanning various categories; 193 of these patches (86%) were accepted by more than a hundred developers via code reviews and integrated into the codebase.

Problem

• Automatically fixing prevalent data races in large-scale industrial codebases
• Addressing diverse racy patterns in complex concurrent programming contexts
• Integrating LLM-based fixes into developer workflows for practical adoption

Innovation

• Combines LLMs with program analysis
• Automatically fixes diverse race patterns
• Integrates into Go development workflows