ConfLogger: Enhance Systems' Configuration Diagnosability through Configuration Logging
Year: 2026
Type: conference-paper
Abstract: Modern configurable systems, including distributed systems and recently popular decentralized systems in Web 3.0, offer customization via intricate configuration spaces, yet such flexibility introduces pervasive configuration-related issues such as misconfigurations and latent software bugs. Existing diagnosability supports focus on post-failure analysis of software behavior to identify configuration issues, but none of these approaches look into whether the software clues sufficient failure information for diagnosis. To fill in the blank, we propose the idea of configuration logging to enhance existing logging practices at the source code level. We develop ConfLogger, the first tool that unifies configuration-aware static taint analysis with LLM-based log generation to enhance software configuration diagnosability. Specifically, our method 1) identifies configuration-sensitive code segments by tracing configuration-related data flow in the whole project, and 2) generates diagnostic logging statements by analyzing configuration code contexts. Evaluation results on eight popular software systems demonstrate the effectiveness of ConfLogger to enhance configuration diagnosability. Specifically, ConfLogger-enhanced logs successfully aid a log-based misconfiguration diagnosis tool to achieve 100% accuracy on error localization in 30 silent misconfiguration scenarios, with 80% directly resolvable through explicit configuration information exposed. In addition, ConfLogger achieves 74% coverage of existing logging points, outperforming baseline LLM-based loggers by 12% and 30%. It also gains 8.6% higher in precision, 79.3% higher in recall, and 26.2% higher in F1 compared to the state-of-the-art baseline in terms of variable logging while also augmenting diagnostic value. A controlled user study on 22 cases further validated its utility, speeding up diagnostic time by 1.25× and improving troubleshooting accuracy by 251.4%.
Authors: Shiwen Shan, Yintong Huo, Yuxin Su, Zhining Wang, Dan Li, Zibin Zheng
Institutions: Sun Yat-sen University, Singapore Management University
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G1285982943, G6775111781
OpenAlex ID: W4415986832
FWCI:
Cites:
Cited by:
Related to: