Effective Performance Issue Diagnosis with Value-Assisted Cost Profiling
Lingmei Weng, Yigong Hu, Peng Huang, Jason Nieh, Junfeng Yang
Abstract
Diagnosing performance issues is often difficult, especially when they occur only during some program executions. Profilers can help with performance debugging, but are ineffective when the most costly functions are not the root causes of performance issues. To address this problem, we introduce a new profiling methodology, value-assisted cost profiling, and a tool vProf. Our insight is that capturing the values of variables can greatly help diagnose performance issues. vProf continuously records values while profiling normal and buggy program executions. It identifies anomalies in the values and the functions where they occur to pinpoint the real root causes of performance issues. Using a set of 15 real-world performance bugs in four widely used applications, we show that vProf is effective at diagnosing all of the issues while other stateof-the-art tools diagnose only a few of them. We further use vProf to diagnose longstanding performance issues in these applications that have been unresolved for over four years.
• Software and its engineering → Software testing and debugging.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext f07f73a4-f8ef-49c6-8050-bf7f1ebde724Cited by top-tier papers5
- FastPERT: Towards Fast Microservice Application Latency Prediction via Structural Inductive Bias over PERT NetworksDa Sun Handason Tam, Huanle Xu, Yang Liu, Siyue Xie et al.AAAI 2025 · 5 citations
- Pushing Performance Isolation Boundaries into Application with pBoxYigong Hu, Gongqi Huang, Peng HuangSOSP 2023 · 2 citations
- More Than Just Functional: LLM-as-a-Critique for Efficient Code GenerationDerui Zhu, Dingfan Chen, Jinfu Chen, Jens Grossklags et al.NeurIPS 2025 · 2 citations
- Diagnosing Performance Issues in Application-Defined ResourcesYigong Hu, You-Liang Huang, Haodong Zheng, Yicheng Liu et al.OSDI 2026 · 1 citation
- Mitigating Application Resource Overload with Targeted Task CancellationYigong Hu, Zeyin Zhang, Yicheng Liu, Yile Gu et al.SOSP 2025
Builds on5
- Automated Reasoning and Detection of Specious Configuration in Large Systems with Symbolic ExecutionYigong Hu, Gongqi Huang, Peng HuangOSDI 2020 · 31 citations
- DMon: Efficient Detection and Correction of Data Locality Problems Using Selective ProfilingTanvir Ahmed Khan, Ian Neal, Gilles Pokam, Barzan Mozafari et al.OSDI 2021 · 31 citations
- On Debugging the Performance of Configurable Software Systems: Developer Needs and Tailored Tool SupportMiguel Velez, Pooyan Jamshidi, Norbert Siegmund, Sven Apel et al.ICSE 2022 · 21 citations
- Argus: Debugging Performance Issues in Modern Desktop Applications with Annotated Causal TracingLingmei Weng, Peng Huang, Jason Nieh, Junfeng YangUSENIX ATC 2021 · 16 citations
- Analyzing system performance with probabilistic performance annotationsDaniele Rogora, Antonio Carzaniga, Amer Diwan, Matthias Hauswirth et al.EuroSys 2020 · 11 citations
Related papers
- Vapro: performance variance detection and diagnosis for production-run parallel applicationsLiyan Zheng, Jidong Zhai, Xiongchao Tang, Haojie Wang et al.PPoPP 2022 · 15 citations
- LDB: An Efficient Latency Profiling Tool for Multithreaded ApplicationsInho Cho, Seo Jin Park, Ahmed Saeed, Mohammad Alizadeh et al.NSDI 2024 · 4 citations
- Relational Debugging - Pinpointing Root Causes of Performance ProblemsXiang (Jenny) Ren, Sitao Wang, Zhuqi Jin, David Lion et al.OSDI 2023 · 5 citations
- DiagConfig: Configuration Diagnosis of Performance Violations in Configurable Software SystemsZhiming Chen, Pengfei Chen, Peipei Wang, Guangba Yu et al.FSE 2023 · 9 citations
- ValueExpert: exploring value patterns in GPU-accelerated applicationsKeren Zhou, Yueming Hao, John M. Mellor-Crummey, Xiaozhu Meng et al.ASPLOS 2022 · 19 citations
