Search for: All records

Debugging is a critical but challenging task for programmers. This paper proposes ChatDBG, an AI-powered debugging assistant. ChatDBG integrates large language models (LLMs) to significantly enhance the capabilities and user-friendliness of conventional debuggers. ChatDBG lets programmers engage in a collaborative dialogue with the debugger, allowing them to pose complex questions about program state, perform root cause analysis for crashes or assertion failures, and explore open-ended queries like why is x null?. To handle these queries, ChatDBG grants the LLM autonomy to take the wheel: it can act as an independent agent capable of querying and controlling the debugger to navigate through stacks and inspect program state. It then reports its findings and yields back control to the programmer. By leveraging the real-world knowledge embedded in LLMs, ChatDBG can diagnose issues identifiable only through the use of domain-specific reasoning. Our ChatDBG prototype integrates with standard debuggers including LLDB and GDB for native code and Pdb for Python. Our evaluation across a diverse set of code, including C/C++ code with known bugs and a suite of Python code including standalone scripts and Jupyter notebooks, demonstrates that ChatDBG can successfully analyze root causes, explain bugs, and generate accurate fixes for a wide range of real-world errors. For the Python programs, a single query led to an actionable bug fix 67% of the time; one additional follow-up query increased the success rate to 85%. ChatDBG has seen rapid uptake; it has already been downloaded more than 75,000 times. 

Memory leaks in web applications are pervasive and difficult to debug. Leaks degrade responsiveness by increasing garbage collection costs and can even lead to browser tab crashes. Previous leak detection approaches designed for conventional applications are ineffective in the browser environment. Tracking down leaks currently requires intensive manual effort by web developers, which is often unsuccessful. This paper introduces BLEAK (Browser Leak debugger), the first system for automatically debugging memory leaks in web applications. BLEAK'S algorithms leverage the observation that in modern web applications, users often repeatedly return to the same (approximate) visual state (e.g., the inbox view in Gmail). Sustained growth between round trips is a strong indicator of a memory leak. To use BLEAK, a developer writes a short script (17-73 LOC on our benchmarks) to drive a web application in round trips to the same visual state. BLEAK then automatically generates a list of leaks found along with their root causes, ranked by return on investment. Guided by BLEAK, we identify and fix over 50 memory leaks in popular libraries and apps including Airbnb, AngularJS, Google Analytics, Google Maps SDK, and jQuery. BLEAK'S median precision is 100%; fixing the leaks it identifies reduces heap growth by an average of 94%, saving from 0.5MB to 8MB per round trip. 

Programs written in C/C++ can suffer from serious memory fragmentation, leading to low utilization of memory, de- graded performance, and application failure due to memory exhaustion. This paper introduces Mesh, a plug-in replace- ment for malloc that, for the first time, eliminates fragmen- tation in unmodified C/C++ applications. Mesh combines novel randomized algorithms with widely-supported virtual memory operations to provably reduce fragmentation, break- ing the classical Robson bounds with high probability. Mesh generally matches the runtime performance of state-of-the- art memory allocators while reducing memory consumption; in particular, it reduces the memory of consumption of Fire- fox by 16% and Redis by 39%.