指令调优的LLM用于领导型HPC系统上解析和挖掘无结构日志
Instruction-Tuned LLMs for Parsing and Mining Unstructured Logs on Leadership HPC Systems
AI总结：
本文提出一种基于指令调优的LLM框架，利用链式推理解析HPC日志，结合领域特定日志模板和示例对LLaMA模型进行微调，实现高精度的日志解析与挖掘，验证了其在大规模日志数据上的有效性。
摘要：
领导级HPC系统产生大量异构且主要无结构的系统日志。由于这些日志来自多样化的软件、硬件和运行时层，它们表现出不一致的格式，使结构提取和模式发现极具挑战性。因此，稳健的日志解析和挖掘对于将原始遥测数据转化为可操作见解至关重要，以揭示运营模式、诊断异常并实现可靠、高效且可扩展的系统分析。最近在大语言模型（LLMs）上的进展为领导级HPC环境中的自动化日志理解提供了新的方向。为了利用这一机会，我们提出了一种领域适应、遵循指令的LLM驱动框架，利用链式推理（CoT）推理来高保真解析HPC日志。我们的方法结合了领域特定的日志模板数据和指令调优的示例，对一个8B参数的LLaMA模型进行微调，专门用于HPC日志分析。我们开发了一种混合微调方法，将通用目的LLM适应到领域特定的日志数据，使隐私保护、本地可部署、快速且节能的日志挖掘方法成为可能。我们对LogHub存储库中的多样化日志数据集进行了实验。评估证实，我们的方法在解析精度上与显著更大的模型，如LLaMA 70B和Anthropic的Claude相当。我们进一步通过解析Frontier超级计算机在四周窗口内超过6亿条生产日志，验证了我们微调的LLM模型的实用价值，揭示了时间动态、节点级异常和工作负载-错误日志相关性中的关键模式。
英文摘要：
Leadership-class HPC systems generate massive volumes of heterogeneous, largely unstructured system logs. Because these logs originate from diverse software, hardware, and runtime layers, they exhibit inconsistent formats, making structure extraction and pattern discovery extremely challenging. Therefore, robust log parsing and mining is critical to transform this raw telemetry into actionable insights that reveal operational patterns, diagnose anomalies, and enable reliable, efficient, and scalable system analysis. Recent advances in large language models (LLMs) offer a promising new direction for automated log understanding in leadership-class HPC environments. To capitalize on this opportunity, we present a domain-adapted, instruction-following, LLM-driven framework that leverages chain-of-thought (CoT) reasoning to parse and structure HPC logs with high fidelity. Our approach combines domain-specific log-template data with instruction-tuned examples to fine-tune an 8B-parameter LLaMA model tailored for HPC log analysis. We develop a hybrid fine-tuning methodology that adapts a general-purpose LLM to domain-specific log data, enabling privacy-preserving, locally deployable, fast, and energy-efficient log-mining approach. We conduct experiments on a diverse set of log datasets from the LogHub repository. The evaluation confirms that our approach achieves parsing accuracy on par with significantly larger models, such as LLaMA 70B and Anthropic's Claude. We further validate the practical utility of our fine-tuned LLM model by parsing over 600 million production logs from the Frontier supercomputer over a four-week window, uncovering critical patterns in temporal dynamics, node-level anomalies, and workload-error log correlations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
