用大模型自动分析海量日志，300小时人力节省，每月省1.5万刀。
Scalable and Efficient Large-Scale Log Analysis with LLMs: An IT Software Support Case Study
- 用大模型处理日志，自动生成问题诊断和摘要。
- 在CPU上高效运行大模型，处理2000+工单仅需极短时间。
- 已上线70个产品线，每月节省1.5万美元人力成本。
IT环境通常配备日志机制以监控系统健康状况并检测问题。然而，生成的日志量巨大，手动检查不现实，凸显了自动化日志分析在IT软件支持中的重要性。本文提出一种基于大语言模型（LLMs）的日志分析工具，用于日志数据处理与问题诊断，实现自动化洞察与摘要生成。我们还提出一种在CPU上高效运行LLMs的新方法，能在不牺牲输出质量的前提下，快速处理大规模日志。该工具自2024年3月起在生产环境部署，覆盖70个软件产品，已处理超过2000个工单，相比传统方法节省300+人时，每月可减少约15,444美元的人力成本。
原文摘要 · Abstract (English)
IT environments typically have logging mechanisms to monitor system health and detect issues. However, the huge volume of generated logs makes manual inspection impractical, highlighting the importance of automated log analysis in IT Software Support. In this paper, we propose a log analytics tool that leverages Large Language Models (LLMs) for log data processing and issue diagnosis, enabling the generation of automated insights and summaries. We further present a novel approach for efficiently running LLMs on CPUs to process massive log volumes in minimal time without compromising output quality. We share the insights and lessons learned from deployment of the tool - in production since March 2024 - scaled across 70 software products, processing over 2000 tickets for issue diagnosis, achieving a time savings of 300+ man hours and an estimated $15,444 per month in manpower costs compared to the traditional log analysis practices.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。