arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.14547cs.DCcs.AI
收藏

面向分布式应用的自定义算子(SDO)

A Self-Defining Operator for Distributed Applications

University of Washington(华盛顿大学)

Shihang Li, Thomas Anderson, Ratul Mahajan, Simon Peter, Luke Zettlemoyer

AI总结:

本研究提出自定义算子(SDO),通过提炼故障经验生成剧本与检测器,仅在检测器触发时调用LLM,在11个开源微服务应用上将复现故障解决时间缩短52%,且成本较低。

摘要:

为了让分布式应用实现高可用运行,算子必须快速诊断并缓解任何故障。基于大语言模型(LLM)的智能体可提供帮助,但与经验丰富的人类算子不同,它们在处理更多故障时不会进步:每次调查都从零开始,即使过去已解决过类似故障,仍会重新推导可能的原因并重新测试假设。我们提出一种自定义算子(SDO),它可通过更新自身的操作行为和记忆随时间进步。当SDO解决一起故障时,会将该经验提炼为两种内容:一是剧本,即针对未来类似故障的可复用诊断指令;二是检测器,即接收应用遥测数据作为输入并输出相关剧本的脚本。SDO会持续运行检测器,仅在检测器触发时调用LLM,因此其令牌成本随故障数量而非操作时间扩展。在11个开源微服务应用上,SDO将复现故障的解决时间缩短了52%,同时保持每起故障的成本较低。SDO为开源项目,访问地址为this https URL。

英文摘要:

To operate distributed applications with high availability, operators must rapidly diagnose and mitigate any incident. LLM-based agents can help, but unlike experienced human operators they do not improve as they handle more incidents. Each investigation starts from scratch, re-deriving likely causes and re-testing hypotheses even when a similar fault was resolved in the past. We present a self-defining operator (SDO) that improves with time by updating its operational behavior and memory. When SDO resolves an incident, it distills that experience into playbooks, which describe reusable diagnostic instructions for future incidents with similar faults, and detectors, scripts that take application telemetry as input and output relevant playbook(s). SDO continuously runs the detectors and invokes LLMs only when one fires, so its token cost scales with incident count rather than with operational time. Across 11 open-source microservice applications, SDO cuts resolution time by 52% on recurring faults while keeping per-incident cost low. SDO is open source at https://github.com/self-defining-systems/sdo.

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。

↑