一句话：通过大规模实证研究KQL查询使用，并基于大语言模型提出Xpert查询推荐，提升云系统事故管理效率。
大规模云系统在现代IT基础设施中至关重要，但系统内事故会造成服务中断并损害用户体验。为快速解决事故，值班工程师需编写领域特定语言（DSL）查询来分析遥测数据，但编写这些查询既困难又耗时。本文对Microsoft大规模云管理系统中用于事故管理的KQL（一种DSL）查询使用情况开展实证研究，分析其使用模式与痛点。基于该研究，本文提出Xpert，利用大语言模型进行KQL查询推荐，以辅助事故管理。研究发现凸显了KQL查询推荐的重要性和可行性。
Large-scale cloud systems play a pivotal role in modern IT infrastructure. However, incidents occurring within these systems can lead to service disruptions and adversely affect user experience. To swiftly resolve such incidents, on-call engineers depend on crafting domain-specific language (DSL) queries to analyze telemetry data. However, writing these queries can be challenging and time-consuming. This paper presents a thorough empirical study on the utilization of queries of KQL, a DSL employed for incident management in a large-scale cloud management system at Microsoft. The findings obtained underscore the importance and viability of KQL queries recommendation to enhance incident management.
@inproceedings{paperbot11292,
title = {Xpert: Empowering Incident Management with Query Recommendations via Large Language Models},
author = {Yuxuan Jiang and Chaoyun Zhang and Shilin He and Zhihao Yang and Minghua Ma and Si Qin and Yu Kang and Yingnong Dang and Saravan Rajmohan and Qingwei Lin and Dongmei Zhang},
booktitle = {ICSE},
year = {2024},
doi = {10.1145/3597503.3639081}
}