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 2408.11428cs.SE
收藏

将现有容器工作负载迁移到 Kubernetes——基于 LLM 的方法与评估

Migrating Existing Container Workload to Kubernetes -- LLM Based Approach and Evaluation

Masaru Ueno, Tetsuya Uchiumi

AI总结:

本研究提出一种基于 Compose 规范的基准测试方法,评估 LLM 生成 Kubernetes 清单的有效性,发现其能弥补简单规范差距,但常省略内联注释且对非典型输入完成准确率低。

摘要:

尽管 Kubernetes 已成为一种广泛使用的开源系统,可自动化管理容器化应用程序,但其复杂性可能构成重大障碍,尤其是对于不熟悉它的应用程序开发人员。一种方法是利用大型语言模型(LLMs)帮助开发人员生成 Kubernetes 清单;然而,目前无法确定输出是否满足给定规范且易于理解。在本研究中,我们提出了一种基准测试方法,用于评估 LLMs 在合成清单方面的有效性,该方法以 Compose 规范(应用程序开发人员广泛采用的标准)作为输入。所提出的基准测试方法表明,LLMs 通常能产生准确的结果,弥补了简单规范中的差距。然而,我们也观察到,为了提高可读性而添加的内联注释经常被省略,并且对于意图不明确的非典型输入,完成准确率较低。

英文摘要:

Although Kubernetes has become a widespread open-source system that automates the management of containerized applications, its complexity can be a significant barrier, particularly for application developers unfamiliar with it. One approach employs large language models (LLMs) to assist developers in generating Kubernetes manifests; however it is currently impossible to determine whether the output satisfies given specifications and is comprehensible. In this study, we proposed a benchmarking method for evaluating the effectiveness of LLMs in synthesizing manifests, using the Compose specification -- a standard widely adopted by application developers -- as input. The proposed benchmarking method revealed that LLMs generally produce accurate results that compensate for simple specification gaps. However, we also observed that inline comments for readability were often omitted, and completion accuracy was low for atypical inputs with unclear intentions.

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。

↑