RESIN: A Holistic Service for Dealing with Memory Leaks in Production Cloud Infrastructure
RESIN: A Holistic Service for Dealing with Memory Leaks in Production Cloud Infrastructure
复制标题
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Chang Lou;Congwei Chen;Peng Huang;Yingnong Dang;Si Qin;Xinsheng Yang;Xukun Li;Qingwei Lin;Murali Chintalapati;Microsoft Azure
中科院分区：
文献类型：
--
作者：
Chang Lou;Congwei Chen;Peng Huang;Yingnong Dang;Si Qin;Xinsheng Yang;Xukun Li;Qingwei Lin;Murali Chintalapati;Microsoft Azure
内存泄漏是一个臭名昭著的问题。尽管付出了巨大的努力，解决大型生产云系统中的内存泄漏问题仍然具有挑战性。现有的解决方案会产生高开销和/或高度不准确。本文介绍了RESIN，这是一种旨在全面解决生产云基础设施中内存泄漏问题的解决方案。 R ESIN 采用分而治之的方法来应对挑战。它首先使用强大的基于分桶化的枢轴方案执行低开销检测，以识别可疑的泄漏实体。然后，它会在适当的时间点在仔细采样的泄漏实体中获取实时堆快照。 R ESIN 分析收集的快照以进行泄漏诊断。最后，R ESIN 自动缓解检测到的泄漏。 R ESIN 已在 Microsoft Azure 的生产环境中运行了 3 年。平均每月报告24张泄漏单，准确率高，开销低，并提供有效的诊断报告。其结果意味着内存不足导致的虚拟机重启次数减少了 41 倍。
Memory leak is a notorious issue. Despite the extensive efforts, addressing memory leaks in large production cloud systems remains challenging. Existing solutions incur high overhead and/or suffer from high inaccuracies. This paper presents R ESIN , a solution designed to holistically address memory leaks in production cloud infrastructure. R ESIN takes a divide-and-conquer approach to tackle the challenges. It performs a low-overhead detection first with a robust bucketization-based pivot scheme to identify suspicious leaking entities. It then takes live heap snapshots at appropriate time points in carefully sampled leak entities. R ESIN analyzes the collected snapshots for leak diagnosis. Finally, R ESIN automatically mitigates detected leaks. R ESIN has been running in production in Microsoft Azure for 3 years. It reports on average 24 leak tickets each month with high accuracy and low overhead, and provides effective diagnosis reports. Its results translate into a 41 × reduction of VM reboots caused by low memory.