一句话：基于大规模云系统实证，刻画节点故障预测中的缺失数据问题，并评估插值方法，发现节点维度与深度学习插值更优。
云系统依赖海量计算节点，节点故障是导致停机的主要原因之一。已有工作通过采集监控指标并构建模型来提前预测节点故障，但基于微软大规模真实云系统的经验，作者发现缺失数据严重阻碍该任务：缺失量巨大，在线最新数据尤为严重，从而限制实时预测性能。本文首先刻画节点故障预测中的缺失数据问题，然后系统评估多种现有数据插值方法。结果表明，节点维度插值优于时间维度插值，而深度学习插值最适合早期预测。这些发现可帮助学术界和工程师处理云节点故障预测及其他数据驱动软件工程场景中的缺失数据问题。
Cloud computing systems have become increasingly popular in recent years. A typical cloud system utilizes millions of computing nodes as the basic infrastructure. Node failure has been identified as one of the most prevalent causes of cloud system downtime. To improve the reliability of cloud systems, many previous studies collected monitoring metrics from nodes and built models to predict node failures before the failures happen. However, based on our experience with large-scale real-world cloud systems in Microsoft, we find that the task of predicting node failure is severely hampered by missing data. There is a large amount of missing data, and the online latest data utilized for prediction is even worse. As a result, the real-time performance of the node prediction model is limited. In this paper, we first characterize the missing data problem for node failure prediction. Then, we evaluate several existing data interpolation approaches, and find that node dimension interpolation approaches outperform time dimension ones and deep learning based interpolation is the best for early prediction. Our findings can help academics and engineers address the missing data problem in cloud node failure prediction and other data-driven software engineering scenarios.
DOI 原文 ·
@inproceedings{paperbot7092,
title = {An empirical investigation of missing data handling in cloud node failure prediction},
author = {Minghua Ma and Yudong Liu and Yuang Tong and Haozhe Li and Pu Zhao and Yong Xu and Hongyu Zhang and Shilin He and Lu Wang and Yingnong Dang and Saravanakumar Rajmohan and Qingwei Lin},
booktitle = {FSE},
year = {2022},
doi = {10.1145/3540250.3558946}
}