基于深度学习的微服务故障检测研究

doi:10.3778/j.issn.1002-8331.2012-0553

摘要/Abstract

摘要： 微服务架构是一种新的架构模式，它致力于为用户提供更加可靠、可维护性和可扩展性更好的软件设计服务。它提倡将单一应用程序划分为若干个独立的服务，每个服务功能各异并通过频繁的信息交互来为用户提供最终价值。虽然微服务架构有着诸多优点，但它也为系统的故障检测带来了更多的挑战：（1）由于微服务架构中存在多个服务，定位故障点变得更加困难；（2）一个服务故障可能会引起连锁反应，造成整个系统的崩溃。因此，如何准确地诊断出微服务架构中的故障，并精确地定位出故障发生的位置是提高微服务架构服务质量（quality of service，QoS）的关键。将深度学习方法引入到微服务架构的故障检测研究中，提出了一个基于门控循环单元（gated recurrent unit，GRU）的故障检测模型MS-GRU。该方法的核心在于它能够从以往的应用数据中分析、学习到导致故障发生的模式信息，并将这些信息用于未来的故障诊断和预测中，从而显著改善微服务架构的服务质量。最后进行了广泛的实验来评估所提出方法的性能，实验结果证明了该方法的有效性和优越性。

关键词: 微服务架构, 故障检测, 门控循环单元（GRU）, 注意力机制, 服务质量

Abstract: Micro-service architecture is a new kind of architecture model, which aims to provide users with more reliable, maintainable and scalable software design services. It encourages to divide a large application into several independent micro-services, each of which has different functions, providing users with better services via frequent information interaction. Although micro-service architecture has a lot of advantages, it also brings more challenges to system fault detection：（1）Since micro-service architecture usually consists of multiple micro-services, it is more difficult to locate the fault point；（2）A failure of one micro-service may cause the whole system to crash. Therefore, how to accurately detect and locate the faults in micro-service architecture has become one of the key problems to improve the QoS（quality of service） of micro-service architecture. This paper introduces the deep learning technique into the research of fault detection of micro-service architecture, and proposes a novel fault detection model, termed as MS-GRU, which is based on GRU（gated recurrent unit）. The core idea of MS-GRU is that it can analyze and learn the pattern information that leads to the failure of systems from previous application data, and leverage the learned pattern information to detect and predict potential faults in the future, thus significantly improving the QoS of micro-service architecture. The paper conducts extensive experiments to evaluate the performance of the proposed method. The experimental results demonstrate the effectiveness and superiority of the proposed method.

Key words: micro-service architecture, fault detection, gated recurrent unit（GRU）, attention mechanism, service quality

庄卫金, 张鸿. 基于深度学习的微服务故障检测研究[J]. 计算机工程与应用, 2022, 58(16): 326-332.

ZHUANG Weijin, ZHANG Hong. Research on Micro-Service Fault Detection Based on Deep Learning[J]. Computer Engineering and Applications, 2022, 58(16): 326-332.

参考文献

[1] 洪华军，吴建波，冷文浩.一种基于微服务架构的业务系统设计与实现[J].计算机与数字工程，2018，46（1）：149-154.
HONG H J，WU J B，LENG W H.Business system design and implementation based on microservice architecture[J].Computer & Digital Engineering，2018，46（1）：149-154.
[2] FOWLER M，LEWIS J.Microservices[EB/OL].（2014-03-25）[2020-11-16].http：//martinfowler.com/articles/microservices.html.
[3] 开金宇.面向可靠性的微服务系统自适应调整技术研究[D].上海：上海大学，2016.
KAI J Y.Research on reliable-oriented adapation on micro-
service system[D].Shanghai：Shanghai University，2016.
[4] UHLE J，TR?GER P.On dependability modeling in a deployed microservice architecture[Z].Potsdam：Operating Systems and Middleware Group，2014.
[5] RAUSAND M，BARROS A，HOYLAND A.System reliability theory：models，statistical methods，and applications[M].New York：John Wiley & Sons，2020.
[6] CHO K，VAN MERRI?NBOER B，GULCEHRE C，et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[J].arXiv：1406.1078，2014.
[7] LIPTON Z C，BERKOWITZ J，ELKAN C.A critical review of recurrent neural networks for sequence learning[J].arXiv：1506.00019，2015.
[8] HOCHREITER S，SCHMIDHUBER J.Long short-term memory[J].Neural Computation，1997，9（8）：1735-1780.
[9] CHANDOLA V，BANERJEE A，KUMAR V.Anomaly detection：a survey[J].ACM Computing Surveys，2009，41（3）：1-58.
[10] 王子勇，王焘，张文博，等.一种基于执行轨迹监测的微服务故障诊断方法[J].软件学报，2017，28（6）：1435-1454.
WANG Z Y，WANG T，ZHANG W B，et al.Fault diagnosis for microservices with execution trace monitoring[J].Journal of Software，2017，28（6）：1435-1454.
[11] 徐康明.基于微服务架构的服务发现与服务可靠性的研究[D].北京：北京邮电大学，2018.
XU K M.Research on service discovery and service reliability based on microservices architecture[D].Beijing：Beijing University of Posts and Telecommunications，2018.
[12] MA S P，FAN C Y，CHUANG Y，et al.Using service dependency graph to analyze and test microservices[C]//2018 IEEE 42nd Annual Computer Software and Applications Conference，2018，2：81-86.
[13] 刘一田，刘士进，郭伟，等.柔性微服务监控框架[J].计算机系统应用，2017，26（10）：139-143.
LIU Y T，LIU S J，GUO W，et al.Flexible microservice monitoring framework[J].Computer Systems & Applications，2017，26（10）：139-143.
[14] ONGARO D，OUSTERHOUT J.In search of an understandable consensus algorithm[C]//2014 USENIX Annual Technical Conference，2014：305-319.
[15] CELESTI A，CARNEVALE L，GALLETTA A，et al.A watchdog service making container-based micro-services reliable in IoT clouds[C]//2017 IEEE 5th International Conference on Future Internet of Things and Cloud，2017：372-378.
[16] HEORHIADI V，RAJAGOPALAN S，JAMJOOM H，et al.Gremlin：systematic resilience testing of microservices[C]//2016 IEEE 36th International Conference on Distributed Computing Systems，2016：57-66.
[17] MAYER B，WEINREICH R.A dashboard for microservice monitoring and management[C]//2017 IEEE International Conference on Software Architecture Workshops，2017：66-69.
[18] 彭天舒.微服务架构下基于特征规则的异常检测研究[D].武汉：华中科技大学，2017.
PENG T S.Research of anomaly detection based on feature results for microservice architecture[D].Wuhan：Huazhong University of Science and Technology，2017.
[19] BAHDANAU D，CHO K，BENGIO Y.Neural machine translation by jointly learning to align and translate[J].arXiv：1409.0473，2014.
[20] CASALE G，MI N，SMIRNI E.Model-driven system capacity planning under workload burstiness[J].IEEE Transactions on Computers，2009，59（1）：66-80.
[21] OTTERSTAD C，YARYGINA T.Low-level exploitation mitigation by diverse microservices[C]//6th European Conference on Service-Oriented and Cloud Computing.Cham：Springer，2017：49-56.
[22] ZHOU X，PENG X，XIE T，et al.Fault analysis and debugging of microservice systems：industrial survey，benchmark system，and empirical study[J].IEEE Transactions on Software Engineering，2021，47（2）：243-260.