Performance Diagnosis in Cloud Microservices using Deep Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Performance Diagnosis in Cloud Microservices using Deep Learning

Abstract

Microservice architectures are increasingly adopted to design large-scale applications. However, the highly distributed nature and complex dependencies of microservices complicate automatic performance diagnosis and make it challenging to guarantee service level agreements (SLAs). In particular, identifying the culprits of a microservice performance issue is extremely difficult as the set of potential root causes is large and issues can manifest themselves in complex ways. This paper presents an application-agnostic system to locate the culprits for mi-croservice performance degradation with fine granularity, including not only the anomalous service from which the performance issue originates but also the culprit metrics that correlate to the service abnormality. Our method first finds potential culprit services by constructing a service dependency graph and next applies an autoencoder to identify abnormal service metrics based on a ranked list of reconstruction errors. Our experimental evaluation based on injection of performance anomalies to a microservice benchmark deployed in the cloud shows that our system achieves a good diagnosis result, with 92% precision in locating culprit service and 85.5% precision in locating culprit metrics.
Fichier principal
Vignette du fichier
main.pdf (431.55 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02948735 , version 1 (25-09-2020)

Identifiers

  • HAL Id : hal-02948735 , version 1

Cite

Li Wu, Jasmin Bogatinovski, Sasho Nedelkoski, Johan Tordsson, Odej Kao. Performance Diagnosis in Cloud Microservices using Deep Learning. AIOPS 2020 - International Workshop on Artificial Intelligence for IT Operations, Dec 2020, Dubai, United Arab Emirates. ⟨hal-02948735⟩
424 View
1457 Download

Share

Gmail Mastodon Facebook X LinkedIn More