Zobraziť v EDS

Enabling Practical Cloud Performance Debugging with Unsupervised Learning

Uložené v:
Podrobná bibliografia
Názov: Enabling Practical Cloud Performance Debugging with Unsupervised Learning
Autori: Yu Gan, Mingyu Liang, Sundar Dev, David Lo, Christina Delimitrou
Zdroj: ACM SIGOPS Operating Systems Review. 56:34-41
Informácie o vydavateľovi: Association for Computing Machinery (ACM), 2022.
Rok vydania: 2022
Predmety: 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, 01 natural sciences
Popis: Cloud applications are increasingly shifting from large monolithic services to complex graphs of loosely-coupled microservices. Despite their benefits, microservices are prone to cascading performance issues, and can lead to prolonged periods of degraded performance. We present Sage, a machine learning-driven root cause analysis system for interactive cloud microservices that is both accurate and practical. We show that Sage correctly identifies the root causes of performance issues across a diverse set of microservices and takes action to address them, leading to more predictable, performant, and efficient cloud systems.
Druh dokumentu: Article
Jazyk: English
ISSN: 0163-5980
DOI: 10.1145/3544497.3544503
Rights: URL: https://www.acm.org/publications/policies/copyright_policy#Background
Prístupové číslo: edsair.doi...........e41d725733c35c26e2b8306aedefe0e4
Databáza: OpenAIRE
Popis
Abstrakt:Cloud applications are increasingly shifting from large monolithic services to complex graphs of loosely-coupled microservices. Despite their benefits, microservices are prone to cascading performance issues, and can lead to prolonged periods of degraded performance. We present Sage, a machine learning-driven root cause analysis system for interactive cloud microservices that is both accurate and practical. We show that Sage correctly identifies the root causes of performance issues across a diverse set of microservices and takes action to address them, leading to more predictable, performant, and efficient cloud systems.
ISSN:01635980
DOI:10.1145/3544497.3544503