Service distribution estimation for microservices using Markovian arrival processes

File Description SizeFormat 
QEST2021_CR.pdfFile embargoed until 18 August 20222.39 MBAdobe PDF    Request a copy
Title: Service distribution estimation for microservices using Markovian arrival processes
Authors: Runan, W
Casale, G
Filieri, A
Item Type: Conference Paper
Abstract: Building performance models for microservices applications in DevOps is costly and error-prone. Accurate service demand distribution estimation is critical to performance model parameterization. However, traditional service demand estimation methods focus on capturing the mean service demand, disregarding higher-order moments of the distribution. To address this limitation, we propose to estimate higher moments of the service demand distribution for a microservice from monitoring traces. We first generate a closed queueing model to abstract a microservice and model the departure process at the queue node as a Markovian arrival process. This allows formulating the estimation of service demand as an optimization problem, which aims to find the optimal parameters of the first multiple moments of the service demand distribution based on the inter-departure times. We then estimate the service demand distribution with a novel maximum likelihood algorithm, and heuristics to mitigate the computational cost of the optimization process for scalability. We apply our method to real traces from a microservice-based application and demonstrate that its estimations lead to greater prediction accuracy than exponential distributions assumed in traditional service demand estimation approaches
Issue Date: 19-Aug-2021
Date of Acceptance: 8-Jun-2021
URI: http://hdl.handle.net/10044/1/90636
DOI: 10.1007/978-3-030-85172-9_17
ISSN: 0302-9743
Publisher: Springer Verlag
Start Page: 310
End Page: 328
Journal / Book Title: Lecture Notes in Computer Science
Volume: 12846
Copyright Statement: © 2021 Springer Nature Switzerland AG. The final publication is available at Springer via https://link.springer.com/chapter/10.1007/978-3-030-85172-9_17
Sponsor/Funder: Commission of the European Communities
Funder's Grant Number: 825040
Conference Name: QEST 2021
Keywords: Science & Technology
Technology
Physical Sciences
Computer Science, Theory & Methods
Operations Research & Management Science
Mathematics, Applied
Computer Science
Mathematics
Service demand distribution
Markovian arrival process
Maximum likelihood estimation
Queueing models
Performance
MODELS
Artificial Intelligence & Image Processing
Publication Status: Published
Start Date: 2021-08-23
Finish Date: 2021-08-27
Conference Place: Paris, France
Embargo Date: 2022-08-18
Online Publication Date: 2021-08-19
Appears in Collections:Computing
Faculty of Engineering