Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

12-2021

Abstract

Microservices-based applications consist of loosely coupled, independently deployable services that encapsulate units of functionality. To implement larger application processes, these microservices must communicate and collaborate. Typically, this follows one of two patterns: (1) choreography, in which communication is done via asynchronous message-passing; or (2) orchestration, in which a controller is used to synchronously manage the process flow. Choosing the right pattern requires the resolution of some trade-offs concerning coupling, chattiness, visibility, and design. To address this problem, we propose a decision framework for microservices collaboration patterns that helps solution architects to crystallize their goals, compare the key factors, and then choose a pattern using a weighted scoring mechanism. In cases where there is no clear preference, a hybrid pattern is suggested which inherits some strengths of both choreography and orchestration. We demonstrate the framework by evaluating the needs of three industry case studies (Danske Bank, LGB Bank, Netflix), showing that it leads to appropriate patterns being suggested. We are not aware of any existing decision frameworks to guide solution architects in choosing a microservices collaboration pattern.

Keywords

microservices, orchestration, choreography, event-based, invocation-based, service-oriented architecture

Discipline

Databases and Information Systems | Software Engineering

Research Areas

Information Systems and Management; Software and Cyber-Physical Systems

Publication

Proceedings of the 25th IEEE International Enterprise Distributed Object Computing Conference (EDOC 2021), Gold Coast, Australia, October 25-29

First Page

134

Last Page

141

Identifier

10.1109/EDOC52215.2021.00024

Publisher

IEEE

City or Country

New York

Share

COinS