You don't need a Microservices Architecture (yet): Monoliths may do the trick

Abstract

Within the past decade, the advent of cloud computing in terms of infrastructure, technology stacks, availability of services and tooling, along with the gradual improvement of its market environment, has driven many organizations to either consider or migrate many existing software systems to the cloud, either fully or partially. A common predicament in most cases, is the existence of a complex, monolithic application, potentially considered legacy at the time, that was not designed to be cloud-native and therefore requires a degree of redesign/reimplementation in order to benefit from cloud deployment. In such cases, the decomposition of the monolith to a set of loosely coupled, highly cohesive and self-contained microservices is a valid recommendation, provided that the organization is prepared to withstand the additional cost, in terms of human and financial resources, along with the unavoidable development overhead, which is inevitable during the early stages. However, the tendency of the tech world to embrace new trends and jump on hype trains for fear of obsoletion, has led to an excessive adoption of the microservices architecture (MSA), even in cases where such an architecture is not viable for the organization, or does not derive from any business requirements. This research focuses on establishing the position of a traditional monolith in the modern software architecture landscape and determine use cases that can still benefit from this paradigm, as well as use cases that could benefit from a partial or full transition to microservices architectures instead. © 2021 ACM.