Does migrating a monolithic system to microservices decrease the technical debt

Abstract Background: The migration from a monolithic system to microservices requires a deep refactoring of the system. Therefore, such a migration usually has a big economic impact and companies tend to postpone several activities during this process, mainly to speed up the migration itself, but also because of the demand for releasing new features. Objective: We monitored the technical debt of an SME while it migrated from a legacy monolithic system to an ecosystem of microservices. Our goal was to analyze changes in the code technical debt before and after the migration to microservices. Method: We conducted a case study analyzing more than four years of the history of a twelve-year-old project (280K Lines of Code) where two teams extracted five business processes from the monolithic system as microservices. For the study, we first analyzed the technical debt with SonarQube and then performed a qualitative study with company members to understand the perceived quality of the system and the motivation for possibly postponed activities. Results: The migration to microservices helped to reduce the technical debt in the long run. Despite an initial spike in the technical debt due to the development of the new microservice, after a relatively short period of time the technical debt tended to grow slower than in the monolithic system.