Optimal Resource Allocation for Containerized Cloud Microservices

Abstract

One significant advantage of microservice cloud architectures is the agility with which microservices may be duplicated to enhance overall service quality and satisfy service-level contracts. However, the complex interactions within microservice meshes introduce new challenges in managing shared hardware resources and in identifying critical resource bottlenecks. In this paper, we formulate the efficient resource management of cloud microservice resources as a constrained optimization problem that is amenable to a solution in real time. A novel optimization-based reactive resource manager is implemented on an open-source platform and compared with the academic state of the art and existing cloud-provider solutions. The proposed optimal solution has resulted in an 268% improvement of the overall microservice deployment cost.