IMPROVING THE EFFICIENCY OF AUTOMATION THE SCALING OF MICROSERVICES IN THE KUBERNETES CONTAINERIZED APPLICATION MANAGEMENT SYSTEM

Abstract

Automatic container scaling in Kubernetes plays an important role in handling incoming requests from web application users. This article analyzes the stages of container scaling, their initialization and subsequent software launch. In order to achieve low latency of user requests in the case of dynamic load, the analysis of the process of automatic scaling of containers and the factors that will affect the scaling process was carried out. Having a full understanding of the processes and mechanisms by which scaling takes place, it became possible to develop a method and strategy for cleaning obstacles that slow down the autoscaling process itself and at the same time preserve the necessary properties of the existing scaling. Acceleration of scaling of containers, which will directly affect the speed of web services, becomes possible precisely because of the elimination of the delay in automatic scaling of containers. The work considered scaling optimization using not only container pre-creation networks, but also the use of container images, which enable the sharing of linked libraries in memory and the extension of Kubernetes’ declarative configuration management approach for parallel creation of multiple container instances. Based on the obtained research results, a method for optimizing the automatic scaling of containerized applications by eliminating the delay during a cold start has been developed. This latency manifests itself in the case of microservice autoscaling, where Kubernetes is expected to scale containers horizontally by creating additional replicas to the required number to handle the required traffic from the outside. The delay caused by the autoscaler affects the processing time of the user’s web service requests.