Performance evaluation of VPN solutions in multi-region kubernetes cluster

Abstract: Containerization is widely recognized as a form of lightweight virtualization in the cloud. Due to its reliability, maturity, and rich capabilities, kubernetes has established itself as the de-facto standard for deployments and maintenance of containers. The availability of a kubernetes cluster for a cloud-native application would depend on the availability of the zone or region where the nodes are running. In general, the kubernetes cluster is deployed in a single shared network, but for higher availability, the nodes of the kubernetes cluster can be deployed in multiple regions. Deploying a multi-region kubernetes cluster aids in providing high availability for the service, allowing the data to be located closer to users, even when they are dispersed globally. However, with greater benefits come greater challenges, and networking in multi-region kubernetes clusters has proven to be a complex issue. Usually, kubernetes in a multi-region environment can be achieved by using tunneling across the worker nodes that are located in multiple regions and by using the VPN protocols as an overlay network. In this thesis, I investigated the performance of different VPN solutions in a multi-region kubernetes cluster and examine how these VPN solutions support kubernetes deployment. A literature review is conducted to identify the most common factors influencing VPN performance and to gather information on the differences between VPN solutions. I compared the response times of the multi-region Kubernetes cluster deployed with VPN solutions to the response times of the single shared region Kubernetes cluster also deployed with VPN solutions. This comparison allowed me to evaluate the performance of the VPN solution in a multi-region Kubernetes cluster. The aim of this thesis is to present the most influential factors, an overview of proposed VPN solutions, and performance comparisons of different VPN solutions in a multi-region kubernetes cluster.