Ferhat Khendek

Leila Abdollahi Vayghan, Mohamed Aymen Saied, Maria Toeroe et al.

The architectural style of microservices has been gaining popularity in recent years. In this architectural style, small and loosely coupled modules are deployed and scaled independently to compose cloud-native applications. Carrier-grade service providers are migrating their legacy applications to a microservice based architecture running on Kubernetes which is an open source platform for orchestrating containerized microservice based applications. However, in this migration, service availability remains a concern. Service availability is measured as the percentage of time the service is provisioned. High Availability (HA) is achieved when the service is available at least 99.999% of the time. In this paper, we identify possible architectures for deploying stateful microservice based applications with Kubernetes and evaluate Kubernetes from the perspective of availability it provides for its managed applications. The results of our experiments show that the repair actions of Kubernetes cannot satisfy HA requirements, and in some cases cannot guarantee service recovery. Therefore, we propose an HA State Controller which integrates with Kubernetes and allows for application state replication and automatic service redirection to the healthy microservice instances by enabling service recovery in addition to the repair actions of Kubernetes. Based on experiments we evaluate our solution and compare the different architectures from the perspective of availability and scaling overhead. The results of our investigations show that our solution can improve the recovery time of stateful microservice based applications by 50%.

Leila Abdollahi Vayghan, Mohamed Aymen Saied, Maria Toeroe et al.

The move towards the microservice based architecture is well underway. In this architectural style, small and loosely coupled modules are developed, deployed, and scaled independently to compose cloud-native applications. However, for carrier-grade service providers to migrate to the microservices architectural style, availability remains a concern. Kubernetes is an open source platform that defines a set of building blocks which collectively provide mechanisms for deploying, maintaining, scaling, and healing containerized microservices. Thus, Kubernetes hides the complexity of microservice orchestration while managing their availability. In a preliminary work we evaluated Kubernetes, using its default configuration, from the availability perspective in a private cloud settings. In this paper, we investigate more architectures and conduct more experiments to evaluate the availability that Kubernetes delivers for its managed microservices. We present different architectures for public and private clouds. We evaluate the availability achievable through the healing capability of Kubernetes. We investigate the impact of adding redundancy on the availability of microservice based applications. We conduct experiments under the default configuration of Kubernetes as well as under its most responsive one. We also perform a comparative evaluation with the Availability Management Framework (AMF), which is a proven solution as a middleware service for managing high-availability. The results of our investigations show that in certain cases, the service outage for applications managed with Kubernetes is significantly high.

Sadaf Mustafiz, Omar Hassane, Guillaume Dupont et al.

The Network Functions Virtualization (NFV) advent is making way for the rapid deployment of network services (NS) for telecoms. Automation of network service management is one of the main challenges currently faced by the NFV community. Explicitly defining a process for the design, deployment, and management of network services and automating it is therefore highly desirable and beneficial for NFV systems. The use of model-driven orchestration means has been advocated in this context. As part of this effort to support automated process execution, we propose a process enactment approach with NFV systems as the target application domain. Our process enactment approach is megamodel-based. An integrated process modelling and enactment environment, MAPLE, has been built into Papyrus for this purpose. Process modelling is carried out with UML activity diagrams. The enactment environment transforms the process model to a model transformation chain, and then orchestrates it with the use of megamodels. In this paper we present our approach and environment MAPLE, its recent extension with new features as well as application to an enriched case study consisting of NS design and onboarding process.