No abstract

Abstract-FLOSS distributions like RedHat and Ubuntu require a lot more complex infrastructures than most other FLOSS projects. In the case of community-driven distributions like Debian, the development of such an infrastructure is often not very organized, leading to new data sources being added in an impromptu manner while hackers set up new services that gain acceptance in the community. Mixing and matching data is then harder than should be, albeit being badly needed for Quality Assurance and data mining. Massive refactoring and integration is not a viable solution either, due to the constraints imposed by the bazaar development model.

Today's emerging needs (Internet of Things applications, Network Function Virtualization services, Mobile Edge computing, etc.) are challenging the classic approach of deploying a few large data centers to provide cloud services. A massively distributed Cloud-Edge architecture could better fit the requirements and constraints of these new trends by deploying on-demand infrastructure services in Point-of-Presences within backbone networks. A key feature in this context is the establishment of connectivity among several virtual infrastructure managers in charge of operating, each one, a subset of the infrastructure. After explaining the networking challenges related to distributed Cloud-Edge infrastructures, this article surveys and analyzes the characteristics and limitations of existing technologies in the field of Software Defined Network that could be used to provide the inter-site connectivity feature. This survey is concluded by discussing some research directions.

In the context of experimental research, testbeds play an important role in enabling reproducibility of experiments, by providing a set of services that help experiments with setting up the experimental environment, and collecting data about it. This paper explores the status of three different testbeds (Chameleon, CloudLab and Grid'5000) regarding features required for, or related to reproducible research, and discusses some open questions on that topic.

Container-based virtualization technologies such as LXC or Docker have gained a lot of interest recently, especially in the HPC context where they could help to address a number of long-running issues. Even if they have proven to perform better than full-fledged, hypervisorbased, virtualization solutions, there are still a lot of questions about the use of container solutions in the HPC context. This paper evaluates the performance of Linux-based container solutions that rely on cgroups and namespaces using the NAS parallel benchmarks, in various configurations. We show that containers technology has matured over the years, and that performance issues are being solved.