$v\text{TNT}$: Unikernels for Efficient and Flexible Internet Probing
Maxime Letemple, Gaulthier Gain, Sami Ben Mariem, Laurent Mathy, Benoît Donnet · 2024
Over the past two decades, network measurement infrastructures have witnessed significant development and widespread adoption. Internet measurement platforms have become common and have demonstrated their relevance in Internet understanding and security observation. However, despite their popularity, those platforms lack of flexibility and reactivity, as they are usually used for longitudinal measurements. Consequently, critical security and Internet-related events may evade detection. Concurrently, the evolution of operating systems towards virtual machines (VMs) has been notable, particularly with the emergence of unikernels—ultra-lightweight VMs tailored for specific applications by including only the essential components. This paper advocates for the integration of unikernels into measurement infrastructures to enhance their flexibility and efficiency. We introduce$v\mathbf{TNT}$, a proof-of-concept unikernel-based implementation of TNT, a traceroute extension capable of discovering MPLS tunnels. This paper documents the full toolchain for porting TNT into a unikernel and evaluates$v\mathbf{TNT}^{\prime}\mathbf{s}$performance in comparison to conventional methodologies. Additionally, we explore a practical use case scenario demonstrating the utility of$v\mathbf{TNT}$. The source code for$v\mathbf{TNT}$is publicly available on Gitlab.