In addition to the already present heterogeneity in the network service and application ecosystem, new challenges come in the form of emerging applications which require deterministic delay performance characteristics that go beyond traditional SLAs. While hard network slicing with strict isolation is a promising candidate for addressing such requirements, it might be overly restrictive and hard to scale, hence leading to an inefficient use of available resources. In contrast, soft slicing can help balancing isolation and determinism by allowing a configurable degree of resource sharing between slices. In this work, we follow a simulation-driven approach to study and quantify the trade-offs between variable isolation and the degree of delay-related determinism in a single-hop environment with multiple applications. The results from this scenario will serve as a foundation towards assessing the end-to-end problem

Stanislav Lange
Marija Gajić
Thomas Zinner
Jane Frances Pajo
Håkon Lønsethagen
Min Xie
Ricard Vilalta
FIRA '22: Proceedings of the ACM SIGCOMM Workshop on Future of Internet Routing & Addressing