Distributed Self-Adjusting Tree Networks

Distributed Self-Adjusting Tree Networks

Abstract

We consider the problem of designing dynamic network topologies that self-adjust to the (possibly changing) traffic pattern they serve. Such demand-aware networks currently receive much attention, especially in the context of datacenters, due to emerging technologies supporting the fast reconfiguration of the physical topology. We present the first fully distributed, provably efficient self-adjusting network. Our network called DiSplayNet relies on algorithms that perform decentralized and concurrent topological adjustments to account for changes in the demand. We present a rigorous formal analysis of the correctness and performance of DiSplayNet, which can be seen as an interesting generalization of analyses known from sequential self-adjusting datastructures. We also report on results from extensive trace-driven simulations.

Grafik Top
Authors
  • Peres, Bruna
  • de Oliveira Souza, Otavio Augusto
  • Goussevskaia, Olga
  • Avin, Chen
  • Schmid, Stefan
Grafik Top
Supplemental Material
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings (Paper)
Event Title
39th IEEE International Conference on Computer Communications (INFOCOM)
Divisions
Communication Technologies
Subjects
Theoretische Informatik
Rechnerperipherie, Datenkommunikationshardware
Event Location
Paris, France
Event Type
Conference
Event Dates
29 Apr - 02 May 2019
Date
April 2019
Export
Grafik Top