Distributed Self-Adjusting Tree Networks

Bruna Peres, Otavio Augusto de Oliveira Souza, Olga Goussevskaya, Chen Avin, Stefan Schmid

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

The performance of many data-centric cloud applications critically depends on the performance of the underlying datacenter network. Reconfigurable optical technologies have recently introduced a novel opportunity to improve datacenter network performance, by allowing to dynamically adjust the network topology according to the demand. However, the vision of self-adjusting networks raises the fundamental question how such networks can be efficiently operated in a scalable and distributed manner. This paper presents DiSplayNet, the first fully distributed self-adjusting network. DiSplayNet relies on algorithms that perform decentralized and concurrent topological adjustments to account for changes in the demand. We propose two natural metrics to evaluate the performance of distributed self-adjusting networks, the amortized work (the cost of routing on and adjusting the network) and the makespan (the time it takes to serve a set of communication requests). We present a rigorous formal analysis of the work and makespan of DiSplayNet, which can be seen as an interesting generalization of analyses known from sequential self-adjusting datastructures. We complement our theoretical contribution with an extensive trace-driven simulation study, shedding light on the opportunities and limitations of leveraging spatial and temporal locality and concurrency in self-adjusting networks.

Original languageEnglish
JournalIEEE Transactions on Cloud Computing
DOIs
StateAccepted/In press - 1 Jan 2021

Keywords

  • Cloud computing
  • Costs
  • Network topology
  • Optical switches
  • Peer-to-peer computing
  • Routing
  • Self-adjusting networks
  • Topology
  • amortized analysis
  • concurrency
  • datacenters
  • decentralization
  • trace-driven simulations

ASJC Scopus subject areas

  • Software
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Distributed Self-Adjusting Tree Networks'. Together they form a unique fingerprint.

Cite this