An Investigation on Software-Defined Networks’ Reactive Routing against BitTorrent - Archive ouverte HAL Access content directly
Journal Articles IET Networks Year : 2015

An Investigation on Software-Defined Networks’ Reactive Routing against BitTorrent

(1) , (2) , (2) , (1)
1
2

Abstract

Technologies in Software-Defined Networks (SDNs) introduce program-matic ways to reorganize the network logical topology. A possible practical usage of SDNs is Reactive Routing, where the logical topology is continuously evolving based on traffic statistics and policies. Usually, the SDNs controllers are considered transparent to the higher layers. It is expected that changes in logical topology may not affect applications. Our goal is to study the impact of logical topology changes on BitTorrent, a popular peer-to-peer protocol in practice. In this paper, we focus on BitTorrent and the experimental results show that BitTorrent may produce the opposite effect to the one expected. We have run 32 BitTorrent clients in an emulated SDN ring topology and changed the virtual topology periodically by removing one link at the time from the ring. The experiments produced lower propagation when logical topology changed periodically than when it was static for BitTorrent traffic. For comparison, we recreated the same experiments using HTTP. For HTTP, we obtained slower propagation when logical topology changed than when it was static. We discuss the results and conclude that high layer protocols need to be carefully studied, and in some cases adapted, before being deployed in SDNs.
Fichier principal
Vignette du fichier
journal-BT-SDN(1).pdf (622.1 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01274250 , version 1 (15-02-2016)
hal-01274250 , version 2 (15-02-2016)

Identifiers

Cite

Damián Vicino, Chung-Horng Lung, Gabriel Wainer, Olivier Dalle. An Investigation on Software-Defined Networks’ Reactive Routing against BitTorrent. IET Networks, 2015, 4 (5), pp.249-254. ⟨10.1049/iet-net.2014.0105⟩. ⟨hal-01274250v2⟩
283 View
420 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More