A Backward-Compatible Protocol for Inter-routing over Heterogeneous Overlay Networks - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

A Backward-Compatible Protocol for Inter-routing over Heterogeneous Overlay Networks

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

Abstract

Overlay networks are logical networks running on the highest level of the OSI stack: they are applicative networks used by millions of users everyday. In many scenarios, it would be desirable for peers belonging to overlays running different protocols to communicate with each other and exchange certain information. However, due to differences in their respective protocols, this communication is often difficult or even impossible to be achieved efficiently, even if the overlays are sharing common objectives and functionalities. In this paper, we address this problem by presenting a new overlay protocol, called OGP (Overlay Gateway Protocol), allowing different existing networks to route messages between each other in a backward-compatible fashion, by making use of specialized peers joined together into a super-overlay. Experimental results on a large scale Grid5000 infrastructure show that having only a small number of nodes running the OGP protocol is sufficient for achieving efficient routing between heterogeneous overlay networks.
Fichier principal
Vignette du fichier
2013-sac-short-13.pdf (109.06 Ko) Télécharger le fichier
Vignette du fichier
2013-sac-poster-13.pdf (431.04 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00906835 , version 1 (13-05-2015)

Identifiers

Cite

Giang Ngo Hoang, Luigi Liquori, Vincenzo Ciancaglini, Petar Maksimovic, Hung Nguyen Chan. A Backward-Compatible Protocol for Inter-routing over Heterogeneous Overlay Networks. 28th Annual ACM Symposium on Applied Computing, SAC 13, Coimbra, Portugal, ACM press, 2013., Mar 2013, coimbra, Portugal. pp.649-651, ⟨10.1145/2480362.2480485⟩. ⟨hal-00906835⟩

Collections

INRIA INRIA2
100 View
150 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More