Fast and scalable simulation of volunteer computing systems using SimGrid

Bruno Donassolo 1 Henri Casanova 2 Arnaud Legrand 3, 4 Pedro Velho 3
1 UFRGS - Instituto de Informática da UFRGS
2 ICS - Information and Computer Sciences [Hawaii]
3 MESCAL - Middleware efficiently scalable
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
4 LIG - Laboratoire d'Informatique de Grenoble
Abstract : Advances in internetworking technology and the decreasing cost-performance ratio of commodity computing components have enabled Volunteer Computing (VC). VC platforms aggregate tens or hundreds of thousands of hosts. These hosts are typically volatile, which raises di cult research questions. Most research in this area relies on simulation. The main issue when developing VC simulators is scalability: How to perform simulations of large-scale VC platforms with reasonable amounts of memory and reasonably fast? To achieve scalability, state-of-the-art VC simulators employ simplistic simulation models and/or target on narrow platform and application scenarios. In this paper we enable VC simulations using the general-purpose SimGrid simulation framework, which provides signi cantly more realistic and exible simulation capabilities than the aforementioned simulators. Our key contribution is a set of improvements to SimGrid so that it brings these bene ts to VC simulations while achieving good scalability.
Document type :
Conference papers
Complete list of metadatas
https://hal.inria.fr/hal-00690629
Contributor : Ist Rennes <>
Submitted on : Tuesday, April 24, 2012 - 9:27:13 AM
Last modification on : Friday, August 2, 2019 - 2:58:45 AM

Identifiers

Collections

INRIA | LIG | GRID5000 | UGA

Citation

Bruno Donassolo, Henri Casanova, Arnaud Legrand, Pedro Velho. Fast and scalable simulation of volunteer computing systems using SimGrid. LSAP 2010 : 2nd Workshop on Large-Scale System and Application Performance, Jun 2010, Chicago, Illinois, United States. pp.605-612, ⟨10.1145/1851476.1851565⟩. ⟨hal-00690629⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

524

Contact


archive-ouverte@inria.fr