FAIL-MPI: How fault-tolerant is fault-tolerant MPI ? - Inria - Institut national de recherche en sciences et technologies du numérique
Rapport (Rapport De Recherche) Année : 2006

FAIL-MPI: How fault-tolerant is fault-tolerant MPI ?

Résumé

One of the topics of paramount importance in the development of Cluster and Grid middleware is the impact of faults since their occurrence probability in a Grid infrastructure and in large-scale distributed system is actually very high. MPI (Message Passing Interface) is a popular abstraction for programming distributed computation applications. FAIL is an abstract language for fault occurrence description capable of expressing complex and realistic fault scenarios. In this paper, we investigate the possibility of using FAIL to inject faults in a fault-tolerant MPI implementation. Our middleware, FAIL-MPI, is used to carry quantitative and qualitative faults and stress testing.
Fichier principal
Vignette du fichier
LRI1450.pdf (158.65 Ko) Télécharger le fichier

Dates et versions

inria-00078183 , version 1 (03-06-2006)

Identifiants

  • HAL Id : inria-00078183 , version 1

Citer

Thomas Herault, William Hoarau, Pierre Lemarinier, Eric Rodriguez, Sébastien Tixeuil. FAIL-MPI: How fault-tolerant is fault-tolerant MPI ?. [Research Report] 1450, 2006, pp.26. ⟨inria-00078183⟩
454 Consultations
268 Téléchargements

Partager

More