Multi-criteria checkpointing strategies: response-time versus resource utilization

Aurélien Bouteiller 1 Franck Cappello 2, 3, 4, 5 Jack Dongarra 1 Amina Guermouche 6, 7 Thomas Hérault 1 Yves Robert 7, 6
4 GRAND-LARGE - Global parallel and distributed computing
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LIFL - Laboratoire d'Informatique Fondamentale de Lille, LRI - Laboratoire de Recherche en Informatique
6 ROMA - Optimisation des ressources : modèles, algorithmes et ordonnancement
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : Failures are increasingly threatening the efficiency of HPC systems, and current projections of Exascale platforms indicate that rollback recovery, the most convenient method for providing fault tolerance to general-purpose applications, reaches its own limits at such scales. One of the reasons explaining this unnerving situation comes from the focus that has been given to per-application completion time, rather than to platform efficiency. In this paper, we discuss the case of uncoordinated rollback recovery where the idle time spent waiting recovering processors is used to progress a different, independent application from the system batch queue. We then propose an extended model of uncoordinated checkpointing that can discriminate between idle time and wasted computation. We instantiate this model in a simulator to demonstrate that, with this strategy, uncoordinated checkpointing per application completion time is unchanged, while it delivers near-perfect platform efficiency.
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/hal-00926606
Contributor : Equipe Roma <>
Submitted on : Tuesday, January 14, 2014 - 3:17:50 PM
Last modification on : Thursday, August 1, 2019 - 2:12:06 PM
Long-term archiving on : Tuesday, April 15, 2014 - 4:18:47 PM

File

europar13.pdf
Files produced by the author(s)

Identifiers

Citation

Aurélien Bouteiller, Franck Cappello, Jack Dongarra, Amina Guermouche, Thomas Hérault, et al.. Multi-criteria checkpointing strategies: response-time versus resource utilization. Euro-Par 2013, 2013, Aachen, Germany. pp.420-431, ⟨10.1007/978-3-642-40047-6_43⟩. ⟨hal-00926606⟩

Share

Metrics

Record views

951

Files downloads

400