Revisiting the double checkpointing algorithm

Abstract : Fast checkpointing algorithms require distributed access to stable storage. This paper revisits the approach base upon double checkpointing, and compares the blocking algorithm of Zheng, Shi and Kalé, with the non-blocking algorithm of Ni, Meneses and Kalé in terms of both performance and risk. We also extend the model that they have proposed to assess the impact of the overhead associated to non-blocking communications. We then provide a new peer-to-peer checkpointing algorithm, called the triple checkpointing algorithm, that can work at constant memory, and achieves both higher efficiency and better risk handling than the double checkpointing algorithm. We provide performance and risk models for all the evaluated protocols, and compare them through comprehensive simulations.
Type de document :
Rapport
[Research Report] RR-8196, 2012
Liste complète des métadonnées

https://hal.inria.fr/hal-00768491
Contributeur : Equipe Roma <>
Soumis le : vendredi 21 décembre 2012 - 16:25:22
Dernière modification le : vendredi 20 avril 2018 - 15:44:27
Document(s) archivé(s) le : dimanche 18 décembre 2016 - 08:10:54

Fichier

RR-8196.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00768491, version 1

Collections

Citation

Jack Dongarra, Thomas Hérault, Yves Robert. Revisiting the double checkpointing algorithm. [Research Report] RR-8196, 2012. 〈hal-00768491〉

Partager

Métriques

Consultations de la notice

239

Téléchargements de fichiers

130