Checkpointing algorithms and fault prediction

Autor:	Aupy, Guillaume, Robert, Yves, Vivien, Frédéric, Zaidouni, Dounia
Rok vydání:	2013
Předmět:	Computer Science - Distributed Parallel and Cluster Computing
Zdroj:	Journal of Parallel and Distributed Computing, Available online 7 November 2013, ISSN 0743-7315
Druh dokumentu:	Working Paper
DOI:	10.1016/j.jpdc.2013.10.010
Popis:	This paper deals with the impact of fault prediction techniques on checkpointing strategies. We extend the classical first-order analysis of Young and Daly in the presence of a fault prediction system, characterized by its recall and its precision. In this framework, we provide an optimal algorithm to decide when to take predictions into account, and we derive the optimal value of the checkpointing period. These results allow to analytically assess the key parameters that impact the performance of fault predictors at very large scale. Comment: Supported in part by ANR Rescue. Published in Journal of Parallel and Distributed Computing. arXiv admin note: text overlap with arXiv:1207.6936
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1302.3752 Zobrazit plný text záznamu View this record from Arxiv