Checkpointing algorithms and fault prediction

Guillaume Aupy (1, 2) , Yves Robert (1, 2) , Frédéric Vivien (1, 2) , Dounia Zaidouni (1, 2)

1 LIP - Laboratoire de l'Informatique du Parallélisme
2 ROMA - Optimisation des ressources : modèles, algorithmes et ordonnancement

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 optimal algorithms to decide whether and when to take predictions into account, and we derive the optimal value of the checkpointing period. These results allow us to analytically assess the key parameters that impact the performance of fault predictors at very large scale.

Mots clés: Algorithms; Checkpoint; Prediction; Fault-tolerance; Resilience; Exascale

Domaines: Calcul parallèle, distribué et partagé [cs.DC]; Performance et fiabilité [cs.PF]

Guillaume Aupy, Yves Robert, Frédéric Vivien, Dounia Zaidouni. Checkpointing algorithms and fault prediction. Journal of Parallel and Distributed Computing, 2013, 74 (2), pp.2048-2064. ⟨10.1016/j.jpdc.2013.10.010⟩. ⟨hal-00908446⟩