Hierarchical Clustering Strategies for Fault Tolerance in Large Scale HPC Systems

Abstract : Future high performance computing systems will need to use novel techniques to allow scientific applications to progress despite frequent failures. Checkpoint-Restart is currently the most popular way to mitigate the impact of failures during long-running executions. Different techniques try to reduce the cost of Checkpoint-Restart, some of them such as local checkpointing and erasure codes aim to reduce the time to checkpoint while others such as uncoordinated checkpoint and message-logging aim to decrease the cost of recovery. In this paper, we study how to combine all these techniques together in order to optimize both: checkpointing and recovery. We present several clustering and topology challenges that lead us to an optimization problem in a four-dimensional space: reliability level, recovery cost, encoding time and message logging overhead. We propose a novel clustering method inspired from brain topology studies in neuroscience and evaluate it with a Tsunami simulation application in TSUBAME2. Our evaluation with 1024 processes shows that our novel clustering method can guarantee good performance for all of the four mentioned dimensions of our optimization problem.
Type de document :
Communication dans un congrès
IEEE Cluster 2012, 2012, Beijing, China. 〈10.1109/CLUSTER.2012.71〉
Liste complète des métadonnées

Littérature citée [27 références]  Voir  Masquer  Télécharger

Contributeur : Thomas Ropars <>
Soumis le : lundi 2 mars 2015 - 21:49:59
Dernière modification le : mardi 24 avril 2018 - 13:37:43
Document(s) archivé(s) le : dimanche 31 mai 2015 - 11:35:22


Fichiers produits par l'(les) auteur(s)




Leonardo Bautista-Gomez, Thomas Ropars, Naoya Maruyama, Franck Cappello, Satoshi Matsuoka. Hierarchical Clustering Strategies for Fault Tolerance in Large Scale HPC Systems. IEEE Cluster 2012, 2012, Beijing, China. 〈10.1109/CLUSTER.2012.71〉. 〈hal-01121947〉



Consultations de la notice


Téléchargements de fichiers