Enhanced cluster computing performance through proportional fairness

Abstract : The performance of cluster computing depends on how concurrent jobs share multiple data center resource types like CPU, RAM and disk storage. Recent research has discussed efficiency and fairness requirements and identified a number of desirable scheduling objectives including so-called dominant resource fairness (DRF). We argue here that proportional fairness (PF), long recognized as a desirable objective in sharing network bandwidth between ongoing flows, is preferable to DRF. The superiority of PF is manifest under the realistic modelling assumption that the population of jobs in progress is a stochastic process. In random traffic the strategy-proof property of DRF proves unimportant while PF is shown by analysis and simulation to offer a significantly better efficiency-fairness tradeoff.
Type de document :
Article dans une revue
Performance Evaluation, Elsevier, 2014, 79, pp.134 - 145. 〈10.1016/j.peva.2014.07.009〉
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal-imt.archives-ouvertes.fr/hal-01112964
Contributeur : Thomas Bonald <>
Soumis le : mercredi 4 février 2015 - 08:49:16
Dernière modification le : jeudi 9 février 2017 - 15:18:54
Document(s) archivé(s) le : mercredi 27 mai 2015 - 16:36:35

Fichier

1404.2266.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Thomas Bonald, James Roberts. Enhanced cluster computing performance through proportional fairness. Performance Evaluation, Elsevier, 2014, 79, pp.134 - 145. 〈10.1016/j.peva.2014.07.009〉. 〈hal-01112964〉

Partager

Métriques

Consultations de
la notice

269

Téléchargements du document

217