Negotiation Strategy of Divisible Tasks for Large Dataset Processing - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Negotiation Strategy of Divisible Tasks for Large Dataset Processing

Résumé

MapReduce is a design pattern for processing large datasets on a cluster. Its performances depend on some data skews and on the runtime environment. In order to tackle these problems, we propose an adaptive multiagent system. The agents interact during the data processing and the dynamic task allocation is the outcome of negotiations. These negotiations aim at improving the workload partition among the nodes within a cluster and so decrease the runtime of the whole process. Moreover, since the negotiations are iterative the system is responsive in case of node performance variations. In this paper, we show how, when a task is divisible, an agent may split it in order to negotiate its subtasks.
Fichier principal
Vignette du fichier
baert17eumas.pdf (537.11 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01900313 , version 1 (21-10-2018)

Identifiants

Citer

Quentin Baert, Anne-Cécile Caron, Maxime Morge, Jean-Christophe Routier. Negotiation Strategy of Divisible Tasks for Large Dataset Processing. 15th European Conference on Multi-Agent Systems, Nov 2017, Évry, France. pp.370-384, ⟨10.1007/978-3-030-01713-2_26⟩. ⟨hal-01900313⟩
78 Consultations
94 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More