Centralized Versus Distributed Schedulers for Multiple Bag-of-Tasks Applications

Olivier Beaumont 1, 2 Larry Carter 3 Jeanne Ferrante 3 Arnaud Legrand 4 Loris Marchal 5, 6 Yves Robert 7
2 CEPAGE - Algorithmics for computationally intensive applications over wide scale distributed platforms
Université Sciences et Technologies - Bordeaux 1, Inria Bordeaux - Sud-Ouest, École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB), CNRS - Centre National de la Recherche Scientifique : UMR5800
4 MESCAL - Middleware efficiently scalable
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
5 GRAAL - Algorithms and Scheduling for Distributed Heterogeneous Platforms
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
7 REMAP - Regularity and massive parallel computing
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : Multiple applications that execute concurrently on heterogeneous platforms compete for CPU and network resources. In this paper we consider the problem of scheduling applications to ensure fair and efficient execution on a distributed network of processors. We limit our study to the case where communication is restricted to a tree embedded in the network, and the applications consist of a large number of independent tasks (Bags of Tasks) that originate at the tree\'s root. The tasks of a given application all have the same computation and communication requirements, but these requirements can vary for different applications. The goal of scheduling is to maximize throughput of each application while ensuring a fair sharing of resources between applications. We can find the optimal asymptotic rates by solving a linear programming problem that expresses all necessary problem constraints, and we show how to construct a periodic schedule from any linear program solution. For single-level trees, the solution is characterized by processing tasks with larger communication-to-computation ratios at children with larger bandwidths. For multi-level trees, this approach requires global knowledge of all application and platform parameters. For large-scale platforms, such global coordination by a centralized scheduler may be unrealistic. Thus, we also investigate decentralized schedulers that use only local information at each participating resource. We assess their performance via simulation, and compare to an optimal centralized solution obtained via linear programming. The best of our decentralized heuristics achieves the same performance on about two-thirds of our test cases, but is far worse in a few cases. While our results are based on simple assumptions and do not explore all parameters (such as the maximum number of tasks that can be held on a node), they provide insight into the important question of fairly and optimally scheduling heterogeneous applications on heterogeneous grids.
Type de document :
Article dans une revue
IEEE Transactions on Parallel and Distributed Systems, Institute of Electrical and Electronics Engineers, 2008, 19, pp.698―709. <10.1109/TPDS.2007.70747>
Liste complète des métadonnées

https://hal.inria.fr/hal-00789424
Contributeur : Arnaud Legrand <>
Soumis le : lundi 18 février 2013 - 11:49:54
Dernière modification le : mercredi 14 décembre 2016 - 01:08:44

Identifiants

Collections

Citation

Olivier Beaumont, Larry Carter, Jeanne Ferrante, Arnaud Legrand, Loris Marchal, et al.. Centralized Versus Distributed Schedulers for Multiple Bag-of-Tasks Applications. IEEE Transactions on Parallel and Distributed Systems, Institute of Electrical and Electronics Engineers, 2008, 19, pp.698―709. <10.1109/TPDS.2007.70747>. <hal-00789424>

Partager

Métriques

Consultations de la notice

235