Scheduling multiple bags of taskson heterogeneous master-worker platforms:centralized versus distributed solutions
نویسندگان
چکیده
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 master-worker platforms where the communication is restricted to a tree embedded in the network. The goal of the scheduling is to obtain the best throughput while enforcing some fairness between applications. We show how to derive an asymptotically optimal periodic schedule by solving a linear program expressing all problem constraints. For single-level trees, the optimal solution can be analytically computed. For large-scale platforms, gathering the global knowledge needed by the linear programming approach might be unrealistic. One solution is to adapt the multi-commodity flow algorithm of Awerbuch and Leighton, but it still requires some global knowledge. Thus, we also investigates heuristic solutions using only local information, and test them via simulations. The best of our heuristics achieves the optimal performance on about two-thirds of our test cases, but is far worse in a few cases. Key-words: Parallel computing, scheduling, divisible load, multiple applications, resource sharing. This text is also available as a research report of the Laboratoire de l’Informatique du Parallélisme http://www.ens-lyon.fr/LIP. Ordonnancement d’applications concurrentes sur plate-forme mâıtre-esclave hétérogène : comparaison des stratégies centralisées et distribuées Résumé : Lorsqu’on exécute plusieurs applications simultanément sur une plate-forme de calcul hétérogène, celles-ci doivent se partager les ressources de calcul (processeurs) et de communication (bande-passante des liens réseau). Dans ce rapport nous nous intéressons à l’ordonnancement efficace et équitable de ces applications sur une plate-forme mâıtre-esclave où les communications sont faites le long d’un arbre inclus dans le réseau. Nous montrons qu’il est possible de calculer un ordonnancement périodique asymptotiquement optimal en utilisant la programmation linéaire. Pour les topologies en étoile (arbre de profondeur 1), nous montrons comment calculer la solution optimale de façon analytique. Pour des plates-formes de grande taille, rassembler l’information globale nécessaire au programme linéaire en un ordonnanceur centralisé peut sembler irréaliste. Une solution est d’adapter l’algorithme des flux concurrents d’Awerbuch et Leighton, mais celui nécessite tout de même quelques informations globales. Nous nous intéressons donc également aux heuristiques n’utilisant que des informations locales, et testons leurs performances par simulation. La meilleure de ces heuristiques atteint les performances optimales dans environ les deux tiers de nos essais, mais peut en être très éloigné dans quelques cas. Mots-clés : Calcul distribué, ordonnancement, tâches divisibles, applications multiples, partage de ressources. Scheduling multiple bags of tasks 3
منابع مشابه
Offline and online scheduling of concurrent bags-of-tasks on heterogeneous platforms
Scheduling problems are already difficult on traditional parallel machines. They become extremely challenging on heterogeneous clusters, even when embarrassingly parallel applications are considered. In this paper we deal with the problem of scheduling multiple applications, made of collections of independent and identical tasks, on a heterogeneous master-worker platform. The applications are s...
متن کاملCoordinator-master-worker model for efficient large scale network simulation
In this work, we propose a coordinator-master-worker (CMW) model for medium to extra-large scale network simulation. The model supports distributed and parallel simulation for a heterogeneous computing node architecture with both multicore CPUs and GPUs. The model aims at maximizing the hardware usage rate while reducing the overall management overhead. In the CMW model, the coordinator is the ...
متن کاملEnergy-aware scheduling of bag-of-tasks applications on master-worker platforms
We consider the problem of scheduling an application composed of independent tasks on a fully heterogeneous master-worker platform with communication costs. We introduce a bi-criteria approach aiming at maximizing the throughput of the application while minimizing the energy consumed by participating resources. Assuming arbitrary superlinear power consumption laws, we investigate different mode...
متن کاملPractical Experiences with Task Scheduling Strategies for Image Processing Application on Heterogeneous Distributed Computing System
Heterogeneous Distributed Computing (HDC) system consists of Workstations (WSs) and Personal Computers (PCs). In HDC system, each WS/PC may have different processor and performance. In order to take advantage of this diversity of processing power of a system, an effective task partitioning, scheduling, and load balancing are needed to get the optimum performance. This paper examines the effecti...
متن کاملAlgorithmic and Scheduling Techniques for Heterogeneous and Distributed Computing
The computing and communication resources of high performance computing systems are becoming heterogeneous, are exhibiting performance fluctuations and are failing in an unforeseeable manner. The Master-Slave (MS) paradigm, that decomposes the computational load into independent tasks, is well-suited for operating in these environments due to its loose synchronization requirements. The applicat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2005