Simulating Grid Schedulers with Deadlines and Co-Allocation
نویسندگان
چکیده
One of the true challenges in resource management in grids is to provide support for co-allocation, that is, the allocation of resources in multiples autonomous subsystems of a grid to single jobs. With reservation-based local schedulers, a grid scheduler can reserve processors with these schedulers to achieve simultaneous processor availability. However, with queuing-based local schedulers, it is much more difficult to guarantee this. In this paper we present mechanisms and policies for working around the lack of reservation mechanisms for jobs with deadlines that require co-allocation, and simulations of these mechanisms and policies. Key-words: Grid, Scheduling, Simulation This text is also available as a research report of the Laboratoire de l’Informatique du Parallélisme http://www.ens-lyon.fr/LIP. Simulation d’ordonnancement sur la Grille avec deadlines et co-allocations Résumé : Un des véritables défis pour la gestion des ressources dans les environnements de type grilles est de fournir un support pour la co-allocation. La co-allocation est l’allocation des ressources dans des sous-systèmes autonomes et différents pour des tâches uniques. Aves des ordonnanceurs locaux à base de réservation, un ordonnanceur de grille peut faire appel à ces derniers pour réserver des processeurs afin d’utiliser efficacement les processeurs disponibles. Cependant, avec des ordonnanceurs locaux à base de système batch, il est beaucoup plus difficile de garantir une utilisation efficace des processeurs. Dans cet article nous proposons des mécanismes et des politiques pour palier au manque de mécanismes de réservation avec une date limite que requiert la co-allocation. Nous avons réalisé des simulations afin de valider ces mécanismes. Mots-clés : Grille, Ordonnancement, Simulation Simulating Grid Schedulers with Deadlines and Co-Allocation 3
منابع مشابه
Characterization of Bandwidth-aware Meta-schedulers for Co-allocating Jobs in a Mini-grid∗
In this paper, we present a bandwidth-centric job communication model that captures the interaction and impact of simultaneously co-allocated jobs in a grid. We compare our dynamic model with previous research that utilizes a fixed execution time penalty for co-allocated jobs. We explore the interaction of simultaneously co-allocated jobs and the contention they often create in the network infr...
متن کاملUsing BeoSim to Evaluate Bandwidth-aware Meta-schedulers for Co-allocating Jobs in a Mini-grid∗
Clusters of commodity processors have become fixtures in research laboratories around the world. Collections of several co-located clusters exist in many larger laboratories, universities, and research parks. This co-location of several resource collections naturally lends itself to the formation of a mini-grid. A mini-grid is distinguished from a traditional computational grid in that the mini...
متن کاملResource Allocation in Grid Computing: An Economic Model
Grid scheduling, that is, the allocation of distributed computational resources to user applications, is one of the most challenging and complex task in Grid computing. The problem of allocating resources in Grid scheduling requires the definition of a model that allows local and external schedulers to communicate in order to achieve an efficient management of the resources themselves. To this ...
متن کاملLocal versus Global Schedulers with Processor Co-allocation in Multicluster Systems
In systems consisting of multiple clusters of processors which employ space sharing for scheduling jobs, such as our Distributed ASCI1 Supercomputer (DAS), coallocation, i.e., the simultaneous allocation of processors to single jobs in different clusters, may be required. We study the performance of co-allocation by means of simulations for the mean response time of jobs depending on a set of s...
متن کاملComputational Experiments for Scheduling Workflow Applications in Grid Environment
The problem of scheduling workflow applications in a grid environment is considered. The problem is divided into two stages: (i) resource allocation, which consists in allocating distributed grid resources to tasks of a workflow in such a way that the resource demands of each task are satisfied, and (ii) scheduling performed by local grid schedulers. Grid resources are divided into computationa...
متن کامل