Applying backfilling over a non-dedicated cluster

The resource utilization level in open laboratories of several universities has been shown to be very low. Our aim is to take advantage of those idle resources for parallel computation without disturbing the local load. In order to provide a system that lets us execute parallel applications in such...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Hanzich, Mauricio, Giné de Solà, Francesc, Hernández Budé, Porfidio, Solsona Theás, Francesc, Luque Fadón, Emilio
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2005
Materias:
Ciencias Informáticas
Distributed Systems
Scheduling
Space-Sharing,
non-dedicated clusters
backfilling
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23171
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-23171
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Distributed Systems
Scheduling
Space-Sharing,
non-dedicated clusters
backfilling
spellingShingle Ciencias Informáticas
Distributed Systems
Scheduling
Space-Sharing,
non-dedicated clusters
backfilling
Hanzich, Mauricio
Giné de Solà, Francesc
Hernández Budé, Porfidio
Solsona Theás, Francesc
Luque Fadón, Emilio
Applying backfilling over a non-dedicated cluster
topic_facet Ciencias Informáticas
Distributed Systems
Scheduling
Space-Sharing,
non-dedicated clusters
backfilling
description The resource utilization level in open laboratories of several universities has been shown to be very low. Our aim is to take advantage of those idle resources for parallel computation without disturbing the local load. In order to provide a system that lets us execute parallel applications in such a non-dedicated cluster, we use an integral scheduling system that considers both Space and Time sharing concerns. For dealing with the Time Sharing (TS) aspect, we use a technique based on the communication-driven coscheduling principle. This kind of TS system has some implications on the Space Sharing (SS) system, that force us to modify the way job scheduling is traditionally done. In this paper, we analyze the relation between the TS and the SS systems in a non-dedicated cluster. As a consequence of this analysis, we propose a new technique, termed 3DBackfilling. This proposal implements the well known SS technique of backfilling, but applied to an environment with a MultiProgramming Level (MPL) of the parallel applications that is greater than one. Besides, 3DBackfilling considers the requirements of the local workload running on each node. Our proposal was evaluated in a PVM/MPI Linux cluster, and it was compared with several more traditional SS policies applied to non-dedicated environments
format Objeto de conferencia
Objeto de conferencia
author Hanzich, Mauricio
Giné de Solà, Francesc
Hernández Budé, Porfidio
Solsona Theás, Francesc
Luque Fadón, Emilio
author_facet Hanzich, Mauricio
Giné de Solà, Francesc
Hernández Budé, Porfidio
Solsona Theás, Francesc
Luque Fadón, Emilio
author_sort Hanzich, Mauricio
title Applying backfilling over a non-dedicated cluster
title_short Applying backfilling over a non-dedicated cluster
title_full Applying backfilling over a non-dedicated cluster
title_fullStr Applying backfilling over a non-dedicated cluster
title_full_unstemmed Applying backfilling over a non-dedicated cluster
title_sort applying backfilling over a non-dedicated cluster
publishDate 2005
url http://sedici.unlp.edu.ar/handle/10915/23171
work_keys_str_mv AT hanzichmauricio applyingbackfillingoveranondedicatedcluster
AT ginedesolafrancesc applyingbackfillingoveranondedicatedcluster
AT hernandezbudeporfidio applyingbackfillingoveranondedicatedcluster
AT solsonatheasfrancesc applyingbackfillingoveranondedicatedcluster
AT luquefadonemilio applyingbackfillingoveranondedicatedcluster
bdutipo_str Repositorios
_version_ 1764820465732288513

Ejemplares similares