CISNE-P: a portable and integral approach for scheduling parallel jobs on non-dedicated clusters

In this work, we present an integral scheduling system for non-dedicated clusters, termed CISNE-P, which ensures the performance required by the local applications, while simultaneously allocating cluster resources to parallel jobs. Our approach solves the problem efficiently by using a social contr...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Torchinsky, Matías, Hanzich, Mauricio, Giné de Solà, Francesc, Solsona Theás, Francesc, Lérida, Josep L., Hernández Budé, Porfidio, Luque Fadón, Emilio
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2006
Materias:
Ciencias Informáticas
Scheduling
planificación en espacio y tiempo compartido
coplanificación
contrato social
space and time sharing scheduling
coscheduling
social contract
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/22754
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-22754
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
Scheduling
planificación en espacio y tiempo compartido
coplanificación
contrato social
space and time sharing scheduling
coscheduling
social contract
spellingShingle Ciencias Informáticas
Scheduling
planificación en espacio y tiempo compartido
coplanificación
contrato social
space and time sharing scheduling
coscheduling
social contract
Torchinsky, Matías
Hanzich, Mauricio
Giné de Solà, Francesc
Solsona Theás, Francesc
Lérida, Josep L.
Hernández Budé, Porfidio
Luque Fadón, Emilio
CISNE-P: a portable and integral approach for scheduling parallel jobs on non-dedicated clusters
topic_facet Ciencias Informáticas
Scheduling
planificación en espacio y tiempo compartido
coplanificación
contrato social
space and time sharing scheduling
coscheduling
social contract
description In this work, we present an integral scheduling system for non-dedicated clusters, termed CISNE-P, which ensures the performance required by the local applications, while simultaneously allocating cluster resources to parallel jobs. Our approach solves the problem efficiently by using a social contract technique. This kind of technique is based on reserving computational resources, preserving a predetermined response time to local users. CISNE-P is a middleware which includes both a previously developed space-sharing job scheduler and a dynamic coscheduling system, a time sharing scheduling component. The experimentation performed in a Linux cluster shows that these two scheduler components are complementary and a good coordination improves global performance significantly. We also compare two different CISNE-P implementations: one developed inside the kernel, and the other entirely implemented in the user space
format Objeto de conferencia
Objeto de conferencia
author Torchinsky, Matías
Hanzich, Mauricio
Giné de Solà, Francesc
Solsona Theás, Francesc
Lérida, Josep L.
Hernández Budé, Porfidio
Luque Fadón, Emilio
author_facet Torchinsky, Matías
Hanzich, Mauricio
Giné de Solà, Francesc
Solsona Theás, Francesc
Lérida, Josep L.
Hernández Budé, Porfidio
Luque Fadón, Emilio
author_sort Torchinsky, Matías
title CISNE-P: a portable and integral approach for scheduling parallel jobs on non-dedicated clusters
title_short CISNE-P: a portable and integral approach for scheduling parallel jobs on non-dedicated clusters
title_full CISNE-P: a portable and integral approach for scheduling parallel jobs on non-dedicated clusters
title_fullStr CISNE-P: a portable and integral approach for scheduling parallel jobs on non-dedicated clusters
title_full_unstemmed CISNE-P: a portable and integral approach for scheduling parallel jobs on non-dedicated clusters
title_sort cisne-p: a portable and integral approach for scheduling parallel jobs on non-dedicated clusters
publishDate 2006
url http://sedici.unlp.edu.ar/handle/10915/22754
work_keys_str_mv AT torchinskymatias cisnepaportableandintegralapproachforschedulingparalleljobsonnondedicatedclusters
AT hanzichmauricio cisnepaportableandintegralapproachforschedulingparalleljobsonnondedicatedclusters
AT ginedesolafrancesc cisnepaportableandintegralapproachforschedulingparalleljobsonnondedicatedclusters
AT solsonatheasfrancesc cisnepaportableandintegralapproachforschedulingparalleljobsonnondedicatedclusters
AT leridajosepl cisnepaportableandintegralapproachforschedulingparalleljobsonnondedicatedclusters
AT hernandezbudeporfidio cisnepaportableandintegralapproachforschedulingparalleljobsonnondedicatedclusters
AT luquefadonemilio cisnepaportableandintegralapproachforschedulingparalleljobsonnondedicatedclusters
bdutipo_str Repositorios
_version_ 1764820467651182596

Ejemplares similares