CISNE-P: a global scheduling oriented to NOW environments

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

Detalles Bibliográficos
Autores: Torchinsky, Matias, Hanzich, Mauricio, Hernández Budé, Porfidio, Luque, Emilio, Giné, Francesc, Solsona Tehàs, Francesc, Lérida Monsó, Josep Lluís
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2007
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10459.1/41500
Acceso en línea:http://hdl.handle.net/10459.1/41500
Access Level:acceso abierto
Palabra clave:Space and time sharing scheduling
Coscheduling
Social contract
Processament en paral·lel (Ordinadors)
Processament distribuït de dades
Cluster, Anàlisi de
Descripción
Sumario: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.