Distributed scheduling and data sharing in late-binding overlays

Pull-based late-binding overlays are used in some of today’s largest computational grids. Job agents are submitted to resources with the duty of retrieving real workload from a central queue at runtime. This helps overcome the problems of these very complex environments, namely, heterogeneity, impre...

Descripción completa

Detalles Bibliográficos
Autores: Huedo Cuesta, Eduardo, Delgado Peris, Antonio, Hernández, José M.
Tipo de recurso: artículo
Fecha de publicación:2014
País:España
Institución:Universidad Complutense de Madrid (UCM)
Repositorio:Docta Complutense
Idioma:inglés
OAI Identifier:oai:docta.ucm.es:20.500.14352/35470
Acceso en línea:https://hdl.handle.net/20.500.14352/35470
Access Level:acceso abierto
Palabra clave:004.42
004.7
Grid and Cluster Computing
Scalable Computing
Peer-to-Peer Architectures and Networks
Reliable Parallel and Distributed Algorithms
Programación de ordenadores (Informática)
Redes
1203.23 Lenguajes de Programación
Descripción
Sumario:Pull-based late-binding overlays are used in some of today’s largest computational grids. Job agents are submitted to resources with the duty of retrieving real workload from a central queue at runtime. This helps overcome the problems of these very complex environments, namely, heterogeneity, imprecise status information and relatively high failure rates. In addition, the late job assignment allows dynamic adaptation to changes in the grid conditions or user priorities. However, as the scale grows, the central assignment queue may become a bottleneck for the whole system. This article presents a distributed scheduling architecture for late-binding overlays, which addresses these scalability issues. Our system lets execution nodes build a distributed hash table and delegates job matching and assignment to them. This reduces the load on the central server and makes the system much more scalable and robust. Moreover, scalability makes fine-grained scheduling possible, and enables new functionalities like the implementation of a distributed data cache on the execution nodes, which helps alleviate the commonly congested grid storage services.