The Impact of Data Replicatino on Job Scheduling Performance in Hierarchical data Grid - Computer Science > Distributed, Parallel, and Cluster ComputingReportar como inadecuado




The Impact of Data Replicatino on Job Scheduling Performance in Hierarchical data Grid - Computer Science > Distributed, Parallel, and Cluster Computing - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Abstract: In data-intensive applications data transfer is a primary cause of jobexecution delay. Data access time depends on bandwidth. The major bottleneck tosupporting fast data access in Grids is the high latencies of Wide AreaNetworks and Internet. Effective scheduling can reduce the amount of datatransferred across the internet by dispatching a job to where the needed dataare present. Another solution is to use a data replication mechanism. Objectiveof dynamic replica strategies is reducing file access time which leads toreducing job runtime. In this paper we develop a job scheduling policy and adynamic data replication strategy, called HRS Hierarchical ReplicationStrategy, to improve the data access efficiencies. We study our approach andevaluate it through simulation. The results show that our algorithm hasimproved 12% over the current strategies.



Autor: Somayeh Abdi, Hossein Pedram, Somayeh Mohamadi

Fuente: https://arxiv.org/







Documentos relacionados