Placement strategies in data grids

摘要

The recent years have witnessed an explosive growth of data in many fields like scientific experiments and engineering applications. In this context, data grids have emerged as a useful technology for managing large amounts of distributed data. Data replication in data grids, which consists in creating multiple copies (aka replicas) of the same file in several storage resources, is an efficient technique that aims to improve response time, reduce the bandwidth consumption and maintain reliability. In this regard, where to place replicas over grid sites has a great impact on the overall grid performance and must be done carefully given some chosen criteria to be satisfied. The present work focuses in details on the utility of placement strategies on the grid performance with respect to several criteria and target goals. We also highlight a synergy between the placement techniques used in data grids and those relied on in other domains, like marketing and electricity.