Using client-side access partitioning for data clustering in big data applications

Abstract

Big data has been playing a critical role in modern information technology. In some big data management systems, to simplify client design, data requests from clients are even distributed to all nodes and then are routed to the final correct data storage inside the data cluster. After performing analysis on this working mechanism, we point out some design problems and advocate the client-side access partitioning, i.e., clients know precisely which node of the cluster should be accessed for sought information. This approach could provide a fast access. We also implement a first-stage application based on client-side access partitioning for evaluation purpose and the result demonstrates our approach is effective.