A Dynamic Adjustment Strategy for File Transformation in Data Grids

Abstract

Abstract. In this paper, we propose a dynamic file transfer scheme with coallocation architecture, called Dynamic Adjustment Strategy, a dynamic file transfer scheme with co-allocation architecture that reduce the file transfer times and improves the performance in Data Grid environments. Our approach reduces the idle time faster servers spend waiting for the slowest server, and decreases file transfer completion time. We also present a new toolkit, called Cyber-Transformer, with a friendly graphical user interface interface running on the client side that makes it easy for inexperienced users to manage replicas and download the files in Data Grid environments. We also provide an effective scheme for reducing the cost of reassembling data blocks.

File replication, maintenance, and consistency management services in data grids

“…If an attempt is made to replicate the same file to a third site in the same region, BHR will see that there is already a duplicate file in the region and terminate. Thus, files will have at most two copies in each region, which means only two links will be available for parallel data downloading [1,2,[30][31][32][33][34] in any one region. This limitation leads to high time costs, thus reducing the effectiveness of an important grid computing feature and adversely affecting overall performance.…”

“…However, data grid technologies, developed to solve these kinds of problems, offer an effective alternative means of utilizing largescale computing power and storage capacities to compute and store data. Grids [11,12,20,21,27,[29][30][31][32][33][34] enable sharing of computing power and storage capacities geographically distributed around the world such that they work together as tremendous virtual computers [1,2] on experiments and simulations. The Globus Toolkit [13,27] is open-source software for building data grid environments.…”

Implementation of a dynamic adjustment strategy for parallel file transfer in co-allocation data grids

“…In our previous work [24,26], we proposed a replica selection cost model and a replica selection service to perform replica selection. These co-allocation strategies do not address the shortcoming of faster servers having to wait for the slowest server to deliver its final block.…”

“…• P BW i : percentage of bandwidth available from server i to client (user node); current bandwidth divided by highest theoretical bandwidth [23,24,26].…”

“…Several co-allocation strategies were presented in our previous work [25][26][27]. An idle-time drawback remains since faster servers must wait for the slowest server to deliver its final block.…”