ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

A NOVEL ON FAST PARALLEL FILE TRANSFER USING REPLICATION?

Journal: International Journal of Computer Science and Mobile Computing - IJCSMC (Vol.3, No. 2)

Publication Date:

Authors : ;

Page : 80-85

Keywords : Data replication; data intensive; grid computing; pipelining; replica;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Data replication is the most critical component of data-intensive grid computing environment. The need for data replication arises in various areas of data analysis such as high-energy physics, bio-informatics, climate modeling and astronomy. In addition to grid data environments, data replication is the key part of various data sharing applications such as digital libraries, persistent archival environment and content distribution. Parallel file replication where a large file needs to be simultaneously replicated to multiple sites is an integral part of data-intensive grid environment. Propose a tool that creates multiple distribution trees by pipelining point-to-point transfer and optimizes the file replication time to multiple sites. One of the key parts in data replication is the replica catalog that manages the mappings for files from the hierarchical namespace to one or more physical file locations, thus providing an efficient and transparent file sharing on a Grid. Managing and coordinating the data movement process is the crucial performance issue.

Last modified: 2014-02-07 21:34:25