@Article{allcock:grid,
  author = {Bill Allcock and Joe Bester and John Bresnahan and Ann L. Chervenak
  and Ian Foster and Carl Kesselman and Sam Meder and Veronika Nefedova and
  Darcy Quesnel and Steven Tuecke},
  title = {Data management and transfer in high-performance computational grid
  environments},
  journal = {Parallel Computing},
  year = {2002},
  month = {May},
  volume = {28},
  number = {5},
  pages = {749--771},
  publisher = {Elsevier Science},
  URL = {http://www.elsevier.com/gej-ng/10/35/21/60/57/31/abstract.html},
  keywords = {computational grid, data transfer, network, I/O, pario-bib},
  abstract = {An emerging class of data-intensive applications involve the
  geographically dispersed extraction of complex scientific information from
  very large collections of measured or computed data. Such applications arise,
  for example, in experimental physics, where the data in question is generated
  by accelerators, and in simulation science, where the data is generated by
  supercomputers. So-called Data Grids provide essential infrastructure for
  such applications, much as the Internet provides essential services for
  applications such as e-mail and the Web. We describe here two services that
  we believe are fundamental to any Data Grid: reliable, high-speed transport
  and replica management. Our high-speed transport service, GridFTP, extends
  the popular FTP protocol with new features required for Data Grid
  applications, such as striping and partial file access. Our replica
  management service integrates a replica catalog with GridFTP transfers to
  provide for the creation, registration, location, and management of dataset
  replicas. We present the design of both services and also preliminary
  performance results. Our implementations exploit security and other services
  provided by the Globus Toolkit.}
}