@InProceedings{yamamoto:astronomical,
  author = {Naotaka Yamamoto and Osama Tatebe and Satoshi Sekiguchi},
  title = {Parallel and distributed astronomical data analysis on grid
  datafarm},
  booktitle = {5th International Workshop on Grid Computing},
  editor = {Buyya, R},
  year = {2004},
  month = {November},
  pages = {461--466},
  institution = {AIST, Grid Technol Res Ctr, Tsukuba Cent 2, Umezono 1-1-1,
  Tsukuba, Ibaraki, Japan; AIST, Grid Technol Res Ctr, Tsukuba, Ibaraki,
  Japan},
  publisher = {IEEE Computer Society Press},
  copyright = {(c)2005 The Thomson Corporation},
  address = {Pittsburgh, PA},
  URL = {http://datafarm.apgrid.org/pdf/Grid2004-yamamoto.pdf},
  keywords = {grid, grid datafarm, astronomical data, pario-app, pario-bib},
  abstract = {A comprehensive study of the whole petabyte-scale archival data
  of astronomical observatories has a possibility of new science and new
  knowledge in the field, while it was not feasible so far due to lack of
  enough data analysis environment. The Grid Datafarm architecture is designed
  for global petabyte-scale data-intensive computing, which provides a Grid
  file system with file replica management for fault tolerance and load
  balancing, and parallel and distributed data computing support for a set of
  files, to meet with the requirements of the comprehensive study of the whole
  archival data. In the paper, we discuss about worldwide parallel and
  distributed data analysis in the observational astronomical field The
  archival data is stored, replicated and dispersed in a Gfarm file system. All
  the astronomical data analysis tools successfully access files in Gfarm file
  system without any code modification, using a syscall hooking library
  regardless of file replica locations. Performance evaluation of the parallel
  data analysis in several ways shows file-affinity process scheduling plays an
  essential role for scalable and efficient parallel file I/O performance. A
  data calibration tools shows scalable file I/O performance, and achieved the
  file I/O performance of 5.9 GB/sec and 4.0 GB/sec for reading and writing
  FITS files, respectively, using 30 cluster nodes (60 CPUs). On-demand file
  replica creation mitigates the overhead of access concentration. Another tool
  shows the performance improvement at a factor of six for reading a shared
  file by creating file replicas.}
}