@Article{gropp:io-redundancy,
  author = {William D. Gropp and Robert Ross and Neill Miller},
  title = {Providing efficient {I/O} redundancy in {MPI} environments},
  journal = {Lecture Notes in Computer Science},
  booktitle = {11th European Parallel Virtural Machine and Message Passing
  Interface Users Group Meeting; September 19-22, 2004; Budapest, HUNGARY},
  editor = {Kranzlmuller, D; Kacsuk, P; Dongarra, J},
  year = {2004},
  month = {November},
  volume = {3241},
  pages = {77--86},
  institution = {Argonne Natl Lab, Div Math \& Comp Sci, 9700 S Cass Ave,
  Argonne, IL 60439 USA; Argonne Natl Lab, Div Math \& Comp Sci, Argonne, IL
  60439 USA},
  publisher = {Springer-Verlag Heidelberg},
  copyright = {(c)2004 Institute for Scientific Information, Inc.},
  URL = {http://www.springerlink.com/link.asp?id=wxx7xg3hb3xftx8b},
  keywords = {fault-tolerance, single-disk failures, MPI-IO, pario-bib},
  abstract = {Highly parallel applications often use either highly parallel
  file systems or large numbers of independent disks. Either approach can
  provide the high data rates necessary for parallel applications. However, the
  failure of a single disk or server can render the data useless. Conventional
  techniques, such as those based on applying erasure correcting codes to each
  file write, are prohibitively expensive for massively parallel scientific
  applications because of the granularity of access at which the codes are
  applied. In this paper we demonstrate a scalable method for recovering from
  single disk failures that is optimized for typical scientific data sets. This
  approach exploits coarser-grained (but precise) semantics to reduce the
  overhead of constructing recovery data and makes use of parallel computation
  (proportional to the data size and independent of number of processors) to
  construct data. Experiments are presented showing the efficiency of this
  approach on a cluster with independent disks, and a technique is described
  for hiding the creation of redundant data within the MPI-IO implementation.}
}