@InProceedings{kotz:workload,
  author = {David Kotz and Nils Nieuwejaar},
  title = {Dynamic File-Access Characteristics of a Production Parallel
  Scientific Workload},
  booktitle = {Proceedings of Supercomputing '94},
  year = {1994},
  month = {November},
  pages = {640--649},
  publisher = {IEEE Computer Society Press},
  copyright = {IEEE},
  address = {Washington, DC},
  earlier = {kotz:workload-tr},
  later = {kotz:jworkload},
  URL = {http://www.cs.dartmouth.edu/~dfk/papers/kotz:workload.ps.gz},
  URLpdf = {http://www.cs.dartmouth.edu/~dfk/papers/kotz:workload.pdf},
  keywords = {parallel file system, file access pattern, multiprocessor file
  system workload, parallel I/O, pario-bib, dfk},
  abstract = {Multiprocessors have permitted astounding increases in
  computational performance, but many cannot meet the intense I/O requirements
  of some scientific applications. An important component of any solution to
  this I/O bottleneck is a parallel file system that can provide high-bandwidth
  access to tremendous amounts of data {\em in parallel\/} to hundreds or
  thousands of processors. \par Most successful systems are based on a solid
  understanding of the characteristics of the expected workload, but until now
  there have been no comprehensive workload characterizations of multiprocessor
  file systems. We began the CHARISMA project in an attempt to fill that gap.
  We instrumented the common node library on the iPSC/860 at NASA Ames to
  record all file-related activity over a two-week period. Our instrumentation
  is different from previous efforts in that it collects information about
  every read and write request and about the {\em mix\/} of jobs running in the
  machine (rather than from selected applications). \par The trace analysis in
  this paper leads to many recommendations for designers of multiprocessor file
  systems. First, the file system should support simultaneous access to many
  different files by many jobs. Second, it should expect to see many small
  requests, predominantly sequential and regular access patterns (although of a
  different form than in uniprocessors), little or no concurrent file-sharing
  between jobs, significant byte- and block-sharing between processes within
  jobs, and strong interprocess locality. Third, our trace-driven simulations
  showed that these characteristics led to great success in caching, both at
  the compute nodes and at the I/O~nodes. Finally, we recommend supporting
  strided I/O requests in the file-system interface, to reduce overhead and
  allow more performance optimization by the file system.},
  comment = {Also at
  http://www.acm.org/pubs/citations/proceedings/supercomputing/198354/p640-kotz
  and http://computer.org/conferen/sc94/kotz.html}
}