@Article{shieh:dsm-pario,
  author = {Ce-Kuen Shieh and Su-Cheong Mac and Jyh-Chang Ueng},
  title = {Improving the performance of distributed shared memory systems via
  parallel file input/output},
  journal = {Journal of systems and software},
  year = {1998},
  month = {December},
  volume = {44},
  number = {1},
  pages = {3--15},
  URL = {http://dx.doi.org/10.1016/S0164-1212(98)10039-0},
  keywords = {distributed shared memory, parallel I/O, file I/O, file system,
  virtual memory, pario-bib},
  comment = {A parallel-I/O scheme for a system using DSM, which has one disk
  per node. The file is initiaally placed on node 0 , Application runs once,
  system then collects informaton about access pattern. The file is
  redistributed across all disks. Application must do all file accesses from
  node 0, but in subsequent runs this causes the block to be read from its disk
  into the local memory of the attached node, and VM-mapped into the correct
  place. Later page faults will move the data to the node needing the data
  first (if the redistribution is done well, that's the same node, so no
  movement is needed). At the end of the program, output data are written to
  the output file, on the local disk. Thus: input files go to node 0 on the
  first run, then are redistributed before second run, and output files are
  created across all nodes but are written only at file close and only to the
  closest disk. Limitations: files must be wholly read during application
  initialization, from node 0. Files must be wholly written out during the
  application completion. Files are immutable. You must have one slow run
  initially. Input files must fit on one disk. I read sections 1-2, then
  skimmed the rest.}
}