@InProceedings{crandall:iochar,
  author = {Phyllis E. Crandall and Ruth A. Aydt and Andrew A. Chien and Daniel
  A. Reed},
  title = {Input/Output Characteristics of Scalable Parallel Applications},
  booktitle = {Proceedings of Supercomputing '95},
  year = {1995},
  month = {December},
  publisher = {IEEE Computer Society Press},
  address = {San Diego, CA},
  URL = {http://doi.acm.org/10.1145/224170.224396},
  keywords = {file access pattern, file system workload, workload
  characterization, parallel I/O, pario-bib},
  abstract = {Rapid increases in computing and communication performance are
  exacerbating the long-standing problem of performance-limited input/output.
  Indeed, for many otherwise scalable parallel applications, input/output is
  emerging as a major performance bottleneck. The design of scalable
  input/output systems depends critically on the input/output requirements and
  access patterns for this emerging class of large-scale parallel applications.
  However, hard data on the behavior of such applications is only now becoming
  available. In this paper, we describe the input/output requirements of three
  scalable parallel applications (electron scattering, terrain rendering, and
  quantum chemistry) on the Intel Paragon XP/S. As part of an ongoing parallel
  input/output characterization effort, we used instrumented versions of the
  application codes to capture and analyze input/output volume, request size
  distributions, and temporal request structure. Because complete traces of
  individual application input/output requests were captured, in-depth,
  off-line analyses were possible. In addition, we conducted informal
  interviews of the application developers to understand the relation between
  the codes' current and desired input/output structure. The results of our
  studies show a wide variety of temporal and spatial access patterns,
  including highly read-intensive and write-intensive phases, extremely large
  and extremely small request sizes, and both sequential and highly irregular
  access patterns. We conclude with a discussion of the broad spectrum of
  access patterns and their profound implications for parallel file caching and
  prefetching schemes.},
  comment = {They use the Pablo instrumentation and analysis tools to
  instrument three scalable applications that use heavy I/O: electron
  scattering, terrain rendering, and quantum chemistry. They look at the volume
  of data moved, the timing of I/O, and the periodic nature of I/O. They do a
  little bit with the access patterns of data within each file. They found a
  HUGE variation in request sizes, amount of I/O, number of files, and so
  forth. Their primary conclusion is thus that file systems should be adaptable
  to different access patterns, preferably under control of the application.
  Note proceedings only available on CD-ROM or WWW.}
}