@TechReport{bordawekar:exemplar-tr2,
  author = {Rajesh Bordawekar},
  title = {Quantitative Characterization and Analysis of the {I/O} Behavior of
  a Commercial Distributed-shared-memory Machine},
  year = {1998},
  month = {March},
  number = {CACR 157},
  institution = {Center of Advanced Computing Research, California Insititute
  of Technology},
  later = {bordawekar:exemplar},
  URL = {http://www.cacr.caltech.edu/~rajesh/exemplar1.html},
  keywords = {parallel I/O, pario-bib, workload characterization, distributed
  shared memory},
  abstract = {This paper presents a unified evaluation of the I/O behavior of a
  commercial clustered DSM machine, the HP Exemplar. Our study has the
  following objectives: (1) To evaluate the impact of different interacting
  system components, namely, architecture, operating system, and programming
  model, on the overall I/O behavior and identify possible performance
  bottlenecks and (2) To provide hints to the users for achieving high
  out-of-box I/O throughput. We find that for the DSM machines that are built
  as a cluster of SMP nodes, integrated clustering of computing and I/O
  resources, both hardware and software, is not advantageous for two reasons.
  First, within an SMP node, the I/O bandwidth is often restricted by the
  performance of the peripheral components and cannot match the memory
  bandwidth. Second, since the I/O resources are shared as a global resource,
  the file-access costs become non-uniform and the I/O behavior of the entire
  system, in terms of the scalability and balance, degrades. We observe that
  the buffered I/O performance is determined not only by the I/O subsystem, but
  also by the programming model, global-shared memory subsystem, and
  data-communication mechanism. Moreover, programming-model support can be
  effectively used to overcome the performance constraints created by the
  architecture and operating system. For example, on the HP Exemplar, users can
  achieve high I/O throughput by using features of the programming model that
  balance the sharing and locality of the user buffers and file systems.
  Finally, we believe that at present, the I/O subsystems are being designed in
  isolation and there is a need for mending the traditional memory-oriented
  design approach to address this problem.}
}