@InProceedings{zhu:case-study,
  author = {Y. F. Zhu and H. Jiang and X. Qin and D. Swanson},
  title = {A case study of parallel I/O for biological sequence search on Linux
  clusters},
  booktitle = {Proceedings of the IEEE International Conference on Cluster
  Computing},
  year = {2003},
  month = {December},
  pages = {308--315},
  institution = {Univ Nebraska, Dept Comp Sci \& Engn, Lincoln, NE 68588 USA},
  publisher = {IEEE Computer Society Press},
  copyright = {(c)2004 Institute for Scientific Information, Inc.},
  address = {Hong Kong, China},
  keywords = {BLAST, CEFT-PVFS, parallel I/O, PVFS, application,
  characterization, I/O access patterns, biology application, pario-app,
  pario-bib},
  abstract = {In this paper we analyze the I/O access patterns of a widely-used
  biological sequence search tool and implement two variations that employ
  parallel-I/O for data access based on PVFS (Parallel Virtual File System) and
  CEFT-PVFS (Cost-Effective Fault-Tolerant PVFS). Experiments show that the two
  variations outperform the original tool when equal or even fewer storage
  devices are used in the former. It is also found that although the
  performance of the two variations improves consistently when initially
  increasing the number of servers, this performance gain from parallel I/O
  becomes insignificant with further increase in server number. We examine the
  effectiveness of two read performance optimization techniques in CEFT-PVFS by
  using this tool as a benchmark. Performance results indicate: (1) Doubling
  the degree of parallelism boosts the read performance to approach that of
  PVFS; (2) Skipping hotspots can substantially improve the I/O performance
  when the load on data servers is highly imbalanced. The I/O resource
  contention due to the sharing of server nodes by multiple applications in a
  cluster has been shown to degrade the performance of the original tool and
  the variation based on PVFS by up to 10 and 21 folds, respectively; whereas,
  the variation based on CEFT-PVFS only suffered a two-fold performance
  degradation.}
}