@InProceedings{zhu:ceft-pvfs,
  author = {Yifeng Zhu and Hong Jiang and Xiao Qin and Dan Feng and David R.
  Swanson},
  title = {Improved Read Performance in a Cost-Effective, Fault-Tolerant
  Parallel Virtual File System {(CEFT-PVFS)}},
  booktitle = {Workshop on Parallel I/O in Cluster Computing and Computational
  Grids},
  year = {2003},
  month = {May},
  pages = {730--735},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo},
  note = {Organized at the IEEE/ACM International Symposium on Cluster
  Computing and the Grid 2003},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190730abs.htm},
  keywords = {parallel I/O, fault-tolerance, read performance, parallel file
  system, PVFS, pario-bib},
  abstract = {Due to the ever-widening performance gap between processors and
  disks, I/O operations tend to become the major performance bottleneck of
  data-intensive applications on modern clusters. If all the existing disks on
  the nodes of a cluster are connected together to establish high performance
  parallel storage systems, the cluster's overall performance can be boosted at
  no additional cost. CEFT-PVFS (a RAID 10 style parallel file system that
  extends the original PVFS), as one such system, divides the cluster nodes
  into two groups, stripes the data across one group in a round-robin fashion,
  and then duplicates the same data to the other group to provide storage
  service of high performance and high reliability. Previous research has shown
  that the system reliability is improved by a factor of more than 40 with
  mirroring while maintaining a comparable write performance. This paper
  presents another benefit of CEFT-PVFS in which the aggregate peak read
  performance can be improved by as much as 100% over that of the original PVFS
  by exploiting the increased parallelism. \par Additionally, when the data
  servers, which typically are also computational nodes in a cluster
  environment, are loaded in an unbalanced way by applications running in the
  cluster, the read performance of PVFS will be degraded significantly. On the
  contrary, in the CEFT-PVFS, a heavily loaded data server can be skipped and
  all the desired data is read from its mirroring node. Thus the performance
  will not be affected unless both the server node and its mirroring node are
  heavily loaded.}
}