@PhdThesis{holland:thesis,
  author = {Mark Holland},
  title = {On-Line Data Reconstruction in Redundant Disk Arrays},
  year = {1994},
  month = {April},
  school = {Carnegie Mellon University},
  URL =
  {http://www.cs.cmu.edu/afs/cs.cmu.edu/project/pdl/ftp/Declustering/Thesis.ps},
  keywords = {parallel I/O, disk arrays, RAID, redundancy, reliability,
  pario-bib},
  abstract = {There exists a wide variety of applications in which data
  availability must be continuous, that is, where the system is never taken
  off-line and any interruption in the accessibility of stored data causes
  significant disruption in the service provided by the application. Examples
  include on-line transaction processing systems such as airline reservation
  systems, and automated teller networks in banking systems. In addition, there
  exist many applications for which a high degree of data availability is
  important, but continuous operation is not required. An example is a research
  and development environment, where access to a centrally-stored CAD system is
  often necessary to make progress on a design project. These applications and
  many others mandate both high performance and high availability from their
  storage subsystems. \par Parity-based redundant disk arrays are very
  attractive storage alternatives for these systems because they offer both low
  cost per megabyte and high data reliability. Unfortunately such systems
  exhibit poor availability characteristics; their performance is severely
  degraded in the presence of a disk failure. This dissertation addresses the
  design of parity-based redundant disk arrays that offer dramatically higher
  levels of performance in the presence of failure than systems comprising the
  current state of the art. \par We consider two primary aspects of the
  failure-recovery problem: the organization of the data and redundancy in the
  array, and the algorithm used to recover the lost data. We apply results from
  combinatorial theory to generate data and parity organizations that minimize
  performance degradation during failure recovery by evenly distributing all
  failure-induced workload over a larger-than-minimal collection of disks. We
  develop a reconstruction algorithm that is able to absorb for
  failure-recovery essentially all of the array's bandwidth that is not
  absorbed by the application process(es). Additionally, we develop a design
  for a redundant disk array targeted at extremely high availability through
  extremely fast failure recovery. This development also demonstrates the
  generality of the presented techniques.},
  comment = {Garth Gibson, advisor.}
}