@Article{bakker:semantic,
  author = {J.A. Bakker},
  title = {Semantic partitioning as a basis for parallel {I/O} in database
  management systems},
  journal = {Parallel Computing},
  year = {2000},
  month = {October},
  volume = {26},
  number = {11},
  pages = {1491--1513},
  URL = {http://dx.doi.org/10.1016/S0167-8191(00)00041-7},
  keywords = {database, parallel I/O, pario-bib},
  abstract = {Modern applications such as `video on demand' require fast
  reading of complete files, which can be supported well by file striping. Many
  conventional applications, however, are only interested in some part of the
  available records. In order to avoid reading attributes irrelevant to such
  applications, each attribute could be stored in a separate (transposed) file;
  Aiming at I/O parallelism, byte-oriented striping could be applied to
  transposed files. However, such a fragmentation ignores the semantics of
  data. This fragmentation cannot be optimized by a database management system
  (DBMS) because a DBMS has to perform its tasks on the basis of data
  semantics. For example, queries must be translated into file operations using
  a scheme that maps a data model to a file system. However, details about
  files, such as the striping width, are invisible to a DBMS. Therefore, we
  propose to store each transposed file related to a composite type on a
  separate, independent disk drive, which means I/O parallelism tuned to a data
  model. As we also aim at system reliability and data availability, each
  transposed file must be duplicated on another drive. Consequently, a DBMS
  also has to guarantee correctness and completeness of the allocation of
  transposed files within an array of disk drives. As a solution independent of
  the underlying data model, we propose an abstract framework consisting of a
  meta model and a set of rules}
}