@Article{kermarrec:ha-psls,
  author = {Anne-Marie Kermarrec and Christine Morin},
  title = {{HA-PSLS}: a highly available parallel single-level store system.},
  journal = {Concurrency and Computation Practice \& Experience},
  booktitle = {European Conference on Parallel Computing; August 2001; UNIV
  MANCHESTER; MANCHESTER, ENGLAND},
  year = {2003},
  month = {August},
  volume = {15},
  number = {10},
  pages = {911--937},
  institution = {Inst Natl Rech Informat \& Automat, IRISA, Campus Univ
  Beulieu, F-35042 Rennes, France; Inst Natl Rech Informat \& Automat, IRISA,
  F-35042 Rennes, France; Microsofr Res, Cambridge CB3 0FB, England},
  publisher = {UK : Wiley, 2003},
  copyright = {(c)2004 IEE; Institute for Scientific Information, Inc.},
  URL = {http://www.irisa.fr/paris/Biblio/Papers/Kermarrec/KerMor02ccpe.pdf},
  keywords = {parallel single level store, high-availability, fault tolerance,
  checkpointing, replication, integration, parallel file systems, shared
  virtual memory, pario-bib},
  abstract = {Parallel single-level store (PSLS) systems integrate a shared
  virtual memory and a parallel file system. They provide programmers with a
  global address space including both memory and file data. PSLS systems
  implemented in a cluster thus represent a natural support for long-running
  parallel applications, combining both the natural shared memory programming
  model and a large and efficient file system. However, the need to tolerate
  failures in such a system increases with the size of applications. We present
  a highly-available parallel single level store system (HA-PSLS), which
  smoothly integrates a backward error recovery high-availability mechanism
  into a PSLS system. Our system is able to tolerate multiple transient
  failures, a single permanent failure, and power cut failures affecting the
  whole cluster, without requiring any specialized hardware. For this purpose,
  HA-PSLS relies on a high degree of integration (and reusability) of
  high-availability and standard features. A prototype integrating our
  high-availability support has been implemented and we show some performance
  results. (24 refs.)}
}