@article{LuckowSchnor2005,
  author    = {Luckow, Andr{\´e} and Schnor, Bettina},
  title     = {Migol : a Fault-Tolerant Service Framework for MPI Applications in the Grid},
  isbn      = {978-3-540-29009-4},
  year      = {2005},
  abstract  = {In a distributed, inherently dynamic Grid environment the reliability of individual resources cannot be guaranteed. The more resources and components are involved the more error-prone is the system. Therefore, it is important to enhance the dependability of the system with fault-tolerance mechanisms. In this paper, we present Migol, a fault-tolerant, self-healing Grid service infrastructure for MPI applications. The benefit of the Grid is that in case of a failure an application may be migrated and restarted from a checkpoint file on another site. This approach requires a service infrastructure which handles the necessary activities transparently for an application. But any migration framework cannot support fault-tolerant applications, if it is not fault-tolerant itself.},
  language  = {en}
}