Lacan, Jérôme Fault-tolerant distributed computing scheme based on erasure codes. (2006) In: NOTERE'2006 : NOuvelles TEchnologies de la REpartition, 06-09 Juin 2006, Toulouse, France .
|
(Document in English)
PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader 158kB |
Abstract
Some emerging classes of distributed computing systems, such peer-to-peer or grid computing computing systems, are composed of heterogeneous computing resources potentially unreliable. This paper proposes to use erasure codes to improve the fault-tolerance of parallel distributed computing applications in this context. A general method to generate redundant processes from a set of parallel processes is presented. This scheme allows the recovery of the result of the application even if some of the processes crash.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Audience (conference): | International conference proceedings |
| Uncontrolled Keywords: | |
| Institution: | Université de Toulouse > Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE) |
| Laboratory name: | Département de Mathématiques, Informatique, Automatique - DMIA (Toulouse, France) - Modelisation et Architecture des Systèmes - MARS |
| Statistics: | download |
| Deposited By: | Jérôme Lacan |
| Deposited On: | 02 Oct 2009 16:06 |
Repository Staff Only: item control page
