Evaluation of Replication and Fault Detection in P2P-MPI

Stéphane Genaud 1 Choopan Rattanapoka 2
1 ALGORILLE - Algorithms for the Grid
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
2 LSIIT / ICPS - Laboratoire de Sciences de l'Image, de l'Informatique et de la Télédétection, équipe ICPS
Abstract : We present in this paper an evaluation of fault management in the grid middleware P2P-MPI. One of P2P-MPI's objective is to support environments using commodity hardware. Hence, running programs is failure prone and a particular attention must be paid to fault management. The fault management covers two issues: fault-tolerance and fault detection. P2P-MPI provides a transparent fault tolerance facility based on replication of computations. Fault detection concerns the monitoring of the program execution by the system. The monitoring is done through a distributed set of modules called failure detectors. In this paper, we report results from several experiments which show the overhead of replication, and the cost of fault detection.
Document type :
Conference papers
Complete list of metadatas
https://hal.inria.fr/inria-00425519
Contributor : Stéphane Genaud <>
Submitted on : Wednesday, October 21, 2009 - 9:18:41 PM
Last modification on : Friday, January 12, 2018 - 1:08:53 AM

Identifiers

Collections

INRIA | GRID5000 | LORIA | UNIV-LORRAINE

Citation

Stéphane Genaud, Choopan Rattanapoka. Evaluation of Replication and Fault Detection in P2P-MPI. 6th High Performance Grid Computing International Workshop in conjunction with International Parallel and Distributed Processing Symposium - IPDPS 2009, May 2009, Rome, Italy. pp.1-8, ⟨10.1109/IPDPS.2009.5160969⟩. ⟨inria-00425519⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

306

Contact


archive-ouverte@inria.fr