Abstract
The major aim of a Grid is to federate several powerful distributed resources within a single virtual entity which can be accessed transparently and efficiently by external users. As a Grid is a distributed and unreliable system involving heterogeneous resources located in different geographical domains, fault-tolerant resource allocation services have to be provided. In particular, when crashes occur, tasks have to be reallocated quickly and automatically, in a completely transparent way from the users’ point of view.
This paper presents Paradis, a system based on a Consensus building block that has been designed and implemented in a Grid dedicated to genomic applications. These time-consuming applications can be split up into a huge number of independent tasks which can be allocated independently on different domains.
This work was supported by the French Ministry of Research – Project GénoGRID of the program ACI “Globalization of computer resources and data”.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Almond, J., Romberg, M.: The unicore project: Uniform access to supercomputing over the web. In: Proceedings of 40th Cray User Group Meeting (1998)
Brasileiro, F., Greve, F., Hurfin, M., Le Narzul, J.-P., Tronel, F.: Eva: an Event- Based Framework for Developing Specialised Communication Protocols. In: Proc. of the 1st IEEE Int. Symp. on Network Computing and Applications, pp. 108–119 (2002)
Chandra, T., Toueg, S.: Unreliable Failure Detectors for Reliable Distributed Systems. JACM 43(2), 225–267 (1996)
Greve, F.: Réponses efficaces au besoin d’accord dans un groupe. Ph.D. Thesis, University of Rennes (November 2002)
Hurfin, M., Macêdo, R., Raynal, M., Tronel, F.: A General Framework to Solve Agreement Problems. Proc. of the 18th IEEE Int. Symposium on Reliable Distributed Systems (SRDS 1999), pp. 56–65 (1999)
Fischer, M.J., Lynch, N.A., Paterson, M.S.: Impossibility of Distributed Consensus with One Faulty Process. JACM 32(2), 374–382 (1985)
Foster, I., Kesselman, C.: The Globus Project.: A Status Report. In: Proc. of the 7th IEEE Heterogeneous Computing Workshop, pp. 4–19 (1998)
Greve, F., Hurfin, M., Raynal, M., Tronel, F.: Primary Component Asynchronous Group Membership as an Instance of Generic Agreement Framework. In: Proc. of the 5th Int. Symposium on Autonomous Decentralized Systems pp. 93–100 (2001)
Lavenier, D., Leroy, H., Hurfin, M., Andonov, R., Mouchard, L., Guinand, Le, F.: projet GénoGRID: une grille expérimentale pour la génomique. Actes des 3èmes Journées Ouvertes Biologie Informatique Mathématiques, pp. 27–31, France (2002)
Pley, J., Andonov, R., Gibrat, J.-F., Marin, A., Poirriez Parallélisations, V.: d’une méthode de reconnaissance de repliements de protéines (FROST). Proc. of the 3th Journées Ouvertes de Biologie, Informatique et Mathématiques, pp. 287–288 (2002)
Powell, D.: Special Issue on Group Communication. CACM 39(4) (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hurfin, M., Le Narzul, JP., Pley, J., Parvédy, P.R. (2004). A Fault-Tolerant Protocol for Resource Allocation in a Grid Dedicated to Genomic Applications. In: Wyrzykowski, R., Dongarra, J., Paprzycki, M., Waśniewski, J. (eds) Parallel Processing and Applied Mathematics. PPAM 2003. Lecture Notes in Computer Science, vol 3019. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24669-5_148
Download citation
DOI: https://doi.org/10.1007/978-3-540-24669-5_148
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21946-0
Online ISBN: 978-3-540-24669-5
eBook Packages: Springer Book Archive