-
Gabriel Antoniu,
Marin Bertier,
Luc Bougé,
Eddy Caron,
Frédéric Desprez,
Mathieu Jan,
Sébastien Monnet,
and Pierre Sens.
GDS: An Architecture Proposal for a Grid Data-Sharing Service.
In Vladimir Getov,
Domenico Laforenza,
and Alexander Reinefeld, editors,Future Generation Grids,
volume XVIII, CoreGrid Series of Proceedings of the Workshop on Future Generation Grids November 1-5, 2004, Dagstuhl, Germany.
Springer Verlag,
2006.
Note: Hal number inria-00000983.
Keywords:
JuxMem,
DIET.
@InCollection{ InCollectionAntoniu.ABBCDJMS_06,
author = {Gabriel Antoniu and Marin Bertier and Luc Boug{\'e} and Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Mathieu Jan and S{\'e}bastien Monnet and Pierre Sens},
booktitle = {{Future Generation Grids}},
editor = {Getov, Vladimir and Laforenza, Domenico and Reinefeld, Alexander},
keywords = {JuxMem,DIET},
note = {hal number inria-00000983},
publisher = {Springer Verlag},
series = {Proceedings of the Workshop on Future Generation Grids November 1-5, 2004, Dagstuhl, Germany},
title = {{GDS}: An Architecture Proposal for a Grid Data-Sharing Service},
url = {https://hal.inria.fr/inria-00000983},
volume = {XVIII, CoreGrid Series},
year = {2006}
}
-
Eddy Caron,
Frédéric Desprez,
Christophe Hamerling,
Jean-Yves L'Excellent,
Marc Pantel,
and Puglisi-Amestoy C..
Use of A Network Enabled Server System for a Sparse Linear Algebra Application.
In Vladimir Getov,
Domenico Laforenza,
and Alexander Reinefeld, editors,Future Generation Grids,
volume XVIII, CoreGrid Series of Proceedings of the Workshop on Future Generation Grids November 1-5, 2004, Dagstuhl, Germany.
Springer Verlag,
2006.
Note: Hal-00688781.
Keywords:
DIET.
@InCollection{ InCollectionCaron.CDHLPC_06,
author = {Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Hamerling, Christophe and L'Excellent, Jean-Yves and Pantel, Marc and Puglisi-Amestoy C.},
booktitle = {{Future Generation Grids}},
editor = {Getov, Vladimir and Laforenza, Domenico and Reinefeld, Alexander},
keywords = {DIET},
note = {hal-00688781},
publisher = {Springer Verlag},
series = {Proceedings of the Workshop on Future Generation Grids November 1-5, 2004, Dagstuhl, Germany},
title = {Use of A Network Enabled Server System for a Sparse Linear Algebra Application},
url = {https://hal.inria.fr/hal-00688781},
volume = {XVIII, CoreGrid Series},
year = {2006}
}
-
Raphaël Bolze,
Franck Cappello,
Eddy Caron,
Michel Daydé,
Frederic Desprez,
Emmanuel Jeannot,
Yvon Jégou,
Stéphane Lanteri,
Julien Leduc,
Noredine Melab,
Guillaume Mornet,
Raymond Namyst,
Pascale Primet,
Benjamin Quetier,
Olivier Richard,
El-Ghazali Talbi,
and Touché Irena.
Grid'5000: a large scale and highly reconfigurable experimental Grid testbed..
International Journal of High Performance Computing Applications,
20(4):481-494,
November 2006.
Note: Hal-00684943.
Keywords:
Grid'5000,
DIET.
@Article{ ArticleBolze.BCCDDJJLLMMNPQRTI_IJHPCA06,
author = {Bolze, Rapha{\"e}l and Cappello, Franck and Caron, Eddy and Dayd{\'e}, Michel and Desprez, Frederic and Jeannot, Emmanuel and J{\'e}gou, Yvon and Lanteri, St{\'e}phane and Leduc, Julien and Melab, Noredine and Mornet,Guillaume and Namyst, Raymond and Primet, Pascale and Quetier, Benjamin and Richard, Olivier and Talbi, El-Ghazali and Touch{\'e} Irena},
journal = {International Journal of High Performance Computing Applications},
keywords = {Grid'5000, DIET},
month = nov,
note = {hal-00684943},
number = {4},
pages = {481-494},
title = {Grid'5000: a large scale and highly reconfigurable experimental Grid testbed.},
url = {https://hal.inria.fr/hal-00684943},
volume = {20},
year = {2006}
}
-
Eddy Caron and Frédéric Desprez.
DIET: A Scalable Toolbox to Build Network Enabled Servers on the Grid.
International Journal of High Performance Computing Applications,
20(3):335-352,
2006.
Note: Hal-01429867.
Keywords:
Grid Computing,
Network Enabled Servers,
Client-servers computing,
DIET.
| Abstract: |
Among existing grid middleware approaches, one simple, powerful, and flexible approach consists of using servers available in different administrative domains through the classical client-server or Remote Procedure Call (RPC) paradigm. Network Enabled Servers implement this model also called GridRPC. Clients submit computation requests to a scheduler whose goal is to find a server available on the grid. The aim of this paper is to give an overview of a middleware developed by the GRAAL team called DIET (for Distributed Interactive Engineering Tool-box). DIET is a hierarchical set of components used for the development of applications based on computational servers on the grid. |
@Article{ ArticleCaron.CD_IJHPCA06,
abstract = {Among existing grid middleware approaches, one simple, powerful, and flexible approach consists of using servers available in different administrative domains through the classical client-server or Remote Procedure Call (RPC) paradigm. Network Enabled Servers implement this model also called GridRPC. Clients submit computation requests to a scheduler whose goal is to find a server available on the grid. The aim of this paper is to give an overview of a middleware developed by the GRAAL team called DIET (for Distributed Interactive Engineering Tool-box). DIET is a hierarchical set of components used for the development of applications based on computational servers on the grid.},
author = {Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric},
journal = {International Journal of High Performance Computing Applications},
keywords = {Grid Computing, Network Enabled Servers, Client-servers computing,DIET},
note = {hal-01429867},
number = {3},
pages = {335-352},
publisher = {SAGE Publications},
title = {{DIET}: A Scalable Toolbox to Build Network Enabled Servers on the Grid},
url = {https://hal.inria.fr/hal-01429867},
volume = {20},
year = {2006}
}
-
Pushpinder Kaur Chouhan,
Holly Dail,
Eddy Caron,
and Frédéric Vivien.
Automatic Middleware Deployment Planning on Clusters.
International Journal of High Performance Computing Applications,
20(4):517-530,
November 2006.
Note: Hal-01429834.
Keywords:
Deployment,
DIET.
@Article{ ArticleChouhan.CDCV_IJHPCA06,
author = {Chouhan, Pushpinder Kaur and Dail, Holly and Caron, Eddy and Vivien, Fr{\'e}d{\'e}ric},
journal = {International Journal of High Performance Computing Applications},
keywords = {Deployment, DIET},
month = nov,
note = {hal-01429834},
number = {4},
pages = {517-530},
title = {Automatic Middleware Deployment Planning on Clusters},
url = {https://hal.inria.fr/hal-01429834},
volume = {20},
year = {2006}
}
-
Abelkader Amar,
Raphaël Bolze,
Aurélien Bouteiller,
Pushpinder Kaur Chouhan,
Andréea Chis,
Yves Caniou,
Eddy Caron,
Holly Dail,
Benjamin Depardon,
Frédéric Desprez,
Jean-Sébastien Gay,
Gaël Le Mahec,
and Alan Su.
DIET: New Developments and Recent Results.
In Lehner et al. (Eds.), editor,
CoreGRID Workshop on Grid Middleware (in conjunction with EuroPar2006),
number 4375 of LNCS,
Dresden, Germany,
pages 150-170,
August 28-29 2006.
Springer.
Note: Hal-01429979.
Keywords:
DIET,
LEGO.
| Abstract: |
Among existing grid middleware approaches, one simple, powerful, and flexible approach consists of using servers available in different administrative domains through the classic client-server or Remote Procedure Call (RPC) paradigm. Network Enabled Servers (NES) implement this model also called GridRPC. Clients submit computation requests to a scheduler whose goal is to find a server available on the grid. The aim of this paper is to give an overview of an NES middleware developed in the GRAAL team called DIET and to describe recent developments. DIET (Distributed Interactive Engineering Toolbox) is a hierarchical set of components used for the development of applications based on computational servers on the grid. |
@InProceedings{ InProceedingsAmar.ABBCCCCDDDGL-MS_06,
abstract = {Among existing grid middleware approaches, one simple, powerful, and flexible approach consists of using servers available in different administrative domains through the classic client-server or Remote Procedure Call (RPC) paradigm. Network Enabled Servers (NES) implement this model also called GridRPC. Clients submit computation requests to a scheduler whose goal is to find a server available on the grid. The aim of this paper is to give an overview of an NES middleware developed in the GRAAL team called DIET and to describe recent developments. DIET (Distributed Interactive Engineering Toolbox) is a hierarchical set of components used for the development of applications based on computational servers on the grid. },
address = {Dresden, Germany},
author = {Amar, Abelkader and Bolze, Rapha{\"e}l and Bouteiller, Aur{\'e}lien and Chouhan, Pushpinder Kaur and Chis, Andr{\'e}ea and Caniou, Yves and Caron, Eddy and Dail, Holly and Depardon, Benjamin and Desprez, Fr{\'e}d{\'e}ric and Gay, Jean-S{\'e}bastien and Le Mahec, Ga{\"e}l and Su, Alan},
booktitle = {CoreGRID Workshop on Grid Middleware (in conjunction with EuroPar2006)},
editor = {Lehner et al. (Eds.)},
keywords = {DIET,LEGO},
month = {August 28-29},
note = {hal-01429979},
number = {4375},
pages = {150-170},
publisher = {Springer},
series = {LNCS},
title = {DIET: New Developments and Recent Results},
url = {https://hal.inria.fr/hal-01429979},
year = {2006}
}
-
Raphaël Bolze,
Eddy Caron,
Frédéric Desprez,
Georg Hoesch,
and Cyril Pontvieux.
A Monitoring and Visualization Tool and Its Application for a Network Enabled Server Platform.
In M. Gavrilova, editor,
Computational Science and Its Applications - ICCSA 2006,
volume 3984 of LNCS,
Glasgow, UK.,
pages 202--213,
May 8-11 2006.
Springer.
Note: Hal-01430514.
Keywords:
Monitoring,
Visualization,
DIET.
@InProceedings{ InProceedingsBolze.BCDHP_06,
address = {Glasgow, UK.},
author = {Bolze, Rapha{\"e}l and Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Hoesch, Georg and Pontvieux, Cyril},
booktitle = {Computational Science and Its Applications - ICCSA 2006},
editor = {M. Gavrilova},
isbn = {3-540-34079-3},
keywords = {Monitoring, Visualization, DIET},
month = {May 8-11},
note = {hal-01430514},
pages = {202--213},
publisher = {Springer},
series = {LNCS},
title = {A Monitoring and Visualization Tool and Its Application for a Network Enabled Server Platform},
url = {https://hal.inria.fr/hal-01430514},
volume = {3984},
year = {2006}
}
-
Eddy Caron,
Andréea Chis,
Frédéric Desprez,
and Alan Su.
Plug-in Scheduler Design for a Distributed Grid Environment.
In ACM/IFIP/USENIX, editor,
4th International Workshop on Middleware for Grid Computing - MGC 2006,
Melbourne, Australia,
November 2006.
Note: In conjunction with ACM/IFIP/USENIX 7th International Middleware Conference 2006. hal number hal-01430509.
Keywords:
DIET,
Scheduling.
@InProceedings{ InProceedingsCaron.CCDS_06,
address = {Melbourne, Australia},
author = {Caron, Eddy and Chis, Andr{\'e}ea and Desprez, Fr{\'e}d{\'e}ric and Su, Alan},
booktitle = {4th International Workshop on Middleware for Grid Computing - MGC 2006},
editor = {ACM/IFIP/USENIX},
keywords = {DIET, Scheduling},
month = nov,
note = {In conjunction with ACM/IFIP/USENIX 7th International Middleware Conference 2006. hal number hal-01430509},
title = {Plug-in Scheduler Design for a Distributed Grid Environment},
url = {https://hal.inria.fr/hal-01430509},
year = {2006}
}
-
Eddy Caron,
Pushpinder Kaur Chouhan,
and Holly Dail.
GoDIET: A Deployment Tool for Distributed Middleware on Grid'5000.
In EXPGRID workshop. Experimental Grid Testbeds for the Assessment of Large-Scale Distributed Applications and Tools. In conjunction with HPDC-15.,
Paris, France,
pages 1-8,
June 2006.
IEEE.
Note: Hal-01430520.
Keywords:
Deployment,
GoDIET,
DIET.
@InProceedings{ InProceedingsCaron.CCD_06,
address = {Paris, France},
author = {Caron, Eddy and Chouhan, Pushpinder Kaur and Holly Dail},
booktitle = {EXPGRID workshop. Experimental Grid Testbeds for the Assessment of Large-Scale Distributed Applications and Tools. In conjunction with HPDC-15.},
keywords = {Deployment,GoDIET,DIET},
month = jun,
note = {hal-01430520},
pages = {1-8},
publisher = {IEEE},
title = {GoDIET: A Deployment Tool for Distributed Middleware on Grid'5000},
url = {https://hal.inria.fr/hal-01430520},
year = {2006}
}
-
Eddy Caron,
Frédéric Desprez,
Charles Fourdrignier,
Franck Petit,
and Cédric Tedeschi.
A Repair Mechanism for Fault-Tolerance for Tree-Structured Peer-to-Peer Systems.
In Yves Robert,
Manish Parashar,
Ramamurthy Badrinath,
and Viktor K. Prasanna, editors,
HiPC'2006. 13th International Conference on High Performance Computing.,
volume 4297 of LNCS,
Bangalore. India,
pages 171-182,
December 18-21 2006.
Springer-Verlag Berlin Heidelberg.
Note: Hal-01430039.
Keywords:
P2P,
Fault Tolerance,
TPLD.
@InProceedings{ InProceedingsCaron.CDFPT_06,
address = {Bangalore. India},
author = {Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Fourdrignier, Charles and Petit, Franck and Tedeschi, C{\'e}dric},
booktitle = {{HiPC'2006}. 13th International Conference on High Performance Computing.},
editor = {Yves Robert and Manish Parashar and Ramamurthy Badrinath and Viktor K. Prasanna},
keywords = {P2P, Fault Tolerance, TPLD},
month = {December 18-21},
note = {hal-01430039},
pages = {171-182},
publisher = {Springer-Verlag Berlin Heidelberg},
series = {LNCS},
title = {A Repair Mechanism for Fault-Tolerance for Tree-Structured Peer-to-Peer Systems},
url = {https://hal.inria.fr/hal-01430039},
volume = {4297},
year = {2006}
}
-
Eddy Caron,
Frédéric Desprez,
and Cédric Tedeschi.
A Dynamic Prefix Tree for the Service Discovery Within Large Scale Grids.
In A. Montresor,
A. Wierzbicki,
and N. Shahmehri, editors,
The Sixth IEEE International Conference on Peer-to-Peer Computing, P2P2006,
Cambridge, UK.,
pages 106-113,
September 2006.
IEEE.
Note: Hal-01429999.
Keywords:
TPLD.
@InProceedings{ InProceedingsCaron.CDT_06,
address = {Cambridge, UK.},
author = {Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Tedeschi, C{\'e}dric},
booktitle = {The Sixth IEEE International Conference on Peer-to-Peer Computing, P2P2006},
editor = {A. Montresor and A. Wierzbicki and N. Shahmehri},
keywords = {TPLD},
month = sep,
note = {hal-01429999},
pages = {106-113},
publisher = {IEEE},
title = {A Dynamic Prefix Tree for the Service Discovery Within Large Scale Grids},
url = {https://hal.inria.fr/hal-01429999},
year = {2006}
}
-
Eddy Caron,
Charles Fourdrignier,
Franck Petit,
and Cédric Tedeschi.
Mécanisme de réparations pour un système P2P de découverte de services.
In Perpi'2006 - Conférences conjointes RenPar'17 / SympA'2006 / CFSE'5 / JC'2006,
Canet en Roussillon,
pages 252-259,
October 4-6 2006.
Note: Hal-01430510.
@InProceedings{ InProceedingsCaron.CFPT_06,
address = {Canet en Roussillon},
author = {Caron, Eddy and Fourdrignier, Charles and Petit, Franck and Tedeschi, C{\'e}dric},
booktitle = {Perpi'2006 - Conf{\'e}rences conjointes RenPar'17 / SympA'2006 / CFSE'5 / JC'2006},
month = {October 4-6},
note = {hal-01430510},
pages = {252-259},
title = {M{\'e}canisme de r{\'e}parations pour un syst{\`e}me P2P de d{\'e}couverte de services},
url = {https://hal.inria.fr/hal-01430510},
year = {2006}
}
-
Pushpinder Kaur Chouhan,
Holly Dail,
Eddy Caron,
and Frédéric Vivien.
How should you structure your hierarchical scheduler?.
In HPDC-15. 15th IEEE International Symposium on High Performance Distributed Computing,
Paris, France,
pages 339-340 (Poster),
June 2006.
IEEE.
Note: Hal-01430511.
Keywords:
Deployment,
DIET.
@InProceedings{ InProceedingsChouhan.CDCV_06,
address = {Paris, France},
author = {Chouhan, Pushpinder Kaur and Dail, Holly and Caron, Eddy and Vivien, Fr{\'e}d{\'e}ric},
booktitle = {HPDC-15. 15th IEEE International Symposium on High Performance Distributed Computing},
keywords = {Deployment, DIET},
month = jun,
note = {hal-01430511},
pages = {339-340 (Poster)},
publisher = {IEEE},
title = {How should you structure your hierarchical scheduler?},
url = {https://hal.inria.fr/hal-01430511},
year = {2006}
}
-
Abelkader Amar,
Raphaël Bolze,
Aurélien Bouteiller,
Andréea Chis,
Yves Caniou,
Eddy Caron,
Pushpinder Kaur Chouhan,
Gaël Le Mahec,
Holly Dail,
Benjamin Depardon,
Frédéric Desprez,
Jean-Sébastien Gay,
and Alan Su.
DIET: New Developments and Recent Results.
Research Report 6027,
INRIA,
November 2006.
Note: Also available as LIP Research Report 2006-31. hal number inria-00115569.
Keywords:
Grid Computing,
Network Enabled Servers,
Client-servers computing,
DIET.
| Abstract: |
Among existing grid middleware approaches, one simple, powerful, and flexible approach consists of using servers available in different administrative domains through the classic client-server or Remote Procedure Call (RPC) paradigm. Network Enabled Servers (NES) implement this model also called GridRPC. Clients submit computation requests to a scheduler whose goal is to find a server available on the grid. The aim of this paper is to give an overview of an NES middleware developed in the GRAAL team called DIET and to describe recent developments. DIET (Distributed Interactive Engineering Toolbox) is a hierarchical set of components used for the development of applications based on computational servers on the grid. |
@TechReport{ TechReportRR-INRIA-6027,
abstract = {Among existing grid middleware approaches, one simple, powerful, and flexible approach consists of using servers available in different administrative domains through the classic client-server or Remote Procedure Call (RPC) paradigm. Network Enabled Servers (NES) implement this model also called GridRPC. Clients submit computation requests to a scheduler whose goal is to find a server available on the grid. The aim of this paper is to give an overview of an NES middleware developed in the GRAAL team called DIET and to describe recent developments. DIET (Distributed Interactive Engineering Toolbox) is a hierarchical set of components used for the development of applications based on computational servers on the grid.},
author = {Amar, Abelkader and Bolze, Rapha{\"e}l and Bouteiller, Aur{\'e}lien and Chis, Andr{\'e}ea and Caniou, Yves and Caron, Eddy and Chouhan, Pushpinder Kaur and Le Mahec, Ga{\"e}l and Dail, Holly and Depardon, Benjamin and Desprez, Fr{\'e}d{\'e}ric and Gay, Jean-S{\'e}bastien and Su, Alan},
institution = {INRIA},
keywords = {Grid Computing, Network Enabled Servers, Client-servers computing, DIET},
month = nov,
note = {Also available as LIP Research Report 2006-31. hal number inria-00115569},
number = {6027},
pages = {24 p.},
title = {DIET: New Developments and Recent Results},
type = {Research Report},
url = {https://hal.inria.fr/inria-00115569},
year = {2006}
}
-
Abelkader Amar,
Raphaël Bolze,
Aurélien Bouteiller,
Andréea Chis,
Yves Caniou,
Eddy Caron,
Pushpinder Kaur Chouhan,
Gaël Le Mahec,
Holly Dail,
Benjamin Depardon,
Frédéric Desprez,
Jean-Sébastien Gay,
and Alan Su.
DIET: New Developments and Recent Results.
Technical report RR2006-31,
Laboratoire de l'Informatique du Parallélisme (LIP),
October 2006.
Note: Also available as INRIA Research Report 6027. hal-01429988.
Keywords:
Grid Computing,
Network Enabled Servers,
Client-servers computing,
DIET.
| Abstract: |
Among existing grid middleware approaches, one simple, powerful, and flexible approach consists of using servers available in different administrative domains through the classic client-server or Remote Procedure Call (RPC) paradigm. Network Enabled Servers (NES) implement this model also called GridRPC. Clients submit computation requests to a scheduler whose goal is to find a server available on the grid. The aim of this paper is to give an overview of an NES middleware developed in the GRAAL team called DIET and to describe recent developments. DIET (Distributed Interactive Engineering Toolbox) is a hierarchical set of components used for the development of applications based on computational servers on the grid. |
@TechReport{ TechReportRR-Laboratoire-RR2006-31,
abstract = {Among existing grid middleware approaches, one simple, powerful, and flexible approach consists of using servers available in different administrative domains through the classic client-server or Remote Procedure Call (RPC) paradigm. Network Enabled Servers (NES) implement this model also called GridRPC. Clients submit computation requests to a scheduler whose goal is to find a server available on the grid. The aim of this paper is to give an overview of an NES middleware developed in the GRAAL team called DIET and to describe recent developments. DIET (Distributed Interactive Engineering Toolbox) is a hierarchical set of components used for the development of applications based on computational servers on the grid.},
author = {Amar, Abelkader and Bolze, Rapha{\"e}l and Bouteiller, Aur{\'e}lien and Chis, Andr{\'e}ea and Caniou, Yves and Caron, Eddy and Chouhan, Pushpinder Kaur and Le Mahec, Ga{\"e}l and Dail, Holly and Depardon, Benjamin and Desprez, Fr{\'e}d{\'e}ric and Gay, Jean-S{\'e}bastien and Su, Alan},
institution = {Laboratoire de l'Informatique du Parall{\'e}lisme (LIP)},
keywords = {Grid Computing, Network Enabled Servers, Client-servers computing, DIET},
month = oct,
note = {Also available as INRIA Research Report 6027. hal-01429988},
number = {RR2006-31},
title = {DIET: New Developments and Recent Results},
url = {https://hal.inria.fr/hal-01429988},
year = 2006
}
-
Gabriel Antoniu,
Eddy Caron,
Frédéric Desprez,
and Mathieu Jan.
Towards a Transparent Data Access Model for the GridRPC Paradigm.
Technical report PI1823,
IRISA,
November 2006.
Note: Also available as INRIA Research Report 6009. hal number inria-00110902.
Keywords:
GridRPC,
Data Sharing,
Persistency,
JUXMEM,
DIET.
| Abstract: |
As grids become more and more attractive for solving complex problems with high computational and storage requirements, the need for adequate grid programming models is considerable. To this purpose, the GridRPC model has been proposed as a grid version of the classical RPC paradigm, with the goal to build NES (Network-Enabled Server) environments. Paradoxically enough, in this model, data management has not been defined and is now explicitly left at the user's charge. The contribution of this paper is to enhance data management in NES by introducing a transparent data access model, available through the concept of grid data-sharing service. Data management (persistent storage, transfer, consistent replication) is totally delegated to the service, whereas the applications simply access shared data via global identifiers. We illustrate our approach using the DIET GridRPC middleware and the JUXMEM data-sharing service. Experiments performed on the Grid'5000 testbed demonstrate the benefits of the proposed approach. |
@TechReport{ TechReportRR-IRISA-PI1823,
abstract = {As grids become more and more attractive for solving complex problems with high computational and storage requirements, the need for adequate grid programming models is considerable. To this purpose, the GridRPC model has been proposed as a grid version of the classical RPC paradigm, with the goal to build NES (Network-Enabled Server) environments. Paradoxically enough, in this model, data management has not been defined and is now explicitly left at the user's charge. The contribution of this paper is to enhance data management in NES by introducing a transparent data access model, available through the concept of grid data-sharing service. Data management (persistent storage, transfer, consistent replication) is totally delegated to the service, whereas the applications simply access shared data via global identifiers. We illustrate our approach using the DIET GridRPC middleware and the JUXMEM data-sharing service. Experiments performed on the Grid'5000 testbed demonstrate the benefits of the proposed approach. },
author = {Antoniu, Gabriel and Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Jan, Mathieu},
institution = {IRISA},
keywords = {GridRPC, Data Sharing, Persistency, JUXMEM, DIET},
month = nov,
note = {Also available as INRIA Research Report 6009. hal number inria-00110902},
number = {PI1823},
title = {Towards a Transparent Data Access Model for the {GridRPC} Paradigm},
url = {http://www.irisa.fr/centredoc/publis/PI/2006/irisapublication.2006-11-02.8327047788},
year = 2006
}
-
Gabriel Antoniu,
Eddy Caron,
Frédéric Desprez,
and Mathieu Jan.
Towards a Transparent Data Access Model for the GridRPC Paradigm.
Technical report RR-6009,
INRIA,
November 2006.
Note: Also available as IRISA Research Report PI1823. hal number inria-00110967.
Keywords:
GridRPC,
Data Sharing,
Persistency,
JUXMEM,
DIET.
| Abstract: |
As grids become more and more attractive for solving complex problems with high computational and storage requirements, the need for adequate grid programming models is considerable. To this purpose, the GridRPC model has been proposed as a grid version of the classical RPC paradigm, with the goal to build NES (Network-Enabled Server) environments. Paradoxically enough, in this model, data management has not been defined and is now explicitly left at the user's charge. The contribution of this paper is to enhance data management in NES by introducing a transparent data access model, available through the concept of grid data-sharing service. Data management (persistent storage, transfer, consistent replication) is totally delegated to the service, whereas the applications simply access shared data via global identifiers. We illustrate our approach using the DIET GridRPC middleware and the JUXMEM data-sharing service. Experiments performed on the Grid'5000 testbed demonstrate the benefits of the proposed approach. |
@TechReport{ TechReportRR-INRIA-RR-6009,
abstract = {As grids become more and more attractive for solving complex problems with high computational and storage requirements, the need for adequate grid programming models is considerable. To this purpose, the GridRPC model has been proposed as a grid version of the classical RPC paradigm, with the goal to build NES (Network-Enabled Server) environments. Paradoxically enough, in this model, data management has not been defined and is now explicitly left at the user's charge. The contribution of this paper is to enhance data management in NES by introducing a transparent data access model, available through the concept of grid data-sharing service. Data management (persistent storage, transfer, consistent replication) is totally delegated to the service, whereas the applications simply access shared data via global identifiers. We illustrate our approach using the DIET GridRPC middleware and the JUXMEM data-sharing service. Experiments performed on the Grid'5000 testbed demonstrate the benefits of the proposed approach. },
author = {Antoniu, Gabriel and Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Jan, Mathieu},
institution = {INRIA},
keywords = {GridRPC, Data Sharing, Persistency, JUXMEM, DIET},
month = nov,
note = {Also available as IRISA Research Report PI1823. hal number inria-00110967},
number = {RR-6009},
title = {Towards a Transparent Data Access Model for the {GridRPC} Paradigm},
url = {https://hal.inria.fr/inria-00110967},
year = 2006
}
-
Alexis Ballier,
Eddy Caron,
Dick Epema,
and Hashim Mohamed.
Simulating Grid Schedulers with Deadlines and Co-Allocation.
Technical report RR-5815,
Institut National de Recherche en Informatique et en Automatique (INRIA),
January 2006.
Note: Also available as LIP Research Report 2006-01 and CoreGRID Technical Report TR-0061. hal number inria-00077051.
@TechReport{ TechReportRR-Institut-RR-5815,
author = {Ballier, Alexis and Caron, Eddy and Epema, Dick and Mohamed, Hashim},
institution = {Institut National de Recherche en Informatique et en Automatique (INRIA)},
month = jan,
note = {Also available as LIP Research Report 2006-01 and CoreGRID Technical Report TR-0061. hal number inria-00077051},
number = {RR-5815},
title = {Simulating Grid Schedulers with Deadlines and Co-Allocation},
url = {https://hal.inria.fr/inria-00077051},
year = 2006
}
-
Alexis Ballier,
Eddy Caron,
Dick Epema,
and Hashim Mohamed.
Simulating Grid Schedulers with Deadlines and Co-Allocation.
Technical report TR-0061,
CoreGRID,
October 2006.
Note: Also available as LIP Research Report 2006-01 and INRIA Research Report RR-5815. hal-01430523.
| Abstract: |
One of the true challenges in resource management in grids is to provide support for co-allocation, that is, the allocation of resources in multiples autonomous subsystems of a grid to single jobs. With reservation-based local schedulers, a grid scheduler can reserve processors with these schedulers to achieve simultaneous processor availability. However, with queuing-based local schedulers, it is much more difficult to guarantee this. In this paper we present mechanisms and policies for working around the lack of reservation mechanisms for jobs with deadlines that require co-allocation, and simulations of these mechanisms and policies. |
@TechReport{ TechReportRR-CoreGRID-TR-0061,
abstract = {One of the true challenges in resource management in grids is to provide support for co-allocation, that is, the allocation of resources in multiples autonomous subsystems of a grid to single jobs. With reservation-based local schedulers, a grid scheduler can reserve processors with these schedulers to achieve simultaneous processor availability. However, with queuing-based local schedulers, it is much more difficult to guarantee this. In this paper we present mechanisms and policies for working around the lack of reservation mechanisms for jobs with deadlines that require co-allocation, and simulations of these mechanisms and policies. },
author = {Ballier, Alexis and Caron, Eddy and Epema, Dick and Mohamed, Hashim},
institution = {CoreGRID},
month = oct,
note = {Also available as LIP Research Report 2006-01 and INRIA Research Report RR-5815. hal-01430523},
number = {TR-0061},
pdf = {http://www.coregrid.net/mambo/images/stories/TechnicalReports/tr-0061.pdf},
title = {Simulating Grid Schedulers with Deadlines and Co-Allocation},
url = {https://hal.inria.fr/hal-01430523},
year = 2006
}
-
Alexis Ballier,
Eddy Caron,
Dick Epema,
and Hashim Mohamed.
Simulating Grid Schedulers with Deadlines and Co-Allocation.
Technical report 2006-01,
Laboratoire de l'Informatique du Parallélisme (LIP),
January 2006.
Note: Also available as INRIA Research Report RR-5815 and CoreGRID Technical Report TR-0061. hal number hal-01430521.
@TechReport{ TechReportRR-Laboratoire-2006-01,
author = {Ballier, Alexis and Caron, Eddy and Epema, Dick and Mohamed, Hashim},
institution = {Laboratoire de l'Informatique du Parall{\'e}lisme (LIP)},
month = jan,
note = {Also available as INRIA Research Report RR-5815 and CoreGRID Technical Report TR-0061. hal number hal-01430521},
number = {2006-01},
pdf = {http://www.ens-lyon.fr/LIP/Pub/Rapports/RR/RR2006/RR2006-01.pdf},
title = {Simulating Grid Schedulers with Deadlines and Co-Allocation},
url = {https://hal.inria.fr/hal-01430521},
year = {2006}
}
-
Raphaël Bolze,
Eddy Caron,
Frédéric Desprez,
Georg Hoesch,
and Cyril Pontvieux.
A Monitoring and Visualization Tool and Its Application for a Network Enabled Server Platform.
Technical report RR-2006-14,
Laboratoire de l'Informatique du Parallélisme (LIP),
April 2006.
Note: Also available as INRIA Research Report 5879. hal-01430516.
Keywords:
Monitoring,
Visualization,
DIET.
@TechReport{ TechReportRR-Laboratoire-RR-2006-14,
author = {Bolze, Rapha{\"e}l and Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Hoesch, Georg and Pontvieux, Cyril},
institution = {Laboratoire de l'Informatique du Parall{\'e}lisme (LIP)},
keywords = {Monitoring, Visualization, DIET},
month = apr,
note = {Also available as INRIA Research Report 5879. hal-01430516},
number = {RR-2006-14},
pdf = {http://www.ens-lyon.fr/LIP/Pub/Rapports/RR/RR2006/RR2006-14.pdf},
title = {A Monitoring and Visualization Tool and Its Application for a Network Enabled Server Platform},
url = {https://hal.inria.fr/hal-01430516},
year = 2006
}
-
Raphaël Bolze,
Eddy Caron,
Frédéric Desprez,
Georg Hoesch,
and Cyril Pontvieux.
A Monitoring and Visualization Tool and Its Application for a Network Enabled Server Platform.
Technical report RR-5879,
Institut National de Recherche en Informatique et en Automatique (INRIA),
April 2006.
Note: Also available as LIP Research Report 2006-14. hal number inria-00071389.
Keywords:
Monitoring,
Visualization,
DIET.
@TechReport{ TechReportRR-Institut-RR-5879,
author = {Bolze, Rapha{\"e}l and Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Hoesch, Georg and Pontvieux, Cyril},
institution = {Institut National de Recherche en Informatique et en Automatique (INRIA)},
keywords = {Monitoring, Visualization, DIET},
month = apr,
note = {Also available as LIP Research Report 2006-14. hal number inria-00071389},
number = {RR-5879},
pdf = {ftp://ftp.inria.fr/INRIA/publication/publi-pdf/RR/RR-5879.pdf},
postscript = {ftp://ftp.inria.fr/INRIA/publication/publi-ps-gz/RR/RR-5879.ps.gz},
title = {A Monitoring and Visualization Tool and Its Application for a Network Enabled Server Platform},
url = {https://hal.inria.fr/inria-00071389},
year = 2006
}
-
Eddy Caron,
Andréea Chis,
Frédéric Desprez,
and Alan Su.
Plug-in Scheduler Design for a Distributed Grid Environment..
Technical report RR2006-41,
Laboratoire de l'Informatique du Parallélisme (LIP),
November 2006.
Note: Also available as INRIA Research Report 6030. hal number hal-01430508.
Keywords:
Grid Computing,
Scheduling,
Performance Prediction,
DIET.
| Abstract: |
This report presents the approach chosen within the DIET (Distributed Interactive Engineering Toolbox) project a GridRPC environment to allow a resource broker to be tuned for specific application classes. Our design allows the use of generic or application dependent performance measures in a simple and seamless way. |
@TechReport{ TechReportRR-Laboratoire-RR2006-41,
abstract = {This report presents the approach chosen within the DIET (Distributed Interactive Engineering Toolbox) project a GridRPC environment to allow a resource broker to be tuned for specific application classes. Our design allows the use of generic or application dependent performance measures in a simple and seamless way.},
author = {Caron, Eddy and Chis, Andr{\'e}ea and Desprez, Fr{\'e}d{\'e}ric and Su, Alan},
institution = {Laboratoire de l'Informatique du Parall{\'e}lisme (LIP)},
keywords = {Grid Computing, Scheduling, Performance Prediction, DIET},
month = nov,
note = {Also available as INRIA Research Report 6030. hal number hal-01430508},
number = {RR2006-41},
pdf = {http://www.ens-lyon.fr/LIP/Pub/Rapports/RR/RR2006/RR2006-41.pdf},
title = {Plug-in Scheduler Design for a Distributed Grid Environment.},
url = {https://hal.inria.fr/hal-01430508},
year = 2006
}
-
Eddy Caron,
Andréea Chis,
Frédéric Desprez,
and Alan Su.
Plug-in Scheduler Design for a Distributed Grid Environment..
Technical report RR-6030,
INRIA,
November 2006.
Note: Also available as LIP Research Report 2006-41. hal number inria-00115949.
Keywords:
Grid Computing,
Scheduling,
Performance Prediction,
DIET.
| Abstract: |
This report presents the approach chosen within the DIET (Distributed Interactive Engineering Toolbox) project a GridRPC environment to allow a resource broker to be tuned for specific application classes. Our design allows the use of generic or application dependent performance measures in a simple and seamless way. |
@TechReport{ TechReportRR-INRIA-RR-6030,
abstract = {This report presents the approach chosen within the DIET (Distributed Interactive Engineering Toolbox) project a GridRPC environment to allow a resource broker to be tuned for specific application classes. Our design allows the use of generic or application dependent performance measures in a simple and seamless way.},
author = {Caron, Eddy and Chis, Andr{\'e}ea and Desprez, Fr{\'e}d{\'e}ric and Su, Alan},
institution = {INRIA},
keywords = {Grid Computing, Scheduling, Performance Prediction, DIET},
month = nov,
note = {Also available as LIP Research Report 2006-41. hal number inria-00115949},
number = {RR-6030},
title = {Plug-in Scheduler Design for a Distributed Grid Environment.},
url = {https://hal.inria.fr/inria-00115949},
year = 2006
}
-
Eddy Caron,
Pushpinder Kaur Chouhan,
and Holly Dail.
GoDIET: A Deployment Tool for Distributed Middleware on Grid 5000.
Technical report RR-5886,
Laboratoire de l'Informatique du Parallélisme (LIP),
April 2006.
Note: Also available as INRIA Research Report 5886. hal number inria-00071382.
Keywords:
Deployment,
ASP,
Grid computing,
DIET.
@TechReport{ TechReportRR-Laboratoire-RR-5886,
author = {Caron, Eddy and Chouhan, Pushpinder Kaur and Dail, Holly},
institution = {Laboratoire de l'Informatique du Parall{\'e}lisme (LIP)},
keywords = {Deployment, ASP, Grid computing,DIET},
month = apr,
note = {Also available as INRIA Research Report 5886. hal number inria-00071382},
number = {RR-5886},
title = {GoDIET: A Deployment Tool for Distributed Middleware on Grid 5000},
url = {https://hal.inria.fr/inria-00071382},
year = 2006
}
-
Eddy Caron,
Pushpinder Kaur Chouhan,
and Holly Dail.
GoDIET: A Deployment Tool for Distributed Middleware on Grid 5000.
Technical report RR-5886,
Institut National de Recherche en Informatique et en Automatique (INRIA),
April 2006.
Note: Also available as LIP Research Report 2006-17. hal number inria-00071382.
Keywords:
Deployment,
ASP,
Grid computing,
DIET.
@TechReport{ TechReportRR-Institut-RR-5886,
author = {Caron, Eddy and Chouhan, Pushpinder Kaur and Dail, Holly},
institution = {Institut National de Recherche en Informatique et en Automatique (INRIA)},
keywords = {Deployment, ASP, Grid computing,DIET},
month = apr,
note = {Also available as LIP Research Report 2006-17. hal number inria-00071382},
number = {RR-5886},
title = {GoDIET: A Deployment Tool for Distributed Middleware on Grid 5000},
url = {https://hal.inria.fr/inria-00071382},
year = 2006
}
-
Eddy Caron,
Frédéric Desprez,
Charles Fourdrignier,
Franck Petit,
and Cédric Tedeschi.
A Repair Mechanism for Fault-Tolerance for Tree-Structured Peer-to-Peer Systems.
Technical report RR6029,
Institut National de Recherche en Informatique et en Automatique (INRIA),
October 2006.
Note: Also available as LIP Research Report 2001-34. hal number inria-00115997.
Keywords:
Fault tolerance,
peer-to-peer,
prefix trees.
| Abstract: |
Facing the limits of traditional tools of resource management within computational grids (related to scale, dynamicity, etc. of the platforms newly considered), new approaches, based on peer-to-peer technologies are emerging. The resource discovery and in particular the service discovery is concerned by this evolution. Among the solutions, a promising one is the indexing of resources using trie structures and more particularly prefix trees. The major advantages of trie-structured approaches is the capability to support search queries on ranges of values with a latency growing logarithmically in the number of nodes in the trie. Those techniques are easy to extend to multicriteria searches. One drawback of using tries is its inherent poor robustness in a dynamic environment, where nodes join and leave the network, leading to the split of the tree into a forest, which results in the impossibility to route requests. Within most recent approaches, the fault-tolerance is a prevention mechanism, often replication-based. The replication can be costly in term of resources required. In this paper, we propose a fault-tolerance protocol that reconnects subtrees a posteriori, after crashes, to have again a connected graph and then reorder the nodes to rebuild a consistent tree. |
@TechReport{ TechReportRR-Institut-RR6029,
abstract = {Facing the limits of traditional tools of resource management within computational grids (related to scale, dynamicity, etc. of the platforms newly considered), new approaches, based on peer-to-peer technologies are emerging. The resource discovery and in particular the service discovery is concerned by this evolution. Among the solutions, a promising one is the indexing of resources using trie structures and more particularly prefix trees. The major advantages of trie-structured approaches is the capability to support search queries on ranges of values with a latency growing logarithmically in the number of nodes in the trie. Those techniques are easy to extend to multicriteria searches. One drawback of using tries is its inherent poor robustness in a dynamic environment, where nodes join and leave the network, leading to the split of the tree into a forest, which results in the impossibility to route requests. Within most recent approaches, the fault-tolerance is a prevention mechanism, often replication-based. The replication can be costly in term of resources required. In this paper, we propose a fault-tolerance protocol that reconnects subtrees a posteriori, after crashes, to have again a connected graph and then reorder the nodes to rebuild a consistent tree.},
author = {Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Fourdrignier, Charles and Petit, Franck and Tedeschi, C{\'e}dric},
institution = {Institut National de Recherche en Informatique et en Automatique (INRIA)},
keywords = {Fault tolerance, peer-to-peer, prefix trees},
month = oct,
note = {Also available as LIP Research Report 2001-34. hal number inria-00115997},
number = {RR6029},
title = {A Repair Mechanism for Fault-Tolerance for Tree-Structured Peer-to-Peer Systems},
url = {https://hal.inria.fr/inria-00115997},
year = 2006
}
-
Eddy Caron,
Frédéric Desprez,
Charles Fourdrignier,
Franck Petit,
and Cédric Tedeschi.
A Repair Mechanism for Fault-Tolerance for Tree-Structured Peer-to-Peer Systems.
Technical report RR2006-34,
Laboratoire de l'Informatique du Parallélisme (LIP),
October 2006.
Note: Also available as INRIA Research Report 6029. hal-01430504.
Keywords:
Fault tolerance,
peer-to-peer,
prefix trees.
| Abstract: |
Facing the limits of traditional tools of resource management within computational grids (related to scale, dynamicity, etc. of the platforms newly considered), new approaches, based on peer-to-peer technologies are emerging. The resource discovery and in particular the service discovery is concerned by this evolution. Among the solutions, a promising one is the indexing of resources using trie structures and more particularly prefix trees. The major advantages of trie-structured approaches is the capability to support search queries on ranges of values with a latency growing logarithmically in the number of nodes in the trie. Those techniques are easy to extend to multicriteria searches. One drawback of using tries is its inherent poor robustness in a dynamic environment, where nodes join and leave the network, leading to the split of the tree into a forest, which results in the impossibility to route requests. Within most recent approaches, the fault-tolerance is a prevention mechanism, often replication-based. The replication can be costly in term of resources required. In this paper, we propose a fault-tolerance protocol that reconnects subtrees a posteriori, after crashes, to have again a connected graph and then reorder the nodes to rebuild a consistent tree. |
@TechReport{ TechReportRR-Laboratoire-RR2006-34,
abstract = {Facing the limits of traditional tools of resource management within computational grids (related to scale, dynamicity, etc. of the platforms newly considered), new approaches, based on peer-to-peer technologies are emerging. The resource discovery and in particular the service discovery is concerned by this evolution. Among the solutions, a promising one is the indexing of resources using trie structures and more particularly prefix trees. The major advantages of trie-structured approaches is the capability to support search queries on ranges of values with a latency growing logarithmically in the number of nodes in the trie. Those techniques are easy to extend to multicriteria searches. One drawback of using tries is its inherent poor robustness in a dynamic environment, where nodes join and leave the network, leading to the split of the tree into a forest, which results in the impossibility to route requests. Within most recent approaches, the fault-tolerance is a prevention mechanism, often replication-based. The replication can be costly in term of resources required. In this paper, we propose a fault-tolerance protocol that reconnects subtrees a posteriori, after crashes, to have again a connected graph and then reorder the nodes to rebuild a consistent tree.},
author = {Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Fourdrignier, Charles and Petit, Franck and Tedeschi, C{\'e}dric},
institution = {Laboratoire de l'Informatique du Parall{\'e}lisme (LIP)},
keywords = {Fault tolerance, peer-to-peer, prefix trees},
month = oct,
note = {Also available as INRIA Research Report 6029. hal-01430504},
number = {RR2006-34},
pdf = {http://www.ens-lyon.fr/LIP/Pub/Rapports/RR/RR2006/RR2006-34.pdf},
title = {A Repair Mechanism for Fault-Tolerance for Tree-Structured Peer-to-Peer Systems},
url = {https://hal.inria.fr/hal-01430504},
year = 2006
}
-
Eddy Caron,
Frédéric Desprez,
and Cédric Tedeschi.
A Dynamic Prefix Tree for the Service Discovery Within Large Scale Grids.
Technical report RR2006-33,
Laboratoire de l'Informatique du Parallélisme (LIP),
October 2006.
Note: Hal-01430005. Also available as INRIA Research Report 6028.
Keywords:
Service discovery,
Computational grids,
Peer-to-peer,
Prefix trees.
| Abstract: |
Within computational grids, some services (software components, linear algebra libraries, etc.) are made available by some servers to some clients. In spite of the growing popularity of such grids, the service discovery, although efficient in many cases, does not reach several requirements. Among them, the flexibility of the discovery and its efficiency on wide-area dynamic platforms are two major issues. Therefore, it becomes crucial to propose new tools coping with such platforms. Emerging peer-to-peer technologies provide algorithms allowing the distribution and the retrieval of data items while addressing the dynamicity of the underlying network. We study in this paper the service discovery in a pure peer-to-peer environment. We describe a new trie-based approach for the service discovery that supports range queries and automatic completion of partial search strings, while providing fault-tolerance, and partially taking into account the topology of the underlying network. We validate this approach both by analysis and simulation. Traditional metrics considered in peer-to-peer systems exhibits interesting complexities within our architecture. The analysis' results are confirmed by some simulation experiments run using several grid's data sets. |
@TechReport{ TechReportRR-Laboratoire-RR2006-33,
abstract = {Within computational grids, some services (software components, linear algebra libraries, etc.) are made available by some servers to some clients. In spite of the growing popularity of such grids, the service discovery, although efficient in many cases, does not reach several requirements. Among them, the flexibility of the discovery and its efficiency on wide-area dynamic platforms are two major issues. Therefore, it becomes crucial to propose new tools coping with such platforms. Emerging peer-to-peer technologies provide algorithms allowing the distribution and the retrieval of data items while addressing the dynamicity of the underlying network. We study in this paper the service discovery in a pure peer-to-peer environment. We describe a new trie-based approach for the service discovery that supports range queries and automatic completion of partial search strings, while providing fault-tolerance, and partially taking into account the topology of the underlying network. We validate this approach both by analysis and simulation. Traditional metrics considered in peer-to-peer systems exhibits interesting complexities within our architecture. The analysis' results are confirmed by some simulation experiments run using several grid's data sets. },
author = {Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Tedeschi, C{\'e}dric},
institution = {Laboratoire de l'Informatique du Parall{\'e}lisme (LIP)},
keywords = {Service discovery, Computational grids, Peer-to-peer, Prefix trees},
month = oct,
note = {hal-01430005. Also available as INRIA Research Report 6028.},
number = {RR2006-33},
pdf = {http://www.ens-lyon.fr/LIP/Pub/Rapports/RR/RR2006/RR2006-33.pdf},
title = {A Dynamic Prefix Tree for the Service Discovery Within Large Scale Grids},
url = {https://hal.inria.fr/hal-01430005},
year = 2006
}
-
Eddy Caron,
Frédéric Desprez,
and Cédric Tedeschi.
A Dynamic Prefix Tree for the Service Discovery Within Large Scale Grids.
Technical report RR-6028,
Institut National de Recherche en Informatique et en Automatique (INRIA),
October 2006.
Note: Also available as LIP Research Report 2001-33. hal number inria-00116111.
Keywords:
Service discovery,
Computational grids,
Peer-to-peer,
Prefix trees.
| Abstract: |
Within computational grids, some services (software components, linear algebra libraries, etc.) are made available by some servers to some clients. In spite of the growing popularity of such grids, the service discovery, although efficient in many cases, does not reach several requirements. Among them, the flexibility of the discovery and its efficiency on wide-area dynamic platforms are two major issues. Therefore, it becomes crucial to propose new tools coping with such platforms. Emerging peer-to-peer technologies provide algorithms allowing the distribution and the retrieval of data items while addressing the dynamicity of the underlying network. We study in this paper the service discovery in a pure peer-to-peer environment. We describe a new trie-based approach for the service discovery that supports range queries and automatic completion of partial search strings, while providing fault-tolerance, and partially taking into account the topology of the underlying network. We validate this approach both by analysis and simulation. Traditional metrics considered in peer-to-peer systems exhibits interesting complexities within our architecture. The analysis' results are confirmed by some simulation experiments run using several grid's data sets. |
@TechReport{ TechReportRR-Institut-RR-6028,
abstract = {Within computational grids, some services (software components, linear algebra libraries, etc.) are made available by some servers to some clients. In spite of the growing popularity of such grids, the service discovery, although efficient in many cases, does not reach several requirements. Among them, the flexibility of the discovery and its efficiency on wide-area dynamic platforms are two major issues. Therefore, it becomes crucial to propose new tools coping with such platforms. Emerging peer-to-peer technologies provide algorithms allowing the distribution and the retrieval of data items while addressing the dynamicity of the underlying network. We study in this paper the service discovery in a pure peer-to-peer environment. We describe a new trie-based approach for the service discovery that supports range queries and automatic completion of partial search strings, while providing fault-tolerance, and partially taking into account the topology of the underlying network. We validate this approach both by analysis and simulation. Traditional metrics considered in peer-to-peer systems exhibits interesting complexities within our architecture. The analysis' results are confirmed by some simulation experiments run using several grid's data sets. },
author = {Caron, Eddy and Desprez, Fr{\'e}d{\'e}ric and Tedeschi, C{\'e}dric},
institution = {Institut National de Recherche en Informatique et en Automatique (INRIA)},
keywords = {Service discovery, Computational grids, Peer-to-peer, Prefix trees},
month = oct,
note = {Also available as LIP Research Report 2001-33. hal number inria-00116111},
number = {RR-6028},
title = {A Dynamic Prefix Tree for the Service Discovery Within Large Scale Grids},
url = {https://hal.inria.fr/inria-00116111},
year = 2006
}