Automatic middleware deployment planning on heterogeneous platforms

Abstract : The use of many distributed, heterogeneous resources as a large collective platformoffers great potential. A key issue for these grid platforms is middleware scalabilityand how middleware services can be mapped on the available resources. Optimizingdeployment is a difficult problem with no existing general solutions. In this paper,we address the following problem: how to perform out an adapted deployment for ahierarchy of servers and resource brokers on a heterogeneous system?Our objective is to generate a best platform from the available nodes so as to fulfillthe clients demands. However, finding the best deployment among heterogeneousresources is a hard problem since it is close to find the best broadcast tree in a generalgraph, which is known to be NP-complete.Thus, in this paper, we present a heuristic for middleware deployment on heterogeneousresources. We apply our heuristic to automatically deploy a distributed ProblemSolving Environment on a large scale grid. We present experiments comparing the automaticallygenerated deployment against a number of other reasonable deployments.
Document type :
Reports
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download

https://hal-lara.archives-ouvertes.fr/hal-02102782
Contributor : Colette Orange <>
Submitted on : Wednesday, April 17, 2019 - 4:15:35 PM
Last modification on : Tuesday, April 23, 2019 - 2:24:08 PM

File

LIP-RR_08-23.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02102782, version 1

Collections

Citation

Eddy Caron, Pushinder Kaur Chouhan, Frédéric Desprez. Automatic middleware deployment planning on heterogeneous platforms. [Research Report] LIP RR-2008-23, Laboratoire de l'informatique du parallélisme. 2008, 2+14p. ⟨hal-02102782⟩

Share

Metrics

Record views

15

Files downloads

30