Improving Many-Task Computing in Scientific Workflows Using P2P Techniques

Jonas Dias 1 Eduardo Ogasawara 1, 2 Daniel De Oliveira 1 Esther Pacitti 3, 4 Marta Mattoso 1
1 COPPE-UFRJ - COPPE - Instituto Alberto Luiz Coimbra de Pós-Graduação e Pesquisa de Engenharia
2 Federal Center of Technological Education
3 ZENITH - Scientific Data Management
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier, CRISAM - Inria Sophia Antipolis - Méditerranée
4 ATLAS - Complex data management in distributed systems
UN - Université de Nantes, Inria Rennes – Bretagne Atlantique
Abstract : Large-scale scientific experiments are usually supported by scientific workflows that may demand high performance computing infrastructure. Within a given experiment, the same workflow may be explored with different sets of parameters. However, the parallelization of the workflow instances is hard to be accomplished mainly due to the heterogeneity of its activities. Many-Task computing paradigm seems to be a candidate approach to support workflow activity parallelism. However, scheduling a huge amount of workflow activities on large clusters may be susceptible to resource failures and overloading. In this paper, we propose Heracles, an approach to apply consolidated P2P techniques to improve Many-Task computing of workflow activities on large clusters. We present a fault tolerance mechanism, a dynamic resource management and a hierarchical organization of computing nodes to handle workflow instances execution properly. We have evaluated Heracles by executing experimental analysis regarding the benefits of P2P techniques on the workflow execution time.
Document type :
Conference papers
Complete list of metadatas

Cited literature [30 references]  Display  Hide  Download
https://hal-lirmm.ccsd.cnrs.fr/lirmm-00641008
Contributor : Fady Draidi <>
Submitted on : Monday, November 14, 2011 - 4:04:57 PM
Last modification on : Tuesday, December 4, 2018 - 2:32:05 PM
Long-term archiving on: Wednesday, February 15, 2012 - 2:27:11 AM

File

paper07-1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : lirmm-00641008, version 1

Collections

CNRS | INRIA | UNIV-NANTES | ZENITH | LIRMM | MIPS | UNIV-MONTPELLIER

Citation

Jonas Dias, Eduardo Ogasawara, Daniel De Oliveira, Esther Pacitti, Marta Mattoso. Improving Many-Task Computing in Scientific Workflows Using P2P Techniques. MTAGS: Many-Task Computing on Grids and Supercomputers, 2010, New Orleans, United States. pp.31-40. ⟨lirmm-00641008⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

556

Files downloads

546

Contact

Informations

CCSD