Skip to Main content Skip to Navigation
Conference papers

Integrating Deadline-Constrained Checkpointing in a Batch Scheduler for Dynamic Environments

Blaise-Omer Yenke 1 Jean-Francois Mehaut 2 Jean-Michel Nlong Ii Rodrigue Chakode 1
1 LIG - Laboratoire d'Informatique de Grenoble
2 MESCAL - Middleware efficiently scalable
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : This paper sets out to present the integration of the scheduling of deadline-constrained checkpointing in a batch scheduler for dynamic environments such as virtual clusters. The checkpointing scheduler implemented focuses on the parallel checkpointing on a unique server of long-running independent applications in a virtual cluster made up of free resources for long periods of an intranet network, assuming that the resources must be released within a delay T . As parallel checkpointing on a unique server can face bandwidth constraints, the checkpointing scheduler uses a func tion that gives the aggregated bandwidth suitable for the parallel checkpointing of m applications of aggregated size V to solve the deadline-constrained checkpointing problem within the deadline T. Specifically, we present the integration of the checkpointing scheduler in the batch scheduler OAR. This implementation uses data from the OAR database for the checkpointing scheduling. It is portable and can be easily modified to interact with any other batch scheduler, provided that the structure of the database is known and an estimator of the bandwidth of the system suitable for parallel checkpointing available. Experimental results obtained on a virtual cluster built on GRID5000 show that the implementation of the checkpointing scheduler does not induce a significant overhead on checkpointing mechanisms. As a consequence, this work aims at providing HPC platforms for a tool to enhance the quality of services offered to end users.
Keywords : Scheduling Checkpointing Batch Scheduler Dynamic Environments
Document type :
Conference papers
Complete list of metadatas
https://hal.inria.fr/inria-00574568
Contributor : Rodrigue Chakode <>
Submitted on : Tuesday, March 8, 2011 - 1:25:05 PM
Last modification on : Thursday, November 19, 2020 - 1:00:27 PM

Identifiers

  • HAL Id : inria-00574568, version 1

Collections

CNRS | INRIA | LIG | GRID5000 | POLYTECH-GRENOBLE | SILECS | UGA

Citation

Blaise-Omer Yenke, Jean-Francois Mehaut, Jean-Michel Nlong Ii, Rodrigue Chakode. Integrating Deadline-Constrained Checkpointing in a Batch Scheduler for Dynamic Environments. SE 2010: Annual International Conference on Software Engineering, Dec 2010, Phuket Beach Resort, Thailand, Thailand. pp.156-163. ⟨inria-00574568⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

311

 

Contact                    Legal Notice                    Personal Data