The Use of Incremental Schedule-based Approach for Efficient Job Scheduling

KLUSÁČEK, Dalibor and Hana RUDOVÁ. The Use of Incremental Schedule-based Approach for Efficient Job Scheduling. In Sixth Doctoral Workshop on Mathematical and Engineering Methods in Computer Science (MEMICS 2010). 2010. ISBN 978-80-87342-10-7.

Basic information

• Original name: The Use of Incremental Schedule-based Approach for Efficient Job Scheduling
• Authors: KLUSÁČEK, Dalibor (203 Czech Republic, guarantor, belonging to the institution) and Hana RUDOVÁ (203 Czech Republic, belonging to the institution).
• Edition: Sixth Doctoral Workshop on Mathematical and Engineering Methods in Computer Science (MEMICS 2010), 2010.

Other information

• Original language: English
• Type of outcome: Conference abstract
• Field of Study: 10201 Computer sciences, information science, bioinformatics
• Country of publisher: Czech Republic
• Confidentiality degree: is not subject to a state or trade secret
• RIV identification code: RIV/00216224:14330/10:00045269
• Organization unit: Faculty of Informatics
• ISBN: 978-80-87342-10-7
• Keywords in English: Grid; scheduling; incremental;efficient
• Tags: International impact, Reviewed

Abstract

Common requirements of users of computational clusters and Grids cannot be easily guaranteed by the current widely used queue-based scheduling approaches. We concentrate on the application of schedule-based methods that improve both the service delivered to the user as well as the traditional objective of machine usage. The Grid/cluster scheduling problem is dynamic due to changing state of the system. In such an environment, scheduling algorithm must be flexible and reasonably fast. Unlike to previous works, our schedule-based algorithms work in an ``incremental fashion", keeping the necessary runtime in an acceptable level while still enabling the application of advanced optimization algorithms. Incremental approach allows to keep the algorithm runtime low in contrast to the situations when the schedule is re-computed from scratch upon each job arrival. Moreover, the schedule-based algorithms show significant improvement in the quality of optimization in comparison with the queue-based methods.

Links

• MSM0021622419, plan (intention): Name: Vysoce paralelní a distribuované výpočetní systémy

Investor: Ministry of Education, Youth and Sports of the CR, Highly Parallel and Distributed Computing Systems

• MUNI/A/0914/2009, interní kód MU: Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace (Acronym: SV-FI MAV)

Investor: Masaryk University, Category A