The importance of complete data sets for job scheduling
simulations

D 2010

The importance of complete data sets for job scheduling simulations

KLUSÁČEK, Dalibor and Hana RUDOVÁ

Basic information

Original name

The importance of complete data sets for job scheduling simulations

Authors

KLUSÁČEK, Dalibor (203 Czech Republic, guarantor, belonging to the institution) and Hana RUDOVÁ (203 Czech Republic, belonging to the institution)

Edition

Heidelberg, Job Scheduling Strategies for Parallel Processing, Revised Selected Papers, p. 132-153, 22 pp. 2010

Publisher

Springer, Lecture Notes in Computer Science 6253

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Germany

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

References:

URL

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/10:00067181

Organization unit

Faculty of Informatics

ISBN

978-3-642-16504-7

ISSN

DOI

http://dx.doi.org/10.1007/978-3-642-16505-4_8

UT WoS

000286164600008

Keywords in English

Grid; Cluster; Scheduling; MetaCentrum; Workload; Failures; Specific Job Requirements

Abstract

V originále

This paper has been inspired by the study of the complex data set from the Czech National Grid MetaCentrum. Unlike other widely used workloads from Parallel Workloads Archive or Grid Workloads Archive, this data set includes additional information concerning machine failures, job requirements and machine parameters which allows to perform more realistic simulations. We show that large differences in the performance of various scheduling algorithms appear when these additional information are used. Moreover, we studied other publicly available workloads and partially reconstructed information concerning their machine failures and job requirements using statistical and analytical models to demonstrate that similar behavior is also expectable for other workloads. We suggest that additional information about both machines and jobs should be incorporated into the workloads archives to allow proper and more realistic simulations.

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

Citovat

KLUSÁČEK, Dalibor and Hana RUDOVÁ. The importance of complete data sets for job scheduling simulations. In Job Scheduling Strategies for Parallel Processing, Revised Selected Papers. Heidelberg: Springer, Lecture Notes in Computer Science 6253, 2010, p. 132-153. ISBN 978-3-642-16504-7. Available from: https://dx.doi.org/10.1007/978-3-642-16505-4_8.

@inproceedings{884609,
   author = {Klusáček, Dalibor and Rudová, Hana},
   address = {Heidelberg},
   booktitle = {Job Scheduling Strategies for Parallel Processing, Revised Selected Papers},
   doi = {http://dx.doi.org/10.1007/978-3-642-16505-4_8},
   keywords = {Grid; Cluster; Scheduling; MetaCentrum; Workload; Failures; Specific Job Requirements},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Heidelberg},
   isbn = {978-3-642-16504-7},
   pages = {132-153},
   publisher = {Springer, Lecture Notes in Computer Science 6253},
   title = {The importance of complete data sets for job scheduling simulations},
   url = {http://www.springer.com/computer/swe/book/978-3-642-16504-7},
   year = {2010}
}

TY  - JOUR
ID  - 884609
AU  - Klusáček, Dalibor - Rudová, Hana
PY  - 2010
TI  - The importance of complete data sets for job scheduling simulations
PB  - Springer, Lecture Notes in Computer Science 6253
CY  - Heidelberg
SN  - 9783642165047
KW  - Grid
KW  - Cluster
KW  - Scheduling
KW  - MetaCentrum
KW  - Workload
KW  - Failures
KW  - Specific Job Requirements
UR  - http://www.springer.com/computer/swe/book/978-3-642-16504-7
N2  - This paper has been inspired by the study of the complex data set from the Czech National Grid MetaCentrum. Unlike other widely used workloads from Parallel Workloads Archive or Grid Workloads Archive, this data set includes additional information concerning machine failures, job requirements and machine parameters which allows to perform more realistic simulations. We show that large differences in the performance of various scheduling algorithms appear when these additional information are used. Moreover, we studied other publicly available workloads and partially reconstructed information concerning their machine failures and job requirements using statistical and analytical models to demonstrate that similar behavior is also expectable for other workloads. We suggest that additional information about both machines and jobs should be incorporated into the workloads archives to allow proper and more realistic simulations.
ER  -

KLUSÁČEK, Dalibor and Hana RUDOVÁ. The importance of complete data sets for job scheduling simulations. In \textit{Job Scheduling Strategies for Parallel Processing, Revised Selected Papers}. Heidelberg: Springer, Lecture Notes in Computer Science 6253, 2010, p.~132-153. ISBN~978-3-642-16504-7. Available from: https://dx.doi.org/10.1007/978-3-642-16505-4\_{}8.

Detailed Information on Publication Record