Multi Resource Fairness: Problems and Challenges

D 2014

Multi Resource Fairness: Problems and Challenges

KLUSÁČEK, Dalibor, Hana RUDOVÁ and Michal JAROŠ

Basic information

Original name

Multi Resource Fairness: Problems and Challenges

Authors

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

Edition

1. vyd. Neuveden, Job Scheduling Strategies for Parallel Processing, p. 81-95, 15 pp. 2014

Publisher

Springer, Lecture Notes in Computer Science 8429

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

References:

webová stránka akce s odkazem na plný text publikace

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/14:00073408

Organization unit

Faculty of Informatics

ISBN

978-3-662-43778-0

ISSN

DOI

http://dx.doi.org/10.1007/978-3-662-43779-7_5

UT WoS

000343045800005

Keywords in English

Multi Resource Fairness; Fairshare; Penalty; Scheduling

Abstract

V originále

Current production resource management and scheduling systems often use some mechanism to guarantee fair sharing of computational resources among different users of the system. For example, the user who so far consumed small amount of CPU time gets higher priority and vice versa. The problem with such a solution is that it does not reflect other consumed resources like RAM, HDD storage capacity or GPU cores. Clearly, diffeffrent users may have highly heterogeneous demands concerning aforementioned resources, yet they are all prioritized only with respect to consumed CPU time. In this paper we show that such a single resource-based approach is unfair and is no longer suitable for nowadays systems. We provide a survey of existing works that somehow try to deal with this situation and we closely analyze and evaluate their characteristics. Next, we propose new enhanced approaches that would allow the development of usable multi resource-aware user prioritization mechanisms. We demonstrate that different consumed resources can be weighted and combined together within a single formula which can be used to establish users' priorities. Moreover, we show that when it comes to multiple resources, it is not always possible to find a suitable solution that would fulfill all fairness-related requirements.

Links

ED3.2.00/08.0144, research and development project

Name: CERIT Scientific Cloud

GAP202/12/0306, research and development project

Name: Dyschnet - Dynamické plánování a rozvrhování výpočetních a síťových zdrojů (Acronym: Dyschnet)

Investor: Czech Science Foundation

Citovat

KLUSÁČEK, Dalibor, Hana RUDOVÁ and Michal JAROŠ. Multi Resource Fairness: Problems and Challenges. Online. In N. Desai and W. Cirne. Job Scheduling Strategies for Parallel Processing. 1st ed. Neuveden: Springer, Lecture Notes in Computer Science 8429, 2014, p. 81-95. ISBN 978-3-662-43778-0. Available from: https://dx.doi.org/10.1007/978-3-662-43779-7_5.

@inproceedings{1113360,
   author = {Klusáček, Dalibor and Rudová, Hana and Jaroš, Michal},
   address = {Neuveden},
   booktitle = {Job Scheduling Strategies for Parallel Processing},
   doi = {http://dx.doi.org/10.1007/978-3-662-43779-7_5},
   edition = {1},
   editor = {N. Desai and W. Cirne},
   keywords = {Multi Resource Fairness; Fairshare; Penalty; Scheduling},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Neuveden},
   isbn = {978-3-662-43778-0},
   pages = {81-95},
   publisher = {Springer, Lecture Notes in Computer Science 8429},
   title = {Multi Resource Fairness: Problems and Challenges},
   url = {http://www.cs.huji.ac.il/~feit/parsched/jsspp13/},
   year = {2014}
}

TY  - JOUR
ID  - 1113360
AU  - Klusáček, Dalibor - Rudová, Hana - Jaroš, Michal
PY  - 2014
TI  - Multi Resource Fairness: Problems and Challenges
PB  - Springer, Lecture Notes in Computer Science 8429
CY  - Neuveden
SN  - 9783662437780
KW  - Multi Resource Fairness
KW  - Fairshare
KW  - Penalty
KW  - Scheduling
UR  - http://www.cs.huji.ac.il/~feit/parsched/jsspp13/
N2  - Current production resource management and scheduling systems often use some mechanism to guarantee fair sharing of computational resources among different users of the system. For example, the user who so far consumed small amount of CPU time gets higher priority and vice versa. The problem with such a solution is that it does not reflect other consumed resources like RAM, HDD storage capacity or GPU cores. Clearly, diffeffrent users may have highly heterogeneous demands concerning aforementioned resources, yet they are all prioritized only with respect to consumed CPU time. In this paper we show that such a single resource-based approach is unfair and is no longer suitable for nowadays systems. We provide a survey of existing works that somehow try to deal with this situation and we closely analyze and evaluate their characteristics. Next, we propose new enhanced approaches that would allow the development of usable multi resource-aware user prioritization mechanisms. We demonstrate that different consumed resources can be weighted and combined together within a single formula which can be used to establish users' priorities. Moreover, we show that when it comes to multiple resources, it is not always possible to find a suitable solution that would fulfill all fairness-related requirements.
ER  -

KLUSÁČEK, Dalibor, Hana RUDOVÁ and Michal JAROŠ. Multi Resource Fairness: Problems and Challenges. Online. In N. Desai and W. Cirne. \textit{Job Scheduling Strategies for Parallel Processing}. 1st ed. Neuveden: Springer, Lecture Notes in Computer Science 8429, 2014, p.~81-95. ISBN~978-3-662-43778-0. Available from: https://dx.doi.org/10.1007/978-3-662-43779-7\_{}5.

Detailed Information on Publication Record