Load balancing across near-homogeneous multi-resource servers

William Leinberger, George Karypis, Vipin Kumar, Rupak Biswas

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

An emerging model for computational grids interconnects similar multi-resource servers from distributed sites. A job submitted to the grid can be executed by any of the servers; however, resource size or balance may be different across servers. One approach to resource management for this grid is to layer a global load distribution system on top of the local job management systems at each site. Unfortunately, classical load distribution policies fail on two aspects when applied to a multi-resource server grid. First, simple load indices may not recognize that a resource imbalance exists at a server. Second, classical job selection policies do not actively correct such a resource imbalanced state. We show through simulation that new policies based on resource balancing perform consistently better than the classical load distribution strategies.

Original languageEnglish (US)
Pages (from-to)60-71
Number of pages12
JournalProceedings of the Heterogeneous Computing Workshop, HCW
StatePublished - Jan 1 2000

Fingerprint

Resource allocation
Servers

Cite this

Load balancing across near-homogeneous multi-resource servers. / Leinberger, William; Karypis, George; Kumar, Vipin; Biswas, Rupak.

In: Proceedings of the Heterogeneous Computing Workshop, HCW, 01.01.2000, p. 60-71.

Research output: Contribution to journalArticle

@article{5b0f890fa35b4d5bb6a659d69d5f1317,
title = "Load balancing across near-homogeneous multi-resource servers",
abstract = "An emerging model for computational grids interconnects similar multi-resource servers from distributed sites. A job submitted to the grid can be executed by any of the servers; however, resource size or balance may be different across servers. One approach to resource management for this grid is to layer a global load distribution system on top of the local job management systems at each site. Unfortunately, classical load distribution policies fail on two aspects when applied to a multi-resource server grid. First, simple load indices may not recognize that a resource imbalance exists at a server. Second, classical job selection policies do not actively correct such a resource imbalanced state. We show through simulation that new policies based on resource balancing perform consistently better than the classical load distribution strategies.",
author = "William Leinberger and George Karypis and Vipin Kumar and Rupak Biswas",
year = "2000",
month = "1",
day = "1",
language = "English (US)",
pages = "60--71",
journal = "Proceedings of the Heterogeneous Computing Workshop, HCW",

}

TY - JOUR

T1 - Load balancing across near-homogeneous multi-resource servers

AU - Leinberger, William

AU - Karypis, George

AU - Kumar, Vipin

AU - Biswas, Rupak

PY - 2000/1/1

Y1 - 2000/1/1

N2 - An emerging model for computational grids interconnects similar multi-resource servers from distributed sites. A job submitted to the grid can be executed by any of the servers; however, resource size or balance may be different across servers. One approach to resource management for this grid is to layer a global load distribution system on top of the local job management systems at each site. Unfortunately, classical load distribution policies fail on two aspects when applied to a multi-resource server grid. First, simple load indices may not recognize that a resource imbalance exists at a server. Second, classical job selection policies do not actively correct such a resource imbalanced state. We show through simulation that new policies based on resource balancing perform consistently better than the classical load distribution strategies.

AB - An emerging model for computational grids interconnects similar multi-resource servers from distributed sites. A job submitted to the grid can be executed by any of the servers; however, resource size or balance may be different across servers. One approach to resource management for this grid is to layer a global load distribution system on top of the local job management systems at each site. Unfortunately, classical load distribution policies fail on two aspects when applied to a multi-resource server grid. First, simple load indices may not recognize that a resource imbalance exists at a server. Second, classical job selection policies do not actively correct such a resource imbalanced state. We show through simulation that new policies based on resource balancing perform consistently better than the classical load distribution strategies.

UR - http://www.scopus.com/inward/record.url?scp=0033906454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033906454&partnerID=8YFLogxK

M3 - Article

SP - 60

EP - 71

JO - Proceedings of the Heterogeneous Computing Workshop, HCW

JF - Proceedings of the Heterogeneous Computing Workshop, HCW

ER -