Experimental study of large-scale computing on virtualized resources

Juan C. Martinez, Lixi Wang, Ming Zhao, S. Masoud Sadjadi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Parallel applications have a pressing need for the utilization of more and more resources to meet users' performance expectations. Unfortunately, these resources are not necessarily available within one single domain. Grid computing provides a solution for scaling out from a single domain; however, it also brings another problem for some applications: resource heterogeneity. Since some applications require having homogeneous resources for their execution, virtualizing the resources is a noble and viable solution. In this paper, we present two parallel applications, namely WRF and mpiBLAST and report the results of different runs scaling them out from 2 to 128 virtual nodes. Later, we analyze the effects of scaling out based on the application's communication behavior.

Original languageEnglish (US)
Title of host publicationProceedings of the 3rd International Workshop on Virtualization Technologies in Distributed Computing, VTDC'09
Pages35-41
Number of pages7
DOIs
StatePublished - 2009
Externally publishedYes
Event3rd International Workshop on Virtualization Technologies in Distributed Computing, VTDC'09 - Barcelona, Spain
Duration: Jun 15 2009Jun 15 2009

Other

Other3rd International Workshop on Virtualization Technologies in Distributed Computing, VTDC'09
CountrySpain
CityBarcelona
Period6/15/096/15/09

Fingerprint

Grid computing
Communication

Keywords

  • Grid computing
  • Performance evaluation
  • Virtualization

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Software

Cite this

Martinez, J. C., Wang, L., Zhao, M., & Sadjadi, S. M. (2009). Experimental study of large-scale computing on virtualized resources. In Proceedings of the 3rd International Workshop on Virtualization Technologies in Distributed Computing, VTDC'09 (pp. 35-41) https://doi.org/10.1145/1555336.1555343

Experimental study of large-scale computing on virtualized resources. / Martinez, Juan C.; Wang, Lixi; Zhao, Ming; Sadjadi, S. Masoud.

Proceedings of the 3rd International Workshop on Virtualization Technologies in Distributed Computing, VTDC'09. 2009. p. 35-41.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Martinez, JC, Wang, L, Zhao, M & Sadjadi, SM 2009, Experimental study of large-scale computing on virtualized resources. in Proceedings of the 3rd International Workshop on Virtualization Technologies in Distributed Computing, VTDC'09. pp. 35-41, 3rd International Workshop on Virtualization Technologies in Distributed Computing, VTDC'09, Barcelona, Spain, 6/15/09. https://doi.org/10.1145/1555336.1555343
Martinez JC, Wang L, Zhao M, Sadjadi SM. Experimental study of large-scale computing on virtualized resources. In Proceedings of the 3rd International Workshop on Virtualization Technologies in Distributed Computing, VTDC'09. 2009. p. 35-41 https://doi.org/10.1145/1555336.1555343
Martinez, Juan C. ; Wang, Lixi ; Zhao, Ming ; Sadjadi, S. Masoud. / Experimental study of large-scale computing on virtualized resources. Proceedings of the 3rd International Workshop on Virtualization Technologies in Distributed Computing, VTDC'09. 2009. pp. 35-41
@inproceedings{ca8240baba5f4f279bf60ef502058d89,
title = "Experimental study of large-scale computing on virtualized resources",
abstract = "Parallel applications have a pressing need for the utilization of more and more resources to meet users' performance expectations. Unfortunately, these resources are not necessarily available within one single domain. Grid computing provides a solution for scaling out from a single domain; however, it also brings another problem for some applications: resource heterogeneity. Since some applications require having homogeneous resources for their execution, virtualizing the resources is a noble and viable solution. In this paper, we present two parallel applications, namely WRF and mpiBLAST and report the results of different runs scaling them out from 2 to 128 virtual nodes. Later, we analyze the effects of scaling out based on the application's communication behavior.",
keywords = "Grid computing, Performance evaluation, Virtualization",
author = "Martinez, {Juan C.} and Lixi Wang and Ming Zhao and Sadjadi, {S. Masoud}",
year = "2009",
doi = "10.1145/1555336.1555343",
language = "English (US)",
isbn = "9781605585802",
pages = "35--41",
booktitle = "Proceedings of the 3rd International Workshop on Virtualization Technologies in Distributed Computing, VTDC'09",

}

TY - GEN

T1 - Experimental study of large-scale computing on virtualized resources

AU - Martinez, Juan C.

AU - Wang, Lixi

AU - Zhao, Ming

AU - Sadjadi, S. Masoud

PY - 2009

Y1 - 2009

N2 - Parallel applications have a pressing need for the utilization of more and more resources to meet users' performance expectations. Unfortunately, these resources are not necessarily available within one single domain. Grid computing provides a solution for scaling out from a single domain; however, it also brings another problem for some applications: resource heterogeneity. Since some applications require having homogeneous resources for their execution, virtualizing the resources is a noble and viable solution. In this paper, we present two parallel applications, namely WRF and mpiBLAST and report the results of different runs scaling them out from 2 to 128 virtual nodes. Later, we analyze the effects of scaling out based on the application's communication behavior.

AB - Parallel applications have a pressing need for the utilization of more and more resources to meet users' performance expectations. Unfortunately, these resources are not necessarily available within one single domain. Grid computing provides a solution for scaling out from a single domain; however, it also brings another problem for some applications: resource heterogeneity. Since some applications require having homogeneous resources for their execution, virtualizing the resources is a noble and viable solution. In this paper, we present two parallel applications, namely WRF and mpiBLAST and report the results of different runs scaling them out from 2 to 128 virtual nodes. Later, we analyze the effects of scaling out based on the application's communication behavior.

KW - Grid computing

KW - Performance evaluation

KW - Virtualization

UR - http://www.scopus.com/inward/record.url?scp=70049097267&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70049097267&partnerID=8YFLogxK

U2 - 10.1145/1555336.1555343

DO - 10.1145/1555336.1555343

M3 - Conference contribution

AN - SCOPUS:70049097267

SN - 9781605585802

SP - 35

EP - 41

BT - Proceedings of the 3rd International Workshop on Virtualization Technologies in Distributed Computing, VTDC'09

ER -