Scheduling malleable applications in multicluster systems

J. Buisson; O.O. Sonmez; H.H. Mohamed; W. Lammers; D.H.J. Epema

doi:10.1109/CLUSTR.2007.4629252

Scheduling malleable applications in multicluster systems

J. Buisson, O.O. Sonmez, H.H. Mohamed, W. Lammers, D.H.J. Epema

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

33 Citations (Scopus)

191 Downloads (Pure)

Abstract

In large-scale distributed execution environments such as multicluster systems and grids, resource availability may vary due to resource failures and because resources may be added to or withdrawn from such environments at any time. In addition, single sites in such systems may have to deal with workloads originating from both local users and from many other sources. As a result, application malleability, that is, the property of applications to deal with a varying amount of resources during their execution, may be very beneficial for performance. In this paper we present the design of the support of and scheduling policies for malleability in our Koala multicluster scheduler with the help of our Dynaco framework for application malleability. In addition, we show the results of experiments with scheduling malleable workloads with Koala in our DAS multicluster testbed.

Original language	English
Title of host publication	Proceedings of the IEEE International Conference on Cluster Computing (ICCC'07, Austin TX, USA, September 17-20, 2007)
Publisher	Institute of Electrical and Electronics Engineers
Pages	372-381
ISBN (Print)	978-1-4244-1387-4
DOIs	https://doi.org/10.1109/CLUSTR.2007.4629252
Publication status	Published - 2007

Access to Document

10.1109/CLUSTR.2007.4629252

Metis255935Final published version, 304 KB

Cite this

Buisson, J., Sonmez, O. O., Mohamed, H. H., Lammers, W., & Epema, D. H. J. (2007). Scheduling malleable applications in multicluster systems. In Proceedings of the IEEE International Conference on Cluster Computing (ICCC'07, Austin TX, USA, September 17-20, 2007) (pp. 372-381). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CLUSTR.2007.4629252

@inproceedings{4b62998821a942bbb9333109ca9263ed,

title = "Scheduling malleable applications in multicluster systems",

abstract = "In large-scale distributed execution environments such as multicluster systems and grids, resource availability may vary due to resource failures and because resources may be added to or withdrawn from such environments at any time. In addition, single sites in such systems may have to deal with workloads originating from both local users and from many other sources. As a result, application malleability, that is, the property of applications to deal with a varying amount of resources during their execution, may be very beneficial for performance. In this paper we present the design of the support of and scheduling policies for malleability in our Koala multicluster scheduler with the help of our Dynaco framework for application malleability. In addition, we show the results of experiments with scheduling malleable workloads with Koala in our DAS multicluster testbed.",

author = "J. Buisson and O.O. Sonmez and H.H. Mohamed and W. Lammers and D.H.J. Epema",

year = "2007",

doi = "10.1109/CLUSTR.2007.4629252",

language = "English",

isbn = "978-1-4244-1387-4",

pages = "372--381",

booktitle = "Proceedings of the IEEE International Conference on Cluster Computing (ICCC'07, Austin TX, USA, September 17-20, 2007)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Scheduling malleable applications in multicluster systems. / Buisson, J.; Sonmez, O.O.; Mohamed, H.H. et al.
Proceedings of the IEEE International Conference on Cluster Computing (ICCC'07, Austin TX, USA, September 17-20, 2007). Institute of Electrical and Electronics Engineers, 2007. p. 372-381.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Scheduling malleable applications in multicluster systems

AU - Buisson, J.

AU - Sonmez, O.O.

AU - Mohamed, H.H.

AU - Lammers, W.

AU - Epema, D.H.J.

PY - 2007

Y1 - 2007

N2 - In large-scale distributed execution environments such as multicluster systems and grids, resource availability may vary due to resource failures and because resources may be added to or withdrawn from such environments at any time. In addition, single sites in such systems may have to deal with workloads originating from both local users and from many other sources. As a result, application malleability, that is, the property of applications to deal with a varying amount of resources during their execution, may be very beneficial for performance. In this paper we present the design of the support of and scheduling policies for malleability in our Koala multicluster scheduler with the help of our Dynaco framework for application malleability. In addition, we show the results of experiments with scheduling malleable workloads with Koala in our DAS multicluster testbed.

AB - In large-scale distributed execution environments such as multicluster systems and grids, resource availability may vary due to resource failures and because resources may be added to or withdrawn from such environments at any time. In addition, single sites in such systems may have to deal with workloads originating from both local users and from many other sources. As a result, application malleability, that is, the property of applications to deal with a varying amount of resources during their execution, may be very beneficial for performance. In this paper we present the design of the support of and scheduling policies for malleability in our Koala multicluster scheduler with the help of our Dynaco framework for application malleability. In addition, we show the results of experiments with scheduling malleable workloads with Koala in our DAS multicluster testbed.

U2 - 10.1109/CLUSTR.2007.4629252

DO - 10.1109/CLUSTR.2007.4629252

M3 - Conference contribution

SN - 978-1-4244-1387-4

SP - 372

EP - 381

BT - Proceedings of the IEEE International Conference on Cluster Computing (ICCC'07, Austin TX, USA, September 17-20, 2007)

PB - Institute of Electrical and Electronics Engineers

ER -

Scheduling malleable applications in multicluster systems

Abstract

Access to Document

Fingerprint

Cite this