article

Modeling and analysis of dynamic coscheduling in parallel and distributed environments

Authors:

Mark S. Squillante,

Anand Sivasubramaniam,

Natarajan Gautam,

Hubertus Franke,

Jose MoreiraAuthors Info & Claims

ACM SIGMETRICS Performance Evaluation Review, Volume 30, Issue 1

Pages 43 - 54

https://doi.org/10.1145/511399.511341

Published: 01 June 2002 Publication History

Abstract

Scheduling in large-scale parallel systems has been and continues to be an important and challenging research problem. Several key factors, including the increasing use of off-the-shelf clusters of workstations to build such parallel systems, have resulted in the emergence of a new class of scheduling strategies, broadly referred to as dynamic coscheduling. Unfortunately, the size of both the design and performance spaces of these emerging scheduling strategies is quite large, due in part to the numerous dynamic interactions among the different components of the parallel computing environment as well as the wide range of applications and systems that can comprise the parallel environment. This in turn makes it difficult to fully explore the benefits and limitations of the various proposed dynamic coscheduling approaches for large-scale systems solely with the use of simulation and/or experimentation.To gain a better understanding of the fundamental properties of different dynamic coscheduling methods, we formulate a general mathematical model of this class of scheduling strategies within a unified framework that allows us to investigate a wide range of parallel environments. We derive a matrix-analytic analysis based on a stochastic decomposition and a fixed-point iteration. A large number of numerical experiments are performed in part to examine the accuracy of our approach. These numerical results are in excellent agreement with detailed simulation results. Our mathematical model and analysis is then used to explore several fundamental design and performance tradeoffs associated with the class of dynamic coscheduling policies across a broad spectrum of parallel computing environments.

References

[1]

C. Anglano. A comparative evaluation of implicit coscheduling strategies for networks of workstations. Proceedings of International Symposium on High Performance Distributed Computing, 2000.

Digital Library

[2]

A. C. Arpaci-Dusseau, D. E. Culler, A. M. Mainwaring. Scheduling with implicit information in distributed systems. Proceedings of ACM SIGMETRICS Conference on Measurement & Modeling of Computer Systems, 1998.

Digital Library

[3]

S. Asmussen. Phase-type distributions and related point processes: Fitting and recent advances. Matrix-Analytic Methods in Stochastic Models, S. R. Chakravarthy & A. S. Alfa (eds.), 137-149, 1997.

[4]

N. J. Boden et al. Myrinet: A gigabit-per-second local area network. IEEE Micro, 15(1):29-36, 1995.

Digital Library

[5]

A. C. Dusseau, R. H. Arpaci, D. E. Culler. Effective distributed scheduling of parallel workloads. Proceedings of ACM SIGMETRICS Conference on Measurement & Modeling of Computer Systems, 25-36, 1996.

Digital Library

[6]

D. G. Feitelson. A survey of scheduling in multiprogrammed parallel systems, Research Report RC 19790(87657), IBM Research Division, 1994.

[7]

D. G. Feitelson, B. Nitzberg. Job characteristics of a production parallel scientific workload on the NASA Ames iPSC/860. Job Scheduling Strategies for Parallel Processing, D. G. Feitelson & L. Rudolph (eds.), 337-360, 1995. Springer-Verlag LNCS Vol. 949.

Digital Library

[8]

A. Feldmann, W. Whitt. Fitting mixtures of exponentials to long-tail distributions to analyze network performance models. Performance Evaluation, 31:245-279, 1998.

Digital Library

[9]

D. Gaver, P. Jacobs, G. Latouche. Finite birth-and-death models in randomly changing environments. Advances in Applied Probability, 16:715-731, 1984.

[10]

A. Horvath, M. Telek. Approximating heavy tailed behaviour with phase type distributions. Advances in Algorithmic Methods for Stochastic Models, G. Latouche & P. Taylor (eds.), 191-214, 2000.

[11]

S. G. Hotovy. Workload evolution on the Cornell Theory Center IBM SP2. Job Scheduling Strategies for Parallel Processing, D. G. Feitelson & L. Rudolph (eds.), 27-40, 1996. Springer-Verlag LNCS Vol. 1162.

Digital Library

[12]

N. Islam, A. Prodromidis, M. S. Squillante. Dynamic partitioning in different distributed-memory environments. Job Scheduling Strategies for Parallel Processing, D. G. Feitelson & L. Rudolph (eds.), 244-270, 1996. Springer-Verlag LNCS Vol. 1162.

Digital Library

[13]

G. Latouche, V. Ramaswami. Introduction to Matrix Analytic Methods in Stochastic Modeling. ASA-SIAM, Philadelphia, 1999.

[14]

J. D. C. Little. A proof of the queuing formula L = λW. Operations Research, 9:383-387, 1961.

Digital Library

[15]

S. Nagar, A. Banerjee, A. Sivasubramaniam, C. R. Das. A closer look at coscheduling approaches for a network of work stations. Proceedings of ACM Symposium on Parallel Algorithms & Architectures, 96-105, 1999.

Digital Library

[16]

M. F. Neuts. Matrix-Geometric Solutions in Stochastic Models: An Algorithmic Approach. The Johns Hopkins University Press, 1981.

[17]

B. F. Nielsen. Modelling long-range dependent and heavy-tailed phenomena by matrix analytic methods. Advances in Algorithmic Methods for Stochastic Models, G. Latouche & P. Taylor (eds.), 265-278, 2000.

[18]

J. K. Ousterhout. Scheduling techniques for concurrent systems. Proceedings of International Conference on Distributed Computing Systems, 22-30, 1982.

[19]

P. G. Sobalvarro. Demand-based coscheduling of parallel jobs on multiprogrammed multiprocessors. PhD thesis, Dept. of Elec. Eng. & Comp. Sci., MIT, Cambridge, MA, 1997.

Digital Library

[20]

M. S. Squillante. A matrix-analytic approach to a general class of G/G/c queues. Research Report, IBM Research Division, 1996.

[21]

M. S. Squillante, F. Wang, M. Papaefthymiou. Stochastic analysis of gang scheduling in parallel and distributed systems. Performance Evaluation, 27&28:273-296, 1996.

Digital Library

[22]

M. S. Squillante, Y. Zhang, A. Sivasubramaniam, N. Gautam, H. Franke, J. Moreira. Analytic modeling and analysis of dynamic coscheduling for a wide spectrum of parallel and distributed environments. Research Report, IBM Research Division, 2000.

[23]

Specification for the Virtual Interface Architecture. http://www.viarch.org.

[24]

Y. Zhang, A. Sivasubramaniam, J. Moreira, H. Franke. A simulation-based study of scheduling mechanisms for a dynamic cluster environment. Proc. of ACM International Conference on Supercomputing, 100-109, 2000.

Digital Library

Cited By

Squillante M(2022)On the quantum entanglement of random walks and queueing systemsQueueing Systems10.1007/s11134-022-09843-x100:3-4(253-255)Online publication date: 28-May-2022
https://doi.org/10.1007/s11134-022-09843-x
Hofmeyr SIancu CColmenares JRoman EAustin B(2016)Time-Sharing Redux for Large-Scale HPC Systems2016 IEEE 18th International Conference on High Performance Computing and Communications; IEEE 14th International Conference on Smart City; IEEE 2nd International Conference on Data Science and Systems (HPCC/SmartCity/DSS)10.1109/HPCC-SmartCity-DSS.2016.0051(301-308)Online publication date: Dec-2016
https://doi.org/10.1109/HPCC-SmartCity-DSS.2016.0051
Kim JChoi GDas C(2008)Coscheduled distributed-Web servers on system area networkJournal of Parallel and Distributed Computing10.1016/j.jpdc.2008.02.00968:8(1033-1043)Online publication date: 1-Aug-2008
https://dl.acm.org/doi/10.1016/j.jpdc.2008.02.009
Show More Cited By

Index Terms

Modeling and analysis of dynamic coscheduling in parallel and distributed environments
1. General and reference
  1. Cross-computing tools and techniques
    1. Performance

Recommendations

Modeling and analysis of dynamic coscheduling in parallel and distributed environments
SIGMETRICS '02: Proceedings of the 2002 ACM SIGMETRICS international conference on Measurement and modeling of computer systems

Scheduling in large-scale parallel systems has been and continues to be an important and challenging research problem. Several key factors, including the increasing use of off-the-shelf clusters of workstations to build such parallel systems, have ...
Adaptive Parallel Job Scheduling with Flexible Coscheduling

Many scientific and high-performance computing applications consist of multiple processes running on different processors that communicate frequently. Because of their synchronization needs, these applications can suffer severe performance penalties if ...
Analytical Modelling in Parallel and Distributed Computing

Comments

Information & Contributors

Information

Published In

cover image ACM SIGMETRICS Performance Evaluation Review

ACM SIGMETRICS Performance Evaluation Review Volume 30, Issue 1

Measurement and modeling of computer systems

June 2002

286 pages

ISSN:0163-5999

DOI:10.1145/511399

Issue’s Table of Contents

SIGMETRICS '02: Proceedings of the 2002 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
June 2002
299 pages
ISBN:1581135319
DOI:10.1145/511334
General Chair:
Richard Muntz
UCLA
,
Program Chairs:
Margaret Martonosi
Princeton University
,
Edmundo de Souza e Silva
UFRJ, Brazil

Copyright © 2002 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 June 2002

Published in SIGMETRICS Volume 30, Issue 1

Check for updates

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

20
Total Citations
View Citations
631
Total Downloads

Downloads (Last 12 months)1
Downloads (Last 6 weeks)0

Reflects downloads up to 01 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Squillante M(2022)On the quantum entanglement of random walks and queueing systemsQueueing Systems10.1007/s11134-022-09843-x100:3-4(253-255)Online publication date: 28-May-2022
https://doi.org/10.1007/s11134-022-09843-x
Hofmeyr SIancu CColmenares JRoman EAustin B(2016)Time-Sharing Redux for Large-Scale HPC Systems2016 IEEE 18th International Conference on High Performance Computing and Communications; IEEE 14th International Conference on Smart City; IEEE 2nd International Conference on Data Science and Systems (HPCC/SmartCity/DSS)10.1109/HPCC-SmartCity-DSS.2016.0051(301-308)Online publication date: Dec-2016
https://doi.org/10.1109/HPCC-SmartCity-DSS.2016.0051
Kim JChoi GDas C(2008)Coscheduled distributed-Web servers on system area networkJournal of Parallel and Distributed Computing10.1016/j.jpdc.2008.02.00968:8(1033-1043)Online publication date: 1-Aug-2008
https://dl.acm.org/doi/10.1016/j.jpdc.2008.02.009
Sharma APrabhu V(2005)Queing Models for Computing and Communication Performance in Distributed Manufacturing Control SystemsInternational Journal of Modelling and Simulation10.2316/Journal.205.2005.4.205-404325:4Online publication date: 2005
https://doi.org/10.2316/Journal.205.2005.4.205-4043
Oliner ASahoo RMoreira JGupta MSivasubramaniam A(2004)Fault-aware job scheduling for bBueGene/L systems18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.10.1109/IPDPS.2004.1302991(64-73)Online publication date: 2004
https://doi.org/10.1109/IPDPS.2004.1302991
Zhang YSquillante MSivasubramaniam ASahoo R(2004)Performance implications of failures in large-scale cluster schedulingProceedings of the 10th international conference on Job Scheduling Strategies for Parallel Processing10.1007/11407522_13(233-252)Online publication date: 13-Jun-2004
https://dl.acm.org/doi/10.1007/11407522_13
Paul AHarel NAdhikari SAgarwalla BRamachandran UMackenzie K(2003)Performance study of a cluster runtime system for dynamic interactive stream-oriented applications2003 IEEE International Symposium on Performance Analysis of Systems and Software. ISPASS 2003.10.1109/ISPASS.2003.1190240(133-142)Online publication date: 2003
https://doi.org/10.1109/ISPASS.2003.1190240
Kalantzis VSquillante MUbaru SHoresh L(2022)On Quantum Algorithms for Random Walks in the Nonnegative Quarter PlaneACM SIGMETRICS Performance Evaluation Review10.1145/3561074.356108950:2(42-44)Online publication date: 30-Aug-2022
https://dl.acm.org/doi/10.1145/3561074.3561089
Sbîrlea AAgrawal KSarkar V(2015)Elastic Tasks: Unifying Task Parallelism and SPMD Parallelism with an Adaptive RuntimeEuro-Par 2015: Parallel Processing10.1007/978-3-662-48096-0_38(491-503)Online publication date: 25-Jul-2015
https://doi.org/10.1007/978-3-662-48096-0_38
Ranadive AKesavan MGavrilovska ASchwan KScott SVallée G(2008)Performance implications of virtualizing multicore cluster machinesProceedings of the 2nd workshop on System-level virtualization for high performance computing10.1145/1435452.1435453(1-8)Online publication date: 31-Mar-2008
https://dl.acm.org/doi/10.1145/1435452.1435453
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents