research-article

The Influence of Different Workload Descriptions on a Heuristic Load Balancing Scheme

Author:

Thomas KunzAuthors Info & Claims

IEEE Transactions on Software Engineering, Volume 17, Issue 7

Pages 725 - 730

https://doi.org/10.1109/32.83908

Published: 01 July 1991 Publication History

Publisher Site

Abstract

A task scheduler based on the concept of a stochastic learning automation, implemented on a network of Unix workstations, is described. Creating an artificial, executable workload, a number of experiments were conducted to determine the effect of different workload descriptions. These workload descriptions characterize the load at one host and determine whether a newly created task is to be executed locally or remotely. Six one-dimensional workload descriptors are examined. Two workload descriptions that are more complex are also considered. It is shown that the best single workload descriptor is the number of tasks in the run queue. The use of the worst workload descriptor, the 1-min load average, resulted in an increase of the mean response time of over 32%, compared to the best descriptor. The two best workload descriptors, the number of tasks in the run queue and the system call rate, are combined to measure a host's load. Experimental results indicate that no performance improvements over the scheduler versions using a one-dimensional workload descriptor can be obtained.

References

[1]

{1} T. L. Casavant and J. G. Kuhl, "A taxonomy of scheduling in general-purpose distributed computing systems," IEEE Trans. Software Eng. , vol. 14, pp. 141-154, Feb. 1988.]]

Digital Library

Google Scholar

[2]

{2} D. L. Eager, E. D. Lazowska, and J. Zahorjan, "Adaptive load sharing in homogeneous distributed systems," IEEE Trans. Software Eng. , vol. SE-12, pp. 662-675, May 1986.]]

Digital Library

Google Scholar

[3]

{3} D. Ferrari, Computer Systems Performance Evaluation . Englewood, Cliffs, NJ: Prentice-Hall, 1978.]]

Google Scholar

[4]

{4} W. E. Leland and T. J. Ott, "Load-balancing heuristics and process behavior," ACM 0-89791-184-9/86/0500-0054.]]

Digital Library

Google Scholar

[5]

{5} R. Mirchandaney and J. A. Stankovic, "Using stochastic learning automata for job scheduling in distributed processing systems," J. Parallel Distributed Comput. , pp. 527-551, 1986.]]

Digital Library

Google Scholar

[6]

{6} K. S. Narendra and M. A. L. Thathachar, "Learning automata--A survey," IEEE Trans. Syst., Man. Cybern. , pp. 323-334, July 1974.]]

Crossref

Google Scholar

[7]

{7} C. C. Price and S. Krishnaprasad, "Software allocation models for distributed systems," in Proc. 5th Int. Conf. on Distributed Computing , 1984, pp. 40-47.]]

Google Scholar

[8]

{8} S. Pulidas, D. Towsley, and J. Stankovic, "Design of efficient parameter estimators for decentralized load balancing policies," Tech. Rep. 87-79, Univ. of Massachusetts, Amherst, Aug. 1987.]]

Digital Library

Google Scholar

[9]

{9} J. A. Stankovic, "The analysis of a decentralized control algorithm for job scheduling utilizing Bayesian decision theory," in Proc. 1981 Int. Conf. on Parallel Processing , 1981, pp. 333-340.]]

Google Scholar

[10]

{10} J. A. Stankovic, "Simulations of three adaptive, decentralized controlled, job scheduling algorithms," Comput. Networks , pp. 199-217, June 1984.]]

Digital Library

Google Scholar

[11]

{11} J. A. Stankovic, "An application of Bayesian decision theory to decentralized control of job scheduling," IEEE Trans. Comput. , pp. 117-130, Feb. 1985.]]

Digital Library

Google Scholar

[12]

{12} J. A. Stankovic, "Stability and distributed scheduling algorithms," IEEE Trans. Software Eng. , vol. SE-11, pp. 1141-1152, Oct. 1985.]]

Digital Library

Google Scholar

[13]

{13} H.S. Stone, "Multiprocessor scheduling with the aid of network flow algorithms," IEEE Trans. Software Eng. , pp. 85-93, Jan. 1977.]]

Digital Library

Google Scholar

[14]

{14} B. Stramm and F. Berman, "Communication-sensitive heuristics and algorithms for mapping compilers," in Proc. ACM SIGPLAN Conf. on Parallel Programming: Experiences with Applications, Languages and Systems , July 1988, pp. 222-234.]]

Digital Library

Google Scholar

[15]

{15} A. Svensson, "History, an intelligent load sharing filter," in Proc. 10th Int. Conf. on Distributed Computing Syst. , May 1990, pp. 546-553.]]

Google Scholar

Cited By

View all

Lan Y(2023)A dynamic load balancing mechanism for distributed systemsJournal of Computer Science and Technology10.1007/BF0294312911:3(195-207)Online publication date: 22-Mar-2023
https://dl.acm.org/doi/10.1007/BF02943129
Verba NChao KLewandowski JShah NJames ATian F(2019)Modeling industry 4.0 based fog computing environments for application analysis and deploymentFuture Generation Computer Systems10.1016/j.future.2018.08.04391:C(48-60)Online publication date: 1-Feb-2019
https://dl.acm.org/doi/10.1016/j.future.2018.08.043
Matias RFerreira AHaddad HWainwright RChbeir R(2018)KloadavgProceedings of the 33rd Annual ACM Symposium on Applied Computing10.1145/3167132.3167253(1122-1128)Online publication date: 9-Apr-2018
https://dl.acm.org/doi/10.1145/3167132.3167253
Show More Cited By

Index Terms

Recommendations

Fuzzy expert system for load balancing in symmetric multiprocessor systems

The aim of this paper is to describe a fuzzy expert system for load balancing in a symmetric multiprocessor environment. Load balancing algorithms are used to share the load of the system fairly among the processors. The developed load balancing ...
Elastic Load Balancing Classic Load Balancers
Dynamic load balancing algorithm for balancing the workload among virtual machine in cloud computing

Performance of the cloud infrastructure is highly depends upon the task scheduling and load balancing. Therefore number of load balancing algorithms and technique are proposed by researchers throughout the world whose aim is to distribute the workload ...

Reviews

Reviewer: Jason Gait

The author describes a distributed real-time task scheduler implemented on an Ethernet of five diskless UNIX workstations. The load-balancing problem is NP-complete, so this paper studies scheduling heuristics. The scheduler is transparent to network topology and to the structure of incoming tasks. The global scheduler receives periodic state information from each local scheduler in the form of a token that allows the global scheduler to dispatch tasks to the local scheduler until the token is revoked. Each local scheduler distributes and revokes tokens based on local workload. The (artificial) workload model is determined by task arrival distribution (Poisson) and the distribution of per task resource requirements (exponential). The author studied nine token distribution and revocation policies based on no load balancing (all tokens revoked except local token), size of local run queue, size of free memory, context switch rate, system call rate, load average, free CPU time, the logical-or of run queue length and system call rate, and the logical-and of run queue length and system call rate. The author did not study the obvious experimental control policy—all tokens valid (completely random task distribution). The best result is obtained by using the run queue length alone to determine token distribution and revocation policy. With this policy, the performance of the global system (measured only by mean response time) is a factor of two better than it is using the worst policy (no load balancing). The author points out, however, that several of the candidate token distribution policies are influenced by tasks that are no longer in the system, possibly predetermining the result. In this paper the author is interested in distributed real time systems. He uses the UNIX network only as a testbed. The casual reader should be warned that these results do not apply to distributed UNIX systems.

Access critical reviews of Computing literature here

Become a reviewer for Computing Reviews.

Comments

Information & Contributors

Information

Published In

cover image IEEE Transactions on Software Engineering

IEEE Transactions on Software Engineering Volume 17, Issue 7

July 1991

95 pages

ISSN:0098-5589

Editor:
Victor R. Basili
Univ. of Maryland, College Park

Issue’s Table of Contents

Publisher

IEEE Press

Publication History

Published: 01 July 1991

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

59
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 10 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Lan Y(2023)A dynamic load balancing mechanism for distributed systemsJournal of Computer Science and Technology10.1007/BF0294312911:3(195-207)Online publication date: 22-Mar-2023
https://dl.acm.org/doi/10.1007/BF02943129
Verba NChao KLewandowski JShah NJames ATian F(2019)Modeling industry 4.0 based fog computing environments for application analysis and deploymentFuture Generation Computer Systems10.1016/j.future.2018.08.04391:C(48-60)Online publication date: 1-Feb-2019
https://dl.acm.org/doi/10.1016/j.future.2018.08.043
Matias RFerreira AHaddad HWainwright RChbeir R(2018)KloadavgProceedings of the 33rd Annual ACM Symposium on Applied Computing10.1145/3167132.3167253(1122-1128)Online publication date: 9-Apr-2018
https://dl.acm.org/doi/10.1145/3167132.3167253
Jiang Y(2016)A Survey of Task Allocation and Load Balancing in Distributed SystemsIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2015.240790027:2(585-599)Online publication date: 1-Feb-2016
https://dl.acm.org/doi/10.1109/TPDS.2015.2407900
Espadas JMolina AJiménez GMolina MRamírez RConcha D(2013)A tenant-based resource allocation model for scaling Software-as-a-Service applications over cloud computing infrastructuresFuture Generation Computer Systems10.1016/j.future.2011.10.01329:1(273-286)Online publication date: 1-Jan-2013
https://dl.acm.org/doi/10.1016/j.future.2011.10.013
Singh HKumar S(2012)Dispatcher Based Dynamic Load Balancing on Web Server SystemInternational Journal of System Dynamics Applications10.4018/ijsda.20120401021:2(15-27)Online publication date: 1-Apr-2012
https://dl.acm.org/doi/10.4018/ijsda.2012040102
Logeswaran RChen L(2010)Load Balancing Algorithms in Distributed Service Architectures for Medical ApplicationsInternational Journal of Healthcare Information Systems and Informatics10.4018/jhisi.20101103055:1(76-90)Online publication date: 1-Jan-2010
https://dl.acm.org/doi/10.4018/jhisi.2010110305
Nandagopal MGokulnath KUthariaraj VAchuthan KBuragohain G(2010)Sender initiated decentralized dynamic load balancing for multi cluster computational grid environmentProceedings of the 1st Amrita ACM-W Celebration on Women in Computing in India10.1145/1858378.1858441(1-4)Online publication date: 16-Sep-2010
https://dl.acm.org/doi/10.1145/1858378.1858441
Bhadani AChaudhary SShyamasundar RDeshpande P(2010)Performance evaluation of web servers using central load balancing policy over virtual machines on cloudProceedings of the Third Annual ACM Bangalore Conference10.1145/1754288.1754304(1-4)Online publication date: 22-Jan-2010
https://dl.acm.org/doi/10.1145/1754288.1754304
Vidhate DPatil AGuleria DMishra B(2010)Dynamic cluster resource allocations for jobs with known memory demandsProceedings of the International Conference and Workshop on Emerging Trends in Technology10.1145/1741906.1741918(64-69)Online publication date: 26-Feb-2010
https://dl.acm.org/doi/10.1145/1741906.1741918
Show More Cited By

Abstract

References

Cited By

Index Terms

Recommendations

Fuzzy expert system for load balancing in symmetric multiprocessor systems

Elastic Load Balancing Classic Load Balancers

Dynamic load balancing algorithm for balancing the workload among virtual machine in cloud computing

Reviews

Access critical reviews of Computing literature here

Comments

Information

Published In

Publisher

Publication History

Author Tags

Qualifiers

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations