Adaptive algorithms for managing a distributed data processing workload

IBM Systems Journal

Volumn 36, Issue 2, 1997, Pages 242-283

  Aman, J ^a,b   Eilert, C K ^a,c,d   Emmes, D ^a   Yocom, P ^a   Dillenberger, D ^a,e,f  

^a IBM   (United States)

^b MVS Software Des and Devmt Area   (United States)

^c S 390 Performance Design Department

^d ILLINOIS INSTITUTE OF TECHNOLOGY   (United States)

^e IBM T J WATSON RESEARCH CENTER   (United States)

^f Research Division

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER OPERATING SYSTEMS; DATA PROCESSING; DISTRIBUTED COMPUTER SYSTEMS; PARALLEL PROCESSING SYSTEMS; PERFORMANCE; RESOURCE ALLOCATION;

DISTRIBUTED DATA PROCESSING WORKLOAD; PERFORMANCE MANAGEMENT; SINGLE SYSTEM IMAGE;

ADAPTIVE ALGORITHMS;

EID: 0030672830     PISSN: 00188670     EISSN: None     Source Type: Journal    
DOI: 10.1147/sj.362.0242     Document Type: Article

References (14)

1. S. Zhou, J. Wang, X. Zheng, and P. Delisle, Utopia: A Load Sharing Facility for Large Heterogeneous Distributed Computer Systems, Technical Report CSRI-257, University of Toronto, Toronto (April 1992).
2. IBM LoadLeveler Administration Guide, Release 2.1, SH26-7220-03, IBM Corporation (August 1995); available through IBM branch offices.
3. D. G. Feitelson, A Survey of Scheduling in Multiprogrammed Parallel Systems, Research Report, IBM T. J. Watson Research Center, Yorktown Heights, NY 10598 (October 1994).
4. P. Yu, "On Robust Transaction Routing and Load Sharing," ACM Transactions on DB Systems 16, No. 3, 476-512 (September 1991).
5. G. Goldberg and P. H. Smith III, The VM/ESA Systems Handbook, J. Ranade, Editor, IBM Series, McGraw-Hill, Inc., New York (1993).
6. T. Agerwala, J. L. Martin, J. H. Mirza, D. C. Sadler, D. M. Dias, and M. Snir, "SP2 System Architecture," IBM Systems Journal 34, No. 2, 152-184 (1995).
7. P. S. Yu, "Performance Analysis of Affinity Clustering on Transaction Processing Coupling Architecture," IEEE Transactions on Knowledge and Data Engineering 6, No. 5, 764-786 (October 1994).
8. E. Berkel and P. Enrico, "Effective Use of MVS Workload Manager Controls," Computer Measurement Group Winter Transactions (1995), pp. 21-38.
9. D. Eager, "Adaptive Load Sharing in Homogeneous Distributed Systems," IEEE Transactions on Software Engineering SE-12, No. 5, 662-675 (May 1986).
10. J. M. Nick, J.-Y. Chung, and N. S. Bowen, "Overview of IBM System/390 Parallel Sysplex - A Commercial Parallel Processing System," 10th International Parallel Processing Symposium (April 1996), pp. 488-495.
11. Service class defining the client's performance goal.
12. Count of observations work classified to this service class using the processor.
13. A multiprogramming level (MPL) slot represents one address space. The multiprogramming level is the number of address spaces resident in central storage at any given time.
14. An I/O cluster is a unique set of devices that are shared by address spaces in the same set of period(s). Changing the I/O priority of one period in an I/O cluster could affect the I/O priority of any of the periods that arc part of the same I/O cluster.