Abstract
Model studies of some integrated, feedback-driven scheduling systems for multiprogrammed-multiprocessor computer systems are presented. The basic control variables used are the data-flow rates for the processes executing on the CPU. The model systems feature simulated continuous-flow and preempt-resume scheduling of input-output activity. Attention is given to the amount of memory resource required for effective processing of the I/O activity (buffer space assignment). The model studies used both distribution-driven and trace-driven techniques. Even relatively simple dynamic schedulers are shown to improve system performance (as measured by user CPU time) over that given by optimal or near-optimal static schedulers imbedded in identical system structures and workload environments. The improvement is greatest under a heavy I/O demand workload.
- 1 Bauer, M.J. A simulation approach to the design of dynamic feedback scheduling algorithms for time-shared computer systems. Proc. Second Syrup. on Simulation of Comptr. Syst., Gaithersburg, Md., June 1974, pp. 165-174 (available from ACM). Google ScholarDigital Library
- 2 Bernstein, A.J., and Sharp, J.C. A policy driven scheduler for a time-sharing system. Comm. ACM 11, 2 (Feb. 1971), 74-78. Google ScholarDigital Library
- 3 Blevins, P.R. Aspects of a dynamically adaptive operating system. Ph.D. Diss., Electr. Eng. Dept., U. of Texas at Austin, Aug. 1972.Google Scholar
- 4 Brice, R.S. A study of feedback coupled resource allocation policies in a multi-processing computer environment. Ph.D. Diss. Comptr. Sci. Dept., U. of Texas at Austin, Aug. 1973. Google ScholarDigital Library
- 5 Buzen, J. Queueing network models of multiprogramming systems. Ph.D. Diss., Harvard U., Cambridge, Mass., May 1971.Google Scholar
- 6 Coffman, E.G. Jr., and Denning, P.J. Operating System Theory. Prentice-Hall, Englewood Cliffs, N.J., 1973. Google ScholarDigital Library
- 7 Howard, J.H. A large-scale dual operating system. Proc. ACM Natl. Conf., Atlanta, Go., 1973, pp. 242-248. Google ScholarDigital Library
- 8 Johnson, D.S. A process oriented model of resource demands in a large multiprocessing computer utility. Ph.D. Diss. Comptr. Sci. Dept., U. of Texas at Austin, Aug. 1972. Google ScholarDigital Library
- 9 Marshall, B.S. Dynamic calculation of dispatching priorities under OS/360 MVT. Datamation 15, 8 (Aug. 1969), 93.Google Scholar
- 10 Pewitt, T.C., and Su, S.Y.W. Resource demand paging and dispatching to optimize resource utilization in an operating system. Proc. First SIGME Symp. on Measurement and Evaluation, Palo Alto, Calif., Oct. 1973, pp. 29-36. Google ScholarDigital Library
- 11 Ryder, K.D. A heuristic approach to task dispatching. IBM Syst. J. 8 (Oct. 1970), 189.Google ScholarDigital Library
- 12 Sherman, S.W. Trace-driven modeling studies of the performance of computer systems. Ph.D. Diss., U. of Texas at Austin, Aug. 1972; also available as TSN-30, Comput. Ctr. Google ScholarDigital Library
- 13 Sherman, S.W., Baskett, F., and Browne, J.C. Trace-driven modeling and analysis of CPU scheduling in a multiprogramming system. Comm. ACM 15, 12 Dec. 1972, 1063-1069. Google ScholarDigital Library
- 14 Sherman, S.W., and Browne, J.C. Trace-driven modeling: Review and overview. Proc. First Syrup. on Simulation of Comptr. Syst. Gaithersburg, Md., June 1973, pp. 201-207. Google ScholarDigital Library
- 15 Spirn, J. Multiqueue scheduling of two tasks. Proc. Int. Syrup. on Comptr. Performance Modeling, Measurement, and Evaluation, Cambridge, Mass., March 1976, pp. 102-108. Google ScholarDigital Library
- 16 Stevens, D.F. On overcoming high-priority paralysis in multiprogramming systems. Comm. ACM 11, 8 (Aug. 1968), 539-541. Google ScholarDigital Library
- 17 Teorey, T.J., and Pinkerton, T.D. A comparative analysis of disk scheduling policies. Comm. ACM 15, 3 (March 1972), 177-184. Google ScholarDigital Library
Index Terms
- Feedback coupled resource allocation policies in the multiprogramming-multiprocessor computer system
Recommendations
Feedback scheduling: an event-driven paradigm
Embedded computing systems today increasingly feature resource constraints and workload variability, which lead to uncertainty in resource availability. This raises great challenges to software design and programming in multitasking environments. In ...
Feedback coupled resource allocation policies in the multiprogramming-multiprocessor computer system
This paper presents model studies of some integrated feedback-driven scheduling systems for a multiprogrammed computer system.
This abstract can present only the conclusions of the studies and little of the supporting data and detail.
The basic format ...
Feedback scheduling of priority-driven control networks
With traditional open-loop scheduling of network resources, the quality-of-control (QoC) of networked control systems (NCSs) may degrade significantly in the presence of limited bandwidth and variable workload. The goal of this work is to maximize the ...
Comments