This Article 
 Bibliographic References 
 Add to: 
The Effect of Scheduling Discipline on Spin Overhead in Shared Memory Parallel Systems
April 1991 (vol. 2 no. 2)
pp. 180-198

Spinning, or busy waiting, is commonly employed in parallel processors when threads ofexecution must wait for some event, such as synchronization with another thread.Because spinning is purely overhead, it is detrimental to both user response time and system throughput. The effects of two environmental factors, multiprogramming and data-dependent execution times, on spinning are discussed, and it is shown how the choice of scheduling discipline can be used to reduce the amount of spinning in each case.

[1] E.F. Gehringer, D.P. Siewiorek, and Z. Segall,Parallel Processing: The Cm*Experience, Digital Press, Billerica, Mass., 1987.
[2] J. Zahorian, E.D. Lazowska, and D.L. Eager, "Spinning versus blocking" in parallel systems with uncertainty," inProc. Int. Symp. Performance Distributed Parallel Syst., Dec. 1988.
[3] T.E. Anderson, E. D. Lazowska, and H. M. Levy, "The performance implications of thread management alternatives for shared-memory multiprocessors,"IEEE Trans. Comput., vol. 38, no. 12, Dec. 1989.
[4] M. Dubois and F.A. Briggs, "An approximate analytical model for asynchronous processes in multiprocessors," inProc. 1982 Int. Conf. Parallel Processing, pp. 290-297.
[5] M. Reiser and S. Lavenberg, "Mean value analysis of closed multichain queueing networks,"J. ACM, vol. 27, no. 2, Apr. 1980.
[6] L. Kleinrock,Queueing Systems: Vol. I: Theory.New York, Wiley, 1975.
[7] Y. Dallery, personal communication, Laboratoire MASI, Universite Pierre et Marie Curie, Paris, France.
[8] T. Lovett and S. Thakkar, "The Symmetry Multiprocessor System," inProc. 1988 Int. Conf. Parallel Processing, Aug. 1988.
[9] J. K. Ousterhout, "Scheduling techniques for concurrent systems," inProc. 3rd Int. Conf. Distributed Comput. Syst., Oct. 1982, pp. 22-30.
[10] D. J. DeWitt, R. Finkel, and M. Solomon, "The CRYSTAL multicomputer: Design and implementation experience,"IEEE Trans. Software Eng., vol. 13, Aug. 1987.
[11] M.-S. Chen and K. G. Shin, "Processor allocation in anN-cube multiprocessorusing Gray codes,"IEEE Trans. Comput., vol. C-36, no. 12, pp. 1396-1407, Dec. 1987.
[12] D.L. Eager, J. Zahorjan, and E. D. Lazowska, "Speedup versus efficiency in parallel systems,"IEEE Trans. Comput., vol. 38, no. 3, Mar. 1989.
[13] M. Young, A. Tevanian, R. Rashid, D. Golub, J. Eppinger, J. Chew, W. Bolosky, D. Black, and R. Baron, "The duality of memory and communication in the implementation of a multiprocessor operating system," inProc Symp. Oper. Syst. Principles, Nov. 1987.
[14] B. Bershad, ED. Lazowska, and H. Levy, "Presto: A System for Object-Oriented Parallel Programming,"Software: Practice and Experience, Vol. 18, No. 8, Aug. 1988, pp. 713-732.
[15] J. Edler, J. Lipkis, and E. Schonberg, "Process management for highly parallel UNIX systems," inProc. USENIX Workshop UNIX and Supercomput., Sept. 1988.
[16] C. Polychronopoulos and D. Kuck, "Guided self-scheduling: A practical scheduling scheme for parallel supercomputers,"IEEE Tran. Comput., 1987.
[17] C. Kruskal and A. Weiss, "Allocating independence subtasks on parallel processors,"IEEE Trans. Software Eng., vol. SE-11, no. 10, pp. 1001-1015, Oct. 1985.
[18] K. W. Dritz and J. M. Boyle, "Beyond "speedup": Performance analysis of parallel programs," Tech. Rep. ANL-87-7, Math. and Comput. Sci. Division, Argonne National Lab., Feb. 1987.

Index Terms:
Index Termsspinning; scheduling discipline; spin overhead; shared memory parallel systems; busywaiting; parallel processors; multiprogramming; data-dependent execution; memoryarchitecture; parallel machines; performance evaluation; scheduling
J. Zahorjan, E.D. Lazowska, D.L. Eager, "The Effect of Scheduling Discipline on Spin Overhead in Shared Memory Parallel Systems," IEEE Transactions on Parallel and Distributed Systems, vol. 2, no. 2, pp. 180-198, April 1991, doi:10.1109/71.89064
Usage of this product signifies your acceptance of the Terms of Use.