M. A. Holliday
ABSTRACT
We address the problem of paged main memory management in the local/remote architecture subclass of shared memory multiprocessors. We consider the case where the operating system has primary responsibility and uses page migration as its main tool. We identify some of the key issues with respect to architectural support (reference history maintenance, and page size), and operating system mechanism (duration between daemon passes, and number of migration daemons).
The experiments were conducted using software implemented page tables on 32-node BBN Butterfly Plus™. Several numeral programs with both synthetic and real data were used as the workload. The primary conclusion is that for the cases considered migration was at best marginally effective. On the other hand, practical migration mechanisms were robust and never significantly degraded performance. The specific results include: 1) Referenced bits with aging can closely approximate Usage fields, 2) larger page sizes are beneficial except when the page is large enough to include locality sets of two processes, and 3) multiple migration daemons can be useful.
Only small regions of the space of architectural, system, and workload parameters were explored. Further investigation of other parameter combinations is clearly warranted.
- 1.BBN Advanced Computers inc., Cambridge, MA. inside the Butterfly Plus, 1987.Google Scholar
- 2.Digital Equipment Corporation. VAX Architecture Handbook, 1986.Google Scholar
- 3.I.S. Duff, R.G. Grimes, J.G. Lewis, and W.C. Poole. Sparse matrix test problems. SIGNUM Newsletter, 17:22, July 1982. Google ScholarDigital Library
- 4.J.R. Goodman and P.J. Woest. The wisconsin multicube: A new large-scale cache-coherent multiprocessor. In Proceedings of the 15th Annual International Symposium on Computer Architecture, pages 422-431, Honolulu, HI, 1988. Google ScholarDigital Library
- 5.J.L. Gustafson, G.R. Montry, and R.E. Benner. Development of parallel methods for a 1024-processor hypercube. SIAM J. Sci. Star. Computing, 9(4):609-638, July 1988.Google ScholarDigital Library
- 6.M.A. HoUiday. Page table management in local/remote architectures. In A CM SIGARCH Int. Conf. on Supercomputing 1988, pages 1-8, Saint Malo, France, July 1988. Google ScholarDigital Library
- 7.L. W. Johnson and R. D. Riess. Numerical Analysis, Second Edition. Addison-Wesley~ Reading, MA, 1982.Google Scholar
- 8.K. Li and P. Hudak. Memory coherence in shared virtual memory systems. In Proceedings of the Fifth A CM Symposium on Principles of Distributed Computing, pages 229-239, 1986. Google ScholarDigital Library
- 9.M.N. Nelson, B.B. Welch, and J.K. Ousterhout. Caching in the sprite network file system. A CM Transactions on Computer Systems, 6(1):134-154, February 1988. Google ScholarDigital Library
- 10.C. Scheurich and M. Dubois. Dynamic page migration in multiprocessors with distributed global memory. In Proceedings of the 8th International Conference on Distributed Computer Systems, pages 162-169, San Jose, CA, 1988.Google ScholarCross Ref
- 11.M. Sen. Programming in C with the Uniform System. BBN Advanced Computers Inc., Cambridge, MA, 1988.Google Scholar
- 12.A.S. Tanenbaum. Operating Systems: Design and Implementation. Prentice-Hall, 1987. Google ScholarDigital Library
- 13.D.A. Wood, S.J. Eggers, G. Gibson, M.D. Hill, J.M. Pendleton, S.A. Pdtchie, G.S. Taylor, R.H. Katz, and D.A. Patterson. An in-cache address translation mechanism. In Proceedings of the 13th Annual International Symposium on Computer Architecture, pages 358-365, Tokyo, Japan, june 1986. Google ScholarDigital Library
Index Terms
- Reference history, page size, and migration daemons in local/remote architectures
Recommendations
Reference history, page size, and migration daemons in local/remote architectures
Special issue: Proceedings of ASPLOS-III: the third international conference on architecture support for programming languages and operating systemsWe address the problem of paged main memory management in the local/remote architecture subclass of shared memory multiprocessors. We consider the case where the operating system has primary responsibility and uses page migration as its main tool. We ...
Improving Total Migration Time in Live Virtual Machine Migration
ICCCT '15: Proceedings of the Sixth International Conference on Computer and Communication Technology 2015Virtualization is the key underlying technology enabling cloud providers to host services for a large number of customers. Live migration is an essential feature of virtualization that allows transfer of virtual machines from one physical server to ...
Comments