Performance Analysis and Optimization of Linear Workflows in Heterogeneous Network Environments

Part of the Computer Communications and Networks book series (CCN)


The advent of next-generation computation-intensive applications in various science fields is pushing computing demands to go far beyond the capability of traditional computing solutions based on standalone PCs. The availability of today’s largest clusters, grids, and supercomputers expedites the development of robust problem-solving environments that marshal those high-performance computing and networking resources and presents a great opportunity to manage and execute large-scale computing workflows for collaborative scientific research. Supporting such scientific workflows and optimizing their end-to-end performance in wide-area networks is crucial to ensuring the success of large-scale distributed scientific applications. We consider a special type of pipeline workflows comprised of a set of linearly arranged modules, and formulate and categorize pipeline mapping problems into six classes with two optimization objectives, i.e., minimum end-to-end delay and maximum frame rate, and three network constraints, i.e., no, contiguous, and arbitrary node reuse. We design a dynamic programming-based optimal solution to the problem of minimum end-to-end delay with arbitrary node reuse and prove the NP-completeness of the rest five problems, for each of which, a heuristic algorithm based on a similar optimization procedure is proposed. These heuristics are implemented and tested on a large set of simulated networks of various scales and their performance superiority is illustrated by extensive simulation results in comparison with existing methods.


Destination Node Disjoint Path Network Link Virtual Node Computing Module 


  1. 1.
    Agarwalla, B., Ahmed, N., Hilley, D., Ramachandran, U.: Streamline: A scheduling heuristic for streaming application on the grid. In: Proceedings of the 13th Multimedia Computing and Networking Conference, San Jose (2006)Google Scholar
  2. 2.
    Ahmed, I., Kwok, Y.: On exploiting task duplication in parallel program scheduling. IEEE Trans. Parallel Distrib. Syst. 9, 872–892 (1998)CrossRefGoogle Scholar
  3. 3.
    Annie, S.W., Yu, H., Jin, S., Lin, K.C.: An incremental genetic algorithm approach to multiprocessor scheduling. IEEE Trans. Parallel Distrib. Syst. 15, 824–834 (2004)CrossRefGoogle Scholar
  4. 4.
    Ausiello, G., Crescenzi, P., Gambosi, G., Kann, V., Marchetti-Spaccamela, A., Protasi, M.: Complexity and Approximation: Combinatorial Optimization Problems and Their Approxima­bility Properties. Springer, Berlin (1999)MATHGoogle Scholar
  5. 5.
    Bajaj, R., Agrawal, D.P.: Improving scheduling of tasks in a heterogeneous environment. IEEE Trans. Parallel Distrib. Syst. 15, 107–118 (2004)CrossRefGoogle Scholar
  6. 6.
    Bashir, A.F., Susarla, V., Vairavan, K.: A statistical study of the performance of a task scheduling algorithm. IEEE Trans. Comput. 32(12), 774–777 (1975)Google Scholar
  7. 7.
    Benoit, A., Hakem, M., Robert, Y.: Optimizing the latency of streaming applications under throughput and reliability constraints. In: Proceedings of the 2009 International Conference on Parallel Processing, Vienna, pp. 325–332, (2009)Google Scholar
  8. 8.
    Benoit, A., Robert, Y.: Mapping pipeline skeletons onto heterogeneous platforms. J. Parallel Distrib. Comput. 68(6), 790–808 (2008)CrossRefGoogle Scholar
  9. 9.
    Boeres, C., Filho, J.V., Rebello, V.E.F.: A cluster-based strategy for scheduling task on heterogeneous processors. In: Proceedings of the 16th Symposium on Computer Architecture and High Performance Computing, Foz Do Iguacu, pp. 214–221 (2004)Google Scholar
  10. 10.
    Bozdag, D., Catalyurek, U., Ozguner, F.: A task duplication based bottom-up scheduling algorithm for heterogeneous environments. In: Proceedings of the 20th International Parallel and Distributed Processing Symposium, Rhodes Island, pp. 12 (2006). doi: 10.1109/IPDPS.2006.1639389
  11. 11.
    Braun, T.D., Siegel, H.J., Beck, N., Boloni, L.L., Maheswaran, M., Reuther, A.I., Robertson, J.P., Theys, M.D., Yao, B., Hensgen, D., Freund, R.F.: A comparison of eleven static heuristics for mapping a class of independent tasks onto heterogeneous distributed computing systems. J. Parallel Distrib. Comput. 61(6), 810–837 (2001)CrossRefGoogle Scholar
  12. 12.
    Buyya, R., Abramson, D., Giddy, J.: Nimrod/G: An architecture for a resource management and scheduling system in a global computational grid. In: Proceedings of the 4th International Conference/Exhibition on the High Performance Computing in the Asia-Pacific Region, vol. 1, Beijing, pp. 283–289 (2000)Google Scholar
  13. 13.
    Cao, J., Jarvis, S.A., Saini, S., Nudd, G.R.: GridFlow: Workflow management for grid computing. In: Proceedings of the 3rd IEEE/ACM International Symposium on Cluster Computing and the Grid, Tokyo, pp. 198–205 (2003)Google Scholar
  14. 14.
    Chatterjee, S., Strosnider, J.: Distributed pipeline scheduling: End-to-end analysis of heterogeneous, multi-resource real-time systems. In: Proceedings of the 15th International Conference on Distributed Computing Systems, Washington, DC, pp. 204–211 (1995)Google Scholar
  15. 15.
    Chaudhary, V., Aggarwal, J.K.: A generalized scheme for mapping parallel algorithms. IEEE Trans. Parallel Distrib. Syst. 4(3), 328–346 (1993)CrossRefGoogle Scholar
  16. 16.
    Chen, L., Agrawal, G.: Resource allocation in a middleware for streaming data. In Proceedings of the 2nd Workshop on Middleware for Grid Computing (2004). doi:10.1145/1028493.1028494Google Scholar
  17. 17.
    Choi, S.Y., Turner, J.: Configuring sessions in programmable networks with capacity constraints. In: Proceedings of IEEE International Conference on Communications, Anchorage, pp. 823–829 (2003)Google Scholar
  18. 18.
    Choi, S.Y., Turner, J., Wolf, T.: Configuring sessions in programmable networks. In: Procee­dings of IEEE INFOCOM, Anchorage, pp. 60–66 (2001)Google Scholar
  19. 19.
    Climate and Carbon Research Institute (CCR): Retrieved from (2010)
  20. 20.
    Cordella, L.P., Foggia, P., Sansone, C., Vento, M.: An improved algorithm for matching large graphs. In: Proceedings of the 3rd IAPR-TC-15 International Workshop on Graph-Based Representations, Venice (2001)Google Scholar
  21. 21.
    Deelman, E., Callaghan, S., Field, E., Francoeur, H., Graves, R., Gupta, N., Gupta, V., Jordan, T.H., Kesselman, C., Maechling, P., Mehringer, J., Mehta, G., Okaya, D., Vahi, K., Zhao, L.: Managing large-scale workflow execution from resource provisioning to provenance tracking: The cybershake example. In: Proceedings of the e-Science Conference, Amsterdam (2006). doi:10.1109/E-SCIENCE.2006.99Google Scholar
  22. 22.
    Deelman, E., Singh, G., Su, M., Blythe, J., Gil, Y., Kesselman, C., Mehta, G., Vahi, K., Berriman, G.B., Good, J., Laity, A., Jacob, J.C., Katz, D.S.: Pegasus: A framework for mapping complex scientific workflows onto distributed systems. J. Sci. Program. 13, 219–237 (2005)Google Scholar
  23. 23.
    Dogan, A., Özgüner, F.: Matching and scheduling algorithms for minimizing execution time and failure probability of applications in heterogeneous computing. IEEE Trans. Parallel Distrib. Syst. 13(3), 308–323 (2002)CrossRefGoogle Scholar
  24. 24.
    Earth System Grid (ESG): Retrieved from (2010)
  25. 25.
    Fortune, S., Hopcroft, J., Wyllie, J.: The directed subgraph homeomorphism problem. Theor. Comput. Sci. 10, 111–121 (1980)MATHCrossRefMathSciNetGoogle Scholar
  26. 26.
    Foster, I.T.: Globus toolkit version 4: Software for service-oriented systems. J. Comput. Sci. Technol. 21(4), 513–520 (2006)CrossRefGoogle Scholar
  27. 27.
    Foster, I.T., Kesselman, C., Tuecke, S.: The anatomy of the grid – Enabling scalable virtual organizations. Int. J. Supercomput. Appl. 15(3), 200–222 (2001)CrossRefGoogle Scholar
  28. 28.
    Garey, M.R., Johnson, D.S.: Computers and Intractability: A Guide to the Theory of NP-Completeness. Freeman, New York (1979)MATHGoogle Scholar
  29. 29.
    Gerasoulis, A., Yang, T.: A comparison of clustering heuristics for scheduling DAGs on multiprocessors. J. Parellel Distrib. Comput. 16(4), 276–291 (1992)MATHCrossRefMathSciNetGoogle Scholar
  30. 30.
    González, D., Almeida, F., Moreno, L., Rodríguez, C.: Towards the automatic optimal mapping of pipeline algorithms. J. Parallel Comput. 29(2), 241–254 (2003)CrossRefGoogle Scholar
  31. 31.
    Gu, Y., Wu, Q.: Optimizing distributed computing workflows in heterogeneous network environments. In: Proceedings of the 11th International Conference on Distributed Computing and Networking, San Jose (2010). doi:  10.1007/978-3-642-11322-2_17
  32. 32.
    Gu, Y., Wu, Q., Benoit, A., Robert, Y.: Optimizing end-to-end performance of distributed applications with linear computing pipelines. In: Proceedings of the 15th International Conference on Parallel and Distributed Systems, Shenzhen (2009)Google Scholar
  33. 33.
    Ilavarasan, E., Thambidurai, P.: Low complexity performance effective task scheduling algorithm for heterogeneous computing environments. J. Comput. Sci. 3(2), 94–103 (2007)CrossRefGoogle Scholar
  34. 34.
    Johnston, W.E.: Computational and data grids in large-scale science and engineering. J. Future Generation Comput. Syst. 18(8), 1085–1100 (2002)MATHCrossRefGoogle Scholar
  35. 35.
    Kwok, Y.K., Ahmad, I.: Dynamic critical-path scheduling: An effective technique for allocating task graph to multiprocessors. IEEE Trans. Parallel Distrib. Syst. 7(5), 506–521 (1996)CrossRefGoogle Scholar
  36. 36.
    Litzkow, M., Livny, M., Mutka, M.: Condor – A hunter of idle workstations. In: Proceedings of the 8th International Conference on Distributed Computing Systems, San Jose, pp. 104–111 (1988)Google Scholar
  37. 37.
    Ma, T., Buyya, R.: Critical-path and priority based algorithms for scheduling workflows with parameter sweep tasks on global grids. In: Proceedings of the 17th International Symposium on Computer Architecture on HPC, Rio de Janeiro, pp. 251–258 (2005)Google Scholar
  38. 38.
    McCreary, C., Khan, A.A., Thompson, J.J., McArdle, M.E.: A comparison of heuristics for scheduling DAGs on multiprocessors. In: Proceedings of the 8th International Symposium on Parallel Processing, Cancun, pp. 446–451 (1994)Google Scholar
  39. 39.
    McDermott, W.J., Maluf, D.A., Gawdiak, Y., Tran, P.B.: Airport simulations using distributed computational resources. DOI: 10.4271/2001-01-2650 (2001)Google Scholar
  40. 40.
    Messmer, B.T.: Efficient graph matching algorithms for preprocessed model graphs. Ph.D. thesis, Institute of Computer Science and Applied Mathematics, University of Bern, Bern, Swtzerland (1996)Google Scholar
  41. 41.
    Mezzacappa, A.: Scidac Scientific discovery through advanced computing. J. Phys. Conf. Ser. 16, 536–540 (2005)CrossRefGoogle Scholar
  42. 42.
    NSF Grand Challenges in eScience Workshop, 2001 (NSF): Retrieved from (2010)
  43. 43.
    Open Science Grid (OSG): Retrieved from (2010)
  44. 44.
    Rahman, M., Venugopal, S., Buyya, R.: A dynamic critical path algorithm for scheduling scientific workflow applications on global grids. In: Proceedings of the 3rd IEEE International Conference on e-Science and Grid Computing, Bangalore, pp 35–42 (2007)Google Scholar
  45. 45.
    Ranaweera, A., Agrawal, D.P.: A task duplication based algorithm for heterogeneous systems. In: Proceedings of IEEE International Parallel and Distributed Processing Symposium, Los Alamitos, pp. 445–450 (2000)Google Scholar
  46. 46.
    Relativistic Heavy Ion Collider (LHC): Retrieved from (2010)
  47. 47.
    Sekhar, A., Manoj, B.S., Murthy, C.S.R.: A state-space search approach for optimizing reliabi­lity and cost of execution in distributed sensor networks. In: Proceedings of International Workshop on Distributed Computing, Kharagpur, pp. 63–74 (2005)Google Scholar
  48. 48.
    Shirazi, B., Wang, M., Pathak, G.: Analysis and evaluation of heuristic methods for static scheduling. J. Parallel Distrib. Comput. 10, 222–232 (1990)CrossRefGoogle Scholar
  49. 49.
    Shroff, P., Watson, D.W., Flann, N.S., Freund, R.F.: Genetic simulated annealing for scheduling data-dependent tasks in heterogeneous environments. In: Proceedings of Heterogeneous Computing Workshop, Honolulu, pp. 98–104 (1996)Google Scholar
  50. 50.
    Spallation Neutron Source (SNS): Retrieved from (2010)
  51. 51.
    Taylor, I.J., Deelman, E., Gannon, D.B., Shields, M. (eds.): Workflows for e-Science: Scientific Workflows for Grids. Springer, Berlin (2007)Google Scholar
  52. 52.
    Terascale Supernova Initiative (TSI): The office of science data-management challenge, Mar.-May 2004. Report from the DOE Office of Science Data-Management Workshops. Technical Report SLAC-R-782, Stanford Linear Accelerator Center, Stanford. Retrieved from (2010)
  53. 53.
    Topcuoglu, H., Hariri, S., Wu, M.Y.: Performance effective and low complexity task scheduling for heterogeneous computing. IEEE Trans. Parallel Distrib. Syst. 13(3), 260–274 (2002)CrossRefGoogle Scholar
  54. 54.
    Ullman, J.D.: NP-complete scheduling problems. J. Comput. Syst. Sci. 10(3), 384–393 (1975)MATHCrossRefMathSciNetGoogle Scholar
  55. 55.
    Wang, L., Siege, H.J., Roychowdhury, V.P., Maciejewski, A.A.: Task matching and scheduling in heterogeneous computing environments using a genetic-algorithm-based approach. J. Parallel Distrib. Comput. 47, 8–22 (1997)CrossRefGoogle Scholar
  56. 56.
    Wieczorek, M., Prodan, R., Fahringer, T.: Scheduling of scientific workflows in the ASKALON grid environment. ACM SIGMOD Record J. 34(3), 56–62 (2005)CrossRefGoogle Scholar
  57. 57.
    Worldwide LHC Computing Grid (WLCG): Retrieved from (2010)
  58. 58.
    Wu, Q., Gu, Y., Zhu, M., Rao, N.S.V.: Optimizing network performance of computing pipelines in distributed environments. In: Proceedings of the 2008 IEEE International Parallel & Distributed Processing Symposium IPDPS 2008Google Scholar
  59. 59.
    Wu, Q., Rao, N.S.V.: On transport daemons for small collaborative applications over wide-area networks. In: Proceedings of the 24th IEEE International Performance Computing and Communications Conference, Phoenix, pp. 159–166 (2005)Google Scholar
  60. 60.
    Wu, Q., Zhu, M., Gu, Y., Rao, N.S.V.: System design and algorithmic development for computational steering in distributed environments. IEEE Trans. Parallel Distrib. Syst. 21(4), 438–451 (2009)CrossRefGoogle Scholar
  61. 61.
    Zhu, Y., Li, B.: Overlay network with linear capacity constraints. IEEE Trans. Parallel Distrib. Syst. 19, 159–173 (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of MemphisMemphisUSA

Personalised recommendations