Advertisement

Identifying the Optimal Level of Parallelism in Transactional Memory Applications

  • Diego Didona
  • Pascal Felber
  • Derin Harmanci
  • Paolo Romano
  • Jörg Schenker
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7853)

Abstract

In this paper we investigate the issue of automatically identifying the “natural” degree of parallelism of an application using software transactional memory (STM), i.e., the workload-specific multiprogramming level that maximizes application’s performance. We discuss the importance of adapting the concurrency level to the workload in two different scenarios, a shared-memory and a distributed STM infrastructure. We propose and evaluate two alternative self-tuning methodologies, explicitly tailored for the considered scenarios. In shared-memory STM, we show that lightweight, black-box approaches relying solely on on-line exploration can be extremely effective. For distributed STMs, we introduce a novel hybrid approach that combines model-driven performance forecasting techniques and on-line exploration in order to take the best of the two techniques, namely enhancing robustness despite model’s inaccuracies, and maximizing convergence speed towards optimum solutions.

Keywords

Decision Module Transactional Memory Software Transactional Memory Transactional Memory System Concurrency Level 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Herlihy, M., Moss, J.E.B.: Transactional memory: Architectural support for lock-free data structures. In: Proc. of ISCA (1993)Google Scholar
  2. 2.
    Harris, T., Larus, J.R., Rajwar, R.: Transactional Memory, 2nd edn. Synthesis Lectures on Computer Architecture. Morgan & Claypool Publisher (2010)Google Scholar
  3. 3.
    Reimer, N., Haenssgen, S., Tichy, W.F.: Dynamically adapting the degree of parallelism with reflexive programs. In: Saad, Y., Yang, T., Ferreira, A., Rolim, J.D.P. (eds.) IRREGULAR 1996. LNCS, vol. 1117, Springer, Heidelberg (1996)CrossRefGoogle Scholar
  4. 4.
    Heiss, H.U., Wagner, R.: Adaptive load control in transaction processing systems. In: Proc. of VLDB (1991)Google Scholar
  5. 5.
    Schroeder, B., Harchol-Balter, M., Iyengar, A., Nahum, E., Wierman, A.: How to determine a good multi-programming level for external scheduling. In: Proc. of ICDE (2006)Google Scholar
  6. 6.
    Abouzour, M., Salem, K., Bumbulis, P.: Automatic tuning of the multiprogramming level in Sybase SQL Anywhere. In: Proc. of ICDE Workshops (2010)Google Scholar
  7. 7.
    Yoo, R.M., Lee, H.H.S.: Adaptive transaction scheduling for transactional memory systems. In: Proc. of SPAA (2008)Google Scholar
  8. 8.
    Mohammad, A., Mikel, L., Christos, K., Kim, J., Chris, K., Ian, W.: Robust adaptation to available parallelism in transactional memory applications. HIPEAC Journal (2008)Google Scholar
  9. 9.
    Ghanbari, S., Soundararajan, G., Chen, J., Amza, C.: Adaptive learning of metric correlations for temperature-aware database provisioning. In: Proc. of ICAC (2007)Google Scholar
  10. 10.
    Zhang, Q., Cherkasova, L., Smirni, E.: A regression-based analytic model for dynamic resource provisioning of multi-tier applications. In: Proc. of ICAC (2007)Google Scholar
  11. 11.
    di Sanzo, P., Ciciani, B., Quaglia, F., Romano, P.: A performance model of multi-version concurrency control. In: Proc. of MASCOTS (2008)Google Scholar
  12. 12.
    Heindl, A., Pokam, G., Adl-Tabatabai, A.R.: An analytic model of optimistic software transactional memory. In: Proc. of ISPASS (2009)Google Scholar
  13. 13.
    Dragojevic, A., Guerraoui, R.: Predicting the scalability of an stm: A pragmatic approach (2010)Google Scholar
  14. 14.
    Rughetti, D., Di Sanzo, P., Ciciani, B., Quaglia, F.: Machine learning-based self-adjusting concurrency in software transactional memory systems. In: Proc. of MASCOTS (2012)Google Scholar
  15. 15.
    Cao Minh, C., Chung, J., Kozyrakis, C., Olukotun, K.: STAMP: Stanford transactional applications for multi-processing. In: Proc. of IISWC (2008)Google Scholar
  16. 16.
    Schenker, J.: Optimistic Synchronization and the Natural Degree of Parallelism of Concurrent Applications — MSc Thesis (June 2012)Google Scholar
  17. 17.
    Couceiro, M., Romano, P., Carvalho, N., Rodrigues, L.: D2stm: Dependable distributed software transactional memory. In: Proc. of PRDC (2009)Google Scholar
  18. 18.
    Narasimha Raghavan, R.V.: Balancing the communication load of state transfer in replicated systems. In: Proc. of SRDS (2011)Google Scholar
  19. 19.
    Jiménez-Peris, R., Patiño-Martínez, M., Alonso, G.: Non-intrusive, parallel recovery of replicated data. In: Proc. of SRDS (2002)Google Scholar
  20. 20.
    Elnikety, S., Dropsho, S., Cecchet, E., Zwaenepoel, W.: Predicting replicated database scalability from standalone database profiling. In: Proc. of EuroSys (2009)Google Scholar
  21. 21.
    Didona, D., Romano, P., Peluso, S., Quaglia, F.: Transactional auto scaler: elastic scaling of in-memory transactional data grids. In: Proc. of ICAC (2012)Google Scholar
  22. 22.
    Singh, R., Sharma, U., Cecchet, E., Shenoy, P.: Autonomic mix-aware provisioning for non-stationary data center workloads. In: Proc. of ICAC (2010)Google Scholar
  23. 23.
    Francesco, M., Manik, S.: Infinispan Data Grid Platform. Packt Publishing (2012)Google Scholar
  24. 24.
    Red Hat/JBoss: JBoss Infinispan (2011), http://www.jboss.org/infinispan
  25. 25.
    TPC Council: TPC-C Benchmark (2011), http://www.tpc.org/tpcc
  26. 26.
    Yu, P.S., Dias, D.M., Lavenberg, S.S.: On the analytical modeling of database concurrency control. ACM Journal (1993)Google Scholar
  27. 27.
    Quinlan, J.R.: Rulequest Cubist, http://www.rulequest.com/cubist-info.html
  28. 28.
    Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers Inc. (1993)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Diego Didona
    • 1
  • Pascal Felber
    • 2
  • Derin Harmanci
    • 2
  • Paolo Romano
    • 1
  • Jörg Schenker
    • 2
  1. 1.Instituto Superior Técnico/INESC-IDPortugal
  2. 2.University of NeuchâtelSwitzerland

Personalised recommendations