Skip to main content

Advertisement

Springer Nature Link
Log in

Rochester Elastic Cache Utility (RECU): Unequal Cache Sharing is Good Economics

  • Published:
International Journal of Parallel Programming Aims and scope Submit manuscript

Abstract

When renting computing power, fairness and overall performance are important for customers and service providers. However, strict fairness usually results in poor performance. In this paper, we study this trade-off. In our experiments, equal cache partitioning results in 131 % higher miss ratios than optimal partitioning. In order to balance fairness and performance, we propose two elastic, or movable, cache allocation baselines: elastic miss ratio baseline (EMB) and elastic cache space baseline (ECB). Furthermore, we study optimal partitions for each baseline with different levels of elasticity, and show that EMB is more effective than ECB. We also classify programs from the SPEC 2006 benchmark suite based on how they benefit or suffer from the elastic baselines, and suggest essential information for customers and service provider to choose a baseline.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Notes

  1. As described below, this miss ratio is predicted based on the Higher Order Theory of locality.

  2. It is also similar to the common-logical time miss ratio defined by [10], which specifies each co-run program’s miss ratio scaled by the interleaved memory accesses from other programs.

References

  1. Brock, J., Ye, C., Ding, C., Li, Y., Wang, X., Luo, Y.: Optimal cache partition-sharing. In: Proceedings of ICPP (2015)

  2. Ghodsi, A., Zaharia, M., Hindman, B., Konwinski, A., Shenker, S., Stoica, I.: Dominant resource fairness: fair allocation of multiple resource types. In: Proceedings of NSDI (2011). http://www.usenix.org/conference/nsdi11/dominant-resource-fairness-fair-allocation-multiple-resource-types

  3. Hsu, L.R., Reinhardt, S.K., Iyer, R.R., Makineni, S.: Communist, utilitarian, and capitalist cache policies on CMPs: caches as a shared resource. In: PACT, pp. 13–22 (2006)

  4. Hu, X., Wang, X., Li, Y., Zhou, L., Luo, Y., Ding, C., Jiang, S., Wang, Z.: LAMA: Optimized locality-aware memory allocation for key-value cache. In: Proceedings of USENIX ATC (2015)

  5. Li, P., Ding, C., Luo, H.: Modeling heap data growth using average liveness. In: Proceedings of ISMM (2014)

  6. Parihar, R., Brock, J., Ding, C., Huang, M.C.: Protection, utilization and collaboration in shared cache through rationing. http://www.cs.rochester.edu/u/cding/Documents/Publications/tr-ration.pdf

  7. Parihar, R., Brock, J., Ding, C., Huang, M.C.: Protection and utilization in shared cache through rationing. In: Proceedings of PACT, pp. 487–488 (2014). doi:10.1145/2628071.2628120

  8. Stone, H.S., Turek, J., Wolf, J.L.: Optimal partitioning of cache memory. IEEE Trans. Comput. 41(9), 1054–1068 (1992). doi:10.1109/12.165388

    Article  Google Scholar 

  9. Suh, G.E., Rudolph, L., Devadas, S.: Dynamic partitioning of shared cache memory. J. Supercomput. 28(1), 7–26 (2004)

    Article  MATH  Google Scholar 

  10. Wang et al.: Optimal program symbiosis in shared cache. In: Proceedings of CCGrid (2015)

  11. Wires, J., Ingram, S., Drudi, Z., Harvey, N.J., Warfield, A., Data, C.: Characterizing storage workloads with counter stacks. In: Proceedings of OSDI, pp. 335–349. USENIX Association (2014)

  12. Xiang, X., Bao, B., Ding, C., Gao, Y.: Linear-time modeling of program working set in shared cache. In: Proceedings of PACT, pp. 350–360 (2011)

  13. Xiang, X., Ding, C., Luo, H., Bao, B.: HOTL: a higher order theory of locality. In: Proceedings of ASPLOS, pp. 343–356 (2013)

  14. Xie, Y., Loh, G.H.: Dynamic classication of program memory behaviors in CMPs. In: CMP-MSI Workshop (2008)

  15. Zahedi, S.M., Lee, B.C.: REF: resource elasticity fairness with sharing incentives for multiprocessors. In: Proceedings of ASPLOS, pp. 145–160 (2014)

Download references

Author information

Authors and Affiliations

  1. University of Rochester, Rochester, NY, 14627, USA

    Chencheng Ye, Jacob Brock & Chen Ding

  2. Huazhong University of Science and Technology, Wuhan, China

    Chencheng Ye & Hai Jin

Authors
  1. Chencheng Ye
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Jacob Brock
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Chen Ding
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Hai Jin
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Chencheng Ye.

Additional information

Chencheng Ye is a student visiting University of Rochester, funded by the Chinese Scholarship Council.

The research is supported in part by the National Science Foundation (Contract Nos. CNS-1319617, CCF-1116104, CCF-0963759), IBM CAS Faculty Fellow program, the National Science Foundation of China (Contract No. 61328201) and a grant from Huawei.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ye, C., Brock, J., Ding, C. et al. Rochester Elastic Cache Utility (RECU): Unequal Cache Sharing is Good Economics. Int J Parallel Prog 45, 30–44 (2017). https://doi.org/10.1007/s10766-015-0384-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10766-015-0384-3

Keywords