Advertisement

A Cost-aware Buffer Management Policy for Flash-based Storage Devices

  • Zhiwen Jiang
  • Yong Zhang
  • Jin Wang
  • Chunxiao Xing
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9049)

Abstract

Flash devices has become an important storage medium in enterprise hybrid storage systems. Buffer manager is a central component of database systems. However, traditional disk-oriented buffer replacement strategies are suboptimal on flash memory due to the read-write asymmetry. In this paper, we propose a cost-aware buffer management policy CARF for flash memory. We devise a novel cost model with low computational overhead to make more accurate decisions about page eviction. Moreover, this cost model can distinguish read and write operations as well as have better scan resistance. Experiments on synthetic and benchmark traces show that CARF achieves up to \(27.9\%\) improvement than state-of-art flash-aware buffer management strategies.

Keywords

Buffer management SSD Cost-aware 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aggarwal, A., Vitter, J.S.: The input/output complexity of sorting and related problems. Comm. of ACM 31(9), 1116–1127 (1988)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Bouganim, L., Jonsson, B., Bonnet, P.: uflip: Understanding flash io patterns. In: CIDR (2009)Google Scholar
  3. 3.
    Debnath, B.K., Sengupta, S., Li, J.: Skimpy stash: ram space skimpy key-value store on flash-based storage. In: SIGMOD, pp. 25–36 (2011)Google Scholar
  4. 4.
    Do, J., Zhang, D., et al. J.M.P.: Turbocharging dbms buffer pool using ssds. In: SIGMOD, pp. 1113–1124 (2011)Google Scholar
  5. 5.
    Effelsberg, W., Harder, T.: Principles of database buffer management. TODS 9(4), 560–595 (1984)CrossRefGoogle Scholar
  6. 6.
    Gal, E., Toledo, S.: Algorithms and data structures for flash memories. ACM Computing Survey (2005)Google Scholar
  7. 7.
    Jiang, S., Zhang, X.: Lirs: an efficient low inter-reference recency set replacement policy to improve buffer cache performance. In: SIGMETRICS, pp. 31–42 (2002)Google Scholar
  8. 8.
    Jiang, Z., Zhang, Y., Wang, J., Xing, C.: A cost-aware buffer management policy for flash-based storage devices. Technical Report (2015)Google Scholar
  9. 9.
    Johnson, T., Shasha, D.: 2q: A low overhead high performance buffer management replacement algorithm. In: PVLDB, pp. 439–450 (1994)Google Scholar
  10. 10.
    Kim, H., Ahn, S.: Bplru: A buffer management scheme for improving random writes in flash storage. In: FAST (2008)Google Scholar
  11. 11.
    Lee, D., Choi, J., Kim, J.H., et al.: Lrfu: A spectrum of policies that subsumes the least recently used and least frequently used policies. IEEE Trans. on Computers 50(12), 1352–1361 (2001)CrossRefMathSciNetGoogle Scholar
  12. 12.
    Lee, S.W., Moon, B.: Design of flash-based dbms: an in-page logging approach. In: SIGMOD, pp. 55–66 (2007)Google Scholar
  13. 13.
    Li, Y., He, B., Yang, R.J., Luo, Q., Yi, K.: Tree indexing on solid state drives. PVLDB 3(1), 1195–1206 (2010)Google Scholar
  14. 14.
    Li, Y., On, S.T., Xu, J., Choi, B., Hu, H.: Optimizing non-indexed join processing in flash storage-based systems. IEEE Trans. on Computers 62(7), 1417–1431 (2012)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Liu, X., Salem, K.: Hybrid storage management for database systems. Proceedings of the VLDB Endowment 6(8), 541–552 (2013)CrossRefGoogle Scholar
  16. 16.
    Lv, Y., Cui, B., He, B., Chen, X.: Operation-aware buffer management in flash-based systems. In: SIGMOD, pp. 13–24 (2011)Google Scholar
  17. 17.
    On, S.T., Gao, S., He, B., Wu, M., Luo, Q., Xu, J.: Fd-buffer: A cost-based adaptive buffer replacement algorithm for flash memory devices. IEEE Trans. on Computers (2013)Google Scholar
  18. 18.
    O’Neil, E.J., O’Neil, P.E., Weikum, G.: The lru-k page replacement algorithm for database disk buffering. In: SIGMOD, pp. 297–306 (1993)Google Scholar
  19. 19.
    Ou, Y., Harder, T.: Clean first or dirty first? a cost-aware self-adaptive buffer replacement policy. In: IDEAS (2010)Google Scholar
  20. 20.
    Ou, Y., Harder, T., Jin, P.: Cfdc: A flash-aware replacement policy for database buffer management. In: DaMoN (2009)Google Scholar
  21. 21.
    Park, S.Y., Jung, D., Kang, J.U., Kim, J.S., Lee, J.: Cflru: a replacement algorithm for flash memory. In: CASES, pp. 234–241 (2006)Google Scholar
  22. 22.
    Tsirogiannis, D., Harizopoulos, S., Shah, M.A., Wiener, J.L., Graefe, G.: Query processing techniques for solid state drives. In: SIGMOD, pp. 59–72 (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Zhiwen Jiang
    • 1
  • Yong Zhang
    • 1
  • Jin Wang
    • 1
  • Chunxiao Xing
    • 1
  1. 1.RIIT, TNList, Department of Computer Science and TechnologyTsinghua UniversityBeijingChina

Personalised recommendations