Analysing an Effect of Buffer Capacity and Periodic Dirty Buffer Flush on Data Lifetime

Analysing an Effect of Buffer Capacity and Periodic Dirty Buffer Flush on Data Lifetime

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2020 by IJETT Journal
Volume-68 Issue-4
Year of Publication : 2020
Authors : Ilhoon Shin, Kyungah Lee
DOI :  10.14445/22315381/IJETT-V68I4P210S

Citation 

MLA Style: Ilhoon Shin, Kyungah Lee "Analysing an Effect of Buffer Capacity and Periodic Dirty Buffer Flush on Data Lifetime" International Journal of Engineering Trends and Technology 68.4(2020):54-58. 

APA Style:Ilhoon Shin, Kyungah Lee. Analysing an Effect of Buffer Capacity and Periodic Dirty Buffer Flush on Data Lifetime  International Journal of Engineering Trends and Technology, 68(4),54-58.

Abstract
This study analyses an effect of buffer capacity and periodic dirty buffer flush on data lifetime on SSDs equipped with large internal buffer and obtains the following results. First, if the internal buffer exists, the proportion of short-lived data decreases. However, when the dirty buffer flush period is shorter than 30 minutes, even if the buffer size increases to 512 MB, most data still has a short lifetime. Second, when the dirty buffer flush period becomes longer (for example, one day), the proportion of short-lived data decreases rapidly as the buffer size increases. As a result, the accuracy of the existing lifetime prediction policy drops drastically. These results indicate that the lifetime prediction policy should be designed considering the presence of the internal buffer in SSDs and the period of dirty buffer flush.

Reference

[1] R. Liu, C. Yang, and W. Wu, "Optimizing NAND flash-based SSDs via retention relaxation," in Proc. USENIX FAST, 2012.
[2] I. Shin, "Applying fast shallow write to short-lived data in solid-state drives," IEICE Electronics Express, vol. 15, pp. 1–9, 2018.
[3] M. Park, K. Lee, and I. Shin, "Evaluating lifetime of server data based on trace analysis," International Journal of Engineering Research and Technology, vol. 12, pp. 1441-1444, 2019.
[4] Y. Yao, X. Kong, J. Zhou, X. Xu, W. Feng, and Z. Liu, "An advanced adaptive least recently used buffer management algorithm for SSD," IEEE Access, vol. 7, pp. 33494–33505, 2019.
[5] I. Shin, "Applying fast shallow write to short-lived data in solid-state drives," Journal of KIIT, vol. 17, pp. 31–38, 2019.
[6] Y. Won, J. Jung, G. Choi, J. Oh, S. Son, J. Hwang, and S. Cho, "Barrier-enabled IO stack for flash storage," in Proc. USENIX FAST, 2018.
[7] A. Ban, "Flash file system," U.S. Patent 5 404 485, Apr. 4, 1995.
[8] Y. Pan, G. Dong, Q. Wu, and T. Zhang, "Quasi-nonvolatile SSD: trading flash memory nonvolatility to improve storage system performance for enterprise applications," in Proc. IEEE HPCA, 2012.
[9] D. Narayanan, A. Donnelly, and A. Rowstron, "Write off-loading: practical power management for enterprise storage," in Proc. USENIX FAST, 2008.

Keywords
Buffer capacity, dirty buffer flush, data lifetime, SSD