Journal of Internet of Things and Convergence (사물인터넷융복합논문지)

The Korea Internet of Things Society (한국사물인터넷학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Performance Measurement and Analysis on the Virtual Memory based FTL Policy through the Changing Map Data Resource

멥 데이터 자원 변화를 통한 가상 메모리 기반 FTL 정책의 성능 측정 및 분석 연구

  • Received : 2022.10.25
  • Accepted : 2022.12.02
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, in order to store and manage big data, research and development of a high-performance storage system capable of stably accessing large data have been actively conducted. In particular, storage systems in data centers and enterprise environments use large amounts of SSD (solid state disk) to manage large amounts of data. In general, SSD uses FTL(flash transfer layer) to hide the characteristics of NAND flash memory, which is a medium, and to efficiently manage data. However, FTL's algorithm has a limitation in using DRAM more to manage the location information of NAND where data is stored as the capacity of SSD increases. Therefore, this paper introduces FTL policies that apply virtual memory to reduce DRAM resources used in FTL. The virtual memory-based FTL policy proposed in this paper manages the map data by using LRU (least recently used) policy to load the mapping information of the recently used data into the DRAM space and store the previously used information in NAND. Finally, through experiments, performance and resource usage consumed during data write processing of virtual memory-based FTL and general FTL are measured and analyzed.

최근 빅데이터를 저장 및 관리하기 위해 대용량 데이터를 안정적으로 접근할 수 있는 고성능의 저장시스템 개발과 연구가 활발하게 진행되고 있다. 특히 데이터센터 및 엔터프라이즈 환경의 저장시스템에서는 대용량의 데이터를 관리하기 위해 대용량의 SSD(solid state disk)가 대량으로 사용되고 있다. 일반적으로 SSD는 미디어인 NAND 플래시 메모리의 특성을 감추고 데이터를 관리를 효율적으로 하기 위해 FTL(flash transfer layer)을 사용한다. 그러나 FTL의 알고리즘은 SSD의 용량이 커질수록 데이터가 저장된 NAND의 위치 정보를 관리하기 위해 DRAM을 많이 사용하는 한계가 있다. 따라서 본 논문에서는 FTL에서 사용하는 DRAM 자원을 줄이기 위한 가상 메모리 (virtual memory)를 적용한 FTL 정책을 소개한다. 본 논문에서 제안하는 가상 메모리 기반 FTL 정책은 LRU(least recently used) 정책을 사용하여 최근 사용된 데이터의 멥핑 정보를 DRAM 공간에 적재하고 이전에 사용된 정보는 NAND에 저장하는 방식으로 멥 데이터를 관리한다. 마지막으로 실험을 통해 가상 메모리 기반의 FTL과 일반 FTL의 데이터 쓰기 처리를 하는 동안 소모되는 성능과 자원의 사용량을 측정하고 분석한다.

Keywords

Acknowledgement

이 논문은 2022학년도 백석대학교 학술연구비 지원을 받아 작성되었음

References

  1. H.S.Lee, "A Prediction-Based Data Read Ahead Policy using Decision Tree for improving the performance of NAND flash memory based storage devices," The Korea Internet of Things Society, Vol.8, No.4, pp.9-15, 2022.
  2. H.S.Lee, "A Safety IO Throttling Method Inducting Differential End of Life to Improving the Reliability of Big Data Maintenance in the SSD based RAID," The Society of Digital Policy & Management, Vol.20, No.5, pp.593-598, 2022.
  3. H.S.Lee, "Performance analysis and prediction through various over-provision on NAND flash memory based storage," The Society of Digital Policy & Management, Vol.20, No.3, pp.343-348, 2022.
  4. H.S.Lee, "A method for optimizing lifetime prediction of a storage device using the frequency of occurrence of defects in NAND flash memory," The Korea Internet of Things Society, Vol.7, No.4, pp.9-14, 2021.
  5. M.K.Kim, I.J.Kim and J.S.Lee, "CMOS-compatible ferroelectric NAND flash memory for high-density, low-power, and high-speed three-dimensional memory," Science Advances, Vol.7, No.3, 2021.
  6. P.Kumari, U.Surendranathan, M.Wasiolek, K. Hattar, N.P.Bhat and B.Ray, "Radiation-Induced Error Mitigation by Read-Retry Technique for MLC 3-D NAND Flash Memory," IEEE Transactions on Nuclear Science, Vol.68, No.5, pp.1032-1039, 2021.
  7. K.Parat and A.Goda, "Scaling Trends in NAND Flash", 2018 IEEE International Electron Devices Meeting (IEDM), pp.211-214, 2018.
  8. G.H.Lee, S.M.Hwang, J.S.Yu and H.J.Kim, "Architecture and Process Integration Overview of 3D NAND Flash Technologies," Open Access Vo.11, No.15, pp.6703, 2021.
  9. S.S.Chae, R.Mativenga, J.Y.Paik, M.Attique, and T.S.Chung, "DSFTL: An efficient FTL for flash memory based storage systems." Electronics Vol.9, No.1, pp.145, 2020.
  10. W.Xie, Y.Chen, and P.C.Poth, "ASA-FTL: An adaptive separation aware flash translation layer for solid state drives," Parallel Computing, Vol.61, pp.3-17, 2017. https://doi.org/10.1016/j.parco.2016.10.006
  11. I.B.Zion, "Key-value FTL over open channel SSD," 12th ACM International Conference on Systems and Storage. pp.192-192, 2020.
  12. D.Skalatos, A.Kokolis, T.Xu, and J.Torrellas, "Elastic Cuckoo Page Tables: Rethinking Virtual Memory Translation for Parallelism," ASPLOS '20: Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, pp.1093-1108, 2020.
  13. D.Ganguly, Z.Zhang, Yang and R.Melhem, "Interplay between hardware prefetcher and page eviction policy in CPU-GPU unified virtual memory," ISCA '19: Proceedings of the 46th International Symposium on Computer Architecture, pp.224-235, 2019.
  14. D.Mishra and P.Kulkarni, "A survey of memory management techniques in virtualized systems," Computer Science Review, Vol.29, pp.56-73, 2018. https://doi.org/10.1016/j.cosrev.2018.06.002
  15. A.A.Titinchi and N.Halasa, "FPGA implementation of simplified Fuzzy LRU replacement algorithm," 16th International Multi-Conference on Systems, Signals & Devices (SSD), pp.657-662, 2019.
  16. Q.Zheng, T.Yang, Y.Kan, X.Tan, J.Yang, and X.Jiang, "On the Analysis of Cache Invalidation With LRU Replacement," IEEE Transactions on Parallel and Distributed Systems, Vol.33, No.3, pp.654-666, 2022.  https://doi.org/10.1109/TPDS.2021.3098459