DOI QR코드

DOI QR Code

마모도 평준화를 위한 File Clustering 알고리즘

A File Clustering Algorithm for Wear-leveling

  • 이태화 (한양대학교 컴퓨터소프트웨어학과) ;
  • 차재혁 (한양대학교 컴퓨터공학)
  • 투고 : 2013.01.18
  • 심사 : 2013.03.22
  • 발행 : 2013.03.31

초록

플래시 메모리 기반의 저장 장치는 고성능, 저전력, 내구성과 경량 등의 특징을 가지고 있어 기존에 사용되고 있던 저장장치를 빠르게 대체하고 있다. 플래시 메모리 기반의 저장 장치는 기존 저장장치인 블록 저장 장치로 가상화하기 위한 계층인 FTL (Flash Translation Layer) 을 가지고 있다. 가비지 컬렉션(Garbage Collection)은 FTL의 주요한 기능으로서 플래시 메모리의 수명과 성능에 큰 영향을 끼친다. 플래시 메모리의 수명은 가비지 컬렉션에 의해 발생되는 지우기의 횟수와 마모도의 영향을 받는다. 본 논문에서는 마모도 평준화 개선을 위해 File 정보를 알 수 있는 환경에서 File Clustering 알고리즘을 제시한다. File Clustering은 같은 File에서의 요청이 또다시 같이 호출 될 것을 기대하여 같은 File로부터 온 요청을 같은 블록에 할당하는 알고리즘이다. 이를 위해 FTL의 기능 중 페이지 할당 정책을 제안하였고, 최소한의 마모도 평준화를 보장하기 위해 MIN-MAX GAP을 사용하였다. 본 논문에서 제안하는 알고리즘을 검증하기 위해 TPC 벤치마크를 이용하였고 이를 통해 마모도 평준화 하지 않은 분산보다 690%이상 값이 개선되었고, 기존에 연구되던 Hot/Cold보다도 좋은 분산을 갖는 것을 보였다.

Storage device based on Flash Memory have many attractive features such as high performance, low power consumption, shock resistance, and low weight, so they replace HDDs to a certain extent. An Storage device based on Flash Memory has FTL(Flash Translation Layer) which emulate block storage devices like HDDs. A garbage collection, one of major functions of FTL, effects highly on the performance and the lifetime of devices. However, there is no de facto standard for new garbage collection algorithms. To solve this problem, we propose File Clustering Algorithm. File Clustering Algorithm respect to update page from same file at the same time. So, these are clustered to same block. For this mechanism, We propose Page Allocation Policy in FTL and use MIN-MAX GAP to guarantee wear leveling. To verify the algorithm in this paper, we use TPC Benchmark. So, The performance evaluation reveals that the proposed algorithm has comparable result with the existing algorithms(No wear leveling, Hot/Cold) and shows approximately 690% improvement in terms of the wear leveling.

키워드

참고문헌

  1. S. K. Lee, S. L. Min, Y. K. Cho, "Current trends on flash memory technology," Journal of KIISE, vol.24, no.12, pp.99-106, Dec. 2006. (in Korean)
  2. Tae-Sun Chung, Dong-Joo Park, Dong-Ho Lee, Sang-Won Lee, and Ha-Joo Song, "System Software for Flash Memory:A Survey", 2004.
  3. Jeong Su Park, Sang Lyul Min, "Flash Memory Wear-Leveling using Regulation Pools", Journal of Korean Institute of Information Scientists and Engineers(KIISE):Computing Practices and Letters, Vol.16 no12 (2010.12)
  4. Soung Hwan Lee, Tae Hoon Lee, Ki Dong Chung, "Adaptive Garbage Collection Policy based on Analysis of Page Ratio for Flash Memory", Journal of Korean Institute of Information Scientists and Engineers(KIISE):Computer System and Theory Vol.36 no.5 (2009.10)
  5. L.-P. Chang, "On efficient wear-leveling for largescale flash-memory storage systems," Proc. of the 2007ACM symposium on Applied computing, pp.1126-1130, 2007.
  6. Y.-H. Chang, J.-W. Hsieh, T.-W. Kuo, "Improving flash wear-leveling by proactively moving static data," IEEE Transactions on Computers, vol.59, no.1, pp.53-65, Jan. 2010. https://doi.org/10.1109/TC.2009.134
  7. Jen-Wei Hsieh, Li-Pin Chang, Tei-Wei Kuo, "Efficient On-line Identification of Hot Data for Flash-Memory Management" ACM symposium on applied computing SAC 05, pp. 838, 2005.
  8. S.-W. Lee, D.-J. Park, T.-S. Chung, D.-H. Lee, S.Park, H.-J. Song, "A log buffer-based flash translation layer using fully-associative sector translation, "ACM Transactions on Embedded Computing Systems (TECS), vol.6, no.3, Jul. 2007.
  9. J. Kim, J.M. Kim, S.H. Noh, S.L. Min, and Y.Cho, "A Space-Efficient Flash Transaction on Consumer Electronics, Vol. 48, No.2, pp.366-375, 2002. https://doi.org/10.1109/TCE.2002.1010143
  10. A. Kawaguchi, S. Nishioka, and H. Motoda, "A flash-memory based File System." Proceedings of the USENIX Technical Conference, 1995.
  11. Sivan Toledo, "Algorithms and Data Structures for Flash Memories" ACM Computing Surveys.
  12. J.-U. Kang, H. Jo, J.-S. Kim, J. Lee, "A superblock-based flash translation layer for NAND flash memory, " Proc. of the 6th ACM & IEEE International Conference on Embedded Software, pp.161-170, 2006.
  13. Xiao-Yu Hu, Robert Haas and Eleftheriou Evangelos, "Write amplification analysis in flash-based solidstate drives", SYSTOR '09, The Israeli Experimental Systems Conference Articale No.10, 2009.
  14. Xiao-Yu Hu, Evangelos Eleftheriou, Robert Haas, llias lliadis and Roman Pletka, "Container Marking:Combining Data Placement, Garbage Collection and Wear Levelling for Flash", MASCOTS, 2011.
  15. Ioannis Koltsidas, Stratis D. Viglas, "Data management over flash memory", SIGMOD '11
  16. Ohhoon Kwon, Kern Koh, Jaewoo Lee, HyokyungBahn, "FeGC:An efficient garbage collection scheme for flash memory based storage systems", The Journal of Systems and Software 84(2011) 1507-1523. https://doi.org/10.1016/j.jss.2011.02.042
  17. Ho-Young Jung, Taehwa Lee, Jaehyuk Cha "An Offline FTL Algorithm to Verify the Endurance of Flash SSD", Journal of Digital Contents Society. Vol.13 no14 p75-81. https://doi.org/10.9728/dcs.2012.13.1.075

피인용 문헌

  1. Implementation of a Light Weight SSD Perpormance Evaluation Simulator based on Linux FUSE vol.20, pp.12, 2019, https://doi.org/10.9728/dcs.2019.20.12.2545
  2. Implementation of a Light Weight SSD Perpormance Evaluation Simulator based on Linux FUSE vol.20, pp.12, 2019, https://doi.org/10.9728/dcs.2019.20.12.2545