정보과학회 논문지 (Journal of KIISE)

  • 제42권3호
  • /
  • Pages.379-389
  • /
  • 2015
  • /
  • 2383-630X(pISSN)
  • /
  • 2383-6296(eISSN)
한국정보과학회 (Korean Institute of Information Scientists and Engineers)
권호 표지
DOI QR코드

DOI QR Code

PRAM 기반의 조인 알고리즘 성능 비교 연구

A Comparative Study of PRAM-based Join Algorithms

  • 최용성 (경기대학교 컴퓨터과학과) ;
  • 온병원 (군산대학교 통계컴퓨터과학과) ;
  • 최규상 (영남대학교 정보통신공학과) ;
  • 이인규 (차세대융합기술연구원 스마트그리드연구센터)
  • 투고 : 2014.09.04
  • 심사 : 2015.01.06
  • 발행 : 2015.03.15
⟨ 이전 논문 다음 논문 ⟩

초록

Phase Change Memory (PCM 또는 PRAM), Magneto Resistive RAM (MRAM)과 같은 차세대 비휘발성 메모리가 등장하면서, Dynamic Random-Access Memory (DRAM)을 PRAM으로 대체하는 연구가 활발히 진행되고 있다. 본 논문에서는 PRAM을 메인 메모리로 사용하는 시스템에서 지금까지 널리 사용되고 있는 기존의 조인 알고리즘(블록 네스티드 조인, 소트-머지 조인, 그레이스 해시 조인, 하이브리드 해시 조인)들을 사용했을 때 발생하는 내구성과 성능 문제를 비교, 분석한다. 본 연구의 실험결과에 의하면 기존의 조인 알고리즘들을 PRAM에 맞게 재설계해야 하는 필요성이 제기되었다. 특히, 본 연구는 조인 알고리즘들을 PRAM에 적용했을 때 발생하는 이슈들을 과학적으로 규명한 첫 시도이다. 그리고 기존의 조인 알고리즘들을 PRAM에 적용했을 때 발생하는 내구성과 성능을 비교하기 위한 PRAM 기반의 시스템을 모델링하고 시뮬레이터를 구현한 것에 연구의 의의를 둘 수 있다.

With the advent of non-volatile memories such as Phase Change Memory (PCM or PRAM) and Magneto Resistive RAM (MRAM), active studies have been carried out on how to replace Dynamic Random-Access Memory (DRAM) with PRAM. In this paper, we study both endurance and performance issues of existing join algorithms that are based on PRAM-based computer systems and have been widely used until now: Block Nested Loop Join, Sort-Merge Join, Grace Hash Join, and Hybrid Hash Join. Our experimental results show that the existing join algorithms need to be redesigned to improve both the endurance and performance of PRAMs. To the best of our knowledge, this is the first research to scientifically study the results of the four join algorithms running on PRAM-based systems. In this work, our main contribution is the modeling and implementation of a PRAM-based simulator for a comparative study of the existing join algorithms.

키워드

과제정보

연구 과제 주관 기관 : 한국연구재단

참고문헌

  1. Hana Institute of Finance, Outlook for non-volatile memory devices and solid state drives, 2009.
  2. M. Qureshi, V. Srinivasan and J. Rivers, Scalable high performance main memory system using phasechange memory technology, Proc. of the 36th Annual International Symposium on Computer Architecture, pp. 24-33, 2009.
  3. D. Woodhouse, JFFS: The journalling flash file system, Proc. of the Linux Symposium, Jul. 2001.
  4. D. Kang, D. Jung, J. Kang and J. Kim, $\mu$-tree: An ordered index structure for NAND flash memory, Proc. of the 7th ACM/IEEE International Conference on Embedded Software, pp. 144-153, 2007.
  5. Y. Li, B. He, J. Yang, Q. Luo and K. Yi, Tree indexing on solid state drives, VLDB Journal, Vol. 3, No. 1, pp. 1195-1206, 2010.
  6. ZDNet Korea, NAND Flash market, 18% growth this year, 2011, Available from http://www.zdnet.co.kr/news/news_view.asp?artice_id=20110120190952
  7. B. Lee, E. Ipek, O. Mutlu and D. Burger, Architecting phase change memory as a scalable dram alternative, Proc. of the 36th Annual International Symposium on Computer Architecture, pp. 2-13, 2009.
  8. S. Cho and H. Lee, Flip-N-Write: A simple deterministic technique to improve PRAM write performance, energy and endurance, Proc. of the 42nd Annual ACM/IEEE International Symposium on Microarchitecture (MICRO 42), pp. 347-357, 2009.
  9. J. Kim, H, Lee, S. Choi and K. Bahng, A PRAM and NAND flash hybrid architecture for highperformance embedded storage subsystems, Proc. of the 8th ACM International Conference on Embedded Software, pp. 31-40, New York, NY, USA, 2008.
  10. S. Nath and A. Kansal, FlashDB: Dynamic selftuning database for NAND flash, Proc. of the 6th International Conference on Information Processing in Sensor Networks, pp. 410-419, 2007.
  11. J. Do and J. Patel, Join processing for Flash SSDs: Remembering past lessons, Proc. of 5th International Workshop on Data Management on New Hardware, Providence, Rhode-Island, USA, Jun. 2009.
  12. J. Patel, M. Carey and M. Vernon, Accurate modeling of the hybrid hash join algorithm, ACM SIGMETRICS Conference, Nashvile, 1994.
  13. A. Silberschatz, H. Korth and S. Sudarshan, Database system concepts, McGraw-Hill Education, 6th Edition, 2011.
  14. L. Haas, M. Carey, M. Livny and A. Shukla, Seeking the truth about ad hoc join costs, VLDB Journal, Vol. 6, No. 3, pp. 241-256, 1993. https://doi.org/10.1007/s007780050043
  15. J. Park, S. Park, S. Lee and C. Park, Performance evaluation of hash join algorithm on flash memory SSDs, Journal of KIISE: Computing Practices and Letters, Vol. 16, No. 11, pp. 1031-1040, 2010.
  16. Y. Kim, S. Kim, Y. Park, S. Jin and K. Rim, A load balancing hash join algorithm for data skew in shared-nothing parallel database system, Journal of KIISE, Vol. 22, No. 8, pp. 1174-1182, 1995.
  17. Y. Shim and J. Lee, A skewed data handling method using spatial hash join algorithm, Journal of KIISE, Vol. 31, No. 1(B), pp. 19-21, 2004.
  18. C. Kim and H. Cho, Implementation of parallel hash join algorithms in a database sharing system, Journal of KIISE, Vol. 29, No. 1B, pp. 43-45, 2002.