Journal of KIISE:Computer Systems and Theory (한국정보과학회논문지:시스템및이론)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

Parallelism-aware Request Scheduling for MEMS-based Storages

MEMS 기반 저장장치를 위한 병렬성 기반 스케줄링 기법

  • 이소윤 (이화여자대학교 컴퓨터학과) ;
  • 반효경 (이화여자대학교 컴퓨터학과) ;
  • 노삼혁 (홍익대학교 정보컴퓨터공학부)
  • Published : 2007.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

MEMS-based storage is being developed as a new storage media. Due to its attractive features such as high-bandwidth, low-power consumption, high-density, and low cost, MEMS storage is anticipated to be used for a wide range of applications from storage for small handhold devices to high capacity mass storage servers. However, MEMS storage has vastly different physical characteristics compared to a traditional disk. First, MEMS storage has thousands of heads that can be activated simultaneously. Second, the media of MEMS storage is a square structure which is different from the platter structure of disks. This paper presents a new request scheduling algorithm for MEMS storage that makes use of the aforementioned characteristics. This new algorithm considers the parallelism of MEMS storage as well as the seek time of requests on the two dimensional square structure. We then extend this algorithm to consider the aging factor so that starvation resistance is improved. Simulation studies show that the proposed algorithms improve the performance of MEMS storage by up to 39.2% in terms of the average response time and 62.4% in terms of starvation resistance compared to the widely acknowledged SPTF (Shortest Positioning Time First) algorithm.

MEMS 기반 저장장치는 높은 대역폭과 저전력성, 고집적도, 저가 등의 특성으로 인해 모바일 기기에서 대용량 서버 시스템에 이르는 다양한 환경에서 사용가능한 차세대 저장장치이다. MEMS 기반 저장장치는 원판이 회전하는 하드디스크와 달리 매체가 사각형 구조로 되어 있으며 하나의 매체에 동시에 읽고 쓸 수 있는 수천 개의 헤드가 존재한다. 본 논문에서는 이와 같은 MEMS 기반 저장장치의 물리적 특성에 적합한 새로운 입출력 요청 스케줄링 기법을 제안한다. 새롭게 제안한 알고리즘은 사각형 평면상에서의 헤드의 탐색 시간뿐 아니라 수천 개의 헤드에 의한 병렬적인 입출력을 고려한다. 또한, 기아 현상(starvation)을 극복하기 위해 알고리즘에 노화 요소(aging factor)를 반영한다. 트레이스 기반 모의 실험을 통해 본 논문이 제안한 스케줄링 알고리즘이 기존의 대표적인 알고리즘인 SPTF(Shortest Positioning Time First) 알고리즘에 비해 평균 응답 시간과 응답 시간의 편차 측면에서 각각 39.2%와 62.4%가 향상됨을 보였다.

Keywords

References

  1. S. Schlosser, J. Griffin, D. Nagle, and G. Ganger, 'Designing computer systems with MEMS-based storage,' 9th Int'l Conf. Architectural Support for Programming Languages and Operating Systems, 2000
  2. J. Griffin, S. Schlosser, G. Ganger, and D. Nagle, 'Modeling and performance of MEMS-based storage devices,' ACM SIGMETRICS Conf., pp. 56-65, 2000
  3. P. Vettiger, M. Despont, U. Drechsler, U. Durig, W. Haberle, M. Lutwyche, H. Rothuizen, R. Stutz, R. Widmer, and G. Binnig, 'The Millipede - More than one thousand tips for future AFM data storage,' IBM Journal Research and Development, Vol.44, No.3, pp.323-340, 2000 https://doi.org/10.1147/rd.443.0323
  4. Samsung Flash Memory, http://www.sarnsung.com/ products/semiconductor /NANDFlash/SLC_LargeBlock/8Gbit/K9K8G08U1A/K9K8G08U1A.htm
  5. B. Hong, S. Brandt, D. Long, E. Miller, K. Glocer, and Z. Peterson, 'Zone-based Shortest Positioning Time First Scheduling for MEMS-based Storage Devices,' 11th IEEE/ACM Symp. Modeling, Analysis, and Simulation of Computer and Tel. Systems, 2003
  6. J. Griffin, S. Schlosser, G. Ganger, and D. Nagle, 'Operating system management of MEMS-based storage devices,' 4th USENIX Symp. Operating Systems Design and Implementation, pp. 227-242, 2000
  7. H. Yu, D. Agrawal, and A. Abbadi, 'Towards optimal I/O scheduling for MEMS-based storage,' 20th IEEE/11th NASA Goddard Conf. Mass Storage Systems and Technologies, 2003
  8. P. Denning, 'Effects of scheduling on file memory operations,' AFIPS Spring Computer Conf. 1967
  9. B. Worthington, G. Ganger, and Y. Patt, 'Scheduling Algorithms for Modern Disk Drives,' ACM SIGMETRICS Conf. pp. 241-251, 1994 https://doi.org/10.1145/183019.183045
  10. S. Schlosser and G. Ganger, 'MEMS-based storage devices and standard disk interfaces: A square peg in a round hole?' 3rd USENIX Conf. File and Storage Technologies, 2004
  11. Center for Highly Integrated Information Processing and Storage Systems, Carnegie Mellon University, http://www.ece.cmu.edu/research/chips/
  12. Hewlett-Packard Laboratories Atomic Resolution Storage, http://www.hpl.hp.com/research/storage.html
  13. D. Jacobson and J. Wilkes, 'Disk scheduling algorithms based on rotational position,' Technical Report HPL-CSP-91-7revl, HP Labs, 1992
  14. Public Software, Storage Systems Department at HP Labs, http://tesla.hpl.hp.com/public_software/