DOI QR코드

DOI QR Code

Performance Evaluation and Analysis of NVMe SSD

Non-volatile Memory Express 인터페이스 기반 저장장치의 성능 평가 및 분석

  • 손용석 (서울대학교 컴퓨터공학부) ;
  • 염헌영 (서울대학교 컴퓨터공학부) ;
  • 한혁 (동덕여자대학교 컴퓨터학과)
  • Received : 2017.02.06
  • Accepted : 2017.05.13
  • Published : 2017.07.15

Abstract

Recently, the demand for high performance non-volatile memory storage devices that can replace existing hard disks has been increasing in environments requiring high performance computing such as data-centers and social network services. The performance of such non-volatile memory can greatly depend on the interface between the host and the storage device. With the evolution of storage interfaces, the non-volatile memory express (NVMe) interface has emerged, which can replace serial attached SCSI and serial ATA (SAS/SATA) interfaces based on existing hard disks. The NVMe interface has a higher level of scalability and provides lower latency than traditional interfaces. In this paper, an evaluation and analysis are conducted of the performance of NVMe storage devices through various workloads. We also compare and evaluate the cost efficiency of NVMe SSD and SATA SSD.

최근 데이터센터, 소셜 네트워크 서비스 등과 같은 고성능 컴퓨팅을 요구하는 환경에서는 기존 하드디스크를 대체할 수 있는 고성능 비휘발성 메모리 저장장치의 수요가 급증하고 있다. 이러한 비휘발성 메모리의 성능은 호스트와 저장장치를 연결해주는 인터페이스에 따라 크게 좌우될 수 있다. 저장장치의 인터페이스는 계속 발전해왔으며, 기존 하드디스크에 기반을 둔 SAS/SATA 인터페이스를 대체할 수 있는 NVMe 인터페이스가 최근에 등장하였다. NVMe 인터페이스는 높은 확장성을 가지며 기존 인터페이스에 비해 낮은 지연시간을 제공한다. 본 논문은 다양한 워크로드를 통해 NVMe 저장장치의 성능을 평가하고 분석한다. 또한 NVMe 저장장치와 기존 SATA 저장장치와의 가격 대비 성능비를 비교하고 평가한다.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. Ibm system storage ds8000 easy tier. http://www.ibm.com/systems/storage/flash/720-820.
  2. Netapp. http://www.netapp.com/us/products/index.aspx
  3. Flasharray, http://www.purestorage.com/
  4. NVMexpress, http://www.nvmexpress.org
  5. Second extended file system. http://e2fsprogs.sourceforge.net
  6. Mathur, A., Cao, M., Bhattacharya, S., Dilger, A., Tomas, A., and Vivier, L., 2007. The new ext4 filesystem: Current status and future plans, Proc. of the Linux Symposium, 2007.
  7. Adam Sweeney, Doug Doucette, Wei Hu, Curtis Anderson, Mike Nishimoto, Geoff Peck, Scalability in the XFS file system, 1996 ATC, San Diego, CA.
  8. Lee, C., Sim, D., Hwang, J., and Cho, S., F2FS: A new file system for flash storage. FAST15.
  9. J. Axboe, "Fiobenchmark, http://freshment.net/projects/fio."
  10. Kim, H., Seshadri, S., Dickey, C. L., and Chiu, L. Evaluating phase change memory for enterprise storage systems: A study of caching and tiering approaches. FAST 14.
  11. Park, S.; Kai Shen, "A performance evaluation of scientific I/O workloads on Flash-based SSDs," CLUSTER '09.
  12. Jaehwan Lee, Donghun Koo, Kyungmin Park, Jiksoo Kim, Soonwook Hwang, "Performance Analysis of Lustre File System using High Performance Storage Devices," KIISE Transactions on Computing Practices, 22.4 (2016.4): 163-169. https://doi.org/10.5626/KTCP.2016.22.4.163
  13. Deoksang Kim, Hyeonsang Eom, Heonyoung Yeom, "Performance Optimization in GlusterFS on SSDs," KIISE Transactions on Computing Practices, 22.2 (2016.2): 95-100. https://doi.org/10.5626/KTCP.2016.22.2.95