计算机科学技术学报 ›› 2019,Vol. 34 ›› Issue (4): 854-868.doi: 10.1007/s11390-019-1946-4

所属专题： Computer Architecture and Systems

• • 上一篇    下一篇

RAID 4SMR:海量存储系统的叠瓦式记录磁盘RAID阵列

Quoc Le, Ahmed Amer, JoAnne Holliday, Member, ACM, IEEE   

  1. Department of Computer Engineering, School of Engineering, Santa Clara University, Santa Clara, CA 95053, U.S.A
  • 收稿日期:2018-09-23 修回日期:2019-03-31 出版日期:2019-07-11 发布日期:2019-07-11
  • 作者简介:Quoc Le is a Ph.D.candidate in the Department of Computer Engineering at the Santa Clara University in Silicon Valley,focusing on disk performance and reliability in data centers.At the same time,he serves as a member of Technical Staff at Apstra,Inc.,working on data center automation.Formerly,he was a senior software developer at data center business unit at Cisco where his team focuses on developing central management of Cisco Unified Computing System (UCS).He received his Master's degree in software engineering from the University of Wisconsin-La Crosse,in 2008.

RAID 4SMR: RAID Array with Shingled Magnetic Recording Disk for Mass Storage Systems

Quoc Le, Ahmed Amer, JoAnne Holliday, Member, ACM, IEEE   

  1. Department of Computer Engineering, School of Engineering, Santa Clara University, Santa Clara, CA 95053, U.S.A
  • Received:2018-09-23 Revised:2019-03-31 Online:2019-07-11 Published:2019-07-11

PDF (PC)

290

补充材料

1

使用叠瓦式记录（SMR）磁盘是提升存储密度的一种方式。基于基本的RAID（独立磁盘冗余阵列）4排列，我们提出了一种使用RAID阵列的SMR磁盘的全新用法。本文提出的方案（称为RAID 4SMR）对提升传统SMR磁盘RAID 4阵列的性能具有潜力。评估显示在RAID阵列中使用更新就地时，与标准的RAID 4相比，具有垃圾收集功能的RAID 4SMR不仅使得SMR磁盘的使用能减少性能损失，而且其性能的改进高达56%。

关键词: 磁盘阵列, 独立磁盘冗余阵列(RAID), 叠瓦式磁记录(SMR), 叠瓦式写入

Abstract: One way to increase storage density is using a shingled magnetic recording (SMR) disk. We propose a novel use of SMR disks with RAID (redundant array of independent disks) arrays, specifically building upon and compared with a basic RAID 4 arrangement. The proposed scheme (called RAID 4SMR) has the potential to improve the performance of a traditional RAID 4 array with SMR disks. Our evaluation shows that compared with the standard RAID 4, when using update in-place in RAID arrays, RAID 4SMR with garbage collection not just can allow the adoption of SMR disks with a reduced performance penalty, but offers a performance improvement of up to 56%.

Key words: disk array, redundant array of independent disks(RAID), shingled magnetic recording(SMR), shingled write

[1] Shiroishi Y, Fukuda K, Tagawa I, Takenoiri S, Tanaka H, Yoshikawa N. Future options for HDD storage. IEEE Transactions on Magnetics, 2009, 45(10):3816-3822.
[2] Tagawa I, Williams M. High density data-storage using shingle-write. http://www.intermagconference.com/intermag2009/src/Program1.pdf, May 2019.
[3] Kryder M, Kim C. After hard drives-What comes next? IEEE Transactions on Magnetics, 2009, 45(10):3406-3413.
[4] Greaves S, Kanai Y, Muraoka H. Shingled recording for 2-3 Tbit/in2. IEEE Transactions on Magnetics, 2009, 45(10):3823-3829.
[5] Aghayev A, Shafaei S, Desnoyers P. Skylight-A window on shingled disk operation. ACM Transactions on Storage, 2015, 11(4):Article No. 16.
[6] Wacha R, Brandt Sent J, Maltzahn C. RAID4S:Adding SSDs to RAID arrays. https://users.soe.ucsc.edu/～carlosm/Papers/S11.pdf, May 2019.
[7] Le Q, Holliday J, Amer A. The peril and promise of shingled disk arrays:How to avoid two disks being worse than one. In Proc. Poster Session at the 10th USENIX Conference on File and Storage Technologies, Feb. 2012.
[8] Jin C, Xi W, Ching Z, Huo F, Lim C. HiSMRfs:A high performance file system for shingled storage array. In Proc. the 30th IEEE Symposium on Mass Storage Systems and Technologies, Jun. 2014, Article No. 1.
[9] Liu W, Feng D, Zeng L, Chen J. Understanding the SWD-based RAID System. In Proc. the 2014 International Conference on Cloud Computing and Big Data, November 2014, pp.175-181.
[10] Lu Z, Zhou G. Design and implementation of hybrid shingled recording RAID system. In Proc. the 14th IEEE Int. Conf. Dependable, Autonomic and Secure Computing, 14th Int. Conf. Pervasive Intelligence and Computing, 2nd Int. Conf. Big Data Intelligence and Computing and Cyber Science and Technology Congress, August 2016, pp.937-942.
[11] Kasiraj P, New R, Souza J, Williams M. System and method for writing data to dedicated bands of a hard disk drive. United States Patent 7490212, 2009. http://www.freepatentsonline.com/7490212.html, March 2019.
[12] Krishnan A, Radhakrishnan R, Vasic B. LDPC decoding strategies for two-dimensional magnetic recording. In Proc. the 2009 Global Communications Conference, Nov. 2009, Article No. 606.
[13] Krishnan A, Radhakrishnan R, Vasic B, Kavcik A, Ryan W, Erden F. 2-D magnetic recording:Read channel modeling and detection. IEEE International Magnetics Conference, 2009, 45(10):3830-3836.
[14] Chan S K, Radhakrishnan R, Eason K, Elidrissi R, Miles J, Vasic B, Krishnan A. Channel models and detectors for two-dimensional magnetic recording. IEEE Transactions on Magnetics, 2010, 46(3):804-811.
[15] Wu Y, O'Sullivan J, Singla N, Indeck R. Iterative detection and decoding for separable two-dimensional intersymbol interference. IEEE Transactions on Magnetics, 2003, 39(4):2115-2120.
[16] Gibson G, Polte M. Directions for shingled-write and two-dimensional magnetic recording system architectures:Synergies with solid-state disks. Technical Report, Carnegie Mellon University Parallel Data Lab, 2009. http://www.pdl.cmu.edu/PDL-FTP/PDSI/CMU-PDL-09-104.pdf, March 2019.
[17] Kadekodi S, Pimpale S, Gibson G. Caveat-scriptor:Write anywhere shingled disks. In Proc. the 7th USENIX Workshop on Hot Topics in Storage and File Systems, July 2015, Article No. 16.
[18] Pease D, Amir A, Real L, Biskeborn B, Richmond M. The linear tape file system. In Proc. the 26th IEEE Symposium on Mass Storage Systems and Technology, May 2010, Article No. 8.
[19] Zhang X, Du D, Hughes J, Kavuri R. HPTFS:A high performance tape file system. In Proc. the 14th NASA Goddard Conference on Mass Storage Systems and Technologies, the 23rd IEEE Symposium on Mass Storage Systems, May 2006.
[20] Lin C, Park D, He W, Du D. H-SWD:Incorporating hot data identification into shingled write disks. In Proc. the 20th IEEE International Symposium on Modelling, Analysis & Simulation of Computer and Telecommunication Systems, August 2012, pp.321-330.
[21] Moal L D, Bandic Z, Guyot C. Shingled file system hostside management of Shingled Magnetic Recording disks. In Proc. the 2012 IEEE International Conference on Consumer Electronics, January 2012, pp.425-426.
[22] He W, Du D. Novel address mappings for shingled write disks. In Proc. the 6th USENIX Workshop on Hot Topics in Storage and File Systems, June 2014, Article No. 6.
[23] Hall D, Marcos J, Coker J. Data handling algorithms for autonomous shingled magnetic recording HDDs. IEEE Transactions on Magnetics, 2012, 48(5):1777-1781.
[24] Ousterhout J, Douglis F. Beating the I/O bottleneck:A case for log-structured file systems. SIGOPS Operating Systems Review, 1989, 23(1):11-28.
[25] Rosenblum M. The design and implementation of a logstructured file system[Ph.D. Thesis]. UC Berkeley, 1992.
[26] Rosenblum M, Ousterhout J. The design and implementation of a log-structured file system. In Proc. the 13th ACM Symposium on Operating System Principles, October 1991, pp.1-15.
[27] Kohl J, Staelin C, Stonebraker M. HighLight:Using a logstructured file system for tertiary storage management. In Proc. the 1993 USENIX Winter Technical Conference, January 1993, pp.435-448.
[28] Selzer M, Bostic K, McKusick M, Staelin C. An implementation of a log-structured file system for UNIX. In Proc. the 1993 USENIX Winter Technical Conference, January 1993, pp.307-326.
[29] Dai H, Neufeld M, Han R. ELF:An efficient log-structured flash file system for micro sensor nodes. In Proc. the 2nd International Conference on Embedded Networked Sensor Systems, November 2004, pp.176-187.
[30] Finlayson R, Cheriton D. Log files:An extended file service exploiting write-once storage. In Proc. the 11th ACM Symposium on Operating Systems Principles, November 1987, pp.139-148.
[31] Lee S, Moon B. Design of flash-based DBMS:An in-page logging approach. In Proc. the 2007 ACM SIGMOD International Conference on Management of Data, June 2007, pp.55-66.
[32] Lomet D. The case for log structuring in database systems. In Proc. the 6th International Workshop on High Performance Transaction Systems, September 1995, pp.136-140.
[33] Neefe J, Roselli D, Costello A, Wang R, Anderson T. Improving the performance of log-structured file systems with adaptive methods. In Proc. the 16th ACM Symposium on Operating Systems Principles, October 1997, pp.238-251.
[34] Casutto Y, Sanvido M, Guyot C, Hall D, Bandic Z. Indirection systems for shingled-recording disk drives. In Proc. the 26th IEEE Symposium on Mass Storage Systems and Technology, May 2010, Article No. 27.
[35] Amer A, Long D, Miller E, Paris J, Schwarz T. Design issues for a shingled write disk system. In Proc. the 26th IEEE Symposium on Mass Storage Systems and Technology, May 2010, Article No. 26.
[36] Jones S, Amer A, Miller E, Long D, Pitchumani R, Strong C. Classifying data to reduce long term data movement in shingled write disks. In Proc. the 31st Symposium on Mass Storage Systems and Technologies, May 2015, Article No. 12.
[37] Schwarz T, Amer A, Kroeger T, Miller E, Long D, Pâris J. RESAR:Reliable storage at exabyte scale. In Proc. the 24th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, September 2016, pp.211-220.
[38] Pâris J, Schwarz T, Long D, Amer A. When MTTDLs are not good enough:Providing better estimates of disk array reliability. In Proc. the 7th International Information and Telecommunication Technologies Symposium, Dec. 2008.
[39] Amer A, Pâris J, Schwarz T, Ciotola V, Larkby-Lahet J. Outshining mirrors:MTTDL of fixed-order spiral layouts. In Proc. the 4th International Workshop on Storage Network Architecture and Parallel I/Os, September 2007, pp.11-16.
[40] Pâris J, Schwarz T, Amer A, Long D. Highly reliable twodimensional RAID arrays for archival storage. In Proc. the 31st IEEE International Performance Computing and Communications Conference, December 2012, pp.324-331.
[41] Greenan K, Plank J, Wylie J. Mean time to meaningless:MTTDL, Markov models, and storage system reliability. In Proc. the 2nd USENIX Workshop on Hot Topics in Storage and File Systems, June 2010, Article No. 7.
[42] Yang M, Chang Y, Wu F, Kuo T, Du D. Virtual persistent cache:Remedy the long latency behavior of hostaware shingled magnetic recording drives. In Proc. the 2017 IEEE/ACM International Conference on Computer-Aided Design, November 2017, pp.17-24.
[43] He W, Du D. SMaRT:An approach to shingled magnetic recording translation. In Proc. the 15th USENIX Conference on File and Storage Technologies, February 2017, pp.121-134.
[44] Le Q, SathyanarayanaRaju K, Amer A, Holliday J. Workload impact on shingled write disks:All-writes can be alright. In Proc. the 19th Annual IEEE/ACM International Symposium on Modelling, Analysis & Simulation of Computer and Telecommunication Systems, July 2011, pp.444-446.
[45] Narayanan D, Donnelly A, Rowstron A. Write off-loading:Practical power management for enterprise storage. In Proc. the 6th USENIX Conference on File and Storage Technologies, February 2008, pp.253-267.
[46] Patterson D, Gibson G, Katz R. A case for redundant arrays of inexpensive disks (RAID). In Proc. the 1988 ACM SIGMOD International Conference on Management of Data, June 1988, pp.109-116.
[47] Chaarawi S, Paris J, Amer A, Schwarz T, Long D. Using a shared storage class memory device to improve the reliability of RAID arrays. In Proc. the 5th Petascale Data Storage Workshop, 2010, pp.1-5.
[48] Le Q, Amer A, Holliday J. SMR disks for mass storage systems. In Proc. the 23rd IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, October 2015, pp.228-231.
[49] Mesnier M, Chen F, Luo T, Akers J. Differentiated storage services. In Proc. the 23rd ACM Symposium on Operating Systems Principles, October 2011, pp.57-70.
[50] Pâris J, Estrada-Galinanes V, Amer A, Rincon C. Using entanglements to increase the reliability of two-dimensional square RAID arrays. In Proc. the 36th IEEE International Performance Computing and Communications Conference, December 2017, Article No. 27.
No related articles found!
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《计算机科学技术学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持：support@magtech.com.cn
总访问量：