A case for redundant arrays of inexpensive disks (RAID)

ABSTRACT

Increasing performance of CPUs and memories will be squandered if not matched by a similar performance increase in I/O. While the capacity of Single Large Expensive Disks (SLED) has grown rapidly, the performance improvement of SLED has been modest. Redundant Arrays of Inexpensive Disks (RAID), based on the magnetic disk technology developed for personal computers, offers an attractive alternative to SLED, promising improvements of an order of magnitude in performance, reliability, power consumption, and scalability. This paper introduces five levels of RAIDs, giving their relative cost/performance, and compares RAID to an IBM 3380 and a Fujitsu Super Eagle.

REFERENCES

• Bell 84: C. G. Bell, The mini and micro industries, Computer, v.17 n.10, p.14-30, Oct. 1984 [doi>10.1109/MC.1984.1658955]
• Joy 85: B Jo~ prc~entauon at ISSCC '85 panel session, Feb 1985
• Siewiorek 82: D P Ssea~orek, C G Bell, and A Ne~ell, Computer Strm tl~rc ~ Prm, lple~ and Example~, p 46
• Moore 75: G E Moore, "Progress sn Digital Integrated Electromcs," Proc IEEE Dtgttal Integrated Electrom6 Device Meeting, (1975), p 11
• Myers 86: G J Myers A Y C Yu, and D L House, "Microprocessor Technology Trend~ " Proc IEEE, Vol 74, no 12, (December 1986), pp 1605-1622
• Garcia 84: H Garc~a Mohna, R Culhngford, P Honeyman, R Lipton, "The Case for Massive Memory," Techmeal Report 326, Dept of EE and CS, Pnnceton Umv, May 1984
• Myers 86: W Myers, "The Compettuveness of the Umted States Disk Industry," IEEE Computer, Vol 19, No 11 (January 1986), pp 85-90
• Frank 87: P D Frank, "Advances m Head Technology," presentaUon at Challenges m Dzsk Technology She, t Course, Institute for Informauon Storage Technology, Santa Clara Untvers~ty, Santa Clara, Cahfomxa, ~mber 15-17, 1987
• Stevens 81: L D Stevens, "The Evoluuon of Magnetic Storage," IBM Journal of Research and Development, Voi 25, No 5, Sept 1981, pp 663-675
• Harker 81: J M Harker et al, "A Quarter Century of Disk File Innovataon," tb~d, pp 677-689
• Amdahl 67: G M Amdahl, "Vahdaty of the single processor approach to achieving large scale computing eapabd~ttes," Procee&ngs AFIPS 1967 Spnng Joint Computer Conference Vol 30 (Aflantte City, New Jersey April 1967), pp 483-485
• Boral 83: H Boral and D J DeWltt, "Database Machines An Ideas Whose Ttme Has Passed9 A Cnttque of the Future of Database Machines," Proc International Conf on Database Mactunes, Edited by H -O Lelheh and M Mtsskoff, Spnnger-Verlag, Berhn, 1983
• IBM 87: "IBM 3380 Dtreet Access Storage Introdueuon," IBM GC 26-4491-0, September 1987
• Gawlick 87: D Gawhek, private eommumeatton, Nov, 1987
• Fujitsu 87: "M2361A Mm~-Dssk Drive Englneenng Speelfleauons," (revased) Feb, 1987, B03P-4825-0001A
• Adaptec 87: AIC-6250, IC Product Grade, Adaptec, stock # DB0003-00 rev B, 1987, p 46
• Livny 87: Miron Livny , Setrag Khoshafian , Haran Boral, Multi-disk management algorithms, Proceedings of the 1987 ACM SIGMETRICS conference on Measurement and modeling of computer systems, p.69-77, May 11-14, 1987, Banff, Alberta, Canada
• Kim 86: M Y Kim, Synchronized disk interleaving, IEEE Transactions on Computers, v.35 n.11, p.978-988, Nov. 1986 [doi>10.1109/TC.1986.1676699]
• Salem 86: Kenneth Salem , Hector Garcia-Molina, Disk Striping, Proceedings of the Second International Conference on Data Engineering, p.336-342, February 05-07, 1986
• Bitton 88: D Bitton and J Gray, "Desk Shadowing," m press, 1988
• Kurzweil 88: F Kurzwell, "Small Dask Arrays - The Emerging Approach to H~gh Performance," presentauon at Spnng COMPCON 88, March 1, 1988, San Francisco, CA
• Hamming 50: R W Hamming, "Error Detecting and Correcting Codes," The Bell System Techmcal Journal, Vol XXVI, No 2 (April 1950), pp 147-160
• Hillis 87: D Htlhs, private eommumeauon, October, 1987
• Park 86: A Park and K Balasubramaman, "Provldmg Fault Tolerance m Parallel Secondary Storage Systems," Department of Computer Science, Prmeeton Omversaty, CS.TR-057-86, Nov 7, 1986
• Maginnis 87: N B Magmms, "Store More, Spend Less Meal-range Opttons Abound,"Computerworld, Nov 16, 1987, p 71
• Denning 78: Peter J. Denning , Donald R. Slutz, Generalized working sets for segment reference strings, Communications of the ACM, v.21 n.9, p.750-759, Sept. 1978 [doi>10.1145/359588.359598]
• Bell 85: Bell, C G, "Mult~s a new class of muitzproeessor computers,"Sc~ence, voL 228 (Alm126, 1985) 462-467

INDEX TERMS

Primary Classification:
  B. Hardware
  B.4 INPUT/OUTPUT AND DATA COMMUNICATIONS

Additional Classification:
  B. Hardware
  B.3 MEMORY STRUCTURES
      B.3.2 Design Styles
          Subjects: Mass storage (e.g., magnetic, optical, RAID)

General Terms:
Design, Performance