The Design of Large-Scale, Do-It-Yourself RAIDs

In this paper we explore the design of “Do-It-Yourself” RAIDs: RAID systems that can assembled by the end user from commercially available disks, enclosures, cables, racks, computers, and networks. We quantitatively evaluate the tradeoffs in cost, performance, and reliability of these DIY-RAID systems. Our principal result is an architecture that scales from 10s to 1000s of disks; we demonstrate that a 1995 implementation would have much lower cost, better and more scalable performance, and roughly the same reliability as commercially available hardware RAID systems. Furthermore, if current trends continue, these DIY-RAIDs will replace near-line tape libraries within a few years.

[1]  Thorsten von Eicken,et al.  Low-latency communication over ATM networks using active messages , 1994, Symposium Record Hot Interconnects II.

[2]  Gregory F. Pfister,et al.  In Search of Clusters , 1995 .

[3]  John H. Hartman,et al.  The Zebra striped network file system , 1995, TOCS.

[4]  Edward K. Lee.  Highly-available, scalable network storage , 1995, Digest of Papers. COMPCON'95. Technologies for the Information Superhighway.

[5]  David E. Culler,et al.  A case for NOW (networks of workstation) , 1995, PODC '95.

[6]  Mendel Rosenblum,et al.  The design and implementation of a log-structured file system , 1991, SOSP '91.

[7]  David A. Patterson,et al.  Computer Architecture - A Quantitative Approach, 5th Edition , 1996 .

[8]  Garth A. Gibson,et al.  RAID-II: a high-bandwidth network file server , 1994, Proceedings of 21 International Symposium on Computer Architecture.

[9]  Charles L. Seitz,et al.  Myrinet: A Gigabit-per-Second Local Area Network , 1995, IEEE Micro.

[10]  John C. S. Lui,et al.  Performance Analysis of Disk Arrays under Failure , 1990, VLDB.

[11]  Thorsten von Eicken,et al.  Low-Latency Communication Over ATM Networks Using Active Messages , 1995, IEEE Micro.

[12]  Srinivasan Seshan,et al.  RAID-II: a high-bandwidth network file server , 1994, ISCA '94.

[13]  Richard P. Martin,et al.  HPAM: an active message layer for a network of hp workstations , 1994, Symposium Record Hot Interconnects II.

[14]  David A. Wood,et al.  Cost-Effective Parallel Computing , 1995, Computer.

[15]  Darrell D. E. Long,et al.  Swift: a storage architecture for large objects , 1991, [1991] Digest of Papers Eleventh IEEE Symposium on Mass Storage Systems.

[16]  Garth A. Gibson,et al.  RAID: high-performance, reliable secondary storage , 1994, CSUR.

[17]  Carl Staelin,et al.  The HP AutoRAID hierarchical storage system , 1995, SOSP.

[18]  Shivakumar Venkataraman,et al.  The TickerTAIP parallel RAID architecture , 1993, ISCA '93.

[19]  Samuel H. Fuller.  Price/performance comparison of C.mmp and the PDP-10 , 1976, ISCA.

[20]  Garth A. Gibson.  Redundant disk arrays: Reliable, parallel secondary storage. Ph.D. Thesis , 1990 .