Skip to main content
SpringerLink
Log in

RAID level selection for heterogeneous disk arrays

  • Published:
Cluster Computing Aims and scope Submit manuscript

Abstract

Heterogeneous Disk Arrays (HDAs) allow resource sharing of their hardware by multiple RAID levels. RAID1 (mirrored disks) and RAID5 (distributed parity arrays) are the two RAID levels considered in this study. They are both single disk failure tolerant (1DFT), but differ significantly in their efficiency in processing database workloads. The goal of the study is to maximize the number of Virtual Array (VA) allocations in HDA. We develop an analysis to estimate the load per VA based on a few parameters: the fraction of accesses to small versus large blocks and the fraction of updates versus reads. A VA is allocated according to the RAID level, which minimizes the anticipated load based on input parameters. Operation in normal and degraded mode is considered for comparison purposes, but in fact allocations are carried out using the higher load in degraded mode to ensure that single disk failures will not result in overload. We report on parametric studies to gain insight into circumstances leading to a RAID1 or RAID5 classification. An allocation experiment with a synthetic workload is used to demonstrate the superiority of HDA with respect to purely RAID1 or RAID5 disk arrays. This analytic study can be extended to 2DFT arrays, namely RAID6 versus 3-way replication.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Alvarez, G.A., Borowsky, E., Go, S., Romer, T.H., Becker-Szendy, R.A., Golding, R.A., Merchant, A., Spasojevic, M., Veitch, A.C., Wilkes, J.: Minerva: an automated resource provisioning tool for large-scale storage systems. ACM Trans. Comput. Syst. 19(4), 483–518 (2001)

    Article  Google Scholar 

  2. Anderson, E., Kallahalla, M., Spence, S., Swaminathan, R., Wang, Q.: Ergastulum: an approach to solving the workload and device configuration problem. Technical Report SSP-2001-5, HP Labs, Palo Alto, CA

  3. Anderson, E., Swaminathan, R., Veitch, A., Alvarez, G.A., Wilkes, J.: Selecting RAID levels for disk arrays. In: Proc. First USENIX Conf. File and Storage Technologies—FAST’02 Conf., Monterey, CA, January 2002, pp. 189–201

  4. Anderson, E., Spence, S., Swaminathan, R., Kallahalla, M., Wang, Q.: Quickly finding near-optimal storage designs. ACM Trans. Comput. Syst. 23(4), 337–374 (2005)

    Article  Google Scholar 

  5. Blaum, M., Brady, J., Bruck, J., Menon, J.: EVENODD: an optimal scheme for tolerating double disk failures in RAID architectures. IEEE Trans. Comput. 44(2), 192–202 (1995)

    Article  MATH  Google Scholar 

  6. Borowsky, E., Golding, R., Merchant, A., Shreier, L., Shriver, E., Spasojevic, M., Wilkes, J.: Using attribute-managed storage to achieve QoS. In: Proc. 5th IFIP Int. Workshop on Quality of Service, Columbia University, New York, NY (1997)

  7. Chen, P.M., Lee, E.K., Gibson, G.A., Katz, R.H., Patterson, D.A.: RAID: High-performance, reliable secondary storage. ACM Comput. Surv. 26(2), 145–185 (1994)

    Article  Google Scholar 

  8. Corbett, P.F., English, B., Goel, A., Grcanac, T., Kleiman, S., Leong, J., Sankar, S.: Row-diagonal parity for double disk failure correction. In: Proc. 3rd USENIX Conf. File and Storage Technologies—FAST’04, San Francisco, CA, March–April 1994, pp. 1–14

  9. IBM, http://www.storage.ibm.com/hdd/prod/ultrastar.htm

  10. Jacob, B., Ng, S.W., Wang, D.T., Systems, Memory: Cache, DRAM, Disk. Morgan Kaufmann, San Francisco (2008)

    Google Scholar 

  11. Joukov, N., Krishnakumar, A.M., Patti, C., Rai, A., Satnur, S., Traeger, A., Zadok, E.: RAIF: redundant array of independent filesystems. In: Proc. 24th IEEE Conf. on Mass Storage Systems and Technologies—MSST’07, San Diego, CA, September 2007

  12. Kleinrock, L.: Queueing Systems: Theory. Wiley-Interscience, New York (1975)

    MATH  Google Scholar 

  13. Menon, J.: A performance comparison of RAID-5 and log-structured arrays. In: Proc. 4th IEEE Int. Symp. on High-Performance Distributed Computing—HPDC, Washington, DC, August 1995, pp. 167–177

  14. Muntz, R.R., Lui, J.C.S.: Performance analysis of disk arrays under failure. In: Proc. 16th Very Large Data Base—VLDB Conf., Brisbane, Australia, August 1990, pp. 162–173

  15. Patterson, D.A., Gibson, G.A., Katz, R.H.: A case for redundant arrays of inexpensive disks. In: Proc. ACM SIGMOD Int. Conf. on Management of Data, Chicago, IL, June 1988, pp. 109–116

  16. PDL, http://www.pdl.cmu.edu/DiskSim/diskspecs.html

  17. Thomasian, A., Menon, J.: RAID5 performance with distributed sparing. IEEE Trans. Parallel Distrib. Syst. 8(6), 640–657 (1997)

    Article  Google Scholar 

  18. Thomasian, A.: Reconstruct versus read-modify writes in RAID. Inf. Process. Lett. 93, 163–168 (2005)

    Article  MathSciNet  MATH  Google Scholar 

  19. Thomasian, A., Han, C.: Heterogeneous disk array architecture and its data allocation policies. In: Proc. Int. Symp. on Performance Evaluation of Computer and Telecommunication Systems—SPECTS’05, Cherry-Hill, NJ, July 2005, pp. 617–624

  20. Thomasian, A., Branzoi, B.A., Han, C.: Performance evaluation of a heterogeneous disk array architecture. In: Proc. 13th IEEE Symp. Modeling, Analysis, and Simulation of Computer and Telecommunication Systems—MASCOTS’05, Atlanta, Georgia, July 2005, pp. 517–520

  21. Thomasian, A.: Access costs in clustered RAID. Comput. J. 48(6), 702–713 (2005)

    Article  MathSciNet  Google Scholar 

  22. Thomasian, A.: Mirrored disk routing and scheduling. Cluster Comput. 9(4), 475–484 (2006)

    Article  Google Scholar 

  23. Thomasian, A., Blaum, M.: Mirrored disk organization reliability analysis. IEEE Trans. Comput. 55(12), 1640–1644 (2006)

    Article  Google Scholar 

  24. Thomasian, A., Fu, G., Ng, S.W.: Analysis of rebuild processing in RAID5 disk arrays. Comput. J. 50(2), 217–231 (2007)

    Article  Google Scholar 

  25. Thomasian, A., Fu, G., Han, C.: Performance of two-disk failure-tolerant disk arrays. IEEE Trans. Comput. TC-56(6), 799–814 (2007)

    Article  MathSciNet  Google Scholar 

  26. Thomasian, A., Xu, J.: Reliability and performance of mirrored disk organizations. Comput. J. 51(6), 615–629 (2008)

    Article  Google Scholar 

  27. Thomasian, A., Xu, J.: Data allocation in disk arrays with multiple RAID levels. ACM Trans. Stor. 6, (2010, to appear)

  28. Thomasian, A., Blaum, M.: Two disk failure tolerant disk arrays: organization, operation, and coding methods. ACM Trans. Stor. 5(4): Article No. 7 (2009)

  29. Welch, B., Unangst, M., Abbasi, Z., Gibson, G., Mueller, B., Small, J., Zelenka, J., Zhou, B.: Scalable performance of Panasas parallel file system. In: Proc. USENIX File and Storage Technologies—FAST’08 Conf., San Jose, CA, February 2008, pp. 17–33

  30. Wilkes, J., Golding, R., Staelin, C., Sullivan, T.: The HP AutoRAID hierarchical storage system. ACM Trans. Comput. Syst. 14(1), 108–136 (1996)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Thomasian & Associates, 17 Meadowbrook Rd., Pleasantville, NY, 10570, USA

    Alexander Thomasian

  2. CS Department, NJIT, Newark, NJ, 07102, USA

    Jun Xu

Authors
  1. Alexander Thomasian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jun Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alexander Thomasian.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Thomasian, A., Xu, J. RAID level selection for heterogeneous disk arrays. Cluster Comput 14, 115–127 (2011). https://doi.org/10.1007/s10586-010-0129-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10586-010-0129-4

Keywords

Search

Navigation