Abstract
The deterministic block distribution method proposed for RAID systems (known as striping) has been a traditional solution for achieving high performance, increased capacity and redundancy all the while allowing the system to be managed as if it were a single device. However, this distribution method requires one to completely change the data layout when adding new storage subsystems, which is a drawback for current applications.
This paper presents AdaptiveZ, an adaptive block placement method based on deterministic zones, which grows dynamically zone-by-zone according to capacity demands. When adapting new storage subsystems, it changes only a fraction of the data layout while preserving a simple management of data due to deterministic placement. AdaptiveZ uses both a mechanism focused on reducing the overhead suffered during the upgrade as well as a heterogeneous data layout for taking advantage of disks with higher capabilities. The evaluation reveals that AdaptiveZ only needs to move a fraction of data blocks to adapt new storage subsystems while delivering an improved performance and a balanced load. The migration scheme used by this approach produces a low overhead within an acceptable time. Finally, it keeps the complexity of the data management at an acceptable level.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Charles, P., Good, N., Jordan, L.L., Lyman, P., Varian, H.R., Pal, J.: How much information? 2003? (2004), http://www2.sims.berkeley.edu/research/projects/ how-much-info-2003/printable_report.pdf
Coffman, K.G., Odlyzko, A.M.: Internet growth: is there a moore’s law for data traffic?, 47–93 (2002)
Grochowski, E., Halem, R.D.: Technological impact of magnetic hard disk drives on storage systems. IBM Syst. J. IBM Corp., 338–346 (2003)
Cortes, T., Labarta, J.: Taking advantage of heterogeneity in disks arrays. Journal of Parallel and distributing Computing 63, 448–464 (2003)
Ailamaki, A., DeWitt, D.J., Hill, M.D., Wood, D.A.: Dbmss on a modern processor: Where does time go?, pp. 266–277 (1999)
Gibson, G., Patterson, D.A., Katz, R.H.: A case for redundant arrays of inexpensive disks (raid). SIGMOD, 109–116 (1988)
Gibson, G.A., Patterson, D.A.: Designing disk arrays for high data reliability. Journal of Parallel and Distributed Computing, 4–27 (1993)
Gonzalez, J.L., Cortes, T.: Increasing the capacity of raid5 by online gradual assimilation. In: Proceedings of the International Workshop on Storage Network Architecture and Parallel I/O, p. 17 (2004)
Gonzalez, J.L., Cortes, T.: Evaluating the effects of upgrading heterogeneous disk arrays. In: SPECTS 2006 (2006)
Santos, J.R., Muntz, R.: Performance analysis of the rio multimedia storage system with heterogeneous disk configurations. In: ACM 1998, pp. 303–308 (1998)
Brinkmann, A., Heidebuer, M., Meyer auf der Heide, F., Rückert, U., Salzwedel, K., Vodisek, M.: V:drive - costs and benefits of an out-of-band storage virtualization system. In: 21st MSST, pp. 153–157 (April 2004)
Miller, E.L., Honicky, R.J.: A fast algorithm for online placement and reorganization of replicated data. In: IPDPS 2003. 17th. International Parallel and Distributed Symposium, pp. 267–268 (April 2003)
Yao, S.D., Zimmermann, R., Goel, A., Shahabi, C.: Scaddar: An efficient randomized technique to reorganize continuous media blocks. In: ICDE 2002. IEEE 18th. International Conference on Data Engineering, p. 473 (2002)
Leffle, S.J., McKusick, M.K., Joy, W.N., Fabry, R.S.: A fast file system for unix. ACM Trans. Comput. Syst., 181–197 (1984)
Chen, P.M., Patterson, D.A.: Maximizing performance in a striped disk array. In: ISCA 1990, pp. 322–331 (1990)
Maulschagen, H.: Logical volume management for linux
Zhang, G., Shu, J., Xue, W., Zheng, W.: Slas: An efficient approach to scaling round-robin striped volumes. Trans. Storage 3(1), 3 (2007)
Labarta, J., Cortes, T.: Hraid: A flexible storage-system simulator. In: Proceedings of the International Conference on parallel and Distributed Processing Techniques and Applications, vol. 163, p. 772. CSREA Press (1999)
Yao, S.D., Shahabi, C., Zimmermann, R.: Broadscale: Efficient scaling of heterogeneous storage systems. Int. J. on Digital Libraries, 98–111 (2006)
Franke, H., Gautam, N., Zhang, Y., Zhang, J., Sivasubramaniam, A., Nagar, S.: Synthesizing representative i/o workloads for tpc-h. In: HPCA, pp. 142–151 (2004)
Madhyastha, T.M., Hong, B., Zhang, B.: Cluster based input/output trace synthesis. In: ipccc 2005 (2005)
OLTP Application I/O. http://traces.cs.umass.edu/index.php/storage/storage
Brinkmann, A., Effert, S., Heidebuer, M., Vodisek, M.: Influence of adaptive data layouts on performance in dynamically changing storage environments. In: PDP 2006, pp. 155–162 (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gonzalez, J.L., Cortes, T. (2007). Adaptive Data Block Placement Based on Deterministic Zones (AdaptiveZ). In: Meersman, R., Tari, Z. (eds) On the Move to Meaningful Internet Systems 2007: CoopIS, DOA, ODBASE, GADA, and IS. OTM 2007. Lecture Notes in Computer Science, vol 4804. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76843-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-76843-2_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76835-7
Online ISBN: 978-3-540-76843-2
eBook Packages: Computer ScienceComputer Science (R0)