Abstract
The Object-based Storage System (OBS) has been proposed as a novel information storage technology in adaptation to the explosive growth in information quantity under the next-generation internet. The OBS treats all storage devices (OSD) and data information as objects, hence, the issues like reducing access delay over WAN, saving limited bandwidth and enhancement of data validity become problems related to the overall performance of OBS. To address these problems, we have the replica-based OBS, which brings forward a new issue on how to manage these replicas. In this paper, we present a multi-dimensional replica management scheme, and study the object searching performance within this mode. We deliver the optimal tree & improved one-path tree on the basis of similarity searching, with detailed replica indexing algorithm and emulation tests. The result of these experiments justifies their better performance in contrast to normal similarity-based indexing algorithm, with lower system cost.
It was supported by the National Basic Research Program of China (973 Program) under Grant No. 2004CB318201.
Chapter PDF
Similar content being viewed by others
References
Guy, R., Heidmenn, J., Mak, W., Page Jr., T., Popek, G., Rothmeier, D.: Implementation of the Ficus Replicated File system. In: Proceedings of the summer Usenix Conference (1990)
Guy, R., Reiher, P., Ratner, D., Gunter, M., Ma, W., Popek, G.: Rumor: Mobile Data Access Through Optimistic Peer-to-Peer Replication. In: Workshop on Mobile Data Access (November 1998)
Page, T., Guy, R., Heidemann, J., Ratner, D., Reiher, P., Goel, A., Kuenning, G., Popek, G.: Perspectives on Optimistically Replicated. Peer-To-Peer Filing, Software - Practice and Experience (1997)
Ranganathan, K., Foster, I.: Identifying Dynamic Replication Strategies For a High performance Data Grid. In: Proceedings of the International Grid Computing Workshop, Denver (November 2001)
Ranganathan, K., Foster, I.: Design and Evaluation of Replication Strategies for a High Performance Data Grid. In: International Conference on Computing in High Energy and Nuclear Physics, Beijing (September 2001)
Ratner, D.H.: Roam: A Scalable Replication System for Mobile and Disconnected Computing, PhDThesis, University of California, Los Angeles, Los Angeles, CA (January 1998)
Terry, D., Theimer, M., Peterson, K., Demers, A., Spreitzer, M., Hausen, C.: Managing Update Conflicts in Bayou, a Weakly Connected Replicated Storage System. In: Proceedings of the fifteenth Symposium on Operating systems Principles, pp. 49–70. ACM, New York (1983)
Vazhkudai, S., Tuecke, S., Foster, I.: Replica Selection in the Globus Data Grid. In: CCGRID 2001. Proceedings of the First IEEE/ACMInternational Conference on Cluster Computing and the Grid, pp. 106–113. IEEE Computer Society Press, Los Alamitos (2001)
Wiesmann, M., Pedone, F., Schiper, A., Kemme, B., Alonso, G.: Understanding Replication in Databases and Distributed Systems. In: ICDCS 2000. Proceedings of the 20th International Conference on Distributed Computing Systems (2000)
Satyanarayanan, M., Kister, J., Kumar, P., Okasaki, M., Siegel, E., Steere, D.: Coda: A Highly Available File System for a Distributed Workstation Environment. IEEE Transactions on Computers 39(4), 447–459 (1990)
Popek, G., Walker, B., Chow, J., Edwards, D., Kline, C., Rudisin, G., Thiel, G.: Locus: A Network Transparent High Reliability Distributed System. In: Proceedings of the Eighth Symposium on Operating Systems Principles, pp. 169–177. ACM, New York (1981)
Leiserson, C.H.: Fat-Trees: Universal Networks for Hardware-Efficient Supercomputing. IEEE Transactions on Computers C-34(10), 892–901 (1985)
Guttman, A.: R-Trees: A dynamic index structure for spatial searching. In: Yormark, B. (ed.) Proc. of the ACM SIGMOD Conf., Boston, pp. 47–57 (1984)
Berkmann, N., Krigel, H.P., Schneider, R., Seeger, B.: The R*-tree: An efficient and robust access method for points and rectangles. In: Hector, G.M., Jagadish, H.V. (eds.) Proc. of the ACM SIGMOD Conf., Atlantic, pp. 322–331 (1990)
Katayama, N., Satoh, S.: The SR-tree: An index structure for high-dimensional nearest neighbor queries. In: Peckham, J. (ed.) Proc. Of the ACM SIGMOD Conf., Tucson, pp. 369–380 (1997)
White, D.A, Jain, R.: Similarity indexing with the SS-tree. In: Stanley, Y.W.S. (ed.) Proc. of the 12th Int’l Conf. on Data Engineering, New Orleans, pp. 516–523. IEEE Computer Society, Los Alamitos (1996)
Ciaccia, P., Patella, M., Zezula, P.: M-tree: An efficient access method for similarity search in metric spaces. In: Jarke, M., Carey, M.J., Dittrich, K.R., Lochovsky, F.H., Loucopoulos, P., Jeusfeld, M.A. (eds.) Proc. of the 23rd VLDB Conf., Athens, pp. 426–435. Morgan Kaufmann Publishers, San Francisco (1997)
Bozkaya, T., Ozsoyoglu, M.: Distance-Based indexing for high-dimensional metric spaces. In: Peckham, J. (ed.) Proc. of the ACM SIGMOD Conf. on Management of Data, Tucson, pp. 357–368 (1997)
Ishikawa, M., Chen, H., Furuse, K., Yu, J.X., Ohbo, N.: MB+tree: A dynamically updatable metric index for similarity search. In: Lu, H., Zhou, A. (eds.) WAIM 2000. LNCS, vol. 1846, Springer, Heidelberg (2000)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tan, Z., Feng, D., He, F., Zhou, K. (2007). Studying of Multi-dimensional Based Replica Management in Object Storage System. In: Denko, M.K., et al. Emerging Directions in Embedded and Ubiquitous Computing. EUC 2007. Lecture Notes in Computer Science, vol 4809. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77090-9_31
Download citation
DOI: https://doi.org/10.1007/978-3-540-77090-9_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77089-3
Online ISBN: 978-3-540-77090-9
eBook Packages: Computer ScienceComputer Science (R0)