Abstract
Load balancing is an attractive problem in storage system. With the fast growth of high-speed network technology and novel storage architecture, smarter storage device becomes an effective way to solve the problem. In this paper, we present an effective object migration & replication policy in our object storage system (OSS), denoted adaptive policy triggering. This policy migrates/replicates object from congested object storage controllers to relatively uncongested object storage controllers according to the information of three facets in the OSS, including metadata server, object storage controller and storage object itself. First, clients interact with the metadata server (MS). So those global policies are triggered by the MS. Second, the OSC has better knowledge of its own load than MS. It is reasonable that local policy is triggered by the OSC. Third, the storage object is encapsulated with data, attributes and methods. These attributes can be set or got when objects are accessed. And object attribute values are good as policy threshold. Furthermore, object methods also can be triggered according to some policies.
This work was supported by the National Basic Research Program of China (973 Program) under Grant No. 2004CB318201, Huo Yingdong Education Foundation under Grant No.91068, the National Science Foundation of China under Grant No.60273074 and No.60303032.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Intel Corporation, Object-Based Storage: The Next Wave of Storage Technology and Devices (January 2004), accessible from http://www.intel.com/labs/storage/osd/
Zeng, L.-F., Feng, D., Qin, L.-j.: SOSS: Smart Object-based Storage System. In: The Third International Conference on Machine Learning and Cybernetics, Shanghai, August 26-29, pp. 3263–3266 (2004)
IBM Storage Tank (March 2004), accessible from http://www.haifa.il.ibm.com/storage.html
White paper: Object Storage Architecture (January 2004), accessible from http://www.panasas.com/activescaleos.html
Braam, P.J.: The Lustre storage architecture. Technical report, Cluster File Systems, Inc. (January 2004), accessible from http://www.lustre.org/docs/lustre.pdf
Westerinen, A., Schnizlein, J., Strassner, J., et al.: Terminology for Policy-Based Management. RFC 3198 (November 2001)
HP AutoRAID: Setting New Standards for Fault-Tolerant Storage (March 2004), accessible from http://www.interex.org/pubcontent/interact/sept95/11spot/spot.html
Feng, D., Zeng, L., Wang, F., Qin, L., Liu, Q.: Adaptive Policy Trigger Mechanism for OBSS. In: The International Conference on Advanced Information Networking and Applications (AINA 2005),Tamkang University, Taipei, Taiwan, March 28 - 30 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Feng, D., Zeng, L. (2005). Adaptive Policy Triggering for Load Balancing. In: Hobbs, M., Goscinski, A.M., Zhou, W. (eds) Distributed and Parallel Computing. ICA3PP 2005. Lecture Notes in Computer Science, vol 3719. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11564621_27
Download citation
DOI: https://doi.org/10.1007/11564621_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29235-7
Online ISBN: 978-3-540-32071-5
eBook Packages: Computer ScienceComputer Science (R0)