Hybrid File System - A Strategy for the Optimization of File System

Article Preview

Abstract:

The hybrid file system is designed to optimize the latency of the response of File System I/Os and extend the capacity of the local file system to cloud by taking the advantage of Internet. Our hybrid file system is consist of SSD, HDD and Amazon S3 cloud file system. We store small files, directory tree and metadata of all the files in SSD, because SSD has a good performance for the response of small and random I/Os. HDD is good at responding big and sequential I/Os, so we use it just like a warehouse to store big files which are linked by the symbolic files in the SSD. We also extend the local file system to cloud in order to enlarge its capacity. In this paper we describe test data of our hybrid file system and also its design and implement details.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 734-737)

Pages:

3129-3132

Citation:

Online since:

August 2013

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

[1] Peter M. Chen, Edward K. Lee, Garth A. Gibson, et al: submitted to ACM Computing Surveys, October 29, (1993).

Google Scholar

[2] Fay Chang, Jeffrey Dean, Sanjay Ghemawat, et al: Bigtable: A Distributed Storage System for Structured Data, in OSDI (2006).

Google Scholar

[3] Jeffrey Dean and Sanjay Ghemawat: MapReduce: Simplied Data Processing on Large Clusters, in OSDI (2004).

Google Scholar

[4] Mark Holland, Garth A. Gibson and Daniel P. Siewiorek: submitted to the Journal of Distributed and Parallel Databases, vol. 2 no. 3, July (1994).

Google Scholar