Cache-Enabled Metadata-Aware Storage in Linux Systems

Article Preview

Abstract:

Hybrid storage systems integrate slower HDDs with faster SSDs to improve overall performance. To this end, various research efforts have investigated how to use SSDs as cache for HDDs. One of them proposes to cache only metadata blocks because all IO requests are accompanied with the requests to the metadata blocks before issuing the requests for the data blocks. However, our evaluation of the method could not confirm the claimed improvement. It motivated us to modify the method to integrate the caching functionality. The implementation of the proposed method in the Linux systems required to address several challenging issues. The evaluation results showed that the proposed method improved the performance by at least 90% over the original scheme. It implicitly means that caching the data blocks has more significant impact on performance than the metadata caching.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

749-753

Citation:

Online since:

July 2013

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] http://www.nvelo.com/

Google Scholar

[2] F. Chen, D. Koufaty and X. Zhang: Hystor: Making the Best Use of Solid State Drives in High Performance Storage Systems, in Proc. of the international conference on Supercomputing, USA, 2011.

DOI: 10.1145/1995896.1995902

Google Scholar

[3] Intel Technical Brief: Intel Smart Response Technology.

Google Scholar

[4] http://www.marvell.com

Google Scholar

[5] http://www.silverstonetek.com.tw

Google Scholar

[6] H. Payer, M. Sanvido, Z. Bandic and C. Kirsch: Combo Drive: Optimizing Cost and Performance in a Heterogeneous Storage Device, in Proc. of the 1st Workshop on integrating solid-state memory into the storage hierarchy, 2009.

Google Scholar

[7] T. Kgil and T. Mudge: a NAND Flash Memory File Cache for Low Power Web Servers, In Proc. of the 2006 international conference on compilers, architecture and synthesis for embedded systems, p.103–112. 2006.

DOI: 10.1145/1176760.1176774

Google Scholar

[8] LEE et al.: A Case for Flash Memory SSD in Enterprise Database Applications, In Proc. of SIGMOD '08, ACM, p.1075–1086. 2008.

Google Scholar

[9] T. Makatos et al.: Using Transparent Compression to Improve SSD-based IO Caches, in Proc. of EuroSys, p.1–14. 2010.

Google Scholar

[10] Narayavan et al.: A. Migrating Server Storage to SSDs: Analysis of Tradeoffs. In Proc. of EuroSys, p.145–158. 2009.

Google Scholar

[11] J. Bonwick and B. Moore: ZFS: The Last Word in File Systems

Google Scholar

[12] Burrows et al.: On-line Data Compression in a Log Structured File System, In Proc. of ASPLOS-V, 1992.

Google Scholar

[13] C. Coffing and J. Brown: A Survey of Modern File Compression Techniques, Oct. 1997.

Google Scholar

[14] S. Liu, J. Jiang and G. Yang: Macss: a Metadata-aware Combo Storage System, in Proc. of 2012 international conference on systems and informatics.

DOI: 10.1109/icsai.2012.6223157

Google Scholar

[15] http://www.tcp.org/tpcc/

Google Scholar