ACM Home Page
Please provide us with feedback. Feedback
Hot mirroring: a method of hiding parity update penalty and degradation during rebuilds for RAID5
Full text PdfPdf (1.37 MB)
Source International Conference on Management of Data archive
Proceedings of the 1996 ACM SIGMOD international conference on Management of data table of contents
Montreal, Quebec, Canada
Pages: 183 - 194  
Year of Publication: 1996
ISBN:0-89791-794-4
Also published in ...
Authors
Kazuhiko Mogi  Institute of Industrial Science, The University of Tokyo
Masaru Kitsuregawa  Institute of Industrial Science, The University of Tokyo
Sponsors
SIGART: ACM Special Interest Group on Artificial Intelligence
SIGMOD: ACM Special Interest Group on Management of Data
SIGACT: ACM Special Interest Group on Algorithms and Computation Theory
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 1,   Downloads (12 Months): 25,   Citation Count: 5
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/233269.233331
What is a DOI?

ABSTRACT

This paper proposes a storage management scheme for disk arrays, named hot mirroring. In this scheme, storage space is partitioned into two regions. One is the mirrored region, which is characterized by high performance and low storage efficiency. The other is the RAID5 region, which is characterized by low performance and high storage efficiency. Hot data blocks are stored in the former area, while cold blocks are stored in the latter. In addition, mirrored pairs and RAID5 stripes are orthogonally laid out, through which the performance degradation during rebuilding is minimized. Hot block clustering in hot mirroring achieves higher performance than conventional RAID5 arrays. The potential of hot mirroring is examined through extensive simulation.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
BD92
Anupam Bhide and Daniel r)ias. RAIl7) Architectures for OLTP. Research Report RC 17879 (78489), IBM Research l.)ivision, Mar. 1992.
 
HD90
HG92
 
HMP93
Robert Y. Hou, Jai Menon, and Yale N. Patt. Balancing I/O Response Tune and Disk Rebuild Time in a RAID5 lT)lsk Array. In Proc. of Hawaii Int. Conf. on System Sciences. pp. 70-79, 1993.
HP93
MC93
 
MK92
jal Menon and Jim Kasson. Methods for Improved Update Performance of Disk Arrays. In Proc. of 25th Hawaii Int. Conf. onSystemSciences, rot. I, pp. 74-83, Jan. 1992.
 
MK94
 
MK95a
 
MK95b
Kazuhiko Mogi and Masaru Katsuregawa. Preliminary Evaluation of Hot Mirroring. IPSJ SIG Notes 95- 1-)BS-104-7, Information Processing Society c~f Japan, Jul. 1995.
 
MK95c
Kazuhiko Mogi and Masaru Kitsuregawa. Performance Evaluation of Hot Mirrored I)lsk Arrays on Disk Failure. IEICE Tech. Report CPSY95-82, Institute of Electronics, Information and Communication Engineering, Dec. 1995.
 
ML90
 
MM91
Jai Menon and Dick Mattson. Performance of Disk Arrays in Transaction Processing Environments. Research Report RJ 8230, IBM Research 1)iv~sion, 1991
MM92
OS93
 
OWS93
PGK88
 
RCB93
RO91
SG93
 
SO91
 
Ter85
Teradata Corporation. DBC/IOI2 Database Computer System Manual Release 2.0, Nov. 1985. Doc. No. C 10- 0001-02.
WGSS95
 
YWD93
Phdxp S. Yu, Kun-Lung Wu, and Asit {)an. Dynamic Parity Grouping for Efficient Parity Buffering to Improve Write Performance of RAID-5 Disk Arrays. Research Report RC 19041 (83137), IBM Research tT)lvlslon, Jut. 1993.


Collaborative Colleagues:
Kazuhiko Mogi: colleagues
Masaru Kitsuregawa: colleagues