ACM Home Page
Please provide us with feedback. Feedback
Memory resource allocation for file system prefetching: from a supply chain management perspective
Full text PdfPdf (1.45 MB)
Source
European Conference on Computer Systems archive
Proceedings of the 4th ACM European conference on Computer systems table of contents
Nuremberg, Germany
SESSION: OS mechanisms table of contents
Pages 75-88  
Year of Publication: 2009
ISBN:978-1-60558-482-9
Authors
Zhe Zhang  North Carolina State University, Raleigh, NC, USA
Amit Kulkarni  North Carolina State University, Raleigh, NC, USA
Xiaosong Ma  North Carolina State University, Raleigh, NC, USA
Yuanyuan Zhou  University of Illinois at Urbana-Champaign, Urbana, IL, USA
Sponsor
ACM: Association for Computing Machinery
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 35,   Downloads (12 Months): 166,   Citation Count: 0
Additional Information:

abstract   references   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/10.1145/1519065.1519075
What is a DOI?

ABSTRACT

As an important technique to hide disk I/O latency, prefetching has been widely studied, and dynamic adaptive prefetching techniques have been deployed in diverse storage environments. However, two issues are not well addressed by previous research: (1) how to handle the prefetching resource allocation between concurrent sequential access streams with different request rates, and (2) how to coordinate prefetching at multiple levels in the data access path.

Interestingly, we found that these problems bear a strong resemblance to situations long studied in the field of supply chain management (SCM), used by retailers such as Wal-Mart. In this paper, we demonstrate how to perform the problem mapping and then apply SCM principles in practice, particularly from the branch of inventory theory, to improve data prefetching performance in storage systems. More specifically, we applied (1) two SCM policies to dynamically configure the sequential prefetching parameters, and (2) an SCM solution to correct the access pattern information distortion in multi-level prefetching. We implemented these SCM-based strategies in the Linux kernel prefetching algorithm and a multi-level storage simulator, and evaluated the performance with three types of workloads. The results indicate that the SCM approaches are able to generate up to a 55.0% of performance improvement for a real-world server workload benchmark, and up to 33.3% for a combination of Linux I/O-intensive applications.


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.

 
1
 
2
T. Andel. Manage inventory, own information. Transportation and Distribution, 1996.
 
3
4
5
 
6
7
8
 
9
Zhifeng Chen, Yuanyuan Zhou, and Kai Li. Evictionbased cache placement for storage caches. In Proceedings of the 2003 USENIX Annual Technical Conference, pages 269--282, Jun 2003. ISBN 1-931971-10-2.
 
10
S. Chopra and P. Meindl. Inventory Management and Production Planning and Scheduling. Prentice-Hall, 2001.
11
 
12
13
 
14
G. Ganger, B.Worthington, and Y. Patt. The disksim simulation environment version 2.0, Dec. 1999.
 
15
 
16
 
17
 
18
 
19
Diwaker Gupta, Sangmin Lee, and Michael Vrable. Difference engine: Harnessing memory redundancy in virtual machines. In Proceedings of the 8th USENIX Symposium on Operating System Design and Implementation (OSDI '08), Berkeley, CA, USA, 2008. USENIX Association.
 
20
21
 
22
L. Kleinrock. Queueing Systems: Volume 2: Computer Applications. John Wiley & Sons, 1976.
 
23
B.O. Koopman. On distributions admitting a sufficient statistic. Transaction of American Mathematics Society, 1936.
 
24
R. L. Lee, P.-C. Yew, and D. H. Lawrie. Data prefetching in shared memory multiprocessors. In Proceedings of the International conference on parallel processing, pages 28--31, 1987.
 
25
26
 
27
 
28
 
29
mit--beer. The mit beer game. http://beergame.mit.edu.
30
 
31
S. Devadas P. Jain and L. Rudolph. Controlling cache pollution in prefetching with software-assisted cache replacement. In Tech. Rep. CSG-462,M.I.T, 2001.
 
32
33
 
34
 
35
Edward Silver, David Pyke, and Rein Peterson. Inventory Management and Production Planning and Scheduling. John Wiley & Sons, 1998. ISBN 978-0471119470.
36
 
37
38
 
39
 
40
 
41
 
42
43

Collaborative Colleagues:
Zhe Zhang: colleagues
Amit Kulkarni: colleagues
Xiaosong Ma: colleagues
Yuanyuan Zhou: colleagues