Scheduled System Maintenance on May 29th, 2015:
IEEE Xplore will be upgraded between 11:00 AM and 10:00 PM EDT. During this time there may be intermittent impact on performance. We apologize for any inconvenience.
By Topic

SoAP: A Strip-oriented Asynchronous Prefetching for Improving the Performance of Parallel Disk Systems

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Yang Liu ; Wuhan Nat. Lab. for Optoelectron., Huazhong Univ. of Sci. & Technol., Wuhan, China ; Feng Wang

We propose a Strip-oriented Asynchronous Prefetching (SoAP) for the parallel disk systems. This technique splits a prefetching request into multiple independent prefetching sub-requests, each of which contains a full data strip to exploit the maximum physical sequentiality of involved disks. In addition, SoAP associates each prefetching sub-request with a relative large time window, allowing every disk in the parallel disk system to flexibly schedule its own prefetching sub-requests with less strict deadlines. To validate SoAP, we implemented a prototype of SoAP by modifying the Software RAID under Linux. Experimental results demonstrate that SoAP outperforms the Linux-like SEQP, STEP and ASP. Compared with SEQP, STEP and ASP, SoAP can speed up the average response time by up to 43.6%, 32.8% and 43%, respectively, and improve system throughput by a factor of 2.6, 1.5 and 3.5, respectively. In a word, SoAP can significantly improve the response time and the throughput of the parallel disk systems simultaneously.

Published in:

High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems (HPCC-ICESS), 2012 IEEE 14th International Conference on

Date of Conference:

25-27 June 2012