By Topic

Optimize Block-Level Cloud Storage System with Load-Balance Strategy

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

5 Author(s)
Li Zhou ; Dept. of Comput. Sci. & Technol., Hangzhou Dianzi Univ., Hangzhou, China ; Yi-Cheng Wang ; Ji-Lin Zhang ; Jian Wan
more authors

Cloud storage systems take advantage of distributed storage technology and virtualization technology, to provide virtual machine clients with customizable storage service. They can be divided into two types: distributed file system and block level storage system. Orthrus is a Light weighted Block-Level Cloud Storage System, which adopt multiple volume servers' architecture to avoid single-point problem in other solutions. However, how to make the servers load balance turn into a new problem appears in this architecture. In this paper we present a dynamic load balance strategy between multiple volume servers. We characterize machine capability and load quantity with black box modeling approach, and implement the load balance strategy based on genetic algorithm. Extensive experimental results show that the aggregated I/O throughputs of ORTHRUS are remarkably improved (about two times) with multiple volume servers, and both I/O throughputs and IOPS are remarkably improved (about 1.8 and 1.2 times respectively) by our dynamic load balance strategy.

Published in:

Parallel and Distributed Processing Symposium Workshops & PhD Forum (IPDPSW), 2012 IEEE 26th International

Date of Conference:

21-25 May 2012