DocumentCode :
2529335
Title :
Frequency Domain Filter Design and Analysis of Request Scheduling in Internet Servers
Author :
Xu, Minghua ; Xu, Cheng-Zhong
Author_Institution :
Dept. of Electr. & Comput. Eng., Wayne State Univ., Detroit, MI
fYear :
2008
fDate :
17-20 June 2008
Firstpage :
866
Lastpage :
873
Abstract :
Internet traffic has a characteristic of strong correlation. This traffic characteristic greatly complicates the problem of server performance modeling and optimization. Conventional time domain analysis has limitations in the study of the impact of complex traffic on server performance, because self-similarity of Internet traffic is often characterized in frequency domain. In this paper, we present a frequency domain filter model to characterize the relationship between server capacity, resource allocation, and service quality for general input traffic. Power spectral density (PSD) shows the strength of variations (power) as a function of frequency. By the model, server scheduler operates as a filter of input traffic that transforms its PSD function into another PSD function of server utilization process. The optimality of the scheduler in second-order statistics is to minimize the power leakage in the transformation. Most Internet traffic has monotonically decreasing PSD functions. For this type of input traffic, we prove that the optimal schedulers have a convex structure. Uniform allocation is an extreme case of the convexity and is proven to be optimal for traffic of independent arrivals. We integrate the convex-structured scheduling principle with GPS discipline and show that the enhanced GPS policy improves the service quality significantly.
Keywords :
Internet; file servers; frequency-domain analysis; higher order statistics; resource allocation; scheduling; telecommunication traffic; Internet servers; Internet traffic self-similarity; convex-structured scheduling; frequency domain filter design; general input traffic; power leakage minimization; power spectral density; request scheduling analysis; resource allocation; second-order statistics; server capacity; server performance modeling; server performance optimization; server utilization; service quality; Frequency domain analysis; Global Positioning System; Information filtering; Information filters; Internet; Optimal scheduling; Resource management; Time domain analysis; Traffic control; Web server; Request scheduling; filter design; frequency domain analysis; resource allocation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Distributed Computing Systems, 2008. ICDCS '08. The 28th International Conference on
Conference_Location :
Beijing
ISSN :
1063-6927
Print_ISBN :
978-0-7695-3172-4
Electronic_ISBN :
1063-6927
Type :
conf
DOI :
10.1109/ICDCS.2008.92
Filename :
4595964
Link To Document :
بازگشت