Title :
Accurate Performance Modeling and Guidance to the Adoption of an Inconsistency Detection Framework
Author :
Lu, Yijun ; Li, Xueming ; Jiang, Hong
Author_Institution :
Dept. of Comput. Sci. & Eng., Univ. of Nebraska-Lincoln, Lincoln, NE
Abstract :
With the increased popularity of replica-based services in distributed systems such as the Grid, consistency control among replicas becomes more and more important. To this end, IDF (inconsistency detection framework), a two-layered overlay-based architecture, has been proposed as a new way to solve this problem-instead of enforcing a predefined consistency control protocol, IDF detects inconsistency in a timely manner when it occurs and resolves it based on applicationspsila semantics.This paper presents a comprehensive analytical study of the two-layer detection mechanism. We develop an analytical model to characterize IDF and, based on this model, evaluating the successful rate of inconsistency detection within the top layer, which directly impacts the performance of IDF. We also derive a unified formula to model the performance of IDF with regard to a wide range of applications. Based on the modeling results, we illustrate how practitioners can use these quantitative insights to tune the IDF parameters for specific applications.
Keywords :
grid computing; consistency control; consistency control protocol; distributed systems; inconsistency detection framework; replica-based services; Analytical models; Bandwidth; Computer architecture; Computer science; Costs; Delay; Internet; Peer to peer computing; Protocols; System performance; Inconsistency detection; Performance modeling;
Conference_Titel :
Networking, Architecture, and Storage, 2008. NAS '08. International Conference on
Conference_Location :
Chongqing
Print_ISBN :
978-0-7695-3187-8
DOI :
10.1109/NAS.2008.12