A Statistical Performance Model of Homogeneous Raidb Clusters A Statistical Performance Model of Homogeneous Raidb Clusters
One type of distributed database is called Redundant Arrays of Inexpensive Databases (RAIDb). RAIDb clusters are middleware-driven to promote interoperability and portability. RAIDb clusters allow for multiple levels of data replication and publish the clustered system as a single, coherent database system.
In this thesis, performance models are created for RAIDb level 1 and level 2 clusters. A statistical three-factor, two-level factorial design is used to evaluate the significance of several factors in a RAIDb cluster. These significant factors are then used to create a regression analysis, and eventually a regression equation, that can be used to predict the performance of RAIDb clusters. This performance model should be a useful predictive tool since the results have a 99% confidence interval.
School:Brigham Young University
School Location:USA - Utah
Source Type:Master's Thesis
Keywords:raidb computer database clusters distributed array
Date of Publication:02/16/2005