"UpSizeR: Synthetically Scaling an Empirical Relational Database"
No Thumbnail Available
Date
2010-12-17
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This paper presents UpSizeR, a software that takes as input an empirical relational dataset D and a scale factor s, and generates a synthetic dataset e D' that is similar to D but s times its size. Such a tool can be useful for scaling up D for scalability testing (s > 1), scaling down for application debugging (s < 1), or anonymization (s = 1).
Experiments with Flickr show that query results and response times on UpSizeR output match those on crawled data. They also accurately predict throughput degradation for a scale out test.