Loading...
Please wait, while we are loading the content...
D-zipfian: a decentralized implementation of zipfian (2013).
| Content Provider | CiteSeerX |
|---|---|
| Author | Barahm, Sumita Gh, Shahram |
| Abstract | Zipfian distribution is used extensively to generate workloads to test, tune, and benchmark data stores. With scalable multi-node database management systems, a centralized single node benchmarking framework that embodies Zipfian may utilize its resources fully and fail to generate work at a sufficiently high rate to evaluate its target system. This means the benchmarking framework must become decentralized and scalable. BG is one such framework. This paper presents BG’s decentralized, parallel implementation of Zipfian named D-Zipfian. D-Zipfian employs multiple nodes that reference data items independently. To produce meaningful results, this scalable technique strives to produce a distribution that is independent of its degree of parallelism, i.e., number of employed nodes. Moreover, it supports heterogeneous nodes that reference data items at different rates. We characterize the behavior of D-Zipfian with different degrees of parallelism and skewness, population sizes, and heterogeneity of its employed nodes. A |
| File Format | |
| Publisher Date | 2013-01-01 |
| Access Restriction | Open |
| Subject Keyword | Decentralized Implementation Employed Node Scalable Technique Strives Parallel Implementation Zipfian Distribution Multiple Node Heterogeneous Node High Rate Different Rate Data Item Population Size Benchmark Data Store Different Degree Centralized Single Node Reference Data Item Meaningful Result Target System Scalable Multi-node Database Management System Benchmarking Framework |
| Content Type | Text |
| Resource Type | Article |
