Predictive Dynamic Load Balancing of Parallel Hash-Joins over Heterogeneous Processors in the Presence of Data Skew
- Predictive Dynamic Load Balancing of Parallel Hash-Joins over Heterogeneous Processors in the Presence of Data Skew
- Dewan, Hasanat M.
Mok, Kui W.
- Computer Science
- Persistent URL:
- Columbia University Computer Science Technical Reports
- Part Number:
- Department of Computer Science, Columbia University
- Publisher Location:
- New York
- In this paper, we present new algorithms to balance the computation of parallel hash joins over heterogeneous processors in the presence of data skew and external loads. Heterogeneity in our model consists of disparate computing elements, as well as general purpose computing ensembles that are subject to external loading. Data skew appears as significant nonuniformities in the distribution of attribute values of underlying relations that are involved in a join. We develop cost models and predictive dynamic load balancing protocols to detect imbalance during the computation of a single large join. Our algorithms can account for imbalance due to data skew as well as heterogeneity in the computing environment. Significant performance gains are reported for a wide range of test cases on a prototype implementation of the system.
- Computer science
- Item views
text | xml
- Suggested Citation:
- Hasanat M. Dewan, Salvatore Stolfo, Mauricio Hernandez, Kui W. Mok, 1994, Predictive Dynamic Load Balancing of Parallel Hash-Joins over Heterogeneous Processors in the Presence of Data Skew, Columbia University Academic Commons, https://doi.org/10.7916/D841755K.