ABSTRACT
Real life databases exhibit highly skewed access patterns. These skewed access patterns can be exploited to partition the data considering the query workload. The presented work proposes Workload Aware Hybrid Partitioning (WAHP). WAHP identifies clusters of attributes which are queried together. It identifies workload aware clusters for the actual query workload using a hybrid combination of horizontal and vertical partitioning. The paper demonstrates WAHP experiment using TPC-C benchmark, where 9% of the actual TPC-C data in workload aware clusters, is able to answer 73% of hottest query-workload with an average execution time gain of 37% against original database.
- Kallman R, Kimura H, Natkins J, Pavlo A, Rasin A, Zdonik S, Jones EP, Madden S, Stonebraker M, Zhang Y, Hugg J. H-store: a high-performance, distributed main memory transaction processing system. Proceedings of the VLDB Endowment. Aug 2008 Google ScholarDigital Library
- Garcia-Molina H, Salem K. Main memory database systems: An overview. IEEE Transactions on Knowledge and Data Engineering, Dec 1992 Google ScholarDigital Library
- Levandoski J, Larson P, Stoica R. Identifying hot and cold data in main-memory databases. In Data Engineering (ICDE), 2013 IEEE 29th International Conference on 2013 Apr 8 (pp. 26--37). IEEE. Google ScholarDigital Library
- Levandoski J, Mokbel M. RDF data-centric storage. In Web Services, 2009. ICWS 2009. IEEE International Conference on 2009 Jul 6 (pp. 911--918). IEEE. Google ScholarDigital Library
- MahmoudiNasab H, Sakr S. Efficient and adaptable query workload-aware management for RDF data. In Web Information Systems Engineering--WISE 2010 2010 Dec 12 (pp. 390--399). Springer Berlin Heidelberg. Google ScholarDigital Library
- TPC-C Benchmark {cited 2016 April 23} available from: http://www.tpc.org/tpcc/detail.aspGoogle Scholar
- Padiya T, Bhise M, Hot and Cold Data Classification for Main Memory Databases, PhD Forum collocated with IEEE International Parallel and Distributed Processing Symposium IPDPS 2015, May 25-29Google Scholar
- Abadi D, Marcus A, Madden S, Hollenbach K. SW-Store: a vertically partitioned DBMS for Semantic Web data management. The VLDB Journal---The International Journal on Very Large Data Bases. 2009 Apr 1;18(2):385-406. Google ScholarDigital Library
- Padiya T, Bhise M, Rajkotiya P. Data Management for Internet of Things. In Region 10 Symposium (TENSYMP), 2015 IEEE 2015 May 13 (pp. 62--65). IEEE. Google ScholarDigital Library
- Shah B, Padiya T, Bhise M. Query Execution for RDF Data Using Structure Indexed Vertical Partitioning. InParallel and Distributed Processing Symposium Workshop (IPDPSW), 2015 IEEE International 2015 May 25 (pp. 575--584). IEEE. Google ScholarDigital Library
- Workload Aware Hybrid Partitioning
Recommendations
DWAHP: Workload Aware Hybrid Partitioning and Distribution of RDF Data
IDEAS '17: Proceedings of the 21st International Database Engineering & Applications SymposiumProliferation of RDF data has reached to a peak where data is partitioned across multiple nodes. Significant contribution for developing solutions to manage RDF data in distributed environment is witnessed in recent years. We propose a workload aware ...
WawPart: Workload-Aware Partitioning of Knowledge Graphs
Advances and Trends in Artificial Intelligence. Artificial Intelligence PracticesAbstractLarge-scale datasets in the form of knowledge graphs are often used in numerous domains, today. A knowledge graph’s size often exceeds the capacity of a single computer system, especially if the graph must be stored in main memory. To overcome ...
A Hybrid Partitioning Strategy for NewSQL Databases: The VoltDB Case
iiWAS2019: Proceedings of the 21st International Conference on Information Integration and Web-based Applications & ServicesSeveral application domains deal with the management of massive data volumes and thousands of OLTP transactions per second. Traditional relational databases cannot cope with these requirements. NewSQL is a new generation of databases that provides both ...
Comments