Benchmark for OLAP on NoSQL Technologies

Abstract : The plethora of data warehouse solutions has created a need comparing these solutions using experimental benchmarks. Existing benchmarks rely mostly on the relational data model and do not take into account other models. In this paper, we propose an extension to a popular benchmark (the Star Schema Benchmark or SSB) that considers non-relational NoSQL models. To avoid data post-processing required for using this data with NoSQL systems, the data is generated in different formats. To exploit at best horizontal scaling, data can be produced in a distributed file system, hence removing disk or partition sizes as limit for the generated dataset. Experimental work proves improved performance of our new benchmark.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01375413
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Monday, October 3, 2016 - 10:53:12 AM
Last modification on : Thursday, October 17, 2019 - 8:54:23 AM
Long-term archiving on : Friday, February 3, 2017 - 1:58:47 PM

File

chevalier_15291.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01375413, version 1
  • OATAO : 15291

Citation

Max Chevalier, Mohammed El Malki, Arlind Kopliku, Olivier Teste, Ronan Tournier. Benchmark for OLAP on NoSQL Technologies. 9th IEEE International Conference on Research Challenges in Information Science (IEEE RCIS 2015), May 2015, Athens, Greece. pp. 480-485. ⟨hal-01375413⟩

Share

Metrics

Record views

589

Files downloads

607