@inbook{cbdecc8884be4c00a198b6f84e380f92,
title = "ETLMR: A Highly Scalable Dimensional ETL Framework based on MapReduce",
abstract = "Abstract. Extract-Transform-Load (ETL) flows periodically populate data warehouses (DWs) with data from different source systems. An increasing challenge for ETL flows is to process huge volumes of data quickly. MapReduce is establishing itself as the de-facto standard for large-scale data-intensive processing. However, MapReduce lacks support for high-level ETL specific constructs, resulting in low ETL programmer productivity. This paper presents a scalable dimensional ETL framework, ETLMR, based on MapReduce. ETLMR has built-in native support for operations on DW-specific constructs such as star schemas, snowflake schemas and slowly changing dimensions (SCDs). This enables ETL developers to construct scalable MapReduce-based ETL flows with very few code lines. To achieve good performance and load balancing, a number of dimension and fact processing schemes are presented, including techniques for efficiently processing different types of dimensions. The paper describes the integration of ETLMR with a MapReduce framework and evaluates its performance on large realistic data sets. The experimental results show that ETLMR achieves very good scalability and compares favourably with other MapReduce data warehousing tools.",
author = "Liu Xiufeng and Christian Thomsen and Pedersen, {Torben Bach}",
note = "The original publications is available at www.springerlink.com",
year = "2013",
doi = "10.1007/978-3-642-37574-3_1",
language = "English",
isbn = "978-3-642-37573-6",
volume = "7790",
series = "Transactions on Large-Scale Data- and Knowledge-Centered Systems",
publisher = "Springer VS",
pages = "1--31",
booktitle = "Transactions on Large-Scale Data- and Knowledge-Centered Systems VIII",
}