期刊名称：Bulletin of the Technical Committee on Data Engineering
出版年度：2012
卷号：35
期号：01
出版社：IEEE Computer Society
摘要：Columnar databases provide a number of benefits with regard to both data storage (e.g.: data compres-
sion) and data processing (e.g.: optimized data access, parallelized decompression, lazy materialization
of intermediate results). Their characteristics are particularly advantageous for exploratory sessions
and ad hoc analytics. The principles of columnar stores can be also combined with a pipelined and
iterative processing, leading toward modern analytic engines able to handle large, rapidly growing data
sets. In this paper, we show how to further enrich such a framework by employing metadata layers
aimed at minimizing the need of data access. In particular, we discuss the current implementation and
the future roadmap for correlated subqueries in Infobright¡¯s RDBMS, where all above-mentioned archi-
tectural features interact with each other in order to improve the query execution.
