Integrating compression and execution in column-oriented database systems

Abstract

Column-oriented database system architectures invite a reevaluation of how and when data in databases is compressed. Storing data in a column-oriented fashion greatly increases the similarity of adjacent records on disk and thus opportunities for compression. The ability to compress many adjacent tuples at once lowers the per-tuple cost of compression, both in terms of CPU and space overheads.In this paper, we discuss how we extended C-Store (a column-oriented DBMS) with a compression sub-system. We show how compression schemes not traditionally used in roworiented DBMSs can be applied to column-oriented systems. We then evaluate a set of compression schemes and show that the best scheme depends not only on the properties of the data but also on the nature of the query workload.

Survey and Comparison of Row /Column Oriented Database and Improved the Performance of Execution Time for a Select Query

“…Again there are some optimizations possible with Column-Stores and are not possible with Row-Stores which can improve performance of Column-Stores compared Row-Stores significantly [2,3]. The rest and the most important is Compression [8]. As data are stored column-by-column, compression can be easily applied on a column.…”

TPC-H Analyzed: Hidden Messages and Lessons Learned from an Influential Benchmark

“…The poster-child use case of compressed execution is aggregation on RLE compressed numerical data [12], however this is only possible in aggregation queries without group-by. This only occurs in TPC-H Q6, but does not apply there either given that the involved l extendedprice column is unlikely to be RLE compressed.…”

Semantic Database Compression System Based on Augmented Vector Quantization

“…Compression can be applied to databases at relation level, page level and tuple or attribute level [7], [8].…”