%0 Conference Paper %1 1164170 %A Harizopoulos, Stavros %A Liang, Velen %A Abadi, Daniel J. %A Madden, Samuel %B VLDB '06: Proceedings of the 32nd international conference on Very large data bases %D 2006 %I VLDB Endowment %K column database vertica warehouse %P 487--498 %T Performance tradeoffs in read-optimized databases %U http://portal.acm.org/citation.cfm?id=1164127.1164170 %X Database systems have traditionally optimized performance for write-intensive workloads. Recently, there has been renewed interest in architectures that optimize read performance by using column-oriented data representation and light-weight compression. This previous work has shown that under certain broad classes of workloads, column-based systems can outperform row-based systems. Previous work, however, has not characterized the precise conditions under which a particular query workload can be expected to perform better on a column-oriented database.In this paper we first identify the distinctive components of a read-optimized DBMS and describe our implementation of a high-performance query engine that can operate on both row and column-oriented data. We then use our prototype to perform an in-depth analysis of the tradeoffs between column and row-oriented architectures. We explore these tradeoffs in terms of disk bandwidth, CPU cache latency, and CPU cycles. We show that for most database workloads, a carefully designed column system can outperform a carefully designed row system, sometimes by an order of magnitude. We also present an analytical model to predict whether a given workload on a particular hardware configuration is likely to perform better on a row or column-based system.

@inproceedings{1164170, abstract = {Database systems have traditionally optimized performance for write-intensive workloads. Recently, there has been renewed interest in architectures that optimize read performance by using column-oriented data representation and light-weight compression. This previous work has shown that under certain broad classes of workloads, column-based systems can outperform row-based systems. Previous work, however, has not characterized the precise conditions under which a particular query workload can be expected to perform better on a column-oriented database.In this paper we first identify the distinctive components of a read-optimized DBMS and describe our implementation of a high-performance query engine that can operate on both row and column-oriented data. We then use our prototype to perform an in-depth analysis of the tradeoffs between column and row-oriented architectures. We explore these tradeoffs in terms of disk bandwidth, CPU cache latency, and CPU cycles. We show that for most database workloads, a carefully designed column system can outperform a carefully designed row system, sometimes by an order of magnitude. We also present an analytical model to predict whether a given workload on a particular hardware configuration is likely to perform better on a row or column-based system.}, added-at = {2007-12-06T04:23:15.000+0100}, author = {Harizopoulos, Stavros and Liang, Velen and Abadi, Daniel J. and Madden, Samuel}, biburl = {https://www.bibsonomy.org/bibtex/2a03c718c615e4e0716eb31c5a482cb87/jhammerb}, booktitle = {VLDB '06: Proceedings of the 32nd international conference on Very large data bases}, description = {Performance tradeoffs in read-optimized databases}, interhash = {234f2ea3bf1d9e115f437919e646563c}, intrahash = {a03c718c615e4e0716eb31c5a482cb87}, keywords = {column database vertica warehouse}, location = {Seoul, Korea}, pages = {487--498}, publisher = {VLDB Endowment}, timestamp = {2007-12-06T04:23:15.000+0100}, title = {Performance tradeoffs in read-optimized databases}, url = {http://portal.acm.org/citation.cfm?id=1164127.1164170}, year = 2006 }