Melnik, S.; Gubarev, A.; Long, J. J.; Romer, G.; Shivakumar, S.; Tolton, M. & Vassilakis, T.: Dremel: interactive analysis of web-scale datasets. In: Proceedings of the VLDB Endowment 3 (2010), Nr. 1-2, S. 330-339
[Volltext]
Dremel is a scalable, interactive ad-hoc query system for analysis of read-only nested data. By combining multi-level execution trees and columnar data layout, it is capable of running aggregation queries over trillion-row tables in seconds. The system scales to thousands of CPUs and petabytes of data, and has thousands of users at Google. In this paper, we describe the architecture and implementation of Dremel, and explain how it complements MapReduce-based computing. We present a novel columnar storage representation for nested records and discuss experiments on few-thousand node instances of the system.
@article{melnik2010dremel,
author = {Melnik, Sergey and Gubarev, Andrey and Long, Jing Jing and Romer, Geoffrey and Shivakumar, Shiva and Tolton, Matt and Vassilakis, Theo},
title = {Dremel: interactive analysis of web-scale datasets},
journal = {Proceedings of the VLDB Endowment},
publisher = {VLDB Endowment},
year = {2010},
volume = {3},
number = {1-2},
pages = {330--339},
url = {http://dl.acm.org/citation.cfm?id=1920841.1920886},
keywords = {google, analysis, interactive, search, dremel, web},
abstract = {Dremel is a scalable, interactive ad-hoc query system for analysis of read-only nested data. By combining multi-level execution trees and columnar data layout, it is capable of running aggregation queries over trillion-row tables in seconds. The system scales to thousands of CPUs and petabytes of data, and has thousands of users at Google. In this paper, we describe the architecture and implementation of Dremel, and explain how it complements MapReduce-based computing. We present a novel columnar storage representation for nested records and discuss experiments on few-thousand node instances of the system.}
}