Relational XQuery systems try to re-use mature relational data management infrastructures to create fast
and scalable XML database technology. This paper describes the main features, key contributions, and lessons learned while
implementing such a system. Its architecture consists of (i) a range-based encoding of XML documents into relational tables,
(ii) a compilation technique that translates XQuery into a basic relational algebra, (iii) a restricted (order) property-aware
peephole relational query optimization strategy, and (iv) a mapping from XML update statements into relational updates.
Thus, this system implements all essential XML database functionalities (rather than a single feature) such that we can
learn from the full consequences of our architectural decisions. While implementing this system, we had to extend the state-of-the-art
with a number of new technical contributions, such as loop-lifted staircase join and efficient relational query evaluation
strategies for XQuery theta-joins with existential semantics. These contributions as well as the architectural lessons learned
are also deemed valuable for other relational back-end engines. The performance and scalability of the resulting system
is evaluated on the XMark benchmark up to data sizes of 11 GB. The performance section also provides an extensive comparison
of all major XMark results published previously, which confirm that the goal of purely relational XQuery processing, namely
speed and scalability, was met.
%0 Conference Paper
%1 15553
%A Boncz, P. A.
%A Grust, T.
%A van Keulen, M.
%A Manegold, S.
%A Rittinger, J.
%A Teubner, J.
%B Proceedings of ACM SIGMOD International Conference on Management of Data 2006
%D 2006
%I ACM
%K column monetdb store xquery
%T MonetDB/XQuery: A Fast XQuery Processor Powered By A Relational Engine
%U http://oai.cwi.nl/oai/asset/15553/15553B.pdf
%X Relational XQuery systems try to re-use mature relational data management infrastructures to create fast
and scalable XML database technology. This paper describes the main features, key contributions, and lessons learned while
implementing such a system. Its architecture consists of (i) a range-based encoding of XML documents into relational tables,
(ii) a compilation technique that translates XQuery into a basic relational algebra, (iii) a restricted (order) property-aware
peephole relational query optimization strategy, and (iv) a mapping from XML update statements into relational updates.
Thus, this system implements all essential XML database functionalities (rather than a single feature) such that we can
learn from the full consequences of our architectural decisions. While implementing this system, we had to extend the state-of-the-art
with a number of new technical contributions, such as loop-lifted staircase join and efficient relational query evaluation
strategies for XQuery theta-joins with existential semantics. These contributions as well as the architectural lessons learned
are also deemed valuable for other relational back-end engines. The performance and scalability of the resulting system
is evaluated on the XMark benchmark up to data sizes of 11 GB. The performance section also provides an extensive comparison
of all major XMark results published previously, which confirm that the goal of purely relational XQuery processing, namely
speed and scalability, was met.
%7 first
@inproceedings{15553,
abstract = {Relational XQuery systems try to re-use mature relational data management infrastructures to create fast
and scalable XML database technology. This paper describes the main features, key contributions, and lessons learned while
implementing such a system. Its architecture consists of (i) a range-based encoding of XML documents into relational tables,
(ii) a compilation technique that translates XQuery into a basic relational algebra, (iii) a restricted (order) property-aware
peephole relational query optimization strategy, and (iv) a mapping from XML update statements into relational updates.
Thus, this system implements all essential XML database functionalities (rather than a single feature) such that we can
learn from the full consequences of our architectural decisions. While implementing this system, we had to extend the state-of-the-art
with a number of new technical contributions, such as loop-lifted staircase join and efficient relational query evaluation
strategies for XQuery theta-joins with existential semantics. These contributions as well as the architectural lessons learned
are also deemed valuable for other relational back-end engines. The performance and scalability of the resulting system
is evaluated on the XMark benchmark up to data sizes of 11 GB. The performance section also provides an extensive comparison
of all major XMark results published previously, which confirm that the goal of purely relational XQuery processing, namely
speed and scalability, was met. },
added-at = {2010-12-20T19:01:01.000+0100},
author = {Boncz, P. A. and Grust, T. and van Keulen, M. and Manegold, S. and Rittinger, J. and Teubner, J.},
biburl = {https://www.bibsonomy.org/bibtex/2fd59739a5f8c153e7a74360bdc14f189/peterboncz},
booktitle = {Proceedings of ACM SIGMOD International Conference on Management of Data 2006},
conferencedate = {2006, June},
conferencelocation = {Chicago, IL, USA},
conferencetitle = {ACM SIGMOD International Conference on Management of Data},
edition = {first},
group = {INS1},
interhash = {22eb6b930cae8e70d762d8abd5a78539},
intrahash = {fd59739a5f8c153e7a74360bdc14f189},
keywords = {column monetdb store xquery},
project = {Non-NWO Project 1:[Ambient Multimedia Databases (N3)]; Non-NWO Project 2:[MonetDB ()]; Non-NWO Project 3:[Pathfinder ()]},
publisher = {ACM},
refereed = {y},
timestamp = {2010-12-20T19:01:01.000+0100},
title = {MonetDB/{XQuery}: {A} {Fast} {XQuery} {Processor} {Powered} {By} {A} {Relational} {Engine}},
url = {http://oai.cwi.nl/oai/asset/15553/15553B.pdf},
year = 2006
}