Output details
11 - Computer Science and Informatics
University of Manchester
Output title
Adaptive join processing in pipelined plans
Type
E - Conference contribution
Name of conference/published proceedings
EDBT: 13th International Conference on Extending Database Technology
Volume number
-
Issue number
-
First page of article
183
ISSN of proceedings
-
Year of publication
2010
URL
-
Number of additional authors
3
Additional information
<15> The compile-time selection of supposedly optimal query-execution plans can be undermined by emergent run-time conditions, thereby requiring run-time strategies to adapt to conditions that lead to sub-optimal performance. This paper is significant in describing and evaluating techniques for changing a query execution plan at run-time, without loss of partially-evaluated work, even for pipelined evaluation and even for blocking query operators. This makes them the most widely applicable by far in this research area. The solutions found were shown empirically to enable significant performance improvements.
Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
4
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
