Transcription of Automatic Database Management System Tuning …
{{id}} {{{paragraph}}}
Example: air traffic controller
Automatic Database Management System Tuning …
Automatic Database Management System Tuning ThroughLarge-scale Machine LearningDana Van AkenAndrew PavloGeoffrey J. GordonBohan ZhangCarnegie Mellon University Carnegie Mellon University Carnegie Mellon UniversityPeking Management System (DBMS) configuration Tuning is anessential aspect of any data-intensive application effort. But thisis historically a difficult task because DBMSs have hundreds ofconfiguration knobs that control everything in the System , suchas the amount of memory to use for caches and how often datais written to storage. The problem with these knobs is that theyare not standardized ( , two DBMSs use a different name for thesame knob), not independent ( , changing one knob can impactothers), and not universal ( , what works for one application maybe sub-optimal for another). Worse, information about the effectsof the knobs typically comes only from (expensive) overcome these challenges, we present an automated approachthat leverages past experience and collects new information to tuneDBMS configurations: we use a combination of supervised and un-supervised machine learning methods to (1) select the most impact-ful knobs, (2) map unseen Database workloads to previous work-loads from which we can transfer experience, and (3) recom
Automatic Database Management System Tuning Through Large-scale Machine Learning Dana Van Aken Andrew Pavlo Geoffrey J. Gordon Bohan Zhang Carnegie Mellon University Carnegie Mellon University Carnegie Mellon University Peking University
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: