Download presentation
Presentation is loading. Please wait.
1
Performance Issues in Adaptive Query Processing Fred Reiss U.C. Berkeley Database Group
2
What Is an Eddy? Query Optimizer Operator Output Static Plan
3
Adaptive Plan Eddy What Is an Eddy? Query Operator Tuple Pool Routing Policy Output
4
Eddy Performance Agenda Goal: Replace the query optimizer Mechanism –Make adaptivity cheap Policy –Simple and effective adaptive routing policy
5
Mechanism Goal: make adaptivity cheap Minimize overhead –Use batching to amortize decisions Offset overhead –Use the tuple pool to cluster similar tuples
6
Policy Goal: simplicity –Want a routing policy that handles a wide variety of situations Randomized routing –Lottery scheduling –Machine learning / statistical models Hybrid/adaptive routing –Use a static optimizer as a subroutine
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.