The fast advancement of AI and machine learning (ML) technologies are reshaping the way people manage and tune databases. Inspired by the pioneering breakthroughs of automatic tuning, we developed AutoTiKV, a machine-learning-based tuning tool that automatically recommends optimal knobs for TiKV. So far, our exploration of automatic tuning has been rewarding.
Last week, we published a post that discusses AutoTiKV's design, its machine learning model, and the automatic tuning workflow. The post also shares the results of experiments we ran to verify whether the tuning results are optimal and as expected, with some interesting and unexpected findings.
The full post is here:
show extended columnsstatement
PushTopNDownTiKVSingleGathertransformation rule in the cascades planner
TiKV and PD:
Committo clean up the pessimistic locks
split checkin the online change configuration