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:
AutoTiKV: TiKV Tuning Made Easy by Machine Learning
tidb:
tikv:
docs-cn:
parser:
Coprocessor SIG:
Last week, we landed 70 PRs in the TiDB repository, 7 PRs in the TiSpark repository, and 46 PRs in the TiKV and PD repositories.
TiDB:
show extended columns
statementreleaseSysSession
ClusterEventsStatementsSummary
tablePushTopNDownTiKVSingleGather
transformation rule in the cascades plannerIndexScan
of IndexJoin
TiSpark:
UTF8
TiKV and PD:
Commit
to clean up the pessimistic lockssplit check
in the online change configurationempty
destroy
ApplySnapshotObserver
keyvisual
service