It was long time ago. The schema was basically one table with a lot of fields and records and multiple small tables with way fewer records. Query in question resulted in small number of rows (because of LIMIT clause).
It was faster to get rows from big table and then run few additional queries to get data for found rows from smaller ones than join everything together in one query. Maybe the nested loop buffer was culprit or whatever. Maybe I ran into edge case of query planner MySQL had 20 years ago. Who knows.
It was faster to get rows from big table and then run few additional queries to get data for found rows from smaller ones than join everything together in one query. Maybe the nested loop buffer was culprit or whatever. Maybe I ran into edge case of query planner MySQL had 20 years ago. Who knows.