Re: hashagg slowdown due to spill changes
От | Tomas Vondra |
---|---|
Тема | Re: hashagg slowdown due to spill changes |
Дата | |
Msg-id | 20200612230625.fezrlwfsgkctk7ok@development обсуждение исходный текст |
Ответ на | Re: hashagg slowdown due to spill changes (Jeff Davis <pgsql@j-davis.com>) |
Ответы |
Re: hashagg slowdown due to spill changes
|
Список | pgsql-hackers |
On Fri, Jun 12, 2020 at 03:29:08PM -0700, Jeff Davis wrote: >On Fri, 2020-06-12 at 14:37 -0700, Andres Freund wrote: >> I don't see why it's ok to force an additional projection in the very >> common case of hashaggs over a few rows. So I think we need to >> rethink >> 4cad2534da6. > >One possibility is to project only spilled tuples, more similar to >Melanie's patch from a while ago: > > >https://www.postgresql.org/message-id/CAAKRu_aefEsv+UkQWqu+ioEnoiL2LJu9Diuh9BR8MbyXuZ0j4A@mail.gmail.com > >Which makes sense, but it's also more code. > I agree, we should revert 4cad2534da and only project tuples when we actually need to spill them. Did any of the WIP patches actually implement that, or do we need to write that patch from scratch? regards -- Tomas Vondra http://www.2ndQuadrant.com PostgreSQL Development, 24x7 Support, Remote DBA, Training & Services
В списке pgsql-hackers по дате отправления: