Re: parallel joins, and better parallel explain

Поиск
Список
Период
Сортировка
От Simon Riggs
Тема Re: parallel joins, and better parallel explain
Дата
Msg-id CANP8+jLPb+Cd21qe3UL0=JrxAyb7MA18qgbtv7DEx5-uLy-jLw@mail.gmail.com
обсуждение исходный текст
Ответ на parallel joins, and better parallel explain  (Robert Haas <robertmhaas@gmail.com>)
Ответы Re: parallel joins, and better parallel explain
Список pgsql-hackers
Дерево обсуждения
On 26 November 2015 at 03:41, Robert Haas <robertmhaas@gmail.com> wrote:
Attached find a patch that does (mostly) two things.  First, it allows
the optimizer to generate plans where a Nested Loop or Hash Join
appears below a Gather node.  This is a big improvement on what we
have today, where only a sequential scan can be parallelized; with
this patch, entire join problems can be parallelized, as long as they
don't need a Merge Join (see below for more on this).

Sounds like good progress.

This gives us multiple copies of the hash table, which means we must either use N * work_mem, or we must limit the hash table to work_mem / N per partial plan.

How can the partial paths share a hash table?

--
Simon Riggs                http://www.2ndQuadrant.com/
PostgreSQL Development, 24x7 Support, Remote DBA, Training & Services

В списке pgsql-hackers по дате отправления:

Предыдущее
От: Michael Paquier
Дата:
Сообщение: Re: pg_stat_replication log positions vs base backups
Следующее
От: Etsuro Fujita
Дата:
Сообщение: Re: Optimization for updating foreign tables in Postgres FDW