Re: WIP: bloom filter in Hash Joins with batches

Поиск
Список
Период
Сортировка
От Shulgin, Oleksandr
Тема Re: WIP: bloom filter in Hash Joins with batches
Дата
Msg-id CACACo5Q0z9vQE8pHc+b6rzHr_TOTNg4=nc4eiQodtD1poOBCCQ@mail.gmail.com
обсуждение исходный текст
Ответ на WIP: bloom filter in Hash Joins with batches  (Tomas Vondra <tomas.vondra@2ndquadrant.com>)
Ответы Re: WIP: bloom filter in Hash Joins with batches  (Tomas Vondra <tomas.vondra@2ndquadrant.com>)
Список pgsql-hackers
Дерево обсуждения
On Tue, Dec 15, 2015 at 11:30 PM, Tomas Vondra <tomas.vondra@2ndquadrant.com> wrote:

Attached is a spreadsheet with results for various work_mem values, and also with a smaller data set (just 30M rows in the fact table), which easily fits into memory. Yet it shows similar gains, shaving off ~40% in the best case, suggesting that this is not just thanks to reduction of I/O when forcing the temp files to disk.
 
A neat idea!  Have you possibly tried to also collect statistics about actual false-positive rates and filter allocation sizes in every of the collected data points?

--
Alex

В списке pgsql-hackers по дате отправления:

Предыдущее
От: "Shulgin, Oleksandr"
Дата:
Сообщение: Re: On-demand running query plans using auto_explain and signals
Следующее
От: Simon Riggs
Дата:
Сообщение: Re: WIP: bloom filter in Hash Joins with batches