Re: 9.5: Better memory accounting, towards memory-bounded HashAgg

Поиск
Список
Период
Сортировка
Искать
От
Jeff Davis
Тема
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg
Дата
Msg-id
1408436713.2335.217.camel@jeff-desktop
Ответ на
Список
Дерево обсуждения
9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Robert Haas <robertmhaas@gmail.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tom Lane <tgl@sss.pgh.pa.us>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg "Tomas Vondra" <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Robert Haas <robertmhaas@gmail.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Robert Haas <robertmhaas@gmail.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tom Lane <tgl@sss.pgh.pa.us>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Simon Riggs <simon@2ndQuadrant.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Andres Freund <andres@2ndquadrant.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Peter Geoghegan <pg@heroku.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Peter Geoghegan <pg@heroku.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jim Nasby <Jim.Nasby@BlueTreble.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Janes <jeff.janes@gmail.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tomas.vondra@2ndquadrant.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tomas.vondra@2ndquadrant.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Michael Paquier <michael.paquier@gmail.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Michael Paquier <michael.paquier@gmail.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Michael Paquier <michael.paquier@gmail.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Andres Freund <andres@2ndquadrant.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Andres Freund <andres@2ndquadrant.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Simon Riggs <simon@2ndQuadrant.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Simon Riggs <simon@2ndQuadrant.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jim Nasby <Jim.Nasby@BlueTreble.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Tomas Vondra <tv@fuzzy.cz>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Robert Haas <robertmhaas@gmail.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Jeff Davis <pgsql@j-davis.com>
Re: 9.5: Better memory accounting, towards memory-bounded HashAgg Peter Geoghegan <pg@heroku.com>
On Thu, 2014-08-14 at 12:52 -0400, Robert Haas wrote:
> It appears to me that the performance characteristics for this version
> are not significantly different from version 1.  I have not looked at
> the code.

While trying to reproduce your results, I noticed what might be around a
1% regression just from adding the 3 fields to MemoryContextData. If I
cut it down to adding just one field, the regression disappears.

The results are fairly noisy, so I could be chasing the wrong thing. But
one reason to believe it is that I pushed the size of MemoryContextData
above 64, which sounds like it might be an important threshold.

Regards,Jeff Davis




В списке pgsql-hackers по дате отправления
От: Michael Paquier
Дата:
От: Jeff Davis
Дата:
FAQ