Re: Running PostgreSQL as fast as possible no matter the consequences

От: Chris Browne
Тема: Re: Running PostgreSQL as fast as possible no matter the consequences
Дата: ,
Msg-id: 8739rfst0h.fsf@cbbrowne.afilias-int.info
(см: обсуждение, исходный текст)
Ответ на: Running PostgreSQL as fast as possible no matter the consequences  (A B)
Ответы: Re: Running PostgreSQL as fast as possible no matter the consequences  (Bruce Momjian)
Список: pgsql-performance

Скрыть дерево обсуждения

Running PostgreSQL as fast as possible no matter the consequences  (A B, )
 Re: Running PostgreSQL as fast as possible no matter the consequences  (Thom Brown, )
  Re: Running PostgreSQL as fast as possible no matter the consequences  (Thom Brown, )
  Re: Running PostgreSQL as fast as possible no matter the consequences  (A B, )
 Re: Running PostgreSQL as fast as possible no matter the consequences  (Guillaume Cottenceau, )
  Re: Running PostgreSQL as fast as possible no matter the consequences  (Marti Raudsepp, )
   Re: Running PostgreSQL as fast as possible no matter the consequences  (Guillaume Cottenceau, )
 Re: Running PostgreSQL as fast as possible no matter the consequences  (Szymon Guz, )
  Re: Running PostgreSQL as fast as possible no matter the consequences  (A B, )
   Re: Running PostgreSQL as fast as possible no matter the consequences  (Marti Raudsepp, )
    Re: Running PostgreSQL as fast as possible no matter the consequences  (Thom Brown, )
    Re: Running PostgreSQL as fast as possible no matter the consequences  (Guillaume Cottenceau, )
     Re: Running PostgreSQL as fast as possible no matter the consequences  (Jon Nelson, )
      Re: Running PostgreSQL as fast as possible no matter the consequences  (Robert Haas, )
       Re: Running PostgreSQL as fast as possible no matter the consequences  (Andy Colson, )
        Re: Running PostgreSQL as fast as possible no matter the consequences  (Robert Haas, )
   Re: Running PostgreSQL as fast as possible no matter the consequences  (Craig Ringer, )
   Re: Running PostgreSQL as fast as possible no matter the consequences  ("Lello, Nick", )
    Re: Running PostgreSQL as fast as possible no matter the consequences  (Dimitri Fontaine, )
    Re: Running PostgreSQL as fast as possible no matter the consequences  (Klaus Ita, )
 Re: Running PostgreSQL as fast as possible no matter the consequences  (Craig Ringer, )
  Re: Running PostgreSQL as fast as possible no matter the consequences  (A B, )
 Re: Running PostgreSQL as fast as possible no matter the consequences  (Devrim GÜNDÜZ, )
  Re: Running PostgreSQL as fast as possible no matter the consequences  (Mladen Gogala, )
 Re: Running PostgreSQL as fast as possible no matter the consequences  (Chris Browne, )
  Re: Running PostgreSQL as fast as possible no matter the consequences  (Bruce Momjian, )
   Re: Running PostgreSQL as fast as possible no matter the consequences  (Fabrízio de Royes Mello, )
   Re: Running PostgreSQL as fast as possible no matter the consequences  (Robert Haas, )
    Re: Running PostgreSQL as fast as possible no matter the consequences  (Bruce Momjian, )
     Re: Running PostgreSQL as fast as possible no matter the consequences  (Jeff Janes, )
      Re: Running PostgreSQL as fast as possible no matter the consequences  (Bruce Momjian, )

 (A B) writes:
> If you just wanted PostgreSQL to go as fast as possible WITHOUT any
> care for your data (you accept 100% dataloss and datacorruption if any
> error should occur), what settings should you use then?

Use /dev/null.  It is web scale, and there are good tutorials.

But seriously, there *are* cases where "blind speed" is of use.  When
loading data into a fresh database is a good time for this; if things
fall over, it may be pretty acceptable to start "from scratch" with
mkfs/initdb.

I'd:
- turn off fsync
- turn off synchronous commit
- put as much as possible onto Ramdisk/tmpfs/similar as possible
--
output = reverse("moc.liamg" "@" "enworbbc")
http://linuxfinances.info/info/lsf.html
43% of all statistics are worthless.


В списке pgsql-performance по дате сообщения:

От: Josh Berkus
Дата:
Сообщение: Re: Major Linux performance regression; shouldn't we be worried about RHEL6?
От: Scott Carey
Дата:
Сообщение: Re: Major Linux performance regression; shouldn't we be worried about RHEL6?