Re: Mapping a database completly into Memory - Mailing list pgsql-performance

From Tom Lane
Subject Re: Mapping a database completly into Memory
Date
Msg-id 10185.1059409557@sss.pgh.pa.us
Whole thread Raw
In response to Re: Mapping a database completly into Memory  (Franco Bruno Borghesi <franco@akyasociados.com.ar>)
Responses Re: Mapping a database completly into Memory
List pgsql-performance
Franco Bruno Borghesi <franco@akyasociados.com.ar> writes:
> wouldn't also increasing shared_buffers to 64 or 128 MB be a good
> performance improvement? This way, pages belonging to heavily used
> indexes would be already cached by the database itself.

Not necessarily.  The trouble with large shared_buffers settings is you
end up with lots of pages being doubly cached (both in PG's buffers and
in the kernel's disk cache), thus wasting RAM.  If we had a portable way
of preventing the kernel from caching the same page, it would make more
sense to run with large shared_buffers.

            regards, tom lane

pgsql-performance by date:

Previous
From: Josh Berkus
Date:
Subject: Re: Mapping a database completly into Memory
Next
From: "Justin Long"
Date:
Subject: Optimization