Re: Question about memory allocations - Mailing list pgsql-performance

From Tom Lane
Subject Re: Question about memory allocations
Date
Msg-id 4918.1176568674@sss.pgh.pa.us
Whole thread Raw
In response to Re: Question about memory allocations  (Ron <rjpeace@earthlink.net>)
List pgsql-performance
Ron <rjpeace@earthlink.net> writes:
> One of the reasons for the wide variance in suggested values for pg
> memory use is that pg 7.x and pg 8.x are =very= different beasts.
> If you break the advice into pg 7.x and pg 8.x categories, you find
> that there is far less variation in the suggestions.
> Bottom line: pg 7.x could not take advantage of larger sums of memory
> anywhere near as well as pg 8.x can.

Actually I think it was 8.1 that really broke the barrier in terms of
scalability of shared_buffers.  Pre-8.1, the buffer manager just didn't
scale well enough to make it useful to use more than a few hundred meg.
(In fact, we never even bothered to fix the shared-memory-sizing
calculations to be able to deal with >2GB shared memory until 8.1;
if you try it in 8.0 it'll probably just crash.)

            regards, tom lane

pgsql-performance by date:

Previous
From: Tom Lane
Date:
Subject: Re: [HACKERS] choose_bitmap_and again (was Re: Strangely Variable Query Performance)
Next
From: Tom Lane
Date:
Subject: Re: [HACKERS] choose_bitmap_and again (was Re: Strangely Variable Query Performance)