Re: 8.3devel slower than 8.2 under read-only load - Mailing list pgsql-hackers

From Gavin M. Roy
Subject Re: 8.3devel slower than 8.2 under read-only load
Date
Msg-id af1bce590711241536s24d3b067u478877039391e075@mail.gmail.com
Whole thread Raw
In response to Re: 8.3devel slower than 8.2 under read-only load  (Gregory Stark <stark@enterprisedb.com>)
List pgsql-hackers
On 11/24/07, Gregory Stark <stark@enterprisedb.com> wrote:
This is a conflict which will affect Postgres in the future as well. Generally
I/O costs win over cpu costs in databases since only relatively small systems
are cpu-bound. Large systems are typically I/O-bound.

That really depends on hardware doesn't it?  I'd say that I'm more concerned with CPU than IO on high-end hardware as a generalization, especially with the scaling issues beyond 32 CPU's.

Regards,

Gavin

pgsql-hackers by date:

Previous
From: Alvaro Herrera
Date:
Subject: Re: [COMMITTERS] pgsql: Add regression tests for MONEY type.
Next
From: Andreas 'ads' Scherbaum
Date:
Subject: quote_literal(integer) does not exist