Re: cpu_tuple_cost

From: Gregory Stark <gsstark(at)mit(dot)edu>
To: pgsql-performance(at)postgresql(dot)org
Subject: Re: cpu_tuple_cost
Date: 2005-03-15 05:30:41
Message-ID: 87psy1mq66.fsf@stark.xeocode.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-performance


Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us> wrote:

> Agreed. I think we should reduce it at least to 3.

Note that changing it from 4 to 3 or even 2 is unlikely to really change much.
Many of the plans people complain about turn out to have critical points
closer to 1.2 or 1.1.

The only reason things work out better with such low values is because people
have data sets that fit more or less entirely in RAM. So values close to 1 or
even equal to 1 actually represent the reality.

The "this day and age" argument isn't very convincing. Hard drive capacity
growth has far outstripped hard drive seek time and bandwidth improvements.
Random access has more penalty than ever.

--
greg

Responses

Browse pgsql-performance by date

  From Date Subject
Next Message Josh Berkus 2005-03-15 06:10:40 Re: cpu_tuple_cost
Previous Message Tom Lane 2005-03-15 02:23:29 Re: cpu_tuple_cost