Re: PostgreSQL reads each 8k block - no larger blocks are used - even on sequential scans

From: Sam Mason <sam(at)samason(dot)me(dot)uk>
To: pgsql-general(at)postgresql(dot)org
Subject: Re: PostgreSQL reads each 8k block - no larger blocks are used - even on sequential scans
Date: 2009-09-27 21:19:42
Message-ID: 20090927211942.GU5407@samason.me.uk
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-general

On Sun, Sep 27, 2009 at 10:01:27PM +0100, Sam Mason wrote:
> Tested by turning on "\timing" mode in psql, dropping
> caches and running:
>
> SELECT 715833344 / 7597.216 / 1024;

Help, I can't do maths! This is overestimating the performance and
should be:

SELECT 715833344 / 7597.216 / 1024 / 1024 * 1000;

After a few more runs to increase confidence, the read performance is
87.17 and a stddev of 2.8. Which seems more reasonable, it should *not*
be going above 90MB/s as often as it was.

--
Sam http://samason.me.uk/

In response to

Browse pgsql-general by date

  From Date Subject
Next Message Nobuhiro Iwamatsu 2009-09-27 23:37:14 Re: getting PostgreSQL to run on superH-based machines
Previous Message Oliver Kohll - Mailing Lists 2009-09-27 21:19:11 Re: generic modelling of data models; enforcing constraints dynamically...