pg.ddx.io  pgsql-performance@postgresql.org mailing list archive  
help / color / mirror / Atom feed
From: Greg Stark <gsstark@mit.edu>
To: Josh Berkus <josh@agliodbs.com>
Cc: Greg Stark <gsstark@mit.edu>
Cc: David Brown <time@bigpond.net.au>
Cc: Gregory Stark <pgsql-performance@postgresql.org>
Subject: Re: cpu_tuple_cost
Date: 16 Mar 2005 14:45:26 -0500
Message-ID: <87psxzjrxl.fsf@stark.xeocode.com> (raw)
In-Reply-To: <200503161003.10916.josh@agliodbs.com>
References: <87psy1mq66.fsf@stark.xeocode.com>
	<42377293.1010801@bigpond.net.au>
	<87acp4kq9o.fsf@stark.xeocode.com>
	<200503161003.10916.josh@agliodbs.com>


Josh Berkus <josh@agliodbs.com> writes:

> Although I can point out that you left out the fact that the disk needs to do 
> a seek to find the beginning of the seq scan area, and even then some file 
> fragmentation is possible.   Finally, I've never seen PostgreSQL manage more 
> than 70% of the maximum read rate, and in most cases more like 30%.     

Hm. I just did a quick test. It wasn't really long enough to get a good
estimate, but it seemed to reach about 30MB/s on this drive that's only
capable of 40-50MB/s depending on the location on the platters.

That's true though, some of my calculated 25% random seeks could be caused by
fragmentation. But it seems like that would be a small part.

> > So what's going on with the empirically derived value of 4? 
> 
> It's not empirically derived; it's a value we plug into an
> internal-to-postgresql formula.

I thought Tom said he got the value by doing empirical tests.

-- 
greg




view thread (20+ messages)  latest in thread

Message-ID: <87psxzjrxl.fsf@stark.xeocode.com>
Permalink:  ../87psxzjrxl.fsf@stark.xeocode.com/
Also on:    postgresql.org/message-id/87psxzjrxl.fsf@stark.xeocode.com

 · 

reply

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Reply to all the recipients using the --to and --cc options:
  reply via email

  To: pgsql-performance@postgresql.org
  Cc: gsstark@mit.edu, josh@agliodbs.com, time@bigpond.net.au
  Subject: Re: cpu_tuple_cost
  In-Reply-To: <87psxzjrxl.fsf@stark.xeocode.com>

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox