To: Christopher Petrilli <petrilli@gmail.com>
Cc: pgsql-performance@postgresql.org
Subject: Re: Impact of checkpoint_segments under continual load conditions 
In-reply-to: <59d991c4050717100874c08a86@mail.gmail.com> 
References: <59d991c4050717100874c08a86@mail.gmail.com>
Comments: In-reply-to Christopher Petrilli <petrilli@gmail.com>
	message dated "Sun, 17 Jul 2005 13:08:34 -0400"
Date: Sun, 17 Jul 2005 14:15:54 -0400
Message-ID: <18942.1121624154@sss.pgh.pa.us>
From: Tom Lane <tgl@sss.pgh.pa.us>

Christopher Petrilli <petrilli@gmail.com> writes:
> I have a unique scenerio.  My DB is under "continual load", meaning
> that I am constantly using COPY to insert new data into the DB.  There
> is no "quiet period" for the database, at least not for hours on end. 
> Normally, checkpoint_segments can help absorb some of that, but my
> experience is that if I crank the number up, it simply delays the
> impact, and when it occurs, it takes a VERY long time (minutes) to
> clear.

If you are using 8.0, you can probably alleviate the problem by making
the bgwriter more aggressive.  I don't have any immediate
recommendations for specific settings though.

A small checkpoint_segments setting is definitely bad news for
performance under heavy load.

			regards, tom lane