Message-ID: <4DC86E28.8020703@2ndQuadrant.com>
Date: Mon, 09 May 2011 18:43:52 -0400
From: Greg Smith <greg@2ndQuadrant.com>
User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US;
	rv:1.9.1.16) Gecko/20110307 Icedove/3.0.11
MIME-Version: 1.0
To: pgsql-performance@postgresql.org
Subject: Re: Postgres refusing to use >1 core
References: <BANLkTimohiUa6rOYdxYTwqmvSUg2CRYMHg@mail.gmail.com>
	<4DC81A3F020000250003D433@gw.wicourts.gov>
	<BANLkTimNTLqQgQeyu=FPOn-5x6F4XnVBJA@mail.gmail.com>
	<4DC81D56020000250003D438@gw.wicourts.gov>
In-Reply-To: <4DC81D56020000250003D438@gw.wicourts.gov>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit

On 05/09/2011 05:59 PM, Kevin Grittner wrote:
> I'm going to pursue this digression just a little further, because
> it probably will be biting you sooner or later.  We make sure to
> configure the BIOS on our database servers to turn off
> hyperthreading.  It really can make a big difference in performance.
>    

You're using connection pooling quite aggressively though.  The sort of 
people who do actually benefit from hyperthreading are the ones who 
don't, where there's lots of CPU time being burnt up in overhead you 
don't see, and that even a virtual HT processor can help handle.  I'm 
not a big fan of the current hyperthreading implementation, but it's not 
nearly as bad as the older ones, and there are situations where it is 
useful.  I am unsurprised you don't ever see them on your workload 
though, you're well tweaked enough to probably be memory or disk limited 
much of the time.

-- 
Greg Smith   2ndQuadrant US    greg@2ndQuadrant.com   Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support  www.2ndQuadrant.us
"PostgreSQL 9.0 High Performance": http://www.2ndQuadrant.com/books