Message-ID: <509A65F5.2020306@boreham.org>
Date: Wed, 07 Nov 2012 06:45:25 -0700
From: David Boreham <david_list@boreham.org>
User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64;
	rv:16.0) Gecko/20121026 Thunderbird/16.0.2
MIME-Version: 1.0
To: pgsql-performance@postgresql.org
Subject: Re: HT on or off for E5-26xx ?
References: <5099D5FA.90802@boreham.org>
	<1352295444.3774.109.camel@lenovo01-laptop03.gunduz.org>
In-Reply-To: <1352295444.3774.109.camel@lenovo01-laptop03.gunduz.org>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: quoted-printable

On 11/7/2012 6:37 AM, Devrim G=C3=9CND=C3=9CZ wrote:
> HT should be good for file servers, or say many of the app servers, or
> small web/mail  servers. PostgreSQL relies on the CPU power, and since
> the HT CPUs don't have the same power as the original CPU, when OS
> submits a job to that particular HTed CPU, query will run significantly
> slow. To avoid issues, I would suggest you to turn HT off on all
> PostgreSQL servers. If you can throw some more money, another 6-core CP=
U
> would give more benefit.
I realize this is the "received knowledge" but it is not supported by=20
the evidence before me (which is that I get nearly 2x the throughput=20
from pgbench using nthreads =3D=3D nhtcores vs nthreads =3D=3D nfullcores=
).=20
Intel's latest HT implementation seems to suffer less from the kinds of=20
resource sharing contention issues seen in older generations.

Once I have the machine's full memory installed I'll run pgbench with HT=20
disabled in the BIOS and post the results.