DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.co.uk;
	h=Message-ID:X-YMail-OSG:Received:X-Mailer:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding;
	b=tcv/UN4sxKKtTS3BJfC/W+fH2LU0JJ/iBOsKsYF/fy+ibP6z2Trd7VxdDT4rZRu4xbDSwBysK2xPu0APZ7FvrQrTDRVackO5QDDf6eF+BA2lbYd2YQN0yrwyV+xucgw34FmDTFMXUtYkS9ONCilikg50S+EJKqvFbkmjf7W7VD0=;
Message-ID: <110350.63036.qm@web26004.mail.ukl.yahoo.com>
Date: Mon, 11 Apr 2011 22:08:09 +0100 (BST)
From: Glyn Astill <glynastill@yahoo.co.uk>
Subject: Re: Linux: more cores = less concurrency.
To: Scott Marlowe <scott.marlowe@gmail.com>
Cc: Kevin Grittner <Kevin.Grittner@wicourts.gov>,
	"Joshua D. Drake" <jd@commandprompt.com>, pgsql-performance@postgresql.org
In-Reply-To: <BANLkTi=zS8Lxutk_4n_i=Bgx8B+BuWVPTQ@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable

=0A=0A--- On Mon, 11/4/11, Scott Marlowe <scott.marlowe@gmail.com> wrote:=
=0A=0A> From: Scott Marlowe <scott.marlowe@gmail.com>=0A> Subject: Re: [PER=
FORM] Linux: more cores =3D less concurrency.=0A> To: "Glyn Astill" <glynas=
till@yahoo.co.uk>=0A> Cc: "Kevin Grittner" <Kevin.Grittner@wicourts.gov>, "=
Joshua D. Drake" <jd@commandprompt.com>, pgsql-performance@postgresql.org=
=0A> Date: Monday, 11 April, 2011, 21:52=0A> On Mon, Apr 11, 2011 at 1:42 P=
M, Glyn=0A> Astill <glynastill@yahoo.co.uk>=0A> wrote:=0A> =0A> > A wild gu=
ess is something like multiple cores=0A> contending for cpu cache, cpu affi=
nity, or some kind of=0A> contention in the kernel, alas a little out of my=
 depth.=0A> >=0A> > It's pretty sickening to think I can't get anything=0A>=
 else out of more than 8 cores.=0A> =0A> Have you tried running the memory =
stream benchmark Greg=0A> Smith had=0A> posted here a while back?=A0 It'll =
let you know if=0A> you're memory is=0A> bottlenecking.=A0 Right now my 48 =
core machines are the=0A> king of that=0A> benchmark with something like 70=
+Gig a second.=0A> =0A=0ANo I haven't, but I will first thing tomorow morni=
ng.  I did run a sysbench memory write test though, if I recall correctly t=
hat gave me somewhere just over 3000 Mb/s=0A=0A