Received: from maia.hub.org (maia-2.hub.org [200.46.204.251]) by mail.postgresql.org (Postfix) with ESMTP id F1B8C1337C88 for ; Mon, 11 Apr 2011 15:40:47 -0300 (ADT) Received: from mail.postgresql.org ([200.46.204.86]) by maia.hub.org (mx1.hub.org [200.46.204.251]) (amavisd-maia, port 10024) with ESMTP id 09534-04-3 for ; Mon, 11 Apr 2011 18:40:28 +0000 (UTC) X-Greylist: domain auto-whitelisted by SQLgrey-1.7.6 Received: from nm14.bullet.mail.ukl.yahoo.com (nm14.bullet.mail.ukl.yahoo.com [217.146.183.188]) by mail.postgresql.org (Postfix) with SMTP id 604631337D67 for ; Mon, 11 Apr 2011 15:23:52 -0300 (ADT) Received: from [217.146.183.184] by nm14.bullet.mail.ukl.yahoo.com with NNFMP; 11 Apr 2011 18:23:51 -0000 Received: from [217.146.183.177] by tm15.bullet.mail.ukl.yahoo.com with NNFMP; 11 Apr 2011 18:23:51 -0000 Received: from [127.0.0.1] by omp1018.mail.ukl.yahoo.com with NNFMP; 11 Apr 2011 18:23:51 -0000 X-Yahoo-Newman-Property: ymail-3 X-Yahoo-Newman-Id: 999883.55530.bm@omp1018.mail.ukl.yahoo.com Received: (qmail 74769 invoked by uid 60001); 11 Apr 2011 18:23:50 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.co.uk; s=s1024; t=1302546230; bh=ihf6FJgrSYuZvKPKWs5LaqUVDjGmYeJGgf/usm7iGAo=; 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=1JGf3tEofbmBweFvD4BnEz6VUXYifBYxQfhF9jBYJj+WK2IXZV8Ky0yIlY8g/AR6GOUpWLsHRdZ50XyJcI17Vcf2lkqr3ea7MuEcr5bFyrTRrCutBJogZ1Uhw5iHePBNH3njNdDtvn03bA+7CT+DzucUSPddvZhaVc1Bl0qTfxU= 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=xy9OiVuVi8MNdefwt9jCPKcuzk9FNjjFR+218jiHHrxwRpqe8OQDye6829Bz6l0DllViHUvLgcu4NdaIQItbED56BzFuSj2UdoevMzvcS9rOSanUCsPbXEueXXBRS1ghqq37kN+51vbmh7m+v1YoNi+ZYFWB8QNZu7j1j87aBGc=; Message-ID: <895662.51387.qm@web26005.mail.ukl.yahoo.com> X-YMail-OSG: _WXGwFMVM1kVJO9wwtG5laqcWuSqxIBSC_janMojzLEoin_ OSa5umIQmc2bz0Q_OKLTcrQMo6fIac_jA5iRLPU2xKC6bdnsm.LGVCpHCRax 6RTBkDVdLNIRbKK6nn25dtHTXAg3nBBhM0qkcpqdlD8ypJlNL2WPe.KqI6sY IS7tH9GDPZ7Z_opnT58iPjzFUJv7L2eIhtFlRczbx.qjDCUcGm1OhnJzLU93 tEaXHyHVSIGFq8V2WccfeB45gaHMGGEQ.A0Zx4pHRL8JDkKUth4IPjjvbUa9 50a7H79nxKq_htm202K4ABW61cOj0knQi94544dZMtnRBm6XmYz7UBhzIUVt tg4Ab7nFmka8g2Nyek7u7nIec69yk25ut Received: from [81.98.134.44] by web26005.mail.ukl.yahoo.com via HTTP; Mon, 11 Apr 2011 19:23:50 BST X-Mailer: YahooMailClassic/12.0.2 YahooMailWebService/0.8.109.295617 Date: Mon, 11 Apr 2011 19:23:50 +0100 (BST) From: Glyn Astill Subject: Re: Linux: more cores = less concurrency. To: Kevin Grittner , "Joshua D. Drake" Cc: pgsql-performance@postgresql.org In-Reply-To: <8b76c51ad6db2e458431ef73bcdd2759@commandprompt.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable X-Virus-Scanned: Maia Mailguard 1.0.1 X-Spam-Status: No, hits=-1.898 tagged_above=-10 required=5 tests=BAYES_00=-1.9, FREEMAIL_FROM=0.001, RCVD_IN_DNSWL_NONE=-0.0001, RFC_ABUSE_POST=0.001 X-Spam-Level: X-Archive-Number: 201104/111 X-Sequence-Number: 43173 =0A=0A--- On Mon, 11/4/11, Joshua D. Drake wrote:=0A= =0A> From: Joshua D. Drake =0A> Subject: Re: [PERFORM= ] Linux: more cores =3D less concurrency.=0A> To: "Kevin Grittner" =0A> Cc: pgsql-performance@postgresql.org, "Glyn Astil= l" =0A> Date: Monday, 11 April, 2011, 19:12=0A> On = Mon, 11 Apr 2011 13:09:15 -0500,=0A> "Kevin Grittner"=0A> =0A> wrote:=0A> > Glyn Astill =0A> wrot= e:=0A> >=A0 =0A> >> The new server uses 4 x 8 core Xeon X7550 CPUs at=0A> 2= Ghz=0A> >=A0 =0A> > Which has hyperthreading.=0A> >=A0 =0A> >> our current = servers are 2 x 4 core Xeon E5320 CPUs=0A> at 2Ghz.=0A> >=A0 =0A> > Which d= oesn't have hyperthreading.=0A> >=A0 =0A=0AYep, off. If you look at the ben= chmarks I took, HT absoloutely killed it.=0A=0A> > PostgreSQL often perform= s worse with hyperthreading=0A> than without. =0A> > Have you turned HT off= on your new machine?=A0 If=0A> not, I would start=0A> > there.=0A> =0A> An= d then make sure you aren't running CFQ.=0A> =0A> JD=0A> =0A=0ANot running = CFQ, running the no-op i/o scheduler.