From owner-freebsd-performance@FreeBSD.ORG Thu Feb 14 10:25:51 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id E3C6516A421 for ; Thu, 14 Feb 2008 10:25:51 +0000 (UTC) (envelope-from kris@FreeBSD.org) Received: from weak.local (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id EC0B913C4E3; Thu, 14 Feb 2008 10:25:50 +0000 (UTC) (envelope-from kris@FreeBSD.org) Message-ID: <47B4172D.3040307@FreeBSD.org> Date: Thu, 14 Feb 2008 11:25:49 +0100 From: Kris Kennaway User-Agent: Thunderbird 2.0.0.9 (Macintosh/20071031) MIME-Version: 1.0 To: Jeremie Le Hen References: <47A79ADA.9050900@paladin.bulgarpress.com> <20080214094011.GA92006@obiwan.tataz.chchile.org> In-Reply-To: <20080214094011.GA92006@obiwan.tataz.chchile.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Todorov , freebsd-performance@freebsd.org Subject: Re: SMP & HTT on 6.3 (P4) X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 14 Feb 2008 10:25:52 -0000 Jeremie Le Hen wrote: > Hi, > > On Tue, Feb 05, 2008 at 01:08:10AM +0200, Todorov wrote: >> -----BEGIN PGP SIGNED MESSAGE----- >> Hash: SHA1 >> >> Hi, >> what do you think for HyperThreading (P4 GHz), which serves FBSD 6.3? >> Now it's disabled by the BIOS but since today I've upgraded the machine >> 5.5 to 6.3 though if under 6.XX series it worths or not. >> >> I've read for performance penalties under 5.XX series w/ HTT on. I'm not >> going to change to ULE (it's said to be better for HTT awareness). > > ULE is broken on RELENG_6. Forget it. If you really want ULE, you'll > have to upgrade to RELENG_7. > > Regarding HTT, I haven't heard of any performance improvement with HTT > on FreeBSD. The scheduler have to be aware of it because HTT processors > share the same cache lines (including L1). Unenlightened scheduling > leads to an increase of cache miss (42% according [1]). This is not the > case on any FreeBSD branch currently. Nonetheless Jeff Roberson is > working on a CPU topology-aware scheduler implementation [2] but this is > not even in -CURRENT yet. It will probably ends up in RELENG_8. Actually with ULE in 7.0 it often seems to help on the workloads I have tested. This is probably because ULE has much better CPU affinity so processes don't bounce around between CPU threads so much. The bottom line with HTT has really always been: try it on your workload and measure whether or not it helps. Kris