From owner-freebsd-amd64@FreeBSD.ORG Wed Mar 15 21:13:16 2006 Return-Path: X-Original-To: freebsd-amd64@freebsd.org Delivered-To: freebsd-amd64@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9581F16A425 for ; Wed, 15 Mar 2006 21:13:16 +0000 (UTC) (envelope-from kris@obsecurity.org) Received: from elvis.mu.org (elvis.mu.org [192.203.228.196]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7EEBC43D70 for ; Wed, 15 Mar 2006 21:13:12 +0000 (GMT) (envelope-from kris@obsecurity.org) Received: from obsecurity.dyndns.org (elvis.mu.org [192.203.228.196]) by elvis.mu.org (Postfix) with ESMTP id 0A1841A4E4D; Wed, 15 Mar 2006 13:13:11 -0800 (PST) Received: by obsecurity.dyndns.org (Postfix, from userid 1000) id 0DE4151FEB; Wed, 15 Mar 2006 16:13:10 -0500 (EST) Date: Wed, 15 Mar 2006 16:13:07 -0500 From: Kris Kennaway To: JoaoBR Message-ID: <20060315211307.GA88339@xor.obsecurity.org> References: <200603140740.38388.joao@matik.com.br> <200603151728.35620.joao@matik.com.br> <20060315203922.GA87806@xor.obsecurity.org> <200603151754.27250.joao@matik.com.br> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="PNTmBPCT7hxwcZjr" Content-Disposition: inline In-Reply-To: <200603151754.27250.joao@matik.com.br> User-Agent: Mutt/1.4.2.1i Cc: freebsd-amd64@freebsd.org, Kris Kennaway Subject: Re: amd64 slower than i386 on identical AMD 64 system? X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 15 Mar 2006 21:13:16 -0000 --PNTmBPCT7hxwcZjr Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Mar 15, 2006 at 05:54:27PM -0300, JoaoBR wrote: > On Wednesday 15 March 2006 17:39, Kris Kennaway wrote: > > > > Yes, but the problem is that you didn't stop and file a bug report > > when you learned of the problems (and then turn off the broken > > option), but instead wrote an email in which you made the broad claim > > that FreeBSD's SMP support was unstable. > > >=20 > whats that now? absolutly not true >=20 > read the thread again and show me where I said that but to help you out: = I=20 > said that I (I!) have problems with X2 processor with very specific memor= y=20 > amount installed on certain hardware when SMP is enabled >=20 > don't turn my words around You said: > I can confirm this too > SMP amd64s are having constant crashes when running >2GB and <4GB of RAM. > In order not getting anything wrong I am talking about X2-SMP mono-chip-M= Bs > this is not happening on dual-chip-MB with two separate processors. > I run the same hardware as UP-amd64 and it never crashes > Since this crashes are more frequent with IPI_PREEMPTION I have now some > servers under test running without PREEMPTION at all and appearently the > crashes are gone The claim in this paragraph is that it is necessary to disable the (default) PREEMPTION option in order for FreeBSD not to crash on these systems, i.e. FreeBSD is unstable by default. But what you actually did was enable the non-default IPI_PREEMPTION option, which may cause crashes, and then instead of just turning it off again you turned off both this and PREEMPTION. Anyway, maybe there is just a language issue and you didn't manage to express yourself well. > > > well, that was my first thought too but makes no sense if the same > > > happens on several different brands, > > > > Why not? It is well-documented that many motherboards need BIOS > > updates to work correctly with dual-core CPUs. > > >=20 > you are more clever than that aren't you? Or do you try to get clever wit= h me? >=20 > means: makes no sense that the bios is broken on all MBs I tried >=20 > overall you cut the important thing where I said that I did tried other b= ios=20 > versions >=20 > and what you say here has nothing to do with all of this because the bios= =20 > updates you're talking about are necessary on certain MBs in order to=20 > recognize the X2 - so we are beyond this point ... No, you haven't ruled it out, only that none of the versions you tried fix your issue. Note what I said earlier: other people use dual core CPUs on FreeBSD/amd64 without stability problems, so it is not a general problem with FreeBSD. Kris --PNTmBPCT7hxwcZjr Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.2.2 (FreeBSD) iD8DBQFEGINhWry0BWjoQKURAqgYAKDCIMimdOuX3ZZfUSBDlqIBJjpAgQCbBnJ+ LiOKwDgfdLwziKCX2oG577M= =sqBZ -----END PGP SIGNATURE----- --PNTmBPCT7hxwcZjr--