From owner-freebsd-i386@FreeBSD.ORG Wed Nov 8 00:30:45 2006 Return-Path: X-Original-To: freebsd-i386@hub.freebsd.org Delivered-To: freebsd-i386@hub.freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3DE3016A407 for ; Wed, 8 Nov 2006 00:30:45 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [216.136.204.21]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5AAF543D75 for ; Wed, 8 Nov 2006 00:30:42 +0000 (GMT) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (gnats@localhost [127.0.0.1]) by freefall.freebsd.org (8.13.4/8.13.4) with ESMTP id kA80Uag8033594 for ; Wed, 8 Nov 2006 00:30:36 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.13.4/8.13.4/Submit) id kA80UaG5033589; Wed, 8 Nov 2006 00:30:36 GMT (envelope-from gnats) Date: Wed, 8 Nov 2006 00:30:36 GMT Message-Id: <200611080030.kA80UaG5033589@freefall.freebsd.org> To: freebsd-i386@FreeBSD.org From: Bruce Evans Cc: Subject: Re: i386/104678: SMP not working on Turion XP Laptop X-BeenThere: freebsd-i386@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Bruce Evans List-Id: I386-specific issues for FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 08 Nov 2006 00:30:45 -0000 The following reply was made to PR i386/104678; it has been noted by GNATS. From: Bruce Evans To: Andrew Pantyukhin Cc: freebsd-gnats-submit@freebsd.org Subject: Re: i386/104678: SMP not working on Turion XP Laptop Date: Wed, 8 Nov 2006 11:29:06 +1100 (EST) On Tue, 7 Nov 2006, Andrew Pantyukhin wrote: > On 11/7/06, Bruce Evans wrote: > > On a similar laptop (HP nx6325 Turion X2 2GHz), I found 2 workarounds: > > I have Fujitsu-Siemens Amilo Pa 1510 Turion X2 TL-56 1.8GHz > > > 1. Boot with battery power only. Usually works. > > ... > These workarounds don't work for me. What does work though > is keeping CPU loaded (at least one core) with something like > "md5 Some timings are still of, > especially with TSC timecounter, but with i8254 and ACPI-fast > it's mostly all right. The TSC is unlikely to work with more than 1 active CPU. Both the i8254 and ACPI-notslow work OK for me, but very slowly (time for reading the counter: i8254: 4-5uS; ACPI-notslow: 1.6-1.7uS). > Just constantly moving mouse (touchpad) in X also helps. I have an nfs latency problem where pinging the interface to keep it active helps a lot. Both behaviours would be explained by interrupts are getting lost somewhere. Bruce