From owner-freebsd-smp@FreeBSD.ORG Thu Apr 3 17:55:53 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 762F337B401 for ; Thu, 3 Apr 2003 17:55:53 -0800 (PST) Received: from web11505.mail.yahoo.com (web11505.mail.yahoo.com [216.136.172.37]) by mx1.FreeBSD.org (Postfix) with SMTP id 3583B43F93 for ; Thu, 3 Apr 2003 17:55:53 -0800 (PST) (envelope-from gesperon@yahoo.com) Message-ID: <20030404015552.15373.qmail@web11505.mail.yahoo.com> Received: from [200.55.139.109] by web11505.mail.yahoo.com via HTTP; Thu, 03 Apr 2003 17:55:52 PST Date: Thu, 3 Apr 2003 17:55:52 -0800 (PST) From: Gabor Esperon To: freebsd-smp@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Subject: DUAL XEON 2.40Mhz SMP APIC_IO Troubles X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 01:55:53 -0000 Hi!!! I have a ProLiant Dual XEON at 2.4Mhz running FreeBSD 5.0 configured as it follows: machine i386 cpu I686_CPU options SMP options APIC_IO But every time the system boots stop running at kernel message: "APIC_IO: Testing 8254 Interrupt Delivery".... and go freezed forever. Does someone have a tip or solution???? ===== Gabor Net/Sys Admin __________________________________________________ Do you Yahoo!? Yahoo! Tax Center - File online, calculators, forms, and more http://tax.yahoo.com From owner-freebsd-smp@FreeBSD.ORG Thu Apr 3 20:29:48 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1ABEC37B401 for ; Thu, 3 Apr 2003 20:29:48 -0800 (PST) Received: from smtp1.Stanford.EDU (smtp1.Stanford.EDU [171.64.14.23]) by mx1.FreeBSD.org (Postfix) with ESMTP id AB95A43FAF for ; Thu, 3 Apr 2003 20:29:47 -0800 (PST) (envelope-from jstockdale@stanford.edu) Received: from quenya (quenya.Stanford.EDU [128.12.44.61]) by smtp1.Stanford.EDU (8.12.9/8.12.9) with ESMTP id h344Tjls021452; Thu, 3 Apr 2003 20:29:45 -0800 (PST) From: "John Stockdale" To: "'Gabor Esperon'" Date: Thu, 3 Apr 2003 20:29:35 -0800 Message-ID: <002801c2fa62$cc5385c0$3d2c0c80@quenya> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook, Build 10.0.2627 In-Reply-To: <20030404015552.15373.qmail@web11505.mail.yahoo.com> X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1106 Importance: Normal cc: freebsd-smp@FreeBSD.ORG Subject: RE: DUAL XEON 2.40Mhz SMP APIC_IO Troubles X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 04:29:48 -0000 What version of FreeBSD 5.0 are you trying? -John -----Original Message----- From: owner-freebsd-smp@freebsd.org [mailto:owner-freebsd-smp@freebsd.org] On Behalf Of Gabor Esperon Sent: Thursday, April 03, 2003 5:56 PM To: freebsd-smp@freebsd.org Subject: DUAL XEON 2.40Mhz SMP APIC_IO Troubles Hi!!! I have a ProLiant Dual XEON at 2.4Mhz running FreeBSD 5.0 configured as it follows: machine i386 cpu I686_CPU options SMP options APIC_IO But every time the system boots stop running at kernel message: "APIC_IO: Testing 8254 Interrupt Delivery".... and go freezed forever. Does someone have a tip or solution???? ===== Gabor Net/Sys Admin __________________________________________________ Do you Yahoo!? Yahoo! Tax Center - File online, calculators, forms, and more http://tax.yahoo.com _______________________________________________ freebsd-smp@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-smp To unsubscribe, send any mail to "freebsd-smp-unsubscribe@freebsd.org" From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 04:13:21 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7584137B404 for ; Fri, 4 Apr 2003 04:13:21 -0800 (PST) Received: from ztxmail04.ztx.compaq.com (ztxmail04.ztx.compaq.com [161.114.1.208]) by mx1.FreeBSD.org (Postfix) with ESMTP id 740AF43FB1 for ; Fri, 4 Apr 2003 04:13:20 -0800 (PST) (envelope-from john.cagle@hp.com) Received: from cceexg12.americas.cpqcorp.net (cceexg12.americas.cpqcorp.net [16.110.250.124]) by ztxmail04.ztx.compaq.com (Postfix) with ESMTP id 041F1792E; Fri, 4 Apr 2003 06:13:20 -0600 (CST) Received: from cceexc19.americas.cpqcorp.net ([16.110.250.85]) by cceexg12.americas.cpqcorp.net with Microsoft SMTPSVC(5.0.2195.2966); Fri, 4 Apr 2003 06:13:19 -0600 X-MimeOLE: Produced By Microsoft Exchange V6.0.6375.0 content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Date: Fri, 4 Apr 2003 06:13:19 -0600 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: DUAL XEON 2.40Mhz SMP APIC_IO Troubles Thread-Index: AcL6TWjh9K0okFPrQ2+azLivd7Xr2AAVi+Yw From: "Cagle, John (ISS-Houston)" To: "Gabor Esperon" X-OriginalArrivalTime: 04 Apr 2003 12:13:19.0907 (UTC) FILETIME=[9492FF30:01C2FAA3] cc: freebsd-smp@freebsd.org Subject: RE: DUAL XEON 2.40Mhz SMP APIC_IO Troubles X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 12:13:21 -0000 If you're using -current (which has a patch for this issue) you'll need to also enable HTT. > -----Original Message----- > From: Gabor Esperon [mailto:gesperon@yahoo.com]=20 > Sent: Thursday, April 03, 2003 7:56 PM > To: freebsd-smp@freebsd.org > Subject: DUAL XEON 2.40Mhz SMP APIC_IO Troubles >=20 >=20 > Hi!!! >=20 > I have a ProLiant Dual XEON at 2.4Mhz running FreeBSD > 5.0 configured as it follows: >=20 > machine i386 > cpu I686_CPU > options SMP > options APIC_IO >=20 > But every time the system boots stop running at kernel > message: "APIC_IO: Testing 8254 Interrupt > Delivery".... and go freezed forever. >=20 > Does someone have a tip or solution???? >=20 > =3D=3D=3D=3D=3D > Gabor > Net/Sys Admin >=20 > __________________________________________________ > Do you Yahoo!? > Yahoo! Tax Center - File online, calculators, forms, and more=20 http://tax.yahoo.com _______________________________________________ freebsd-smp@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-smp To unsubscribe, send any mail to "freebsd-smp-unsubscribe@freebsd.org" From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 07:04:59 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id DA55137B401; Fri, 4 Apr 2003 07:04:59 -0800 (PST) Received: from h00609772adf0.ne.client2.attbi.com (h00609772adf0.ne.client2.attbi.com [24.61.43.152]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9183A43FAF; Fri, 4 Apr 2003 07:04:58 -0800 (PST) (envelope-from rodrigc@attbi.com) Received: from h00609772adf0.ne.client2.attbi.com (localhost.ne.attbi.com [127.0.0.1])h34F5IcJ015132; Fri, 4 Apr 2003 10:05:19 -0500 (EST) (envelope-from rodrigc@h00609772adf0.ne.client2.attbi.com) Received: (from rodrigc@localhost)h34F5Ijx015131; Fri, 4 Apr 2003 10:05:18 -0500 (EST) Date: Fri, 4 Apr 2003 10:05:18 -0500 From: Craig Rodrigues To: John Baldwin Message-ID: <20030404150518.GA15112@attbi.com> References: <20030326023737.GA85101@attbi.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4i cc: freebsd-smp@FreeBSD.org Subject: Re: atomic_dec_and_test() in FreeBSD? X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 15:05:00 -0000 On Wed, Mar 26, 2003 at 12:13:21PM -0500, John Baldwin wrote: > > I am the port maintainer of the Apache Portable Runtime (apr) library. > > apr has some atomic functions. For FreeBSD, this is what is defined: > > > > /** > > * decrement the atomic variable by 1 > > * @param mem pointer to the atomic value > > * @return zero if the value is zero, otherwise non-zero > > */ > > int apr_atomic_dec(volatile apr_atomic_t *mem); > > > > [snip] > > > >#define apr_atomic_dec(mem) atomic_subtract_int(mem,1) > > > > > > This is obviously quite wrong. > > > > So are you saying that I should replace this with: > > > > int apr_atomic_dec(volatile apr_atomic_t *mem); > > > > int apr_atomic_dec(volatile apr_atomic_t *mem){ > > apr_atomic_t x > > do { > > x = *mem; > > } while (atomic_cmpset_int(mem, x, x - 1) == 0); > > if (x == 1) > > /* foo just dropped to zero */ > > > > > > ??????? > > } > > > > Can you give more guidance? > > You could do this: > > apr_atomic_t x; > > do { > x = *mem; > } while (atomic_cmpset_int(mem, x, x - 1) == 0); > return (x - 1) This macro exists on -CURRENT, but I can't seem to find it on FreeBSD 4.7. What is the equivalent solution on that platform? Thanks. -- Craig Rodrigues http://home.attbi.com/~rodrigc rodrigc@attbi.com From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 11:34:20 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 95AD637B401 for ; Fri, 4 Apr 2003 11:34:20 -0800 (PST) Received: from mail.speakeasy.net (mail14.speakeasy.net [216.254.0.214]) by mx1.FreeBSD.org (Postfix) with ESMTP id D0BEA43FA3 for ; Fri, 4 Apr 2003 11:34:19 -0800 (PST) (envelope-from jhb@FreeBSD.org) Received: (qmail 31279 invoked from network); 4 Apr 2003 19:34:25 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender )encrypted SMTP for ; 4 Apr 2003 19:34:25 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.12.8/8.12.8) with ESMTP id h34JYHOv031322; Fri, 4 Apr 2003 14:34:17 -0500 (EST) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.4 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <20030404150518.GA15112@attbi.com> Date: Fri, 04 Apr 2003 14:34:17 -0500 (EST) From: John Baldwin To: Craig Rodrigues cc: freebsd-smp@FreeBSD.org Subject: Re: atomic_dec_and_test() in FreeBSD? X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 19:34:20 -0000 On 04-Apr-2003 Craig Rodrigues wrote: > On Wed, Mar 26, 2003 at 12:13:21PM -0500, John Baldwin wrote: >> > I am the port maintainer of the Apache Portable Runtime (apr) library. >> > apr has some atomic functions. For FreeBSD, this is what is defined: >> > >> > /** >> > * decrement the atomic variable by 1 >> > * @param mem pointer to the atomic value >> > * @return zero if the value is zero, otherwise non-zero >> > */ >> > int apr_atomic_dec(volatile apr_atomic_t *mem); >> > >> > [snip] >> > >> >#define apr_atomic_dec(mem) atomic_subtract_int(mem,1) >> > >> > >> > This is obviously quite wrong. >> > >> > So are you saying that I should replace this with: >> > >> > int apr_atomic_dec(volatile apr_atomic_t *mem); >> > >> > int apr_atomic_dec(volatile apr_atomic_t *mem){ >> > apr_atomic_t x >> > do { >> > x = *mem; >> > } while (atomic_cmpset_int(mem, x, x - 1) == 0); >> > if (x == 1) >> > /* foo just dropped to zero */ >> > >> > >> > ??????? >> > } >> > >> > Can you give more guidance? >> >> You could do this: >> >> apr_atomic_t x; >> >> do { >> x = *mem; >> } while (atomic_cmpset_int(mem, x, x - 1) == 0); >> return (x - 1) > > > > This macro exists on -CURRENT, but I can't seem to find it > on FreeBSD 4.7. What is the equivalent solution on that platform? 4.7 doesn't have a real good equivalent. However, on 4.7 you can probably just do: s = splhigh(); x--; zero = x == 0; splx(s); if (x == 0) /* refcount is zero */ In fact, depending on what you do in the zero case, you probably would need to do: s = splhigh(); if (--x == 0) /* refcount is zero, call free(), etc. */ splx(s); -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 11:39:08 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id BF78937B401 for ; Fri, 4 Apr 2003 11:39:08 -0800 (PST) Received: from relay.pair.com (relay.pair.com [209.68.1.20]) by mx1.FreeBSD.org (Postfix) with SMTP id 927B743FBD for ; Fri, 4 Apr 2003 11:39:07 -0800 (PST) (envelope-from rooneg@electricjellyfish.net) Received: (qmail 28783 invoked from network); 4 Apr 2003 19:39:06 -0000 Received: from softdnserror (HELO electricjellyfish.net) (64.246.81.227) by relay.pair.com with SMTP; 4 Apr 2003 19:39:06 -0000 X-pair-Authenticated: 64.246.81.227 Message-ID: <3E8DDF5A.5040005@electricjellyfish.net> Date: Fri, 04 Apr 2003 14:39:06 -0500 From: Garrett Rooney User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.3b) Gecko/20030130 X-Accept-Language: en-us, en MIME-Version: 1.0 To: John Baldwin References: In-Reply-To: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit cc: freebsd-smp@FreeBSD.org Subject: Re: atomic_dec_and_test() in FreeBSD? X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 19:39:09 -0000 John Baldwin wrote: >On 04-Apr-2003 Craig Rodrigues wrote: > > >>On Wed, Mar 26, 2003 at 12:13:21PM -0500, John Baldwin wrote: >> >> >>>>I am the port maintainer of the Apache Portable Runtime (apr) library. >>>>apr has some atomic functions. For FreeBSD, this is what is defined: >>>> >>>>/** >>>> * decrement the atomic variable by 1 >>>> * @param mem pointer to the atomic value >>>> * @return zero if the value is zero, otherwise non-zero >>>> */ >>>>int apr_atomic_dec(volatile apr_atomic_t *mem); >>>> >>>>[snip] >>>> >>>>#define apr_atomic_dec(mem) atomic_subtract_int(mem,1) >>>> >>>> >>>>This is obviously quite wrong. >>>> >>>>So are you saying that I should replace this with: >>>> >>>>int apr_atomic_dec(volatile apr_atomic_t *mem); >>>> >>>>int apr_atomic_dec(volatile apr_atomic_t *mem){ >>>> apr_atomic_t x >>>> do { >>>> x = *mem; >>>> } while (atomic_cmpset_int(mem, x, x - 1) == 0); >>>> if (x == 1) >>>> /* foo just dropped to zero */ >>>> >>>> >>>> ??????? >>>>} >>>> >>>>Can you give more guidance? >>>> >>>> >>>You could do this: >>> >>> apr_atomic_t x; >>> >>> do { >>> x = *mem; >>> } while (atomic_cmpset_int(mem, x, x - 1) == 0); >>> return (x - 1) >>> >>> >> >>This macro exists on -CURRENT, but I can't seem to find it >>on FreeBSD 4.7. What is the equivalent solution on that platform? >> >> > >4.7 doesn't have a real good equivalent. However, on 4.7 you can >probably just do: > > s = splhigh(); > x--; > zero = x == 0; > splx(s); > if (x == 0) > /* refcount is zero */ > >In fact, depending on what you do in the zero case, you probably >would need to do: > > s = splhigh(); > if (--x == 0) > /* refcount is zero, call free(), etc. */ > splx(s); > > > I believe Craig is looking for a user space solution, not kernel space. -garrett From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 11:45:56 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5E34037B401 for ; Fri, 4 Apr 2003 11:45:56 -0800 (PST) Received: from mail.speakeasy.net (mail15.speakeasy.net [216.254.0.215]) by mx1.FreeBSD.org (Postfix) with ESMTP id A1D7943F75 for ; Fri, 4 Apr 2003 11:45:55 -0800 (PST) (envelope-from jhb@FreeBSD.org) Received: (qmail 3356 invoked from network); 4 Apr 2003 19:46:00 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender )encrypted SMTP for ; 4 Apr 2003 19:46:00 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.12.8/8.12.8) with ESMTP id h34JjnOv031364; Fri, 4 Apr 2003 14:45:49 -0500 (EST) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.4 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <3E8DDF5A.5040005@electricjellyfish.net> Date: Fri, 04 Apr 2003 14:45:50 -0500 (EST) From: John Baldwin To: Garrett Rooney cc: freebsd-smp@FreeBSD.org Subject: Re: atomic_dec_and_test() in FreeBSD? X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 19:45:56 -0000 On 04-Apr-2003 Garrett Rooney wrote: > John Baldwin wrote: > >>On 04-Apr-2003 Craig Rodrigues wrote: >> >> >>>On Wed, Mar 26, 2003 at 12:13:21PM -0500, John Baldwin wrote: >>> >>> >>>>>I am the port maintainer of the Apache Portable Runtime (apr) library. >>>>>apr has some atomic functions. For FreeBSD, this is what is defined: >>>>> >>>>>/** >>>>> * decrement the atomic variable by 1 >>>>> * @param mem pointer to the atomic value >>>>> * @return zero if the value is zero, otherwise non-zero >>>>> */ >>>>>int apr_atomic_dec(volatile apr_atomic_t *mem); >>>>> >>>>>[snip] >>>>> >>>>>#define apr_atomic_dec(mem) atomic_subtract_int(mem,1) >>>>> >>>>> >>>>>This is obviously quite wrong. >>>>> >>>>>So are you saying that I should replace this with: >>>>> >>>>>int apr_atomic_dec(volatile apr_atomic_t *mem); >>>>> >>>>>int apr_atomic_dec(volatile apr_atomic_t *mem){ >>>>> apr_atomic_t x >>>>> do { >>>>> x = *mem; >>>>> } while (atomic_cmpset_int(mem, x, x - 1) == 0); >>>>> if (x == 1) >>>>> /* foo just dropped to zero */ >>>>> >>>>> >>>>> ??????? >>>>>} >>>>> >>>>>Can you give more guidance? >>>>> >>>>> >>>>You could do this: >>>> >>>> apr_atomic_t x; >>>> >>>> do { >>>> x = *mem; >>>> } while (atomic_cmpset_int(mem, x, x - 1) == 0); >>>> return (x - 1) >>>> >>>> >>> >>>This macro exists on -CURRENT, but I can't seem to find it >>>on FreeBSD 4.7. What is the equivalent solution on that platform? >>> >>> >> >>4.7 doesn't have a real good equivalent. However, on 4.7 you can >>probably just do: >> >> s = splhigh(); >> x--; >> zero = x == 0; >> splx(s); >> if (x == 0) >> /* refcount is zero */ >> >>In fact, depending on what you do in the zero case, you probably >>would need to do: >> >> s = splhigh(); >> if (--x == 0) >> /* refcount is zero, call free(), etc. */ >> splx(s); >> >> >> > > I believe Craig is looking for a user space solution, not kernel space. Argh, I couldn't remember. Well, one could always use a mutex to protect the count I suppose. One must be using some sort of threads library for this to even make sense in userland. -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 11:52:23 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8612C37B401 for ; Fri, 4 Apr 2003 11:52:23 -0800 (PST) Received: from relay.pair.com (relay.pair.com [209.68.1.20]) by mx1.FreeBSD.org (Postfix) with SMTP id 5DE5043F75 for ; Fri, 4 Apr 2003 11:52:22 -0800 (PST) (envelope-from rooneg@electricjellyfish.net) Received: (qmail 33673 invoked from network); 4 Apr 2003 19:52:21 -0000 Received: from softdnserror (HELO electricjellyfish.net) (64.246.81.227) by relay.pair.com with SMTP; 4 Apr 2003 19:52:21 -0000 X-pair-Authenticated: 64.246.81.227 Message-ID: <3E8DE275.6040000@electricjellyfish.net> Date: Fri, 04 Apr 2003 14:52:21 -0500 From: Garrett Rooney User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.3b) Gecko/20030130 X-Accept-Language: en-us, en MIME-Version: 1.0 To: John Baldwin References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit cc: freebsd-smp@FreeBSD.org Subject: Re: atomic_dec_and_test() in FreeBSD? X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 19:52:23 -0000 John Baldwin wrote: >>I believe Craig is looking for a user space solution, not kernel space. >> >> > >Argh, I couldn't remember. Well, one could always use a mutex to >protect the count I suppose. One must be using some sort of threads >library for this to even make sense in userland. > yeah, the default implementation of this function in APR uses mutexes to ensure that the increment is atomic, but craig is looking for a way to implement the 'platform specific faster way to do it without a mutex'. worst case, we can just use the default impl on freebsd 4.x and use atomic_cmpset_int on 5.x. -garrett From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 11:54:10 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1C0ED37B408; Fri, 4 Apr 2003 11:54:10 -0800 (PST) Received: from phoenix.infradead.org (phoenix.infradead.org [195.224.96.167]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9C63443FA3; Fri, 4 Apr 2003 11:54:07 -0800 (PST) (envelope-from hch@infradead.org) Received: from hch by phoenix.infradead.org with local (Exim 4.10) id 191XGH-0007jL-00; Fri, 04 Apr 2003 20:54:05 +0100 Date: Fri, 4 Apr 2003 20:54:05 +0100 From: Christoph Hellwig To: Garrett Rooney Message-ID: <20030404205405.A29698@infradead.org> References: <3E8DE275.6040000@electricjellyfish.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5.1i In-Reply-To: <3E8DE275.6040000@electricjellyfish.net>; from rooneg@electricjellyfish.net on Fri, Apr 04, 2003 at 02:52:21PM -0500 cc: freebsd-smp@FreeBSD.org cc: John Baldwin Subject: Re: atomic_dec_and_test() in FreeBSD? X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 19:54:10 -0000 On Fri, Apr 04, 2003 at 02:52:21PM -0500, Garrett Rooney wrote: > yeah, the default implementation of this function in APR uses mutexes to > ensure that the increment is atomic, but craig is looking for a way to > implement the 'platform specific faster way to do it without a mutex'. > worst case, we can just use the default impl on freebsd 4.x and use > atomic_cmpset_int on 5.x. Just FYI, the i386 atomic.h from Linux doesn't rely on any kernel features so you could in theory just copy it over. But I guess the licensing stand against this. From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 12:46:05 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8BE5037B401 for ; Fri, 4 Apr 2003 12:46:05 -0800 (PST) Received: from fledge.watson.org (fledge.watson.org [204.156.12.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id B5D2143FA3 for ; Fri, 4 Apr 2003 12:46:04 -0800 (PST) (envelope-from arr@watson.org) Received: from fledge.watson.org (localhost [127.0.0.1]) by fledge.watson.org (8.12.9/8.12.9) with ESMTP id h34KkPYX062787 for ; Fri, 4 Apr 2003 15:46:25 -0500 (EST) (envelope-from arr@watson.org) Received: from localhost (arr@localhost)h34KkOjB062784 for ; Fri, 4 Apr 2003 15:46:25 -0500 (EST) X-Authentication-Warning: fledge.watson.org: arr owned process doing -bs Date: Fri, 4 Apr 2003 15:46:24 -0500 (EST) From: "Andrew R. Reiter" To: freebsd-smp@freebsd.org Message-ID: <20030404153953.S62312@fledge.watson.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Subject: namecache X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 20:46:05 -0000 Helo Awhile back I shot a patch to this list for review that locked down some stuff in the namecache arena. I feel the patch was OK, but not great. What I want to do is something w/o any locks, but I dont feel I have a good enough grasp of that code base to do something really well since I know it would most likely require a rewrite of that code. I know solaris restructured their namecache implementation to do something similar. Tho, I am not sure about irix or others. To the point; anyone know of any good papers on this subject (namecache implementations)? Thanks, Andrew -- Andrew R. Reiter arr@watson.org arr@FreeBSD.org From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 13:56:39 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 095ED37B401 for ; Fri, 4 Apr 2003 13:56:39 -0800 (PST) Received: from imo-m05.mx.aol.com (imo-m05.mx.aol.com [64.12.136.8]) by mx1.FreeBSD.org (Postfix) with ESMTP id 51C9B43FB1 for ; Fri, 4 Apr 2003 13:56:38 -0800 (PST) (envelope-from TheLassoKing@aol.com) Received: from TheLassoKing@aol.com by imo-m05.mx.aol.com (mail_out_v34.21.) id n.1c3.7acf728 (4446) for ; Fri, 4 Apr 2003 16:56:32 -0500 (EST) From: TheLassoKing@aol.com Message-ID: <1c3.7acf728.2bbf5990@aol.com> Date: Fri, 4 Apr 2003 16:56:32 EST To: freebsd-smp@FreeBSD.org MIME-Version: 1.0 X-Mailer: 6.0 sub 10577 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit X-Content-Filtered-By: Mailman/MimeDel 2.1.1 Subject: SMP X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 21:56:39 -0000 SMP From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 14:00:14 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9928F37B401 for ; Fri, 4 Apr 2003 14:00:14 -0800 (PST) Received: from puffin.mail.pas.earthlink.net (puffin.mail.pas.earthlink.net [207.217.120.139]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1587643F3F for ; Fri, 4 Apr 2003 14:00:14 -0800 (PST) (envelope-from tlambert2@mindspring.com) Received: from pool0021.cvx22-bradley.dialup.earthlink.net ([209.179.198.21] helo=mindspring.com) by puffin.mail.pas.earthlink.net with asmtp (SSLv3:RC4-MD5:128) (Exim 3.33 #1) id 191ZEJ-00022j-00; Fri, 04 Apr 2003 14:00:12 -0800 Message-ID: <3E8E001C.B39BF3ED@mindspring.com> Date: Fri, 04 Apr 2003 13:58:52 -0800 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: "Andrew R. Reiter" References: <20030404153953.S62312@fledge.watson.org> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-ELNK-Trace: b1a02af9316fbb217a47c185c03b154d40683398e744b8a4e3bb364a9d9390abecbf53400910595e350badd9bab72f9c350badd9bab72f9c350badd9bab72f9c cc: freebsd-smp@freebsd.org Subject: Re: namecache X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 22:00:14 -0000 "Andrew R. Reiter" wrote: > Awhile back I shot a patch to this list for review that locked down some > stuff in the namecache arena. I feel the patch was OK, but not great. > > What I want to do is something w/o any locks, but I dont feel I have a > good enough grasp of that code base to do something really well since I > know it would most likely require a rewrite of that code. I know solaris > restructured their namecache implementation to do something similar. Tho, > I am not sure about irix or others. > > To the point; anyone know of any good papers on this subject (namecache > implementations)? Solaris Internals: Core Kernel Architecture Jim Mauro, Richard McDougall Prentice Hall ISBN: 0130224960 The Magic Garden Explained: The Internals of Unix System V Release 4: An Open Systems Design Berny Goodheart, James Cox, John R. Mashey Prentice Hall ISBN: 0130981389 The first one has a discussion of the structures and how they got rid of the locks in Solaris (they got rid of the LRU, as a list). Note: Both refer to it as "DNLC" or "Directory Name Lookup Cache". -- Terry From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 14:03:36 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9123137B401 for ; Fri, 4 Apr 2003 14:03:36 -0800 (PST) Received: from fledge.watson.org (fledge.watson.org [204.156.12.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id C8AD243F75 for ; Fri, 4 Apr 2003 14:03:35 -0800 (PST) (envelope-from arr@watson.org) Received: from fledge.watson.org (localhost [127.0.0.1]) by fledge.watson.org (8.12.9/8.12.9) with ESMTP id h34M3uYX063440; Fri, 4 Apr 2003 17:03:56 -0500 (EST) (envelope-from arr@watson.org) Received: from localhost (arr@localhost)h34M3uvo063437; Fri, 4 Apr 2003 17:03:56 -0500 (EST) X-Authentication-Warning: fledge.watson.org: arr owned process doing -bs Date: Fri, 4 Apr 2003 17:03:55 -0500 (EST) From: "Andrew R. Reiter" To: Terry Lambert In-Reply-To: <3E8E001C.B39BF3ED@mindspring.com> Message-ID: <20030404170317.K63340@fledge.watson.org> References: <20030404153953.S62312@fledge.watson.org> <3E8E001C.B39BF3ED@mindspring.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII cc: freebsd-smp@freebsd.org Subject: Re: namecache X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 22:03:36 -0000 On Fri, 4 Apr 2003, Terry Lambert wrote: :"Andrew R. Reiter" wrote: :> Awhile back I shot a patch to this list for review that locked down some :> stuff in the namecache arena. I feel the patch was OK, but not great. :> :> What I want to do is something w/o any locks, but I dont feel I have a :> good enough grasp of that code base to do something really well since I :> know it would most likely require a rewrite of that code. I know solaris :> restructured their namecache implementation to do something similar. Tho, :> I am not sure about irix or others. :> :> To the point; anyone know of any good papers on this subject (namecache :> implementations)? : : Solaris Internals: Core Kernel Architecture : Jim Mauro, Richard McDougall : Prentice Hall : ISBN: 0130224960 : : The Magic Garden Explained: The Internals of Unix : System V Release 4: An Open Systems Design : Berny Goodheart, James Cox, John R. Mashey : Prentice Hall : ISBN: 0130981389 : :The first one has a discussion of the structures and how they got :rid of the locks in Solaris (they got rid of the LRU, as a list). : :Note: Both refer to it as "DNLC" or "Directory Name Lookup Cache". I read the stuff in the Solaris book (I've got that one), but I've not read the section in Magic Garden (despite owning it as well). I'll read further. Thanks! Andrew -- Andrew R. Reiter arr@watson.org arr@FreeBSD.org From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 14:53:45 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C670E37B401 for ; Fri, 4 Apr 2003 14:53:45 -0800 (PST) Received: from stork.mail.pas.earthlink.net (stork.mail.pas.earthlink.net [207.217.120.188]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2EB6E43FBF for ; Fri, 4 Apr 2003 14:53:45 -0800 (PST) (envelope-from tlambert2@mindspring.com) Received: from pool0021.cvx22-bradley.dialup.earthlink.net ([209.179.198.21] helo=mindspring.com) by stork.mail.pas.earthlink.net with asmtp (SSLv3:RC4-MD5:128) (Exim 3.33 #1) id 191a45-0000Jy-00; Fri, 04 Apr 2003 14:53:42 -0800 Message-ID: <3E8E0CA7.E21BA871@mindspring.com> Date: Fri, 04 Apr 2003 14:52:23 -0800 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: "Andrew R. Reiter" References: <20030404153953.S62312@fledge.watson.org> <3E8E001C.B39BF3ED@mindspring.com> <20030404170317.K63340@fledge.watson.org> Content-Type: text/plain; charset=EUC-KR Content-Transfer-Encoding: 7bit X-ELNK-Trace: b1a02af9316fbb217a47c185c03b154d40683398e744b8a47ee1eb3b3c88b9af779f4e5b90c3bd75350badd9bab72f9c350badd9bab72f9c350badd9bab72f9c cc: freebsd-smp@freebsd.org Subject: Re: namecache X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Apr 2003 22:53:46 -0000 "Andrew R. Reiter" wrote: > On Fri, 4 Apr 2003, Terry Lambert wrote: > :"Andrew R. Reiter" wrote: > :> Awhile back I shot a patch to this list for review that locked down some > :> stuff in the namecache arena. I feel the patch was OK, but not great. > :> > :> What I want to do is something w/o any locks, but I dont feel I have a > :> good enough grasp of that code base to do something really well since I > :> know it would most likely require a rewrite of that code. I think the rewrite will be necessary. It should be very easy, just knowing the Solaris data structures. For both the Solaris and SVR4 DNLC, the one thing I would caution you against is a *really* blind reimplementation. The SVR4 code, with which I am very familiar, did not allow entries with a NULL vp for the lookup target. In point of face, you should allow this. The reason is that a negative cache is twice as valuable as a postive cache, for any list of data that must be linearly iterated. The reason is that, on a hit, you iterate, on average 50% of the entries before you find the one you are looking for; on a miss, you must iterate all 100% of the entries, to make sure they are not the one. As a common example, as you look for a file before you go to create it; when this happens, you iterate all directory entries in the directory in which the create is taking place, and you do not find the item. So you go to create it; the insertion algorithm *again* iterates it, because it does not know if it is a create or replace operation. If you had a cache entry, it would still need to iterate the entries, but it could avoid the compare operation that would otherwise be necessary, and only look for free space to put the entry. A possible optimization would cache the offset of a first-fit entry in the NULL vp valued DNLC entry. This gives you a search start point for the insert which is "likely" to still be valid, and you can search from that point onward, because the earlier entries are likely to remain "too small". Maybe it should be bounded against "cache poisoning" (e.g. you should maybe limit the total number of negative entries to some maximum less than the size of the whole cache). Not sure this is valid, since you could "poison" with positive entries, too. Another possible optimization, which may be no good on FreeBSD is to add entries on traversal. This optimization is best suited to Samba, Appletalk, and similar servers, which expect the directory entry to be identical to the inode, so you have to have the inode information available immediately following knowing the directory entry is there. You'd only do this in the VOP_READDIR iteration case, not everywhere you iterate for just one file lookup, but it will gain you at least 15% performance on diretory operations on a file server for PC's (such servers iterate, then stat each file to get stat data to return both stat data and names as a single block of "file entry information"). > I read the stuff in the Solaris book (I've got that one), but I've not > read the section in Magic Garden (despite owning it as well). > > I'll read further. Really, either one is enough to write the implementation. The SVR4 book has API definitions, though, so it might be useful to you to use both books, if you are having trouble, and don't want to use the BSD namecache API for some reason. > Thanks! You're welcome. -- Terry From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 18:33:10 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C67F637B401 for ; Fri, 4 Apr 2003 18:33:10 -0800 (PST) Received: from web11507.mail.yahoo.com (web11507.mail.yahoo.com [216.136.172.39]) by mx1.FreeBSD.org (Postfix) with SMTP id 5C14143F3F for ; Fri, 4 Apr 2003 18:33:10 -0800 (PST) (envelope-from gesperon@yahoo.com) Message-ID: <20030405023310.37582.qmail@web11507.mail.yahoo.com> Received: from [200.55.139.109] by web11507.mail.yahoo.com via HTTP; Fri, 04 Apr 2003 18:33:10 PST Date: Fri, 4 Apr 2003 18:33:10 -0800 (PST) From: Gabor Esperon To: "Cagle, John (ISS-Houston)" In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii cc: freebsd-smp@freebsd.org Subject: RE: DUAL XEON 2.40Mhz SMP APIC_IO Troubles X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 05 Apr 2003 02:33:11 -0000 Hi!!! Thanks for anwser me... today me FreeBSD system was upgraded to -current and it is working very well but the "options HTT" line is not yet recognized by config(8)... why?? --- "Cagle, John (ISS-Houston)" wrote: > If you're using -current (which has a patch for this > issue) you'll need > to also enable HTT. > > > -----Original Message----- > > From: Gabor Esperon [mailto:gesperon@yahoo.com] > > Sent: Thursday, April 03, 2003 7:56 PM > > To: freebsd-smp@freebsd.org > > Subject: DUAL XEON 2.40Mhz SMP APIC_IO Troubles > > > > > > Hi!!! > > > > I have a ProLiant Dual XEON at 2.4Mhz running > FreeBSD > > 5.0 configured as it follows: > > > > machine i386 > > cpu I686_CPU > > options SMP > > options APIC_IO > > > > But every time the system boots stop running at > kernel > > message: "APIC_IO: Testing 8254 Interrupt > > Delivery".... and go freezed forever. > > > > Does someone have a tip or solution???? > > > > ===== > > Gabor > > Net/Sys Admin > > > > __________________________________________________ > > Do you Yahoo!? > > Yahoo! Tax Center - File online, calculators, > forms, and more > http://tax.yahoo.com > _______________________________________________ > freebsd-smp@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-smp > To unsubscribe, send any mail to "freebsd-smp-unsubscribe@freebsd.org" ===== Gabor Net/Sys Admin __________________________________________________ Do you Yahoo!? Yahoo! Tax Center - File online, calculators, forms, and more http://tax.yahoo.com From owner-freebsd-smp@FreeBSD.ORG Fri Apr 4 18:36:06 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id EF00B37B401 for ; Fri, 4 Apr 2003 18:36:06 -0800 (PST) Received: from odin.ac.hmc.edu (Odin.AC.HMC.Edu [134.173.32.75]) by mx1.FreeBSD.org (Postfix) with ESMTP id 60BA843FA3 for ; Fri, 4 Apr 2003 18:36:06 -0800 (PST) (envelope-from brdavis@odin.ac.hmc.edu) Received: from odin.ac.hmc.edu (IDENT:brdavis@localhost.localdomain [127.0.0.1]) by odin.ac.hmc.edu (8.12.8/8.12.3) with ESMTP id h352a1LA012903; Fri, 4 Apr 2003 18:36:01 -0800 Received: (from brdavis@localhost) by odin.ac.hmc.edu (8.12.8/8.12.3/Submit) id h352a1g3012900; Fri, 4 Apr 2003 18:36:01 -0800 Date: Fri, 4 Apr 2003 18:36:01 -0800 From: Brooks Davis To: Gabor Esperon Message-ID: <20030404183601.A9585@Odin.AC.HMC.Edu> References: <20030405023310.37582.qmail@web11507.mail.yahoo.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-md5; protocol="application/pgp-signature"; boundary="CE+1k2dSO48ffgeK" Content-Disposition: inline User-Agent: Mutt/1.2.5.1i In-Reply-To: <20030405023310.37582.qmail@web11507.mail.yahoo.com>; from gesperon@yahoo.com on Fri, Apr 04, 2003 at 06:33:10PM -0800 X-Virus-Scanned: by amavisd-milter (http://amavis.org/) on odin.ac.hmc.edu cc: freebsd-smp@freebsd.org Subject: Re: DUAL XEON 2.40Mhz SMP APIC_IO Troubles X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 05 Apr 2003 02:36:07 -0000 --CE+1k2dSO48ffgeK Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, Apr 04, 2003 at 06:33:10PM -0800, Gabor Esperon wrote: > Hi!!! >=20 > Thanks for anwser me... today me FreeBSD system was > upgraded to -current and it is working very well but > the "options HTT" line is not yet recognized by > config(8)... why?? It was removed. You can choose to enable or disable the use of logical CPUs with the machdep.hlt_logical_cpus sysctl. -- Brooks --=20 Any statement of the form "X is the one, true Y" is FALSE. PGP fingerprint 655D 519C 26A7 82E7 2529 9BF0 5D8E 8BE9 F238 1AD4 --CE+1k2dSO48ffgeK Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.1 (GNU/Linux) iD8DBQE+jkEQXY6L6fI4GtQRAnF8AKDik22pEYpo7K0q8gFUoo7mv/amMgCfav+q PJjOuDxKUiFEzr6RoLEuG7I= =lUgs -----END PGP SIGNATURE----- --CE+1k2dSO48ffgeK--