From owner-freebsd-smp Sun Aug 11 22:19:28 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id WAA01646 for smp-outgoing; Sun, 11 Aug 1996 22:19:28 -0700 (PDT) Received: from parkplace.cet.co.jp (parkplace.cet.co.jp [202.32.64.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id WAA01631 for ; Sun, 11 Aug 1996 22:19:24 -0700 (PDT) Received: from localhost (michaelh@localhost) by parkplace.cet.co.jp (8.7.5/CET-v2.1) with SMTP id FAA07166; Mon, 12 Aug 1996 05:19:17 GMT Date: Mon, 12 Aug 1996 14:19:17 +0900 (JST) From: Michael Hancock To: freebsd-fs@freebsd.org cc: freebsd-smp@freefall.freebsd.org Subject: lockmgr In-Reply-To: <199608100908.CAA25008@freefall.freebsd.org> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I came across this link by accident. It describes lockmgr. http://www.sigmasoft.com/~tholo/Locking.html Regards, Mike Hancock From owner-freebsd-smp Mon Aug 12 08:46:04 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA25071 for smp-outgoing; Mon, 12 Aug 1996 08:46:04 -0700 (PDT) Received: from phaeton.artisoft.com (phaeton.Artisoft.COM [198.17.250.211]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id IAA25048 for ; Mon, 12 Aug 1996 08:45:43 -0700 (PDT) Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id IAA25328; Mon, 12 Aug 1996 08:40:12 -0700 From: Terry Lambert Message-Id: <199608121540.IAA25328@phaeton.artisoft.com> Subject: Re: lockmgr To: michaelh@cet.co.jp (Michael Hancock) Date: Mon, 12 Aug 1996 08:40:12 -0700 (MST) Cc: freebsd-fs@freebsd.org, freebsd-smp@freefall.freebsd.org In-Reply-To: from "Michael Hancock" at Aug 12, 96 02:19:17 pm X-Mailer: ELM [version 2.4 PL24] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > > I came across this link by accident. It describes lockmgr. > > http://www.sigmasoft.com/~tholo/Locking.html > Pretty cool; thanks. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. From owner-freebsd-smp Tue Aug 13 04:04:55 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id EAA07232 for smp-outgoing; Tue, 13 Aug 1996 04:04:55 -0700 (PDT) Received: from ceylon.informatik.uni-rostock.de (ceylon.informatik.uni-rostock.de [139.30.5.237]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id EAA07197; Tue, 13 Aug 1996 04:04:42 -0700 (PDT) Received: by ceylon.informatik.uni-rostock.de id NAA24919; Tue, 13 Aug 1996 13:04:38 +0200 Received: by donau.informatik.uni-rostock.de id NAA00326; Tue, 13 Aug 1996 13:04:37 +0200 Date: Tue, 13 Aug 1996 13:04:37 +0200 From: Gunther Hipper Message-Id: <199608131104.NAA00326@donau.informatik.uni-rostock.de> To: freebsd-smp@FreeBSD.ORG, freebsd-hackers@FreeBSD.ORG, freebsd-hardware@FreeBSD.ORG Subject: Anyone Experiences with Intel TXC Chipset or GA-586DX/GA-586HX motherboard ?? Cc: gunther@ceylon.informatik.uni-rostock.de X-Sun-Charset: US-ASCII Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi to you all ! I've a certain problem because I would like to buy new motherboards which should be albe to run FreeBSD. The boards are Gigabyte GA-586HX and/or GA-586DX both (hopefully) state of the art ... but I don't yet know any guy using them. The Chipset is an Intel TXC 82439HX Rev.01h in both boards. Until now, we always used Gigabyte boards - everything works fine with GA-486DX and GA-486ATE (Triton Chipset). Now my questions: Is anyone using one or both of these boards ? Are there any problems or are certain problems to be expected running FreeBSD ? Mention: I do _not_ explicitly care about SMP on the GA-586DX Dual-CPU-Slot board. If it's running - okay, but for the moment a single processor should be enough. Propably, the board should be Intel-SMP conform. This is an Intel chipset, hell, is'nt it ? I'd be glad if someone could give me some hints. Gunther Gunther Hipper | University of Rostock | Department of Computer Science | Tel +49 381 498 3391 Albert-Einstein-Str. 21 | Fax +49 381 498 3440 18051 Rostock - Germany | Email Gunther.Hipper@informatik.uni-rostock.de From owner-freebsd-smp Fri Aug 16 10:24:40 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA01468 for smp-outgoing; Fri, 16 Aug 1996 10:24:40 -0700 (PDT) Received: from groa.uct.ac.za (groa.uct.ac.za [137.158.128.7]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id KAA01455 for ; Fri, 16 Aug 1996 10:24:35 -0700 (PDT) From: rv@groa.uct.ac.za Received: by groa.uct.ac.za via sendmail with stdio id for freebsd-smp@freebsd.org; Fri, 16 Aug 1996 19:24:31 +0200 (SAT) (Smail-3.2 1996-Jul-4 #1 built 1996-Jul-21) Message-Id: Subject: SMP on Intel MG15 To: freebsd-smp@freebsd.org Date: Fri, 16 Aug 1996 19:24:30 +0200 (SAT) X-Mailer: ELM [version 2.4 PL25] Content-Type: text Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, I have just received an Intel Xtended Xpress/MG15 with dual P54C-133 Pentiums on loan for 2 weeks and would like to try out FreeBSD's SMP code on it. Is the code in a state to test and if so, where can I find it. I am also willing to give logins if you would like to do any testing yourself - assuming you are doing the SMP development. The only drawback is that our Internet link is quite loaded, so to be worth anything you will get best response from 22:00-05:00 GMT. This machine is quite a beast with dual PCI bus, onboard AHA2940 (dual) and various other nice features. I believe this motherboard is used in top end HP and Compaq Pentium servers. In my preliminary setup with 2.1.5-RELEASE, the kernel doesn't detect the extra PCI bus (even with an extra pci1 in the kernel config) - perhaps I have missed something, so will dig a little deeper. -Russell From owner-freebsd-smp Fri Aug 16 11:28:55 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA05418 for smp-outgoing; Fri, 16 Aug 1996 11:28:55 -0700 (PDT) Received: from smtp-gw01.ny.us.ibm.net (smtp-gw01.ny.us.ibm.net [165.87.194.252]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id LAA05413 for ; Fri, 16 Aug 1996 11:28:50 -0700 (PDT) Received: (from uucp@localhost) by smtp-gw01.ny.us.ibm.net (8.6.9/8.6.9) id SAA49990; Fri, 16 Aug 1996 18:28:32 GMT Date: Fri, 16 Aug 1996 18:28:32 GMT Received: from slip139-92-60-114.zu.ch.ibm.net(139.92.60.114) by smtp-gw01.ny.us.ibm.net via smap (V1.3mjr) id sma%PoDmb; Fri Aug 16 18:26:58 1996 Message-ID: X-Mailer: XFMail 0.3-beta [p0] on FreeBSD In-Reply-To: Reply-To: ofehr@access.ch From: Oliver Fehr To: Subject: RE: SMP on Intel MG15 Cc: Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Fri Aug 16 19:24:30 1996 rv@groa.uct.ac.za wrote: >>Hi, > >I have just received an Intel Xtended Xpress/MG15 with dual >P54C-133 Pentiums on loan for 2 weeks and would like to try >out FreeBSD's SMP code on it. Is the code in a state to test >and if so, where can I find it. > >I am also willing to give logins if you would like to do any >testing yourself - assuming you are doing the SMP development. >The only drawback is that our Internet link is quite loaded, so >to be worth anything you will get best response from 22:00-05:00 >GMT. > >This machine is quite a beast with dual PCI bus, onboard AHA2940 >(dual) and various other nice features. I believe this motherboard >is used in top end HP and Compaq Pentium servers. In my preliminary >setup with 2.1.5-RELEASE, the kernel doesn't detect the extra PCI >bus (even with an extra pci1 in the kernel config) - perhaps I >have missed something, so will dig a little deeper. > > -Russell Hi Russel You can find the code at ftp://freefall.freebsd.org/pub/smp. I've just started looking at it, so I can't really say if it works. I will try to test it on a dec celebris dp 133 running FreeBSD-2.2-960501-SNAP (yes I know, it's outdated, but it's working so far). cheers Oliver From owner-freebsd-smp Fri Aug 16 11:54:35 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA07262 for smp-outgoing; Fri, 16 Aug 1996 11:54:35 -0700 (PDT) Received: from bacall.lodgenet.com (bacall.lodgenet.com [205.138.147.242]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id LAA07252 for ; Fri, 16 Aug 1996 11:54:28 -0700 (PDT) Received: (from mail@localhost) by bacall.lodgenet.com (8.6.12/8.6.12) id NAA20578; Fri, 16 Aug 1996 13:53:20 -0500 Received: from garbo.lodgenet.com(204.124.123.250) by bacall via smap (V1.3) id sma020576; Fri Aug 16 13:53:19 1996 Received: from jake.lodgenet.com (jake.lodgenet.com [204.124.120.30]) by garbo.lodgenet.com (8.6.12/8.6.9) with ESMTP id NAA02345; Fri, 16 Aug 1996 13:53:27 -0500 Received: from localhost (localhost [127.0.0.1]) by jake.lodgenet.com (8.7.5/8.6.12) with SMTP id NAA07229; Fri, 16 Aug 1996 13:53:45 -0500 (CDT) Message-Id: <199608161853.NAA07229@jake.lodgenet.com> X-Authentication-Warning: jake.lodgenet.com: Host localhost [127.0.0.1] didn't use HELO protocol X-Mailer: exmh version 1.6.2 7/18/95 To: ofehr@access.ch cc: rv@groa.uct.ac.za, freebsd-smp@freebsd.org Subject: Re: SMP on Intel MG15 In-reply-to: Your message of "Fri, 16 Aug 1996 18:28:32 GMT." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Fri, 16 Aug 1996 13:53:45 -0500 From: "Eric L. Hernes" Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Oliver Fehr writes: > >You can find the code at ftp://freefall.freebsd.org/pub/smp. > Yikes, that stuff is really old, try this in a supfile: src-sys release=smp host=sup.FreeBSD.org hostbase=/home base=/usr prefix=/usr/src/smp/cvs delete old use-rel-suffix I'm running on a dual P-90 Titan-II, haven't had a panic all week! > >cheers Oliver > eric. -- erich@lodgenet.com http://rrnet.com/~erich erich@rrnet.com From owner-freebsd-smp Fri Aug 16 12:08:11 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA08235 for smp-outgoing; Fri, 16 Aug 1996 12:08:11 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.DIALix.COM [192.203.228.67]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id MAA08230 for ; Fri, 16 Aug 1996 12:08:06 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.7.5/8.7.3) with ESMTP id DAA15302; Sat, 17 Aug 1996 03:06:31 +0800 (WST) Message-Id: <199608161906.DAA15302@spinner.DIALix.COM> X-Mailer: exmh version 1.6.6 3/24/96 To: "Eric L. Hernes" cc: ofehr@access.ch, rv@groa.uct.ac.za, freebsd-smp@freebsd.org Subject: Re: SMP on Intel MG15 In-reply-to: Your message of "Fri, 16 Aug 1996 13:53:45 EST." <199608161853.NAA07229@jake.lodgenet.com> Date: Sat, 17 Aug 1996 03:06:30 +0800 From: Peter Wemm Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk "Eric L. Hernes" wrote: > Oliver Fehr writes: > > > >You can find the code at ftp://freefall.freebsd.org/pub/smp. > > > Yikes, that stuff is really old, try this in a supfile: > > src-sys release=smp host=sup.FreeBSD.org hostbase=/home base=/usr > prefix=/usr/src/smp/cvs delete old use-rel-suffix > > I'm running on a dual P-90 Titan-II, haven't had a panic all week! > > > > >cheers Oliver > > > > eric. BTW, I just updated the majordomo 'info' file for this list: ========= FREEBSD-SMP Tech discussion list for those involved in implementing SMP support under FreeBSD. Not for the casual reader, this is only likely to be of use to the developers. Note that this list gets some rather long commit messages! The last few were over 40K each. To get the code, you need a supfile entry something like this: src-sys release=smp host=sup.FreeBSD.org hostbase=/home base=/home/smp \ prefix=/home/smp delete old use-rel-suffix (I dont think the line can be broken with a backslash, make sure it's all one long line in your supfile) This will fetch the CVS repository files into the /home/smp directory on your machine. Note that sup is very inefficient on this repository as it fetches the entire file whenever the file changes in any way. Alternatively, you can fetch the deltas via CTM from ftp://freefall.freebsd.org:/pub/CTM/smp-cur/* CTM is far more efficient with network traffic and only sends CHANGES between file revisions, not the entire file like sup. The other alternatives are to get cvsup, it works just like sup, but has CTM's efficiency. see ftp://freefall.freebsd.org/pub/CVSup/* Lastly, if you have an account with commit access on freefall, you can set your CVSROOT to /home/smp. Like the main repository, you can access it remotely. Once you set up rsh or ssh to your freefall account, you can (on your local machine) set your CVSROOT to yourname@freefall.freebsd.org:/home/smp and simply "cvs checkout -P sys". If you don't know how to drive sup/ctm/cvsup and can't figure it out from the manuals, you are probably looking at the wrong list.. As always, remember this is ALPHA-grade software. Expect it to crash and burn every so often. It doesn't yet work on all MPSPEC compliant hardware. It's only "known" to work on older ASUS PCI/E P54NP4 dual-pentium motherboard. Others have reported success on other hardware, but nobody has a complete list. Other than that, Welcome aboard! ========= Cheers, -Peter From owner-freebsd-smp Fri Aug 16 12:48:36 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA11089 for smp-outgoing; Fri, 16 Aug 1996 12:48:36 -0700 (PDT) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id MAA11082 for ; Fri, 16 Aug 1996 12:48:33 -0700 (PDT) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id NAA11760; Fri, 16 Aug 1996 13:47:30 -0600 Message-Id: <199608161947.NAA11760@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: Peter Wemm cc: "Eric L. Hernes" , ofehr@access.ch, rv@groa.uct.ac.za, freebsd-smp@freebsd.org Subject: Re: SMP on Intel MG15 In-reply-to: Your message of "Sat, 17 Aug 1996 03:06:30 +0800." <199608161906.DAA15302@spinner.DIALix.COM> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Fri, 16 Aug 1996 13:47:30 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > BTW, I just updated the majordomo 'info' file for this list: It would be helpful if the smp mailing list were added to the FreeBSD mail-list search page. > As always, remember this is ALPHA-grade software. Expect it to crash > and burn every so often. It doesn't yet work on all MPSPEC compliant > hardware. It's only "known" to work on older ASUS PCI/E P54NP4 > dual-pentium motherboard. Others have reported success on other hardware, > but nobody has a complete list. So lets start a list. I have been running it for several weeks on a gigabyte GA586DX512, which is a dual 75/200mHz ATX formfactor board. I am using it with 2 P5 133mHz parts, type SU022. Problems that I have noticed: 1: must disable 2nd CPU b4 'halt'ing or disks never sync. 2: SIGFPE sometimes wedges the system. 3: some things take significantly LONGER to run. make world takes about 45 minutes longer for me to do with the second CPU enabled. 4: the 'time' command can't be trusted, sometinmes I see times that are completely wrong. On the other hand it seems quite stable (other than the above problems) and stays up for me till halted. It runs X11, has done many 'make world's without complaint, and does the network thing just fine. I've offered before, and offer again, if there's anything I can do to help with development please let me know! -- Steve Passe | powered by smp@csn.net | FreeBSD From owner-freebsd-smp Fri Aug 16 13:31:12 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA13996 for smp-outgoing; Fri, 16 Aug 1996 13:31:12 -0700 (PDT) Received: from tripe.macc.wisc.edu (tripe.macc.wisc.edu [144.92.30.192]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id NAA13987 for ; Fri, 16 Aug 1996 13:31:08 -0700 (PDT) Received: (from jeffb@localhost) by tripe.macc.wisc.edu (8.7.5/8.7.3) id PAA20222 for freebsd-smp@freebsd.org; Fri, 16 Aug 1996 15:31:03 -0500 (CDT) Message-Id: <199608162031.PAA20222@tripe.macc.wisc.edu> Subject: Re: SMP on Intel MG15 To: freebsd-smp@freebsd.org Date: Fri, 16 Aug 1996 15:31:01 -0500 (CDT) From: "Jeff Bartig" In-Reply-To: <199608161906.DAA15302@spinner.DIALix.COM> from "Peter Wemm" at Aug 17, 96 03:06:30 am X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Peter Wemm said: > BTW, I just updated the majordomo 'info' file for this list: > ========= > FREEBSD-SMP ..... > As always, remember this is ALPHA-grade software. Expect it to crash > and burn every so often. It doesn't yet work on all MPSPEC compliant > hardware. It's only "known" to work on older ASUS PCI/E P54NP4 > dual-pentium motherboard. Others have reported success on other hardware, > but nobody has a complete list. Is anyone using a dual processor Pentium Pro board? I'm about to get a new system (the last one I'll probably get for a long time, so it will be something fast). Our PC hardware person is recommending a Supermicro P6DNE (similar to the P6DNF, from what I've been told). Is anyone using these boards? Any recommendations on other P6 boards? Jeff -- Jeff Bartig | University of Wisconsin - Madison 1210 W Dayton, Rm 3219 | Division of Information Technology Work Phone: (608) 262-8336 | Network Engineering Technology E-Mail: jeffb@doit.wisc.edu | From owner-freebsd-smp Fri Aug 16 14:36:06 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA20074 for smp-outgoing; Fri, 16 Aug 1996 14:36:06 -0700 (PDT) Received: (from jmb@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA20053; Fri, 16 Aug 1996 14:36:02 -0700 (PDT) From: "Jonathan M. Bresler" Message-Id: <199608162136.OAA20053@freefall.freebsd.org> Subject: FreeBSD-smp now accepts messages of 100,000 bytes To: peter@spinner.dialix.com (Peter Wemm) Date: Fri, 16 Aug 1996 14:36:01 -0700 (PDT) Cc: erich@lodgenet.com, ofehr@access.ch, rv@groa.uct.ac.za, freebsd-smp@freebsd.org In-Reply-To: <199608161906.DAA15302@spinner.DIALix.COM> from "Peter Wemm" at Aug 17, 96 03:06:30 am X-Mailer: ELM [version 2.4 PL24] Content-Type: text Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > Note that this list gets some rather long commit messages! The last few > were over 40K each. i have reconfigured the list for messages of upto 100,000 bytes. jmb -- Jonathan M. Bresler FreeBSD Postmaster jmb@FreeBSD.ORG FreeBSD--4.4BSD Unix for PC clones, source included. http://www.freebsd.org/ PGP 2.6.2 Fingerprint: 31 57 41 56 06 C1 40 13 C5 1C E3 E5 DC 62 0E FB From owner-freebsd-smp Fri Aug 16 14:54:13 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA21374 for smp-outgoing; Fri, 16 Aug 1996 14:54:13 -0700 (PDT) Received: from critter.tfs.com ([140.145.230.177]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id OAA21358; Fri, 16 Aug 1996 14:54:09 -0700 (PDT) Received: from critter.tfs.com (localhost.tfs.com [127.0.0.1]) by critter.tfs.com (8.7.5/8.7.3) with ESMTP id XAA02975; Fri, 16 Aug 1996 23:53:37 +0200 (MET DST) To: "Jeff Bartig" cc: freebsd-smp@freebsd.org Subject: Re: SMP on Intel MG15 In-reply-to: Your message of "Fri, 16 Aug 1996 15:31:01 CDT." <199608162031.PAA20222@tripe.macc.wisc.edu> Date: Fri, 16 Aug 1996 23:53:36 +0200 Message-ID: <2973.840232416@critter.tfs.com> From: Poul-Henning Kamp Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >Is anyone using a dual processor Pentium Pro board? I tried it on a HP a month ago. quite nice. -- Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. whois: [PHK] | phk@ref.tfs.com TRW Financial Systems, Inc. Future will arrive by its own means, progress not so. From owner-freebsd-smp Sat Aug 17 05:16:25 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id FAA21296 for smp-outgoing; Sat, 17 Aug 1996 05:16:25 -0700 (PDT) Received: from groa.uct.ac.za (groa.uct.ac.za [137.158.128.7]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id FAA21291 for ; Sat, 17 Aug 1996 05:16:22 -0700 (PDT) From: rv@groa.uct.ac.za Received: by groa.uct.ac.za via sendmail with stdio id for freebsd-smp@freebsd.org; Sat, 17 Aug 1996 14:16:19 +0200 (SAT) (Smail-3.2 1996-Jul-4 #1 built 1996-Jul-21) Message-Id: Subject: Re: SMP on Intel MG15 To: freebsd-smp@freebsd.org Date: Sat, 17 Aug 1996 14:16:18 +0200 (SAT) In-Reply-To: from "rv@groa.uct.ac.za" at Aug 16, 96 07:24:30 pm X-Mailer: ELM [version 2.4 PL25] Content-Type: text Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I wrote: > I have just received an Intel Xtended Xpress/MG15 with dual > P54C-133 Pentiums on loan for 2 weeks and would like to try > out FreeBSD's SMP code on it. Is the code in a state to test > and if so, where can I find it. Many thanks for all the info. A status report: 1) The SMP kernel doesn't compile if you have: options "I586_FAST_BCOPY" (Not serious, I just removed it) 2) The machine locks up shortly after the SMP kernel load: FreeBSD/SMP: Multiprocessor motherboard Boot cpunumber=0x0 [ machines freezes ] I presume this means that the machine is reporting the number of CPUs in a non-recognised format. APIC supports appears to be enabled in the BIOS. -Russell From owner-freebsd-smp Sat Aug 17 08:07:16 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA29756 for smp-outgoing; Sat, 17 Aug 1996 08:07:16 -0700 (PDT) Received: from al.imforei.apana.org.au (root@al.imforei.apana.org.au [202.12.89.41]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id IAA29750 for ; Sat, 17 Aug 1996 08:07:09 -0700 (PDT) Received: (from pjchilds@localhost) by al.imforei.apana.org.au (8.7.5/8.7.3) id AAA28573; Sun, 18 Aug 1996 00:36:57 +0930 (CST) Date: Sun, 18 Aug 1996 00:36:57 +0930 (CST) From: Peter Childs Message-Id: <199608171506.AAA28573@al.imforei.apana.org.au> To: rv@groa.uct.ac.za, freebsd-smp@freebsd.org Subject: Re: SMP on Intel MG15 X-Newsreader: TIN [version 1.2 PL2] Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk In article <4v4ddu$n7q@al.imforei.apana.org.au> you wrote: : 2) The machine locks up shortly after the SMP kernel load: : FreeBSD/SMP: Multiprocessor motherboard : Boot cpunumber=0x0 : [ machines freezes ] : I presume this means that the machine is reporting the number of : CPUs in a non-recognised format. APIC supports appears to be : enabled in the BIOS. Don't you need to put the number of cpu's in the kernel config? Check the mailing list archive for SMP and i think you'll find that you do. Peter -- Peter Childs --- http://www.imforei.apana.org.au/~pjchilds Finger pjchilds@al.imforei.apana.org.au for public PGP key From owner-freebsd-smp Sat Aug 17 10:36:53 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA05796 for smp-outgoing; Sat, 17 Aug 1996 10:36:53 -0700 (PDT) Received: from groa.uct.ac.za (groa.uct.ac.za [137.158.128.7]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id KAA05790 for ; Sat, 17 Aug 1996 10:36:49 -0700 (PDT) From: rv@groa.uct.ac.za Received: by groa.uct.ac.za via sendmail with stdio id for freebsd-smp@freebsd.org; Sat, 17 Aug 1996 19:36:44 +0200 (SAT) (Smail-3.2 1996-Jul-4 #1 built 1996-Jul-21) Message-Id: Subject: Re: SMP on Intel MG15 To: pjchilds@imforei.apana.org.au (Peter Childs) Date: Sat, 17 Aug 1996 19:36:44 +0200 (SAT) Cc: freebsd-smp@freebsd.org In-Reply-To: <199608171506.AAA28573@al.imforei.apana.org.au> from "Peter Childs" at Aug 18, 96 00:36:57 am X-Mailer: ELM [version 2.4 PL25] Content-Type: text Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Peter Childs wrote: > Don't you need to put the number of cpu's in the kernel config? Here is my kernel config file - it is there, perhaps unfortunately otherwise I could fix it easily. :-) -Russell # machine "i386" cpu "I586_CPU" ident SMP maxusers 100 options CHILD_MAX=128 options OPEN_MAX=128 options GPL_MATH_EMULATE #Support for x87 emulation options INET #InterNETworking options FFS #Berkeley Fast Filesystem options NFS #Network Filesystem options "CD9660" #ISO 9660 Filesystem options PROCFS #Process filesystem options "COMPAT_43" #Compatible with BSD 4.3 [KEEP THIS!] options SCSI_DELAY=5 #Be pessimistic about Joe SCSI device options SCSI_REPORT_GEOMETRY options UCONSOLE #Allow users to grab the console options FAILSAFE #Be conservative #options "I586_FAST_BCOPY" options SYSVSHM options SYSVSEM options SYSVMSG options DDB options UCONSOLE options MROUTING # Multicast routing # Symmetrical Multi Processor options SMP options "NCPU=2" config kernel root on sd0 controller isa0 controller eisa0 controller pci0 controller pci1 controller fdc0 at isa? port "IO_FD1" bio irq 6 drq 2 vector fdintr disk fd0 at fdc0 drive 0 controller ahc0 controller scbus0 device sd0 device st0 device cd0 #Only need one of these, the code dynamically grows # syscons is the default console driver, resembling an SCO console device sc0 at isa? port "IO_KBD" tty irq 1 vector scintr # Mandatory, don't remove device npx0 at isa? port "IO_NPX" irq 13 vector npxintr device sio0 at isa? port "IO_COM1" tty irq 4 vector siointr device sio1 at isa? port "IO_COM2" tty irq 3 vector siointr device lpt0 at isa? port? tty irq 7 vector lptintr device lpt1 at isa? port? tty device de0 device ed0 at isa? port 0x280 net irq 5 iomem 0xd8000 vector edintr device ed1 at isa? port 0x300 net irq 5 iomem 0xd8000 vector edintr pseudo-device loop pseudo-device ether pseudo-device log pseudo-device pty 16 pseudo-device gzip # Exec gzipped a.out's #pseudo-device ccd 4 #Concatenated disk driver # KTRACE enables the system-call tracing facility ktrace(2). # This adds 4 KB bloat to your kernel, and slightly increases # the costs of each syscall. #options KTRACE #kernel tracing From owner-freebsd-smp Sat Aug 17 11:45:18 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA08153 for smp-outgoing; Sat, 17 Aug 1996 11:45:18 -0700 (PDT) Received: from critter.tfs.com ([140.145.230.177]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id LAA08144; Sat, 17 Aug 1996 11:45:14 -0700 (PDT) Received: from critter.tfs.com (localhost.tfs.com [127.0.0.1]) by critter.tfs.com (8.7.5/8.7.3) with ESMTP id UAA05654; Sat, 17 Aug 1996 20:44:44 +0200 (MET DST) To: rv@groa.uct.ac.za cc: pjchilds@imforei.apana.org.au (Peter Childs), freebsd-smp@freebsd.org Subject: Re: SMP on Intel MG15 In-reply-to: Your message of "Sat, 17 Aug 1996 19:36:44 +0200." Date: Sat, 17 Aug 1996 20:44:43 +0200 Message-ID: <5652.840307483@critter.tfs.com> From: Poul-Henning Kamp Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk In message , rv@groa.uct.ac.za writes: >Peter Childs wrote: >> Don't you need to put the number of cpu's in the kernel config? > >Here is my kernel config file - it is there, perhaps unfortunately >otherwise I could fix it easily. :-) > >options "NCPU=2" Well, actually it needs to be max(cpu_id[]) + 1 -- Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. whois: [PHK] | phk@ref.tfs.com TRW Financial Systems, Inc. Future will arrive by its own means, progress not so. From owner-freebsd-smp Sat Aug 17 12:08:49 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA08900 for smp-outgoing; Sat, 17 Aug 1996 12:08:49 -0700 (PDT) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id MAA08895 for ; Sat, 17 Aug 1996 12:08:46 -0700 (PDT) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id NAA20026; Sat, 17 Aug 1996 13:08:14 -0600 Message-Id: <199608171908.NAA20026@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: rv@groa.uct.ac.za cc: pjchilds@imforei.apana.org.au (Peter Childs), freebsd-smp@freebsd.org Subject: Re: SMP on Intel MG15 In-reply-to: Your message of "Sat, 17 Aug 1996 19:36:44 +0200." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 17 Aug 1996 13:08:14 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, >In article <4v4ddu$n7q@al.imforei.apana.org.au> you wrote: > >: 2) The machine locks up shortly after the SMP kernel load: > >: FreeBSD/SMP: Multiprocessor motherboard >: Boot cpunumber=0x0 >: [ machines freezes ] > >: I presume this means that the machine is reporting the number of >: CPUs in a non-recognised format. APIC supports appears to be >: enabled in the BIOS. "Boot cpunumber=0x0" is correct, this says that it is booting off CPU #0, ie the 1st CPU. here's my dmesg output, note that the first 3 lines only appear because I modified machdep.c to print them after /var/log/messages was active (default prints too early): FreeBSD/SMP: Multiprocessor motherboard Boot cpunumber=0x0 Number of CPUS found: 2 FreeBSD 2.2-CURRENT #1: Sat Aug 17 12:42:29 MDT 1996 root@rick.systemsix.com:/usr/src/sys-SMP.3/compile/SMPNN Calibrating clock(s) relative to mc146818A clock... i586 clock: 133668441 Hz, i8254 clock: 1193470 Hz CPU: Pentium (133.63-MHz 586-class CPU) Origin = "GenuineIntel" Id = 0x52c Stepping=12 Features=0x3bf real memory = 67108864 (65536K bytes) avail memory = 62853120 (61380K bytes) ... --- >I wrote: >> I have just received an Intel Xtended Xpress/MG15 with dual I would hate to think Intel can't make an Intel SMP compliant motherboard. Is this particular board known to have ever run an SMP OS? Can you read the s-spec of the chips? this is a 3 digit number starting with SX,SK,S?. I believe I earlier wrote: > I am using it with 2 P5 133mHz parts, type SU022 which is wrong, I am using 2 SY022 chips (according to my notes of a call with the vendor, the chips are buried too deep in the system to check right now) -- Steve Passe | powered by smp@csn.net | FreeBSD From owner-freebsd-smp Sat Aug 17 12:36:38 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA09482 for smp-outgoing; Sat, 17 Aug 1996 12:36:38 -0700 (PDT) Received: from uruk.org (uruk.org [198.145.95.253]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id MAA09477 for ; Sat, 17 Aug 1996 12:36:34 -0700 (PDT) From: erich@uruk.org Received: from loopback (loopback [127.0.0.1]) by uruk.org (8.7.4/8.7.3) with SMTP id MAA08515; Sat, 17 Aug 1996 12:37:38 -0700 (PDT) Message-Id: <199608171937.MAA08515@uruk.org> X-Authentication-Warning: uruk.org: Host loopback [127.0.0.1] didn't use HELO protocol To: Steve Passe cc: freebsd-smp@freebsd.org Subject: Re: SMP on Intel MG15 In-reply-to: Your message of "Sat, 17 Aug 1996 13:08:14 MDT." <199608171908.NAA20026@clem.systemsix.com> Date: Sat, 17 Aug 1996 12:37:38 -0700 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi all! As someone who used an Xtended Xpress box as a primary implementation platform for generalizing the Linux-SMP code, I think comments are in order... FWIW, I've got these mostly fixed in a version I'm playing with, and if I can get synched up with the changes coming across and some other fixes in, then I'll post them to the list to be merged in. I still need to discuss some important issues with the folks involved with FreeBSD development... I've just been sorta lazy with it since I've been busy with some other things. Steve Passe writes: > >In article <4v4ddu$n7q@al.imforei.apana.org.au> you wrote: > > > >: 2) The machine locks up shortly after the SMP kernel load: > > > >: FreeBSD/SMP: Multiprocessor motherboard > >: Boot cpunumber=0x0 > >: [ machines freezes ] > > > >: I presume this means that the machine is reporting the number of > >: CPUs in a non-recognised format. APIC supports appears to be > >: enabled in the BIOS. > > "Boot cpunumber=0x0" is correct, this says that it is booting off CPU #0, > ie the 1st CPU. > > here's my dmesg output, note that the first 3 lines only > appear because I modified machdep.c to print them after > /var/log/messages was active (default prints too early): > > FreeBSD/SMP: Multiprocessor motherboard > Boot cpunumber=0x0 I might know your problem. Some of the nastiest bugs in Linux-SMP before I fixed it, and that is definitely still in FreeBSD-SMP, are the following presumptions: (1) boot CPU is APIC id #0 (this is true on Xtended Xpress boxes, but not on many Pentium Pro machines). (2) APICs are numbered consecutively. #2 is FALSE on an Xtended Xpress box. The one I tested with was numbered: 0, 2, 3, 4. NOTE that FreeBSD-SMP is currently hard-coded to expect the next CPU after the boot CPU to be #1. I'd say this is your problem. > Number of CPUS found: 2 This is probably reporting what the MP Config Table said, not how many it was able to boot (so this is irrelevant from the point of view of APIC numbering). > >I wrote: > >> I have just received an Intel Xtended Xpress/MG15 with dual > > I would hate to think Intel can't make an Intel SMP compliant > motherboard. Is this particular board known to have ever run > an SMP OS? I don't know about the "MG15" part, but Intel is almost rabid about getting Windows NT to run on their SMP boxes. If you look in the BIOS settings, you'll note that the "MPS version" is either 1.1 or 1.4 (in the version I had, you could set it). For purposes of FreeBSD or Linux, this version number doesn't currently matter. For Windows NT, it does, and you need to set it to 1.4. The reason is that Windows NT uses all kinds of information about the bus structure heirarchy. > Can you read the s-spec of the chips? this is a 3 > digit number starting with SX,SK,S?. I believe I earlier wrote: > > I am using it with 2 P5 133mHz parts, type SU022 > which is wrong, I am using 2 SY022 chips (according to my > notes of a call with the vendor, the chips are buried too > deep in the system to check right now) I'd be suspicious of FreeBSD unless I was sure it identified them correctly, as Intel is always adding new designations when new steppings of a chip come out. -- Erich Stefan Boleyn \_ E-mail (preferred): Mad Genius wanna-be, CyberMuffin \__ (finger me for other stats) Web: http://www.uruk.org/~erich/ Motto: "I'll live forever or die trying" From owner-freebsd-smp Sat Aug 17 13:14:43 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA13144 for smp-outgoing; Sat, 17 Aug 1996 13:14:43 -0700 (PDT) Received: from phaeton.artisoft.com (phaeton.Artisoft.COM [198.17.250.211]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id NAA13133 for ; Sat, 17 Aug 1996 13:14:39 -0700 (PDT) Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id MAA06585; Sat, 17 Aug 1996 12:56:09 -0700 From: Terry Lambert Message-Id: <199608171956.MAA06585@phaeton.artisoft.com> Subject: Re: SMP on Intel MG15 To: smp@csn.net (Steve Passe) Date: Sat, 17 Aug 1996 12:56:08 -0700 (MST) Cc: rv@groa.uct.ac.za, pjchilds@imforei.apana.org.au, freebsd-smp@freebsd.org In-Reply-To: <199608171908.NAA20026@clem.systemsix.com> from "Steve Passe" at Aug 17, 96 01:08:14 pm X-Mailer: ELM [version 2.4 PL24] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > I would hate to think Intel can't make an Intel SMP compliant > motherboard. Is this particular board known to have ever run > an SMP OS? Can you read the s-spec of the chips? this is a 3 > digit number starting with SX,SK,S?. I believe I earlier wrote: > > I am using it with 2 P5 133mHz parts, type SU022 > which is wrong, I am using 2 SY022 chips (according to my > notes of a call with the vendor, the chips are buried too > deep in the system to check right now) The Intel Multiprocessing Specification documents two methods of probing out MP support. A board only has to implement one of them to be compliant. I believe the FreeBSD SMP code requires the MP configuration table, which the spec says (4.0. P 6): 2. The MP Configuration Table. This table is optional. Probably it would help to, as part of the boot process for an SMP kernel, to print out the contents of the MP Floating Pointer Structure Fields. Byte 11 of this table, if non-zero, specifies a default configuration type. Only types 1-7 are defined by the 1.1 version of the specification. It would be interesting to know if: o Bytes 4-7 are zero, indicating there is no configuration table available o Byte 9 is not 0x01, indicating a version 1 MP spec compliant board. o Byte 11 is zero, indicating a non-default configuration o Bits 0..6 of byte 12 are non-zero (indicating an error or a future MP definition is being used) o Bytes 13-15 are non-zero (also indicating an error or a future MP definition is being used) Note that the 1.1 defined default configurations support only 2 CPU's maximum. For Byte 11 non-zero, the host OS is supposed to have a static MP Configuration Table provided in the case that Bytes 4-7 are also zero (if they are non-zero, then the MP Configuration Table supplied by the system overrides the precompiled tables). I believe SMP FreeBSD does not currently support a non-zero Byte 11 correctly. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers.