From owner-freebsd-smp Sun Apr 20 01:09:37 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id BAA10926 for smp-outgoing; Sun, 20 Apr 1997 01:09:37 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id BAA10921 for ; Sun, 20 Apr 1997 01:09:32 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id CAA05909 for ; Sun, 20 Apr 1997 02:09:30 -0600 (MDT) Message-Id: <199704200809.CAA05909@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: smp@freebsd.org Subject: Lets go for it! Mime-Version: 1.0 Content-Type: text/plain Date: Sun, 20 Apr 1997 02:09:30 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, "make world" completes with todays files, APIC_IO, SMP_INVLTLB, on dual P6s. It appears that the post Lite2 SMP kernel is basically sound at this point! I think we should consider merging the SMP tree into -current. --- Its time to get serious. Up to now we've just kinda' been playing around... We need to formalize some architechural plans for how we want to proceed. White papers need to be prepared on the major subsections, both documenting how things currently work, and how we propose to change them. Areas that require attention include: a new INTerrupt model that is based upon APIC features and symmetric I/O handling. conversion from the current "giant lock" model to fine grained locking. improved and additional IPI functionality. These include cpu shutdown, signal propigation, TLB & PTE invalidation, global cache flush, etc. proper handling of timing code. propagate the 'tick' to all cpus, enforce the correct handling of proc time-slices, etc. ??? --- I'm going to be doing additions to the web pages towards this end. There will be a collection of white papers, significant mailings to hit the list, design documents as they evolve, a "to-do" list, etc. Any and all suggestions are welcome. I've already added a "bugs" page: http://www.freebsd.org/~fsmp/SMP/bugs.html Please review and report any outstanding bugs that I've missed. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Sun Apr 20 01:53:31 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id BAA12190 for smp-outgoing; Sun, 20 Apr 1997 01:53:31 -0700 (PDT) Received: from nlsystems.com (nlsys.demon.co.uk [158.152.125.33]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id BAA12183 for ; Sun, 20 Apr 1997 01:53:26 -0700 (PDT) Received: from herring.nlsystems.com (herring.nlsystems.com [10.0.0.2]) by nlsystems.com (8.8.5/8.8.5) with SMTP id JAA01462; Sun, 20 Apr 1997 09:52:41 +0100 (BST) Date: Sun, 20 Apr 1997 09:52:40 +0100 (BST) From: Doug Rabson Reply-To: Doug Rabson To: Peter Wemm cc: smp@freebsd.org Subject: Re: cvs commit: /home/smp/sys/kern init_smp.c In-Reply-To: <199704191728.BAA00592@spinner.DIALix.COM> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Sun, 20 Apr 1997, Peter Wemm wrote: > Doug Rabson wrote: > > On Sat, 19 Apr 1997, Peter Wemm wrote: > > > > > Peter Wemm wrote: > > > > peter 97/04/19 08:35:16 > > > > > > > > Modified: home/smp/sys/kern init_smp.c > > > ^^^^^^^^^^^^^^^^ > > > > Log: > > > > change #include to - solves lockmgr panic! > > > > update the idle proc create code to use the "new" style fork that doesn > 't > > > > "return" from the fork() function call - it now boots! > > > > (I'm running smp_active=2 right now) > > > > > > OOPS! Slip of the fingers with a remote commit.. Sorry, this message went > > > to the wrong commit mailing list.. :-] (Background for those on > > > -committers, the smp kernel was put on hold while the lite2 stuff was being > > > sorted out in -current. It was resync'ed a few days ago, which broke it > > > somewhat.) > > > > I must be doing something wrong. I cvsup'ed, updated and built but I > > still get the lockmgr panic :-(. Are there any pending fixes that I don't > > have yet maybe? > > Hmm.. No.. I have 4 other touched files, and they have #ifdef > WORK_IN_PROGRESS around the changes, this is not defined. > > Did you rerun config and "make clean depend"? I did rerun config and not with the -n flag either so I got a completely fresh compile directory. I have a P6 system but I don't think that makes much difference since Steve has reported success with a P6 system. I will try again today. I am sure I have done something stupid. -- Doug Rabson Mail: dfr@nlsystems.com Nonlinear Systems Ltd. Phone: +44 181 951 1891 From owner-freebsd-smp Sun Apr 20 02:37:38 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id CAA13685 for smp-outgoing; Sun, 20 Apr 1997 02:37:38 -0700 (PDT) Received: from weenix.guru.org (phantasma.bevc.blacksburg.va.us [198.82.200.65]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id CAA13680 for ; Sun, 20 Apr 1997 02:37:34 -0700 (PDT) Received: (from kmitch@localhost) by weenix.guru.org (8.8.5/8.8.5) id FAA00766; Sun, 20 Apr 1997 05:37:27 -0400 (EDT) From: Keith Mitchell Message-Id: <199704200937.FAA00766@weenix.guru.org> Subject: Q) SMP Kernel compilation To: smp@csn.net Date: Sun, 20 Apr 1997 05:37:27 -0400 (EDT) Cc: smp@freebsd.org X-Mailer: ELM [version 2.4ME+ PL30 (25)] 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 > Hi, > > I have the following compilation error as of Apr. 19th, 2300GMT > > SMP source. What am I wrong? > > > > # make depend; make > have you updated all the rest of your source recently, followed by a > "make world"? todays SMP tree is tied to the 3.0-current post Lite-2 merge > code. in other words you need to get everything else up to date to be able > to use todays SMP code. > assumming everything else is current, clean the old objects out first, ie: > make clean; make depend; make (in your SMP kernel build directory) I had the same problem with USER_LDT defined in the kernel config. I also have problems getting the linux emaulation lkm working. Both work fine with the UP kernel. (both UP and SMP kernel are from April 19th around 5:00PM EDT). The linux lkm gives undefined references like: /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment Also, when compiling the lkm's with the smp kernel, I still get a lot of files tring to include opt_smp.h and opt_smp_invltlb.h. I don't know if these errors occur anywhere else in the tree. -- Keith Mitchell Head Administrator: acm.vt.edu Email: kmitch@weenix.guru.org PGP key available upon request http://weenix.guru.org/~kmitch Address and URL (c) 1997 Keith Mitchell - All Rights Reserverd Unauthorized use or duplication prohibited From owner-freebsd-smp Sun Apr 20 03:10:12 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id DAA14487 for smp-outgoing; Sun, 20 Apr 1997 03:10:12 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id DAA14470 for ; Sun, 20 Apr 1997 03:10:01 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id SAA06622; Sun, 20 Apr 1997 18:09:19 +0800 (WST) Message-Id: <199704201009.SAA06622@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Keith Mitchell cc: smp@csn.net, smp@freebsd.org Subject: Re: Q) SMP Kernel compilation In-reply-to: Your message of "Sun, 20 Apr 1997 05:37:27 -0400." <199704200937.FAA00766@weenix.guru.org> Date: Sun, 20 Apr 1997 18:09:18 +0800 From: Peter Wemm Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Keith Mitchell wrote: > > > Hi, > > > I have the following compilation error as of Apr. 19th, 2300GMT > > > SMP source. What am I wrong? > > > > > > # make depend; make > > > have you updated all the rest of your source recently, followed by a > > "make world"? todays SMP tree is tied to the 3.0-current post Lite-2 merge > > code. in other words you need to get everything else up to date to be able > > to use todays SMP code. > > > assumming everything else is current, clean the old objects out first, ie: > > make clean; make depend; make (in your SMP kernel build directory) > > I had the same problem with USER_LDT defined in the kernel config. I also > have problems getting the linux emaulation lkm working. Both work fine Ahh, USER_LDT.. I have not tested that... I wouldn't be suprised if that is plain broken in the smp tree at the moment. > with the UP kernel. (both UP and SMP kernel are from April 19th around > 5:00PM EDT). The linux lkm gives undefined references like: > > /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment > /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment > /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment > /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment > /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment > /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment > /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment > /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment > /lkm/linux_mod.o: Undefined symbol `_curproc' referenced from text segment > > > Also, when compiling the lkm's with the smp kernel, I still get a lot of > files tring to include opt_smp.h and opt_smp_invltlb.h. I don't know if > these errors occur anywhere else in the tree. I don't like to risk my system with LKM's when mixing up different kernel versions.. If you were able to load a SMP lkm on a -current kernel, it could be a disaster, and vice versa. If you want Linux compat, compile with "options COMPAT_LINUX" and play it safe since it's statically compiled in. I think we've got a lot of work to make the LKM's smp-loadable. Cheers, -Peter From owner-freebsd-smp Sun Apr 20 04:28:49 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id EAA16426 for smp-outgoing; Sun, 20 Apr 1997 04:28:49 -0700 (PDT) Received: from housing1.stucen.gatech.edu (ken@housing1.stucen.gatech.edu [130.207.52.71]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id EAA16421 for ; Sun, 20 Apr 1997 04:28:47 -0700 (PDT) Received: (from ken@localhost) by housing1.stucen.gatech.edu (8.8.5/8.8.5) id HAA29122; Sun, 20 Apr 1997 07:28:23 -0400 (EDT) From: Kenneth Merry Message-Id: <199704201128.HAA29122@housing1.stucen.gatech.edu> Subject: Re: Lets go for it! In-Reply-To: <199704200809.CAA05909@Ilsa.StevesCafe.com> from Steve Passe at "Apr 20, 97 02:09:30 am" To: smp@csn.net (Steve Passe) Date: Sun, 20 Apr 1997 07:28:23 -0400 (EDT) Cc: smp@freebsd.org X-Mailer: ELM [version 2.4ME+ PL31 (25)] 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 Steve Passe wrote... > Hi, > > "make world" completes with todays files, APIC_IO, SMP_INVLTLB, on dual P6s. > It appears that the post Lite2 SMP kernel is basically sound at this point! Just so folks will know that this doesn't just work for Steve... I cvsupped -current at about 0100 EDT on Sunday, and did a make world with a -current uniproc kernel. I had some initial problems with ps, w, etc., hanging with the uniproc kernel, but with the SMP kernel, everything seems to work okay. Go figure...I'll say something if I see that hanging problem again. > I think we should consider merging the SMP tree into -current. Yeah, that would be cool. :) Ken -- Kenneth Merry ken@ulc199.residence.gatech.edu Disclaimer: I don't speak for GTRI, GT, or Elvis. From owner-freebsd-smp Sun Apr 20 05:18:33 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id FAA18085 for smp-outgoing; Sun, 20 Apr 1997 05:18:33 -0700 (PDT) Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id FAA18078 for freebsd-smp; Sun, 20 Apr 1997 05:18:31 -0700 (PDT) Date: Sun, 20 Apr 1997 05:18:31 -0700 (PDT) From: Peter Wemm Message-Id: <199704201218.FAA18078@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/include segments.h Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk peter 97/04/20 05:18:31 Modified: i386/include segments.h Log: fix USER_LDT breakage that I inflicted on the world Revision Changes Path 1.9 +2 -2 sys/i386/include/segments.h From owner-freebsd-smp Sun Apr 20 05:29:20 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id FAA18342 for smp-outgoing; Sun, 20 Apr 1997 05:29:20 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id FAA18334; Sun, 20 Apr 1997 05:28:56 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id UAA08091; Sun, 20 Apr 1997 20:28:47 +0800 (WST) Message-Id: <199704201228.UAA08091@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Peter Wemm cc: freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/include segments.h In-reply-to: Your message of "Sun, 20 Apr 1997 05:18:31 MST." <199704201218.FAA18078@freefall.freebsd.org> Date: Sun, 20 Apr 1997 20:28:46 +0800 From: Peter Wemm Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Peter Wemm wrote: > peter 97/04/20 05:18:31 > > Modified: i386/include segments.h > Log: > fix USER_LDT breakage that I inflicted on the world Incidently, this makes it compile, but I'm not certain it'll work... There might be some ugly conflicts if two processes with ldt's were running in parallel. (The same problem happens with the tss selector - my hack there was to have gdt declared as gdt[NGDT + NCPU] and use a per-cpu entry in the tail of the gdt. This isn't exactly wonderful though. Cheers, -Peter From owner-freebsd-smp Sun Apr 20 06:34:03 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id GAA21094 for smp-outgoing; Sun, 20 Apr 1997 06:34:03 -0700 (PDT) Received: from nlsystems.com (nlsys.demon.co.uk [158.152.125.33]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id GAA21088 for ; Sun, 20 Apr 1997 06:33:54 -0700 (PDT) Received: from herring.nlsystems.com (herring.nlsystems.com [10.0.0.2]) by nlsystems.com (8.8.5/8.8.5) with SMTP id OAA00291; Sun, 20 Apr 1997 14:32:48 +0100 (BST) Date: Sun, 20 Apr 1997 14:32:48 +0100 (BST) From: Doug Rabson To: Peter Wemm cc: smp@freebsd.org Subject: Re: cvs commit: /home/smp/sys/kern init_smp.c In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Sun, 20 Apr 1997, Doug Rabson wrote: > > I did rerun config and not with the -n flag either so I got a completely > fresh compile directory. I have a P6 system but I don't think that makes > much difference since Steve has reported success with a P6 system. > > I will try again today. I am sure I have done something stupid. My problem appeared to be with the kernel config file that I was using. I hacked a new one from GENERIC and got a lot further. Now I get through the device probes and I can hear the machine start booting into multiuser mode but I can't see anything. Nothing is printed after the last device probe. The machine hangs later on when it is trying to start mpd. If I break into DDB, all the boot messages appear in a lump; sounds like some kind of wierd interrupt problem to me. Kernel config is: # # GENERIC -- Generic machine with WD/AHx/NCR/BTx family disks # # For more information read the handbook part System Administration -> # Configuring the FreeBSD Kernel -> The Configuration File. # The handbook is available in /usr/share/doc/handbook or online as # latest version from the FreeBSD World Wide Web server # # # An exhaustive list of options and more detailed explanations of the # device lines is present in the ./LINT configuration file. If you are # in doubt as to the purpose or necessity of a line, check first in LINT. # # $Id: GENERIC,v 1.90 1997/04/14 00:35:20 gibbs Exp $ machine "i386" cpu "I386_CPU" cpu "I486_CPU" cpu "I586_CPU" cpu "I686_CPU" ident GENERIC maxusers 10 options MATH_EMULATE #Support for x87 emulation options INET #InterNETworking options FFS #Berkeley Fast Filesystem options NFS #Network Filesystem options MSDOSFS #MSDOS Filesystem options "CD9660" #ISO 9660 Filesystem options PROCFS #Process filesystem options "COMPAT_43" #Compatible with BSD 4.3 [KEEP THIS!] options SCSI_DELAY=15 #Be pessimistic about Joe SCSI device options BOUNCE_BUFFERS #include support for DMA bounce buffers options UCONSOLE #Allow users to grab the console options FAILSAFE #Be conservative options USERCONFIG #boot -c editor options VISUAL_USERCONFIG #visual boot -c editor options DDB options UKKEYMAP options SYSVSHM options SYSVSEM options SYSVMSG options AHC_TAGENABLE options KTRACE options "CONSPEED=(115200)" # SMP kernel config file options: options SMP # Symmetric MultiProcessor Kernel options APIC_IO # Symmetric (APIC) I/O options NCPU=2 # number of CPUs options NBUS=2 # number of busses options NAPIC=1 # number of IO APICs options NINTR=24 # number of INTs options SMP_INVLTLB # #options SMP_PRIVPAGES # BROKEN, DO NOT use! #options SMP_AUTOSTART # BROKEN, DO NOT use! #options SERIAL_DEBUG # com port debug output options IPFIREWALL #firewall options IPFIREWALL_VERBOSE #print information about # dropped packets options "IPFIREWALL_VERBOSE_LIMIT=100" #limit verbosity options IPDIVERT #divert sockets config kernel root on wd0 controller isa0 controller eisa0 controller pci0 controller fdc0 at isa? port "IO_FD1" bio irq 6 drq 2 vector fdintr disk fd0 at fdc0 drive 0 # A single entry for any of these controllers (ncr, ahb, ahc, amd) is # sufficient for any number of installed devices. controller ahc0 controller scbus0 device sd0 device od0 #See LINT for possible `od' options. 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 # Enable this and PCVT_FREEBSD for pcvt vt220 compatible console driver #device vt0 at isa? port "IO_KBD" tty irq 1 vector pcrint #options PCVT_FREEBSD=210 # pcvt running on FreeBSD >= 2.0.5 #options XSERVER # include code for XFree86 #options FAT_CURSOR # start with block cursor # If you have a ThinkPAD, uncomment this along with the rest of the PCVT lines #options PCVT_SCANSET=2 # IBM keyboards are non-std device npx0 at isa? port "IO_NPX" irq 13 vector npxintr # # Laptop support (see LINT for more options) # device apm0 at isa? disable flags 0x31 # Advanced Power Management 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 sio2 at isa? disable port "IO_COM3" tty irq 5 vector siointr device sio3 at isa? disable port "IO_COM4" tty irq 9 vector siointr device lpt0 at isa? port? tty irq 7 vector lptintr device lpt1 at isa? port? tty device mse0 at isa? port 0x23c tty irq 5 vector mseintr device psm0 at isa? port "IO_KBD" conflicts tty irq 12 vector psmintr # Order is important here due to intrusive probes, do *not* alphabetize # this list of network interfaces until the probes have been fixed. # Right now it appears that the ie0 must be probed before ep0. See # revision 1.20 of this file. device de0 device fxp0 device vx0 pseudo-device loop pseudo-device ether pseudo-device log pseudo-device sl 1 # ijppp uses tun instead of ppp device #pseudo-device ppp 1 pseudo-device tun 1 pseudo-device pty 16 pseudo-device gzip # Exec gzipped a.out's pseudo-device bpfilter 4 -- Doug Rabson Mail: dfr@nlsystems.com Nonlinear Systems Ltd. Phone: +44 181 951 1891 From owner-freebsd-smp Sun Apr 20 09:17:48 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id JAA28525 for smp-outgoing; Sun, 20 Apr 1997 09:17:48 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA28520 for ; Sun, 20 Apr 1997 09:17:41 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id KAA06759; Sun, 20 Apr 1997 10:17:06 -0600 (MDT) Message-Id: <199704201617.KAA06759@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Doug Rabson cc: Peter Wemm , smp@freebsd.org Subject: Re: cvs commit: /home/smp/sys/kern init_smp.c In-reply-to: Your message of "Sun, 20 Apr 1997 14:32:48 BST." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 20 Apr 1997 10:17:05 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, assumming that your hardware can boot a COMPLETELY GENERIC UP kernel, build an SMP kernel that is COMPLETELY GENERIC, ie start with GENERIC and add ONLY: options SMP # Symmetric MultiProcessor Kernel options NCPU=2 # number of CPUs options APIC_IO # Symmetric (APIC) I/O options SMP_INVLTLB # boot -v and -s, see how far you get... -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Sun Apr 20 09:29:07 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id JAA29157 for smp-outgoing; Sun, 20 Apr 1997 09:29:07 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA29152 for ; Sun, 20 Apr 1997 09:29:01 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id AAA09522; Mon, 21 Apr 1997 00:28:23 +0800 (WST) Message-Id: <199704201628.AAA09522@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Steve Passe cc: Doug Rabson , smp@freebsd.org Subject: Re: cvs commit: /home/smp/sys/kern init_smp.c In-reply-to: Your message of "Sun, 20 Apr 1997 10:17:05 CST." <199704201617.KAA06759@Ilsa.StevesCafe.com> Date: Mon, 21 Apr 1997 00:28:22 +0800 From: Peter Wemm Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Steve Passe wrote: > Hi, > > assumming that your hardware can boot a COMPLETELY GENERIC UP kernel, build > an SMP kernel that is COMPLETELY GENERIC, ie start with GENERIC and add ONLY: > > options SMP # Symmetric MultiProcessor Kernel > options NCPU=2 # number of CPUs > options APIC_IO # Symmetric (APIC) I/O > options SMP_INVLTLB # > > boot -v and -s, see how far you get... Another thought.. Doug, Have you used -r or -D flags to 'cvs update' in the past? They are sticky.. It might be an idea to redo a cvs update on your tree with: "cvs update -d -P -A" to be sure... I know that's kinda obvious, but I thought I'd mention it just in case.. > -- > Steve Passe | powered by > smp@csn.net | Symmetric MultiProcessor FreeBSD > Cheers, -Peter From owner-freebsd-smp Sun Apr 20 12:23:56 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id MAA07885 for smp-outgoing; Sun, 20 Apr 1997 12:23:56 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.visint.co.uk [194.207.134.1]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA07879 for ; Sun, 20 Apr 1997 12:23:50 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.visint.co.uk [194.207.134.1]) by bagpuss.visint.co.uk (8.7.5/8.7.3) with SMTP id UAA20170 for ; Sun, 20 Apr 1997 20:31:12 +0100 (BST) Date: Sun, 20 Apr 1997 20:31:08 +0100 (BST) From: Stephen Roome To: freebsd-smp@freebsd.org Subject: Problems 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've just installed a gigabyte GA586DX board here with two P133's on it. I cvsupped down the smp stuff and compiled it, it seems to work, however ps, w, and all those other useful commands fail miserably. I expect I need to do a make world, but would rather cheat and just make those little portions of 'world' that I can get away with. So, can someone let me know what parts of world need to be built and what parts don't, for me to at least have ps working. -- Steve Roome Technical Systems Manager, Vision Interactive Ltd. E: steve@visint.co.uk M: +44 (0) 976 241 342 T: +44 (0) 117 973 0597 F: +44 (0) 117 923 8522 From owner-freebsd-smp Sun Apr 20 13:07:28 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id NAA10623 for smp-outgoing; Sun, 20 Apr 1997 13:07:28 -0700 (PDT) Received: from thelab.hub.org (hal-ns1-08.netcom.ca [207.181.94.72]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA10588 for ; Sun, 20 Apr 1997 13:07:17 -0700 (PDT) Received: from thelab.hub.org (localhost [127.0.0.1]) by thelab.hub.org (8.8.5/8.8.2) with SMTP id RAA05393; Sun, 20 Apr 1997 17:03:22 -0300 (ADT) Date: Sun, 20 Apr 1997 17:03:22 -0300 (ADT) From: The Hermit Hacker To: Stephen Roome cc: freebsd-smp@freebsd.org Subject: Re: Problems In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Sun, 20 Apr 1997, Stephen Roome wrote: > > I've just installed a gigabyte GA586DX board here with two P133's on it. > > I cvsupped down the smp stuff and compiled it, it seems to work, however > ps, w, and all those other useful commands fail miserably. > > I expect I need to do a make world, but would rather cheat and just make > those little portions of 'world' that I can get away with. > > So, can someone let me know what parts of world need to be built and what > parts don't, for me to at least have ps working. Before doing ps/w, you have to rebuild lib/libkvm...that's the only library that I *know* of that needs to be rebuilt when kernel structures change :( Marc G. Fournier Systems Administrator @ hub.org primary: scrappy@hub.org secondary: scrappy@{freebsd|postgresql}.org From owner-freebsd-smp Sun Apr 20 13:22:46 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id NAA12564 for smp-outgoing; Sun, 20 Apr 1997 13:22:46 -0700 (PDT) Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id NAA12514 for freebsd-smp; Sun, 20 Apr 1997 13:22:39 -0700 (PDT) Date: Sun, 20 Apr 1997 13:22:39 -0700 (PDT) From: Steve Passe Message-Id: <199704202022.NAA12514@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/i386 mp_machdep.c sys/i386/include smptests.h sys/i386/conf options.i386 sys/i386/isa clock.c isa.c Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/20 13:22:36 Modified: i386/conf options.i386 Log: added option SMP_TIMER_NC this option informs the kernel that the motherboard MP table incorrectly states that the 8254 timer is connected to the IO APIC. it replaces the #define in smptests.h: FAKE_8254_NC Revision Changes Path 1.18 +2 -1 sys/i386/conf/options.i386 Modified: i386/i386 mp_machdep.c Log: use option SMP_TIMER_NC this option informs the kernel that the motherboard MP table incorrectly states that the 8254 timer is connected to the IO APIC. it replaces the #define in smptests.h: FAKE_8254_NC Revision Changes Path 1.37 +7 -8 sys/i386/i386/mp_machdep.c Modified: i386/include smptests.h Log: removed #defines for: FAKE_8254_NC, IRQ_LO_NC, IRQ_HI_NC FAKE_8254_NC is replaced by i386/conf/options.i386: option SMP_TIMER_NC IRQ_LO_NC is now default for APIC_IO IRQ_HI_NC is removed, need never demonstrated Revision Changes Path 1.9 +1 -14 sys/i386/include/smptests.h Modified: i386/isa clock.c isa.c Log: replaced #define for: IRQ_LO_NC with APIC_IO IRQ_LO_NC is now default for APIC_IO Revision Changes Path 1.16 +21 -22 sys/i386/isa/clock.c 1.17 +7 -14 sys/i386/isa/isa.c From owner-freebsd-smp Sun Apr 20 14:18:21 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id OAA17415 for smp-outgoing; Sun, 20 Apr 1997 14:18:21 -0700 (PDT) Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id OAA17408 for freebsd-smp; Sun, 20 Apr 1997 14:18:18 -0700 (PDT) Date: Sun, 20 Apr 1997 14:18:18 -0700 (PDT) From: Steve Passe Message-Id: <199704202118.OAA17408@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/i386 mp_machdep.c Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/20 14:18:17 Modified: i386/i386 mp_machdep.c Log: added #defines to verify that both APIC_IO and SMP_INVLTLB are set, or that neither are set. Setting SMP_INVLTLB without APIC_IO will cause a kernel panic. Setting APIC_IO without SMP_INVLTLB is prone to page (memory) corruption. Revision Changes Path 1.38 +11 -1 sys/i386/i386/mp_machdep.c From owner-freebsd-smp Sun Apr 20 15:22:01 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id PAA21075 for smp-outgoing; Sun, 20 Apr 1997 15:22:01 -0700 (PDT) Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id PAA21068 for freebsd-smp; Sun, 20 Apr 1997 15:21:59 -0700 (PDT) Date: Sun, 20 Apr 1997 15:21:59 -0700 (PDT) From: Steve Passe Message-Id: <199704202221.PAA21068@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/i386 mpapic.c sys/i386/include mpapic.h Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/20 15:21:58 Modified: i386/include mpapic.h i386/i386 mpapic.c Log: changed default behaviour from FAST_IPI to FAST_IPI_NOT. added default #define for APICIPI_BANDAID. The purpose of these changes is to create a short-term fix for the APIC_IO freeze problem. Undefining FAST_IPI changes the calls from inlines to real functions, only real effect should be speed, and I can't see any measurable difference so far. APICIPI_BANDAID invokes a "lazy delivery" mode for IPIs where we bail out after an arbitrary period, assumming we are in the "dead-lock" condition, but that the IPI will eventually get delivered. The early exit should allow the mplock to be freed, and the dead-lock to be avoided. IF it still hasn't been delivered by the next call to apicIPI (and after waiting a LONG time in this next call) we finally panic. This new method may add some SLIGHT statistical chance of corrupted memory, as we don't wait for the SMP_INVLTBL IPI to definately reach the target CPU, but since the current model already has that failing (it's NOT sync'ed with the target CPU(s)) I *think* its better than not using it. And it should be much better than the possible disk corruption fron hitting big red to unfreeze the system. To revert to the old behaviour change i386/include/mpapic.h from: #define FAST_IPI_NOT #define APICIPI_BANDAID to: #define FAST_IPI #define APICIPI_BANDAID_NOT Revision Changes Path 1.11 +3 -2 sys/i386/include/mpapic.h 1.27 +37 -1 sys/i386/i386/mpapic.c From owner-freebsd-smp Sun Apr 20 17:27:20 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id RAA29582 for smp-outgoing; Sun, 20 Apr 1997 17:27:20 -0700 (PDT) Received: from kvikk.uit.no (kvikk.Uit.No [129.242.4.32]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id RAA29575 for ; Sun, 20 Apr 1997 17:27:17 -0700 (PDT) Received: from sprint.cc.uit.no (sprint.Cc.Uit.No [129.242.5.198]) by kvikk.uit.no (8.8.5/8.8.5) with ESMTP id CAA07362 for ; Mon, 21 Apr 1997 02:27:13 +0200 (MDT) Received: from slibo.cc.uit.no (slibo.Cc.Uit.No [129.242.5.36]) by sprint.cc.uit.no (8.8.5/8.8.5) with ESMTP id CAA08186 for ; Mon, 21 Apr 1997 02:27:11 +0200 (METDST) Received: from localhost (terjem@localhost) by slibo.cc.uit.no (8.8.5/8.8.5) with ESMTP id CAA03466 for ; Mon, 21 Apr 1997 02:27:11 +0200 (METDST) Message-Id: <199704210027.CAA03466@slibo.cc.uit.no> X-Mailer: exmh version 2.0gamma 1/27/96 To: freebsd-smp@freefall.freebsd.org Subject: Current runs fine on 4 CPU's as well Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 21 Apr 1997 02:27:11 +0200 From: Terje Normann Marthinussen Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Just sup'ed current, made the world and a new SMP kernel (suped 1 hour ago). Have done a couple of kernel makes and some other minor work. Everything seems to work fine with on our 4 CPU HP Netserver 5/133 LS4 About time to remove /** FIXME: remove this when NCPU > 2 is tested */ if ( mp_naps > 1 ) { printf( "\nWarning: current SMP kernel only tested with 2 CPUs.\n" ); printf( "Please report the results to: \n" ); printf( " to continue...\n" ); cngetc(); } from mp_machdep.c? It's been running on 4 CPU's now since december, and I've only had two crashes since then. It's not heavily loaded, but when it once in a while is loaded, it quite loaded chewing data that needs 50-100MB of memory and sometimes causing heavy paging as well (got 128MB on it). It's been amazingly stable so far. Terje Marthinussen terjem@cc.uit.no From owner-freebsd-smp Sun Apr 20 18:28:18 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id SAA03989 for smp-outgoing; Sun, 20 Apr 1997 18:28:18 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id SAA03984 for ; Sun, 20 Apr 1997 18:28:15 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id TAA08535; Sun, 20 Apr 1997 19:28:09 -0600 (MDT) Message-Id: <199704210128.TAA08535@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Terje Normann Marthinussen cc: freebsd-smp@freefall.freebsd.org Subject: Re: Current runs fine on 4 CPU's as well In-reply-to: Your message of "Mon, 21 Apr 1997 02:27:11 +0200." <199704210027.CAA03466@slibo.cc.uit.no> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 20 Apr 1997 19:28:09 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, > Just sup'ed current, made the world and a new SMP kernel (suped 1 hour ago). > ... > It's been running on 4 CPU's now since december, and I've only had two > crashes since then. It's not heavily loaded, but when it once in a while > is loaded, it quite loaded chewing data that needs 50-100MB of memory > and sometimes causing heavy paging as well (got 128MB on it). Cyrus recently identified a dead-lock in the APIC_IO version. The symptom is a complete freeze of the system while doing heavy IO. Are you using the APIC_IO version? When you say "crash", do you mean spontanious reboot, panic, or freeze? Earlier today I commited a "bandaid" that should help with this problem. Did you get the version of mpapic.h that has "#define APICIPI_BANDAID" in it? -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Sun Apr 20 19:13:33 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id TAA06802 for smp-outgoing; Sun, 20 Apr 1997 19:13:33 -0700 (PDT) Received: from kvikk.uit.no (kvikk.Uit.No [129.242.4.32]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id TAA06793 for ; Sun, 20 Apr 1997 19:13:29 -0700 (PDT) Received: from sprint.cc.uit.no (sprint.Cc.Uit.No [129.242.5.198]) by kvikk.uit.no (8.8.5/8.8.5) with ESMTP id EAA08056; Mon, 21 Apr 1997 04:13:23 +0200 (MDT) Received: from slibo.cc.uit.no (slibo.Cc.Uit.No [129.242.5.36]) by sprint.cc.uit.no (8.8.5/8.8.5) with ESMTP id EAA08669; Mon, 21 Apr 1997 04:13:22 +0200 (METDST) Received: from localhost (terjem@localhost) by slibo.cc.uit.no (8.8.5/8.8.5) with ESMTP id EAA03641; Mon, 21 Apr 1997 04:13:21 +0200 (METDST) Message-Id: <199704210213.EAA03641@slibo.cc.uit.no> X-Mailer: exmh version 2.0gamma 1/27/96 To: Steve Passe cc: freebsd-smp@freefall.freebsd.org Subject: Re: Current runs fine on 4 CPU's as well In-reply-to: Your message of "Sun, 20 Apr 1997 19:28:09 METDST." <199704210128.TAA08535@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 21 Apr 1997 04:13:21 +0200 From: Terje Normann Marthinussen Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk >Hi, > >> Just sup'ed current, made the world and a new SMP kernel (suped 1 hour ago). >> ... >> It's been running on 4 CPU's now since december, and I've only had two >> crashes since then. It's not heavily loaded, but when it once in a while >> is loaded, it quite loaded chewing data that needs 50-100MB of memory >> and sometimes causing heavy paging as well (got 128MB on it). > >Cyrus recently identified a dead-lock in the APIC_IO version. The symptom >is a complete freeze of the system while doing heavy IO. Yes, I've followed the discussion. However, I've never seen the symptom, and it has made me wonder, probably just luck. In most cases the things this machine have done so far while running FreeBSD, has been tuned to fit into memory. However, I had one case while running the last pre-lite code, where I totally miscalculated memory need for an application here. I should run 3 instances in parallell and the code frequently traversed some large arrays. I thought all three processes should run nice in 90MB, however, I did something very stupid so each process used 60MB instead of 30. Had it trashing like mad on two 7200rpm FW HP disks while I was away for 4 days. It didn't manage to do much work due to the trashing, but it didn't crash either. On the other side, this machine is standing in a server room. And since it hasn't yet been put to the work it should do, it seldom has to deal with more than a couple of shell users, and only does some chewing when we don't have spare disk/cpu other more powerfull boxes. So, I'll have to admit that the usage it's probably not the best to find bugs. >Are you using the APIC_IO version? Used APIC_IO since before christmas. >When you say "crash", do you mean spontanious reboot, panic, or freeze? One reboot during the night and one panic that I never cared to follow up. Might have been other reboots, but at least I haven't seen them. Well, I should admit, there is one more, it was when I tested the famous FP exception problem. But running code that one knows will crash the system hardly counts in this case. >Earlier today I commited a "bandaid" that should help with this problem. >Did you get the version of mpapic.h that has "#define APICIPI_BANDAID" in it? Yes. Terje Marthinussen terjem@cc.uit.no From owner-freebsd-smp Sun Apr 20 22:23:33 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id WAA16487 for smp-outgoing; Sun, 20 Apr 1997 22:23:33 -0700 (PDT) Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id WAA16480 for freebsd-smp; Sun, 20 Apr 1997 22:23:31 -0700 (PDT) Date: Sun, 20 Apr 1997 22:23:31 -0700 (PDT) From: Steve Passe Message-Id: <199704210523.WAA16480@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/i386 mp_machdep.c Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/20 22:23:30 Modified: i386/i386 mp_machdep.c Log: removed the uneeded printf() asking for feedback from >2 CPU users. Revision Changes Path 1.39 +1 -9 sys/i386/i386/mp_machdep.c From owner-freebsd-smp Sun Apr 20 23:27:39 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id XAA18829 for smp-outgoing; Sun, 20 Apr 1997 23:27:39 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id XAA18813 for ; Sun, 20 Apr 1997 23:27:35 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id AAA10015; Mon, 21 Apr 1997 00:27:30 -0600 (MDT) Message-Id: <199704210627.AAA10015@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: "John W. DeBoskey" cc: freebsd-smp@freebsd.org Subject: Re: kernel for Dell 6100 4way In-reply-to: Your message of "Fri, 04 Apr 1997 00:14:47 EST." <199704040514.AA07258@iluvatar.unx.sas.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 21 Apr 1997 00:27:30 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > Could someone make a NCPU=4 kernel available for ftp? I'm having > trouble grabbing the correct code (via cvsup) due to the firewall that I > must work behind(socks trouble). The machine is a Dell 6100 with 4 200Mhz > PPro processors. I created a pair of SMP reference kernels (2 & 4 cpu) so that people can test them under -current without loading the entire tree and building: http://www.freebsd.org/~fsmp/SMP/files/kernel.2cpu.gz http://www.freebsd.org/~fsmp/SMP/files/kernel.4cpu.gz There are links to both on the main page. These are synced to 3.0-current as of 970418, with SMP patches thru 970420. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Mon Apr 21 00:00:21 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id AAA25212 for smp-outgoing; Mon, 21 Apr 1997 00:00:21 -0700 (PDT) Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id AAA25195 for freebsd-smp; Mon, 21 Apr 1997 00:00:18 -0700 (PDT) Date: Mon, 21 Apr 1997 00:00:18 -0700 (PDT) From: Steve Passe Message-Id: <199704210700.AAA25195@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/conf LINT Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/21 00:00:16 Modified: i386/conf LINT Log: add entries for building SMP kernels. Revision Changes Path 1.2 +409 -99 sys/i386/conf/LINT From owner-freebsd-smp Mon Apr 21 00:32:31 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id AAA26697 for smp-outgoing; Mon, 21 Apr 1997 00:32:31 -0700 (PDT) Received: from nlsystems.com (nlsys.demon.co.uk [158.152.125.33]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id AAA26683 for ; Mon, 21 Apr 1997 00:32:25 -0700 (PDT) Received: from herring.nlsystems.com (herring.nlsystems.com [10.0.0.2]) by nlsystems.com (8.8.5/8.8.5) with SMTP id IAA00305; Mon, 21 Apr 1997 08:31:50 +0100 (BST) Date: Mon, 21 Apr 1997 08:31:50 +0100 (BST) From: Doug Rabson To: Steve Passe cc: Peter Wemm , smp@freebsd.org Subject: Re: cvs commit: /home/smp/sys/kern init_smp.c In-Reply-To: <199704201617.KAA06759@Ilsa.StevesCafe.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Sun, 20 Apr 1997, Steve Passe wrote: > Hi, > > assumming that your hardware can boot a COMPLETELY GENERIC UP kernel, build > an SMP kernel that is COMPLETELY GENERIC, ie start with GENERIC and add ONLY: > > options SMP # Symmetric MultiProcessor Kernel > options NCPU=2 # number of CPUs > options APIC_IO # Symmetric (APIC) I/O > options SMP_INVLTLB # > > boot -v and -s, see how far you get... It was similar to the last config I tried but stopping in single user mode meant that I could capture the dmesg output. Basically, nothing printed on the console except kernel printfs appears until I try to break into the debugger with Ctl-SysRq. That seems to trigger some kind of delayed interrupt in syscons and the text appears. It doesn't matter whether DDB is in the kernel or not. Something odd is happening interrupt-wise. Maybe the clock isn't running? Copyright (c) 1992-1997 FreeBSD Inc. Copyright (c) 1982, 1986, 1989, 1991, 1993 The Regents of the University of California. All rights reserved. FreeBSD 3.0-SMP #0: Mon Apr 21 08:19:21 BST 1997 dfr@herring.nlsystems.com:/mnt/herring/a/dfr/smp/sys/compile/SMP FreeBSD/SMP: Multiprocessor motherboard cpu0 (BSP): apic id: 1, version: 0x00040011 cpu1 (AP): apic id: 0, version: 0x00040011 io0 (APIC): apic id: 2, version: 0x00170011 Calibrating clock(s) ... i8254 clock: 1193310 Hz CLK_USE_I8254_CALIBRATION not specified - using default frequency CPU: Pentium Pro (686-class CPU) Origin = "GenuineIntel" Id = 0x619 Stepping=9 Features=0xfbff,MTRR,PGE,MCA,CMOV> real memory = 68153344 (66556K bytes) avail memory = 63934464 (62436K bytes) bdevsw_add_generic: adding D_DISK flag for device 7 bdevsw_add_generic: adding D_DISK flag for device 16 bdevsw_add_generic: adding D_DISK flag for device 17 pcibus_setup(1): mode 1 addr port (0x0cf8) is 0x8000005c pcibus_setup(1a): mode1res=0x80000000 (0x80000000) pcibus_check: device 0 [class=60000] [hdr=0] is there (id=12378086) Probing for devices on PCI bus 0: configuration mode 1 allows 32 devices. chip0 rev 2 on pci0:0:0 chip1 rev 1 on pci0:7:0 chip2 rev 0 on pci0:7:1 mapreg[20] type=1 addr=0000ffa0 size=0010. I/O Recovery Timing: 8-bit 3.5 clocks, 16-bit 3.5 clocks Extended BIOS: disabled Lower BIOS: disabled Coprocessor IRQ13: disabled Mouse IRQ12: disabled Interrupt Routing: A: , B: , C: , D: MB0: , MB1: vga0 rev 1 int a irq 17 on pci0:18:0 Freeing (NOT implimented) irq 11 for ISA cards. mapreg[10] type=0 addr=ffafc000 size=4000. mapreg[14] type=0 addr=fe000000 size=800000. fxp0 rev 1 int a irq 18 on pci0:19:0 Freeing (NOT implimented) irq 9 for ISA cards. mapreg[10] type=0 addr=febff000 size=1000. mapreg[14] type=1 addr=0000ef80 size=0020. mapreg[18] type=0 addr=ff900000 size=100000. reg16: virtual=0xf4d16000 physical=0xfebff000 size=0x1000 fxp0: Ethernet address 00:a0:c9:30:2c:7b ahc0 rev 0 int a irq 19 on pci0:20:0 Freeing (NOT implimented) irq 10 for ISA cards. mapreg[10] type=1 addr=0000ec00 size=0100. mapreg[14] type=0 addr=ffafb000 size=1000. reg16: ioaddr=0xec00 size=0x100 ahc0: Reading SEEPROM...done. internal50 cable is present internal68 cable is present brdctl == 0x2c external cable not present eprom is present brdctl == 0xec low byte termination disabled, high byte termination enabled ahc0: aic7880 Wide Channel, SCSI Id=7, 16 SCBs ahc0: Downloading Sequencer Program...ahc0: 386 instructions downloaded Done ahc0: Probing channel A ahc0: waiting for scsi devices to settle scbus0 at ahc0 bus 0 ahc0: target 0 using 16Bit transfers ahc0: target 0 synchronous at 20.0MHz, offset = 0x8 sd0 at scbus0 target 0 lun 0 sd0: type 0 fixed SCSI 2 sd0: Direct-Access 4157MB (8515173 512 byte sectors) sd0: with 5720 cyls, 8 heads, and an average 186 sectors/track ahc0: target 6 synchronous at 10.0MHz, offset = 0xf cd0 at scbus0 target 6 lun 0 cd0: type 5 removable SCSI 2 cd0: CD-ROM cd present [258777 x 2048 byte records] pci0: uses 9461760d bytes of memory from fe000000 upto ffafffff. pci0: uses 304d bytes of I/O space from ec00 upto ffaf. Probing for devices on the ISA bus: sc0: the current keyboard controller command byte 0065 kbdio: RESET_KBD return code:00fa kbdio: RESET_KBD status:00aa sc0 at 0x60-0x6f irq 1 on motherboard sc0: VGA color <16 virtual consoles, flags=0x0> ed0 not found at 0x280 ed1 not found at 0x300 fe0 not found at 0x300 sio0 at 0x3f8-0x3ff irq 4 on isa sio0: type 16550A sio1 at 0x2f8-0x2ff irq 3 on isa sio1: type 16550A sio2: disabled, not probed. sio3: disabled, not probed. lpt0 at 0x378-0x37f irq 7 on isa lpt0: Interrupt-driven port lp0: TCP/IP capable interface lpt1 not found mse0: wrong signature ff mse0 not found at 0x23c psm0: disabled, not probed. fdc0 at 0x3f0-0x3f7 irq 6 drq 2 on isa fdc0: NEC 72065B fd0: 1.44MB 3.5in wdc0 not found at 0x1f0 wdc1 not found at 0x170 bt0 not found at 0x330 uha0 not found at 0x330 aha0 not found at 0x330 aic0 not found at 0x340 nca0 not found at 0x1f88 nca1 not found at 0x350 sea0 not found wt0 not found at 0x300 mcd0: timeout getting status mcd0 not found at 0x300 matcdc0 not found at 0x230 scd0 not found at 0x230 ie0: unknown board_id: f000 ie0 not found at 0x300 ie1: unknown board_id: f000 ie1 not found at 0x360 ep0 not found at 0x300 ex0 not found le0 not found at 0x300 lnc0 not found at 0x280 ze0 not found at 0x300 zp0 not found at 0x300 npx0 on motherboard npx0: INT 16 interface apm0: disabled, not probed. imasks: bio c0080040, tty f004009a, net f004009a BIOS Geometries: 0:0211fe3f 0..529=530 cylinders, 0..254=255 heads, 1..63=63 sectors 0 accounted for Device configuration finished. Considering FFS root f/s. changing root device to sd0a configure() finished. Enabled INTs: 1, 2, 3, 4, 6, 7, 8, 18, 19, imen: 0x00f3fe21 sd0s1: type 0xa5, start 63, end = 8514449, size 8514387 : OK SMP: All idle procs online. No debugger in kernel No debugger in kernel No debugger in kernel -- Doug Rabson Mail: dfr@nlsystems.com Nonlinear Systems Ltd. Phone: +44 181 951 1891 From owner-freebsd-smp Mon Apr 21 00:58:39 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id AAA27865 for smp-outgoing; Mon, 21 Apr 1997 00:58:39 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id AAA27860 for ; Mon, 21 Apr 1997 00:58:36 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id BAA10368; Mon, 21 Apr 1997 01:58:29 -0600 (MDT) Message-Id: <199704210758.BAA10368@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Doug Rabson cc: smp@freebsd.org Subject: Re: cvs commit: /home/smp/sys/kern init_smp.c In-reply-to: Your message of "Mon, 21 Apr 1997 08:31:50 BST." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 21 Apr 1997 01:58:29 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, >It was similar to the last config I tried but stopping in single user mode >meant that I could capture the dmesg output. Basically, nothing printed >on the console except kernel printfs appears until I try to break into the >debugger with Ctl-SysRq. That seems to trigger some kind of delayed >interrupt in syscons and the text appears. It doesn't matter whether DDB >is in the kernel or not. > >Something odd is happening interrupt-wise. Maybe the clock isn't running? kinda smells like it... you've been trying since yesterday so we can't blame todays defaulting of IRQ_LO_NC. I don't see an MP table around here for your system, if you've already sent one I guess I need another. What make and model of board is it? Haven't you successfully been using it with SMP b4 the Lite2 merge? I just put a set of reference SMP kernels on the main web page, you might want to grab the 2 CPU version and see if that works. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Mon Apr 21 01:24:42 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id BAA29054 for smp-outgoing; Mon, 21 Apr 1997 01:24:42 -0700 (PDT) Received: from nlsystems.com (nlsys.demon.co.uk [158.152.125.33]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id BAA29047 for ; Mon, 21 Apr 1997 01:24:36 -0700 (PDT) Received: from herring.nlsystems.com (herring.nlsystems.com [10.0.0.2]) by nlsystems.com (8.8.5/8.8.5) with SMTP id JAA00397; Mon, 21 Apr 1997 09:24:33 +0100 (BST) Date: Mon, 21 Apr 1997 09:24:33 +0100 (BST) From: Doug Rabson To: Steve Passe cc: smp@freebsd.org Subject: Re: cvs commit: /home/smp/sys/kern init_smp.c In-Reply-To: <199704210758.BAA10368@Ilsa.StevesCafe.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Mon, 21 Apr 1997, Steve Passe wrote: > Hi, > > >It was similar to the last config I tried but stopping in single user mode > >meant that I could capture the dmesg output. Basically, nothing printed > >on the console except kernel printfs appears until I try to break into the > >debugger with Ctl-SysRq. That seems to trigger some kind of delayed > >interrupt in syscons and the text appears. It doesn't matter whether DDB > >is in the kernel or not. > > > >Something odd is happening interrupt-wise. Maybe the clock isn't running? > > kinda smells like it... you've been trying since yesterday so we can't blame > todays defaulting of IRQ_LO_NC. I don't see an MP table around here for your > system, if you've already sent one I guess I need another. What make > and model of board is it? Haven't you successfully been using it with SMP > b4 the Lite2 merge? I haven't had this machine working with SMP at all yet. It is a new machine and it arrived after Lite2. Since I have been working on the Lite2 code with this machine, it hasn't been practical to try out the SMP kernel until now. The board is a SuperMicro P6DNE. The mptable is: =============================================================================== MPTable, version 2.0.6 ------------------------------------------------------------------------------- MP Floating Pointer Structure: location: BIOS physical address: 0x000fb070 signature: '_MP_' length: 16 bytes version: 1.1 checksum: 0x21 mode: Virtual Wire ------------------------------------------------------------------------------- MP Config Table Header: physical address: 0x000f5320 signature: 'PCMP' base table length: 284 version: 1.1 checksum: 0x43 OEM ID: 'INTEL ' Product ID: '440FX ' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 27 local APIC address: 0xfee00000 extended table length: 0 extended table checksum: 0 ------------------------------------------------------------------------------- MP Config Base Table Entries: -- Processors: APIC ID Version State Family Model Step Flags 1 0x11 BSP, usable 6 1 9 0xfbff 0 0x11 AP, usable 6 1 9 0xfbff -- Bus: Bus ID Type 0 PCI 1 ISA -- I/O APICs: APIC ID Version State Address 2 0x11 usable 0xfec00000 -- I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 1 0 2 0 INT conforms conforms 1 1 2 1 INT conforms conforms 1 0 2 2 INT conforms conforms 1 3 2 3 INT conforms conforms 1 4 2 4 INT conforms conforms 1 5 2 5 INT conforms conforms 1 6 2 6 INT conforms conforms 1 7 2 7 INT active-hi edge 1 8 2 8 INT conforms conforms 1 9 2 9 INT conforms conforms 1 10 2 10 INT conforms conforms 1 11 2 11 INT conforms conforms 1 12 2 12 INT conforms conforms 1 13 2 13 INT conforms conforms 1 14 2 14 INT conforms conforms 1 15 2 20 INT active-lo level 0 18:A 2 17 INT active-lo level 0 19:A 2 18 INT active-lo level 0 20:A 2 19 SMI conforms conforms 1 0 2 23 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 0 0:A 255 0 NMI conforms conforms 0 0:A 255 1 ------------------------------------------------------------------------------- # SMP kernel config file options: options SMP # Symmetric MultiProcessor Kernel options APIC_IO # Symmetric (APIC) I/O options NCPU=2 # number of CPUs options NBUS=2 # number of busses options NAPIC=1 # number of IO APICs options NINTR=24 # number of INTs options SMP_INVLTLB # #options SMP_PRIVPAGES # BROKEN, DO NOT use! #options SMP_AUTOSTART # BROKEN, DO NOT use! #options SERIAL_DEBUG # com port debug output =============================================================================== > > I just put a set of reference SMP kernels on the main web page, you might > want to grab the 2 CPU version and see if that works. Will do. -- Doug Rabson Mail: dfr@nlsystems.com Nonlinear Systems Ltd. Phone: +44 181 951 1891 From owner-freebsd-smp Mon Apr 21 01:38:02 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id BAA29637 for smp-outgoing; Mon, 21 Apr 1997 01:38:02 -0700 (PDT) Received: from nlsystems.com (nlsys.demon.co.uk [158.152.125.33]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id BAA29628 for ; Mon, 21 Apr 1997 01:37:57 -0700 (PDT) Received: from herring.nlsystems.com (herring.nlsystems.com [10.0.0.2]) by nlsystems.com (8.8.5/8.8.5) with SMTP id JAA00295; Mon, 21 Apr 1997 09:37:32 +0100 (BST) Date: Mon, 21 Apr 1997 09:37:32 +0100 (BST) From: Doug Rabson To: Peter Wemm cc: Steve Passe , smp@freebsd.org Subject: Re: cvs commit: /home/smp/sys/kern init_smp.c In-Reply-To: <199704201628.AAA09522@spinner.DIALix.COM> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Mon, 21 Apr 1997, Peter Wemm wrote: > Steve Passe wrote: > > Hi, > > > > assumming that your hardware can boot a COMPLETELY GENERIC UP kernel, build > > an SMP kernel that is COMPLETELY GENERIC, ie start with GENERIC and add ONLY: > > > > options SMP # Symmetric MultiProcessor Kernel > > options NCPU=2 # number of CPUs > > options APIC_IO # Symmetric (APIC) I/O > > options SMP_INVLTLB # > > > > boot -v and -s, see how far you get... > > Another thought.. Doug, Have you used -r or -D flags to 'cvs update' in > the past? They are sticky.. It might be an idea to redo a cvs update on your > tree with: "cvs update -d -P -A" to be sure... I know that's kinda > obvious, but I thought I'd mention it just in case.. No. I just rm -rf'ed the source tree and started again to make sure. I remember getting bitten by sticky tags in the past... -- Doug Rabson Mail: dfr@nlsystems.com Nonlinear Systems Ltd. Phone: +44 181 951 1891 From owner-freebsd-smp Mon Apr 21 01:59:17 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id BAA00551 for smp-outgoing; Mon, 21 Apr 1997 01:59:17 -0700 (PDT) Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id BAA00544 for freebsd-smp; Mon, 21 Apr 1997 01:59:15 -0700 (PDT) Date: Mon, 21 Apr 1997 01:59:15 -0700 (PDT) From: Peter Wemm Message-Id: <199704210859.BAA00544@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/isa sio.c sys/kern kern_fork.c sys/pci pcireg.h sys/i386/i386 swtch.s Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk peter 97/04/21 01:59:15 Modified: i386/i386 swtch.s i386/isa sio.c kern kern_fork.c pci pcireg.h Log: Merge in 970418 -> 970421 changes. Revision Changes Path 1.36 +7 -7 sys/i386/i386/swtch.s 1.17 +11 -5 sys/i386/isa/sio.c 1.11 +2 -2 sys/kern/kern_fork.c 1.7 +7 -1 sys/pci/pcireg.h From owner-freebsd-smp Mon Apr 21 02:10:43 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id CAA01242 for smp-outgoing; Mon, 21 Apr 1997 02:10:43 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id CAA01233; Mon, 21 Apr 1997 02:10:15 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id RAA16756; Mon, 21 Apr 1997 17:09:54 +0800 (WST) Message-Id: <199704210909.RAA16756@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Peter Wemm cc: freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/isa sio.c sys/kern kern_fork.c sys/pci pcireg.h sys/i386/i386 swtch.s In-reply-to: Your message of "Mon, 21 Apr 1997 01:59:15 MST." <199704210859.BAA00544@freefall.freebsd.org> Date: Mon, 21 Apr 1997 17:09:53 +0800 From: Peter Wemm Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Peter Wemm wrote: > peter 97/04/21 01:59:15 > > Modified: i386/i386 swtch.s > i386/isa sio.c > kern kern_fork.c > pci pcireg.h > Log: > Merge in 970418 -> 970421 changes. Just as a BTW, the other major things that came in with the 970421 import were Doug's NFS fixes, some timeout() fixes, and some other things that escape my memory.. Ah, including the vfork() fix from John Dyson - that change could be interesting since it excercises the shared vmspace system but on multiple cpu's... Cheers, -Peter From owner-freebsd-smp Mon Apr 21 02:26:52 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id CAA01672 for smp-outgoing; Mon, 21 Apr 1997 02:26:52 -0700 (PDT) Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id CAA01665 for freebsd-smp; Mon, 21 Apr 1997 02:26:50 -0700 (PDT) Date: Mon, 21 Apr 1997 02:26:50 -0700 (PDT) From: Peter Wemm Message-Id: <199704210926.CAA01665@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/i386 machdep.c sys/vm vm_kern.c vm_kern.h vm_object.c Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk peter 97/04/21 02:26:50 Modified: i386/i386 machdep.c vm vm_kern.c vm_kern.h vm_object.c Log: Check in something I was tinkering with some time ago, but doesn't look like it's going to work in it's present form until some magic is done with the PTD structure in processes that are sharing address spaces. This commit is to mainly get it out of my hair. Revision Changes Path 1.39 +17 -0 sys/i386/i386/machdep.c 1.2 +32 -36 sys/vm/vm_kern.c 1.2 +5 -1 sys/vm/vm_kern.h 1.2 +322 -140 sys/vm/vm_object.c From owner-freebsd-smp Mon Apr 21 02:30:05 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id CAA01885 for smp-outgoing; Mon, 21 Apr 1997 02:30:05 -0700 (PDT) Received: from nlsystems.com (nlsys.demon.co.uk [158.152.125.33]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id CAA01834; Mon, 21 Apr 1997 02:29:57 -0700 (PDT) Received: from herring.nlsystems.com (herring.nlsystems.com [10.0.0.2]) by nlsystems.com (8.8.5/8.8.5) with SMTP id KAA00421; Mon, 21 Apr 1997 10:29:22 +0100 (BST) Date: Mon, 21 Apr 1997 10:29:22 +0100 (BST) From: Doug Rabson To: Steve Passe cc: freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/i386 mp_machdep.c sys/i386/include smptests.h sys/i386/conf options.i386 sys/i386/isa clock.c isa.c In-Reply-To: <199704202022.NAA12514@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 On Sun, 20 Apr 1997, Steve Passe wrote: > fsmp 97/04/20 13:22:36 > > Modified: i386/conf options.i386 > Log: > added option SMP_TIMER_NC > this option informs the kernel that the motherboard MP table incorrectly > states that the 8254 timer is connected to the IO APIC. > it replaces the #define in smptests.h: FAKE_8254_NC That did it! I added SMP_TIMER_NC to my config and I am now up and running with the SuperMicro P6DNE machine. -- Doug Rabson Mail: dfr@nlsystems.com Nonlinear Systems Ltd. Phone: +44 181 951 1891 From owner-freebsd-smp Mon Apr 21 02:31:19 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id CAA01954 for smp-outgoing; Mon, 21 Apr 1997 02:31:19 -0700 (PDT) Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id CAA01942 for freebsd-smp; Mon, 21 Apr 1997 02:31:15 -0700 (PDT) Date: Mon, 21 Apr 1997 02:31:15 -0700 (PDT) From: Peter Wemm Message-Id: <199704210931.CAA01942@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/conf LINT Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk peter 97/04/21 02:31:14 Modified: i386/conf LINT Log: Document why the SMP_AUTOSTART and SMP_PRIVPAGES are broken. Autostart is broken simply because of a race or bug somewhere. Privpages is broken because of an architecture problem - private pages are incompatable with a shared PTD and page tables - which we now have as a result of a fully implemented rfork(RFPROC|RFMEM). Revision Changes Path 1.3 +2 -2 sys/i386/conf/LINT From owner-freebsd-smp Mon Apr 21 03:07:03 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id DAA03346 for smp-outgoing; Mon, 21 Apr 1997 03:07:03 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id DAA03337; Mon, 21 Apr 1997 03:06:43 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id SAA17187; Mon, 21 Apr 1997 18:06:04 +0800 (WST) Message-Id: <199704211006.SAA17187@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Doug Rabson cc: Steve Passe , freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/i386 mp_machdep.c sys/i386/include smptests.h sys/i386/conf options.i386 sys/i386/isa clock.c isa.c In-reply-to: Your message of "Mon, 21 Apr 1997 10:29:22 +0100." Date: Mon, 21 Apr 1997 18:06:03 +0800 From: Peter Wemm Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Doug Rabson wrote: > On Sun, 20 Apr 1997, Steve Passe wrote: > > > fsmp 97/04/20 13:22:36 > > > > Modified: i386/conf options.i386 > > Log: > > added option SMP_TIMER_NC > > this option informs the kernel that the motherboard MP table incorrectly > > states that the 8254 timer is connected to the IO APIC. > > it replaces the #define in smptests.h: FAKE_8254_NC > > That did it! I added SMP_TIMER_NC to my config and I am now up and > running with the SuperMicro P6DNE machine. Hmm.. I wonder how the hell we can detect this sort of problem at runtime? Having to twiddle half a dozen compile-time options to get a system booted isn't my idea of a good outcome.. I think the "best" answer is to decouple the idt slots and spl* bit patterns, then we can do things like spreading the idt load and have "lots" of interrupt sources... (eg: multiple apics) > -- > Doug Rabson Mail: dfr@nlsystems.com > Nonlinear Systems Ltd. Phone: +44 181 951 1891 Cheers, -Peter From owner-freebsd-smp Mon Apr 21 04:30:16 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id EAA07589 for smp-outgoing; Mon, 21 Apr 1997 04:30:16 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.visint.co.uk [194.207.134.1]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id EAA07584 for ; Mon, 21 Apr 1997 04:30:11 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.visint.co.uk [194.207.134.1]) by bagpuss.visint.co.uk (8.7.5/8.7.3) with SMTP id MAA00822; Mon, 21 Apr 1997 12:37:42 +0100 (BST) Date: Mon, 21 Apr 1997 12:37:42 +0100 (BST) From: Stephen Roome To: The Hermit Hacker cc: freebsd-smp@freebsd.org Subject: Re: Problems In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Sun, 20 Apr 1997, The Hermit Hacker wrote: > On Sun, 20 Apr 1997, Stephen Roome wrote: > > So, can someone let me know what parts of world need to be built and what > > parts don't, for me to at least have ps working. > > Before doing ps/w, you have to rebuild lib/libkvm...that's the only > library that I *know* of that needs to be rebuilt when kernel structures > change :( Okay, that's done and ps/w etc. now works properly. I'll get hold of top next. My final wondering point is wether it's worth or necessary to try another make world. Maybe it'll work now with a new kvm installed? Also, do I actually need to recompile programs for them to take full advantage of more CPU's or does the kernel handle this? Oh, and does anyone have experience they could share on stability as a web server ? The web pages at freebsd.org are... underfunded ? (Obviously I have no idea how SMP works, I got a 2:1 in my advanced computer architecture course at university hence I'm never going to understand any real-world problems) > > Marc G. Fournier > Systems Administrator @ hub.org > primary: scrappy@hub.org secondary: scrappy@{freebsd|postgresql}.org > > Steve Roome Technical Systems Manager, Vision Interactive Ltd. E: steve@visint.co.uk M: +44 (0) 976 241 342 T: +44 (0) 117 973 0597 F: +44 (0) 117 923 8522 From owner-freebsd-smp Mon Apr 21 06:22:57 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id GAA12718 for smp-outgoing; Mon, 21 Apr 1997 06:22:57 -0700 (PDT) Received: from weenix.guru.org (kmitch@phantasma.bevc.blacksburg.va.us [198.82.200.65]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id GAA12711 for ; Mon, 21 Apr 1997 06:22:51 -0700 (PDT) Received: (from kmitch@localhost) by weenix.guru.org (8.8.5/8.8.5) id JAA01735 for smp@freebsd.org; Mon, 21 Apr 1997 09:22:49 -0400 (EDT) From: Keith Mitchell NIS Message-Id: <199704211322.JAA01735@weenix.guru.org> Subject: SMP kernel freezes To: smp@freebsd.org Date: Mon, 21 Apr 1997 09:22:49 -0400 (EDT) X-Mailer: ELM [version 2.4ME+ PL30 (25)] 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 My SMP kernel has frozen twice now in the last 24 hours. My system is based off of -current from 4/19 and off of -smp as of 4/19. The first time it froze was during the system backup which is moderately I/O intensize. The second time, I was just typing a command on the command-line when it froze. My mptable output is already on file (weenix.guru.org) My kernel config is: # # WEENIX -- kernel config file for weenix.guru.org # # $Id: WEENIX,v 1.1.2.1 1997/03/16 23:38:45 kmitch Exp $ # machine "i386" cpu "I586_CPU" cpu "I686_CPU" ident WEENIX maxusers 20 options MATH_EMULATE #Support for x87 emulation options INET #InterNETworking options FFS #Berkeley Fast Filesystem options NFS #Network Filesystem options MSDOSFS #MSDOS Filesystem options "CD9660" #ISO 9660 Filesystem options PROCFS #Process filesystem options KERNFS #Kernel filesystem options DEVFS #Device filesystem options "EXT2FS" #Linux filesystem options "COMPAT_43" #Compatible with BSD 4.3 [KEEP THIS!] options SCSI_DELAY=15 #Be pessimistic about Joe SCSI device options UCONSOLE #Allow users to grab the console options FAILSAFE #Be conservative options USERCONFIG #boot -c editor options VISUAL_USERCONFIG #visual boot -c editor options SYSVMSG #System V Shared Memory options SYSVSHM #System V Shared Memory options SYSVSEM #System V Shared Memory options QUOTA #User Quotas options KTRACE #Kernel Tracing options LINUX #Linux Binary Compat options COMPAT_LINUX #Linux Binary Compat options IPFIREWALL #Firewall support options IPFIREWALL_VERBOSE #Verbose Firewall support options COM_MULTIPORT #Multiport serial card options INCLUDE_CONFIG_FILE #Include config in kernel config kernel root on sd0 controller isa0 controller eisa0 controller pci0 controller fdc0 at isa? port "IO_FD1" bio irq 6 drq 2 vector fdintr disk fd0 at fdc0 drive 0 disk fd1 at fdc0 drive 1 # # SMP options # options SMP options APIC_IO options SMP_INVLTLB # # SCSI options # options AHC_SCBPAGING_ENABLE options SCSI_REPORT_GEOMETRY controller ahc0 controller scbus0 at ahc0 bus 0 controller scbus1 at ahc0 bus 1 device sd0 at scbus0 target 0 device sd1 at scbus0 target 3 device st0 at scbus? device cd0 at scbus? device worm0 at scbus? # # Emulations # options "IBCS2" #SCO Compatibility # 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 # # Serial Devices # device sio0 at isa? port "IO_COM1" tty irq 4 vector siointr device sio1 at isa? port 0x3e8 tty flags 0x485 vector siointr device sio2 at isa? port 0x1a8 tty flags 0x485 vector siointr device sio3 at isa? port 0x1e8 tty flags 0x485 vector siointr device sio4 at isa? port 0x1f8 tty irq 3 flags 0x485 vector siointr device lpt0 at isa? port? tty irq 7 vector lptintr device psm0 at isa? port "IO_KBD" conflicts tty irq 12 vector psmintr # # Network Devices # device de0 # # Pseudo devices # pseudo-device loop pseudo-device ether pseudo-device log pseudo-device vn 3 pseudo-device sl 1 pseudo-device ccd 3 pseudo-device snp 3 pseudo-device ppp 1 pseudo-device tun 1 pseudo-device pty 32 pseudo-device gzip pseudo-device speaker pseudo-device bpfilter 4 -- Keith Mitchell Head Administrator: acm.vt.edu Email: kmitch@weenix.guru.org PGP key available upon request http://weenix.guru.org/~kmitch Address and URL (c) 1997 Keith Mitchell - All Rights Reserved Unauthorized use or duplication prohibited From owner-freebsd-smp Mon Apr 21 06:38:09 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id GAA13814 for smp-outgoing; Mon, 21 Apr 1997 06:38:09 -0700 (PDT) Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id GAA13799 for freebsd-smp; Mon, 21 Apr 1997 06:38:04 -0700 (PDT) Date: Mon, 21 Apr 1997 06:38:04 -0700 (PDT) From: Peter Wemm Message-Id: <199704211338.GAA13799@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/conf options.i386 sys/i386/isa clock.c isa.c Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk peter 97/04/21 06:38:03 Modified: i386/conf options.i386 i386/isa clock.c isa.c Log: Fix $Id$ spam Revision Changes Path 1.19 +1 -1 sys/i386/conf/options.i386 1.17 +1 -1 sys/i386/isa/clock.c 1.18 +1 -1 sys/i386/isa/isa.c From owner-freebsd-smp Mon Apr 21 07:00:39 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id HAA15264 for smp-outgoing; Mon, 21 Apr 1997 07:00:39 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id HAA15256 for ; Mon, 21 Apr 1997 07:00:30 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id WAA19023; Mon, 21 Apr 1997 22:00:01 +0800 (WST) Message-Id: <199704211400.WAA19023@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Keith Mitchell NIS cc: smp@freebsd.org Subject: Re: SMP kernel freezes In-reply-to: Your message of "Mon, 21 Apr 1997 09:22:49 -0400." <199704211322.JAA01735@weenix.guru.org> Date: Mon, 21 Apr 1997 22:00:00 +0800 From: Peter Wemm Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Keith Mitchell NIS wrote: > My SMP kernel has frozen twice now in the last 24 hours. My system is > based off of -current from 4/19 and off of -smp as of 4/19. The first > time it froze was during the system backup which is moderately I/O > intensize. The second time, I was just typing a command on the command-line > when it froze. [..] > # SCSI options > # > options AHC_SCBPAGING_ENABLE > options SCSI_REPORT_GEOMETRY > controller ahc0 I suspect the ahc controller "bit" you. I resync'ed with -current 970421 a short while ago - there were a some changes to the ahc code. Cheers, -Peter From owner-freebsd-smp Mon Apr 21 07:08:00 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id HAA15615 for smp-outgoing; Mon, 21 Apr 1997 07:08:00 -0700 (PDT) Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id HAA15608 for freebsd-smp; Mon, 21 Apr 1997 07:07:56 -0700 (PDT) Date: Mon, 21 Apr 1997 07:07:56 -0700 (PDT) From: Peter Wemm Message-Id: <199704211407.HAA15608@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/isa isa.c Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk peter 97/04/21 07:07:55 Modified: i386/isa isa.c Log: Attempt to repair the recently broken code for AUTO_EOI_1 and AUTO_EOI_2 in non-APIC mode. This kind of thing is important before we can merge back into -current. Revision Changes Path 1.19 +14 -6 sys/i386/isa/isa.c From owner-freebsd-smp Mon Apr 21 07:27:28 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id HAA16519 for smp-outgoing; Mon, 21 Apr 1997 07:27:28 -0700 (PDT) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id HAA16514; Mon, 21 Apr 1997 07:27:19 -0700 (PDT) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id QAA20618; Mon, 21 Apr 1997 16:00:54 +0200 (MET DST) Received: (from andreas@localhost) by klemm.gtn.com (8.8.5/8.8.2) id MAA18374; Mon, 21 Apr 1997 12:39:07 +0200 (CEST) Message-ID: <19970421123907.55305@klemm.gtn.com> Date: Mon, 21 Apr 1997 12:39:07 +0200 From: Andreas Klemm To: Doug Rabson Cc: Steve Passe , freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/i386 mp_machdep.c sys/i386/include smptests.h sys/i386/conf options.i386 sys/i386/isa clock.c isa.c References: <199704202022.NAA12514@freefall.freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 In-Reply-To: ; from Doug Rabson on Mon, Apr 21, 1997 at 10:29:22AM +0100 X-Disclaimer: A free society is one where it is safe to be unpopular X-Operating-System: FreeBSD 2.2-STABLE Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Mon, Apr 21, 1997 at 10:29:22AM +0100, Doug Rabson wrote: > On Sun, 20 Apr 1997, Steve Passe wrote: > > > fsmp 97/04/20 13:22:36 > > > > Modified: i386/conf options.i386 > > Log: > > added option SMP_TIMER_NC > > this option informs the kernel that the motherboard MP table incorrectly > > states that the 8254 timer is connected to the IO APIC. > > it replaces the #define in smptests.h: FAKE_8254_NC > > That did it! I added SMP_TIMER_NC to my config and I am now up and > running with the SuperMicro P6DNE machine. Congradulations ! -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-smp Mon Apr 21 07:51:05 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id HAA19213 for smp-outgoing; Mon, 21 Apr 1997 07:51:05 -0700 (PDT) Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id HAA19206 for freebsd-smp; Mon, 21 Apr 1997 07:51:03 -0700 (PDT) Date: Mon, 21 Apr 1997 07:51:03 -0700 (PDT) From: Peter Wemm Message-Id: <199704211451.HAA19206@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/i386 swtch.s trap.c Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk peter 97/04/21 07:51:03 Modified: i386/i386 swtch.s trap.c Log: Fix a couple of glitches that prevented compiling in !SMP mode Revision Changes Path 1.37 +4 -0 sys/i386/i386/swtch.s 1.19 +2 -0 sys/i386/i386/trap.c From owner-freebsd-smp Mon Apr 21 09:39:56 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id JAA28765 for smp-outgoing; Mon, 21 Apr 1997 09:39:56 -0700 (PDT) Received: from phaeton.artisoft.com (phaeton.Artisoft.COM [198.17.250.50]) by freefall.freebsd.org (8.8.5/8.8.5) with SMTP id JAA28752; Mon, 21 Apr 1997 09:39:46 -0700 (PDT) Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id JAA13674; Mon, 21 Apr 1997 09:37:36 -0700 From: Terry Lambert Message-Id: <199704211637.JAA13674@phaeton.artisoft.com> Subject: Re: cvs commit: sys/i386/i386 mp_machdep.c sys/i386/include smptests.h sys/i386/conf options.i386 sys/i386/isa clock.c isa.c To: peter@spinner.dialix.com (Peter Wemm) Date: Mon, 21 Apr 1997 09:37:36 -0700 (MST) Cc: dfr@nlsystems.com, fsmp@freefall.freebsd.org, freebsd-smp@freefall.freebsd.org In-Reply-To: <199704211006.SAA17187@spinner.DIALix.COM> from "Peter Wemm" at Apr 21, 97 06:06:03 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 > > > Modified: i386/conf options.i386 > > > Log: > > > added option SMP_TIMER_NC > > > this option informs the kernel that the motherboard MP table incorrectly > > > states that the 8254 timer is connected to the IO APIC. > > > it replaces the #define in smptests.h: FAKE_8254_NC > > > > That did it! I added SMP_TIMER_NC to my config and I am now up and > > running with the SuperMicro P6DNE machine. > > Hmm.. I wonder how the hell we can detect this sort of problem at > runtime? Having to twiddle half a dozen compile-time options to get a > system booted isn't my idea of a good outcome.. > > I think the "best" answer is to decouple the idt slots and spl* bit > patterns, then we can do things like spreading the idt load and have > "lots" of interrupt sources... (eg: multiple apics) The timer would be causing non-APIC int's, right? One way might be to count int's, and if the timer has not changed over some N count, then assume it's incorrectly identified. This should be front-loaded, so the timer check doesn't occur all the time. Alternately, request a patch for the MPtable from the vendor, since this is a known problem? Or ask them how NT copes? Regards, 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 Mon Apr 21 10:04:57 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id KAA00799 for smp-outgoing; Mon, 21 Apr 1997 10:04:57 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA00778; Mon, 21 Apr 1997 10:04:37 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id BAA24655; Tue, 22 Apr 1997 01:00:52 +0800 (WST) Message-Id: <199704211700.BAA24655@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Terry Lambert cc: dfr@nlsystems.com, fsmp@freefall.freebsd.org, freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/i386 mp_machdep.c sys/i386/include smptests.h sys/i386/conf options.i386 sys/i386/isa clock.c isa.c In-reply-to: Your message of "Mon, 21 Apr 1997 09:37:36 MST." <199704211637.JAA13674@phaeton.artisoft.com> Date: Tue, 22 Apr 1997 01:00:51 +0800 From: Peter Wemm Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Terry Lambert wrote: [...on detecting busted mptable...] > Or ask them how NT copes? I'm sticking my neck out here, I really do not remember exactly what happens (I've moved house recently, I have no idea where in hell my mpspec docs are at the moment), so here goes.. If my memory is correct, activating the apic is supposed to disable the diverted interrupts from being sent to the 8259's. If that's the case, then it should be a ``simple'' matter of leaving the 8259 active.. Once the apic has gone online, the interrupts should (I think) be presented to the apic only. On broken setups, the timer would go to the 8259 still. I think the main problem is the imen masking system, it only supports 28 interrupt sources, on the apic on typical 430HX pentium systems, there are 24 irq sources (I presume the P6 boards have a similar apic), and another 4 ipi sources put us at the limit. We need to "fix" this somehow, probably by grouping the interrupts by class for spl masking, and do lazy masking for individual interrupt sources. That could allow us to have more than one apic _and_ the 8259 "online", all going to seperate idt vectors. That allows us to spread the vectors out too, to get benefit from the per-priority-level fifos. I don't recall the specifics of why only one interrupt is supported via the daisy chaining at present. I don't remember whether Steve was simply using AUTO_EOI and passing throught the trigger to the apic, or if it was to avoid having to have seperate masks, or whether it was to try and round-robin the timer across the cpus. Cheers, -Peter From owner-freebsd-smp Mon Apr 21 10:11:52 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id KAA01241 for smp-outgoing; Mon, 21 Apr 1997 10:11:52 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA01220; Mon, 21 Apr 1997 10:11:19 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id LAA11721; Mon, 21 Apr 1997 11:11:17 -0600 (MDT) Message-Id: <199704211711.LAA11721@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Peter Wemm cc: freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/conf options.i386 sys/i386/isa clock.c isa.c In-reply-to: Your message of "Mon, 21 Apr 1997 06:38:04 PDT." <199704211338.GAA13799@freefall.freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 21 Apr 1997 11:11:17 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, > Modified: i386/conf options.i386 > i386/isa clock.c isa.c > Log: > Fix $Id$ spam Pass Stevie the pointed hat!!! Sorry Peter, I forgot that I need to use -ko for my local RCS checkins. Am I correct in believeing that this issue goes away when we are merged into -current? -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Mon Apr 21 10:14:09 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id KAA01367 for smp-outgoing; Mon, 21 Apr 1997 10:14:09 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA01345; Mon, 21 Apr 1997 10:13:43 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id LAA11738; Mon, 21 Apr 1997 11:13:42 -0600 (MDT) Message-Id: <199704211713.LAA11738@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Peter Wemm cc: freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/isa isa.c In-reply-to: Your message of "Mon, 21 Apr 1997 07:07:56 PDT." <199704211407.HAA15608@freefall.freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 21 Apr 1997 11:13:41 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, > peter 97/04/21 07:07:55 > > Modified: i386/isa isa.c > Log: > Attempt to repair the recently broken code for AUTO_EOI_1 and AUTO_EOI_2 > in non-APIC mode. This kind of thing is important before we can merge > back into -current. I am assumming I broke this, guessing that those AUTO_EOI defs in default_irq() were NOT my invention as my memory said, but part of the original code... I will be able to recvsup in an hour or two and see just what I stomped... -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Mon Apr 21 10:16:56 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id KAA01467 for smp-outgoing; Mon, 21 Apr 1997 10:16:56 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA01462 for ; Mon, 21 Apr 1997 10:16:53 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id LAA11695; Mon, 21 Apr 1997 11:08:30 -0600 (MDT) Message-Id: <199704211708.LAA11695@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Peter Wemm cc: Doug Rabson , freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/i386 mp_machdep.c sys/i386/include smptests.h sys/i386/conf options.i386 sys/i386/isa clock.c isa.c In-reply-to: Your message of "Mon, 21 Apr 1997 18:06:03 +0800." <199704211006.SAA17187@spinner.DIALix.COM> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 21 Apr 1997 11:08:30 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, > > That did it! I added SMP_TIMER_NC to my config and I am now up and > > running with the SuperMicro P6DNE machine. > > Hmm.. I wonder how the hell we can detect this sort of problem at > runtime? Having to twiddle half a dozen compile-time options to get a > system booted isn't my idea of a good outcome.. this has been evident to me for quite a while, just haven't had time to deal with it. It's particularily frustrating since this is a clear case of defective hardware. the solution: if ( TIMER_IRQ_IN_MPTABLE ) { setupAPICTimerIRQ(); spin( aWhile ); if ( intcount > 0 ) return 1; } setupMixedModeTimerIRQ() spin( aWhile ); if ( intcount > 0 ) return 1; panic( "this eats it!!!" ); -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Mon Apr 21 11:14:31 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id LAA04149 for smp-outgoing; Mon, 21 Apr 1997 11:14:31 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA04139 for ; Mon, 21 Apr 1997 11:14:16 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id CAA25486; Tue, 22 Apr 1997 02:13:29 +0800 (WST) Message-Id: <199704211813.CAA25486@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Steve Passe cc: freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/isa isa.c In-reply-to: Your message of "Mon, 21 Apr 1997 11:13:41 CST." <199704211713.LAA11738@Ilsa.StevesCafe.com> Date: Tue, 22 Apr 1997 02:13:28 +0800 From: Peter Wemm Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Steve Passe wrote: > Hi, > > > peter 97/04/21 07:07:55 > > > > Modified: i386/isa isa.c > > Log: > > Attempt to repair the recently broken code for AUTO_EOI_1 and AUTO_EOI_2 > > in non-APIC mode. This kind of thing is important before we can merge > > back into -current. > > I am assumming I broke this, guessing that those AUTO_EOI defs in default_irq () > were NOT my invention as my memory said, but part of the original code... > I will be able to recvsup in an hour or two and see just what I stomped... Yeah.. :-) AUTO_EOI_[12] are long-standing features from the UP kernel. Cheers, -Peter From owner-freebsd-smp Mon Apr 21 11:23:49 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id LAA04598 for smp-outgoing; Mon, 21 Apr 1997 11:23:49 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA04572 for ; Mon, 21 Apr 1997 11:23:38 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id CAA25625; Tue, 22 Apr 1997 02:22:52 +0800 (WST) Message-Id: <199704211822.CAA25625@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Steve Passe cc: dg@root.com, freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/isa isa.c In-reply-to: Your message of "Tue, 22 Apr 1997 02:13:28 +0800." <199704211813.CAA25486@spinner.DIALix.COM> Date: Tue, 22 Apr 1997 02:22:52 +0800 From: Peter Wemm Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Peter Wemm wrote: > Steve Passe wrote: > > Hi, > > > > > peter 97/04/21 07:07:55 > > > > > > Modified: i386/isa isa.c > > > Log: > > > Attempt to repair the recently broken code for AUTO_EOI_1 and AUTO_EOI_ 2 > > > in non-APIC mode. This kind of thing is important before we can merge > > > back into -current. > > > > I am assumming I broke this, guessing that those AUTO_EOI defs in default_i rq > () > > were NOT my invention as my memory said, but part of the original code... > > I will be able to recvsup in an hour or two and see just what I stomped... > > Yeah.. :-) AUTO_EOI_[12] are long-standing features from the UP kernel. Which I should mention, AUTO_EOI_1 is thought to work on all systems, but AUTO_EOI_2 is thought to not work on a good number of systems. I seem to have crossed wires somewhere thought, I thought AUTO_EOI_1 was turned on by default quite some time ago, but it doesn't seem that way in the code. Perhaps it was done on the 2.1 branch only or something. DG, are you listening? :-) Do you remember anything about this? > Cheers, > -Peter > Cheers, -Peter From owner-freebsd-smp Mon Apr 21 11:50:50 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id LAA06409 for smp-outgoing; Mon, 21 Apr 1997 11:50:50 -0700 (PDT) Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.19]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA06403 for ; Mon, 21 Apr 1997 11:50:43 -0700 (PDT) Received: (from bde@localhost) by godzilla.zeta.org.au (8.8.5/8.6.9) id EAA16329; Tue, 22 Apr 1997 04:46:40 +1000 Date: Tue, 22 Apr 1997 04:46:40 +1000 From: Bruce Evans Message-Id: <199704211846.EAA16329@godzilla.zeta.org.au> To: peter@spinner.dialix.com, smp@csn.net Subject: Re: cvs commit: sys/i386/isa isa.c Cc: dg@root.com, freebsd-smp@freefall.freebsd.org Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk >Which I should mention, AUTO_EOI_1 is thought to work on all systems, but >AUTO_EOI_2 is thought to not work on a good number of systems. I seem to AUTO_EOI_1 is thought to work on all systems except phk's laptop :-)... >have crossed wires somewhere thought, I thought AUTO_EOI_1 was turned on >by default quite some time ago, but it doesn't seem that way in the code. ... so it didn't stat enabled by default for long. Bruce From owner-freebsd-smp Mon Apr 21 11:54:29 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id LAA06670 for smp-outgoing; Mon, 21 Apr 1997 11:54:29 -0700 (PDT) Received: from uruk.org (root@ns.uruk.org [198.145.95.253]) by freefall.freebsd.org (8.8.5/8.8.5) with SMTP id LAA06661 for ; Mon, 21 Apr 1997 11:54:25 -0700 (PDT) Received: from uruk.org [127.0.0.1] (erich) by uruk.org with esmtp (Exim 0.53 #1) id E0wJNMB-0007ay-00; Mon, 21 Apr 1997 10:58:27 -0700 To: Steve Passe cc: freebsd-smp@freefall.freebsd.org Subject: Writing APIC document In-reply-to: Your message of "Mon, 21 Apr 1997 12:15:29 MDT." <199704211815.MAA11952@Ilsa.StevesCafe.com> Date: Mon, 21 Apr 1997 10:58:27 -0700 From: Erich Boleyn Message-Id: Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Steve Passe wrote: > One of my top priorities now is to write a whitepaper for the webpage > describe the current (and possible future) inplimentation of the APIC > code, along with all the WHYs of the design. it's fairly arcane, and > even the author (meaning me) forgets why some of the wierder stuff > is in there. (remember all the 'fun' we had getting the AP startup > IPIs working? talk about code that makes no sense at all!!!) I'm working on a similar doc, but it is specifically about the APIC "architecture" (ahem), the important differences and similarities in the implementations, and how they are used in the Intel MP Spec. -- 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 Mon Apr 21 12:06:01 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id MAA07338 for smp-outgoing; Mon, 21 Apr 1997 12:06:01 -0700 (PDT) Received: from critter.dk.tfs.com (phk.cybercity.dk [195.8.129.17]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA07295; Mon, 21 Apr 1997 12:05:14 -0700 (PDT) Received: from critter (localhost [127.0.0.1]) by critter.dk.tfs.com (8.8.5/8.8.5) with ESMTP id VAA01863; Mon, 21 Apr 1997 21:04:18 +0200 (CEST) To: Bruce Evans cc: peter@spinner.dialix.com, smp@csn.net, dg@root.com, freebsd-smp@freefall.freebsd.org From: Poul-Henning Kamp Subject: Re: cvs commit: sys/i386/isa isa.c In-reply-to: Your message of "Tue, 22 Apr 1997 04:46:40 +1000." <199704211846.EAA16329@godzilla.zeta.org.au> Date: Mon, 21 Apr 1997 21:04:18 +0200 Message-ID: <1861.861649458@critter> Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk In message <199704211846.EAA16329@godzilla.zeta.org.au>, Bruce Evans writes: >>Which I should mention, AUTO_EOI_1 is thought to work on all systems, but >>AUTO_EOI_2 is thought to not work on a good number of systems. I seem to > >AUTO_EOI_1 is thought to work on all systems except phk's laptop :-)... > >>have crossed wires somewhere thought, I thought AUTO_EOI_1 was turned on >>by default quite some time ago, but it doesn't seem that way in the code. > >... so it didn't stat enabled by default for long. Well, I had more than my laptop complain actually. The problem seems to be a fair share of the systems that use power management, with or without APM. Can we make it a flag settable with "boot -c", then we can try to enable it again... -- Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. whois: [PHK] | phk@tfs.com TRW Financial Systems, Inc. Power and ignorance is a disgusting cocktail. From owner-freebsd-smp Mon Apr 21 13:29:44 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id NAA11714 for smp-outgoing; Mon, 21 Apr 1997 13:29:44 -0700 (PDT) Received: from root.com (implode.root.com [198.145.90.17]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA11692 for ; Mon, 21 Apr 1997 13:29:42 -0700 (PDT) Received: from localhost (localhost [127.0.0.1]) by root.com (8.8.5/8.6.5) with SMTP id NAA07077; Mon, 21 Apr 1997 13:31:07 -0700 (PDT) Message-Id: <199704212031.NAA07077@root.com> X-Authentication-Warning: implode.root.com: localhost [127.0.0.1] didn't use HELO protocol To: Peter Wemm cc: Steve Passe , freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/isa isa.c In-reply-to: Your message of "Tue, 22 Apr 1997 02:22:52 +0800." <199704211822.CAA25625@spinner.DIALix.COM> From: David Greenman Reply-To: dg@root.com Date: Mon, 21 Apr 1997 13:31:07 -0700 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk >Perhaps it was done on the 2.1 branch only or something. DG, are you >listening? :-) Do you remember anything about this? I'm listening, but Bruce and Poul have answered this already. -DG David Greenman Core-team/Principal Architect, The FreeBSD Project From owner-freebsd-smp Mon Apr 21 15:33:59 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id PAA18287 for smp-outgoing; Mon, 21 Apr 1997 15:33:59 -0700 (PDT) Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id PAA18275 for freebsd-smp; Mon, 21 Apr 1997 15:33:56 -0700 (PDT) Date: Mon, 21 Apr 1997 15:33:56 -0700 (PDT) From: Steve Passe Message-Id: <199704212233.PAA18275@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/i386 autoconf.c mp_machdep.c mpapic.c Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/21 15:33:56 Modified: i386/i386 autoconf.c mp_machdep.c mpapic.c Log: busted by the style police. how's this guys? Revision Changes Path 1.15 +2 -2 sys/i386/i386/autoconf.c 1.40 +235 -235 sys/i386/i386/mp_machdep.c 1.28 +79 -79 sys/i386/i386/mpapic.c From owner-freebsd-smp Mon Apr 21 19:03:24 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id TAA05522 for smp-outgoing; Mon, 21 Apr 1997 19:03:24 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id TAA05515 for ; Mon, 21 Apr 1997 19:03:21 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id UAA13431 for ; Mon, 21 Apr 1997 20:03:18 -0600 (MDT) Message-Id: <199704220203.UAA13431@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: smp@freebsd.org Subject: Rogue board classification Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 21 Apr 1997 20:03:18 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, >> this option informs the kernel that the motherboard MP table incorrectly >> states that the 8254 timer is connected to the IO APIC. >> it replaces the #define in smptests.h: FAKE_8254_NC > >That did it! I added SMP_TIMER_NC to my config and I am now up and >running with the SuperMicro P6DNE machine. I need a show of hands: who has a SuperMicro P6DNE board running SMP *with* APIC_IO? if so, did you have to use FAKE_8254_NC (or SMP_TIMER_NC) to get it working? -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Mon Apr 21 19:29:59 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id TAA06725 for smp-outgoing; Mon, 21 Apr 1997 19:29:59 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id TAA06719 for ; Mon, 21 Apr 1997 19:29:56 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id UAA13580; Mon, 21 Apr 1997 20:29:53 -0600 (MDT) Message-Id: <199704220229.UAA13580@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Steve Price cc: smp@freebsd.org Subject: Re: Rogue board classification In-reply-to: Your message of "Mon, 21 Apr 1997 21:15:49 CDT." <335C1F55.41C67EA6@hiwaay.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 21 Apr 1997 20:29:53 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > > who has a SuperMicro P6DNE board running SMP *with* APIC_IO? > > if so, did you have to use FAKE_8254_NC (or SMP_TIMER_NC) to get it > > working? > > I have one and yes I had to use FAKE_8254_NC. 2nd report, I have thus added the P6DNE to the rogue page. Current users should be aware that the "#define FAKE_8254_NC" has been removed from smptests.h. It is now handled as a kernel config option called SMP_TIMER_NC for details, see: http://www.freebsd.org/~fsmp/SMP/timernc.html -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Mon Apr 21 21:55:19 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id VAA13626 for smp-outgoing; Mon, 21 Apr 1997 21:55:19 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id VAA13621 for ; Mon, 21 Apr 1997 21:55:16 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id WAA14074 for ; Mon, 21 Apr 1997 22:54:57 -0600 (MDT) Message-Id: <199704220454.WAA14074@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: smp@freebsd.org Subject: hardware list Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 21 Apr 1997 22:54:57 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, I'm updating the list of known working hardware. Please take a moment and fill out the following form: ------------------------------------ cut -------------------------------------- --- Make/Model of motherboard: --- Http links to manufacturer and/or board info: --- SMP kernel works [yes/no]: --- APIC_IO works [yes/no]: --- Special #defines/options needed: --- Comments: ------------------------------------ cut -------------------------------------- -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Mon Apr 21 22:16:19 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id WAA14693 for smp-outgoing; Mon, 21 Apr 1997 22:16:19 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id WAA14687 for ; Mon, 21 Apr 1997 22:16:16 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id XAA14148 for ; Mon, 21 Apr 1997 23:16:15 -0600 (MDT) Message-Id: <199704220516.XAA14148@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: smp@freebsd.org Subject: Re: hardware list Date: Mon, 21 Apr 1997 23:16:15 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk --- Make/Model of motherboard: Giga-byte GA586DX --- Http links to manufacturer and/or board info: http://www.giga-byte.com/GA586DX.html --- SMP kernel works [yes/no]: yes --- APIC_IO works [yes/no]: yes --- Special #defines/options needed: none --- Comments: works reliably, probably has bridged PCI card problem. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Mon Apr 21 22:17:02 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id WAA14721 for smp-outgoing; Mon, 21 Apr 1997 22:17:02 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id WAA14716 for ; Mon, 21 Apr 1997 22:16:59 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id XAA14156 for ; Mon, 21 Apr 1997 23:16:58 -0600 (MDT) Message-Id: <199704220516.XAA14156@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: smp@freebsd.org Subject: Re: hardware list Date: Mon, 21 Apr 1997 23:16:58 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk --- Make/Model of motherboard: Giga-byte GA686DX --- Http links to manufacturer and/or board info: http://www.giga-byte.com/GA686DX.html --- SMP kernel works [yes/no]: yes --- APIC_IO works [yes/no]: yes --- Special #defines/options needed: none --- Comments: works reliably, probably has bridged PCI card problem. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Mon Apr 21 22:58:15 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id WAA16477 for smp-outgoing; Mon, 21 Apr 1997 22:58:15 -0700 (PDT) Received: from housing1.stucen.gatech.edu (ken@housing1.stucen.gatech.edu [130.207.52.71]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id WAA16472 for ; Mon, 21 Apr 1997 22:58:12 -0700 (PDT) Received: (from ken@localhost) by housing1.stucen.gatech.edu (8.8.5/8.8.5) id BAA24823; Tue, 22 Apr 1997 01:57:59 -0400 (EDT) From: Kenneth Merry Message-Id: <199704220557.BAA24823@housing1.stucen.gatech.edu> Subject: Re: hardware list In-Reply-To: <199704220454.WAA14074@Ilsa.StevesCafe.com> from Steve Passe at "Apr 21, 97 10:54:57 pm" To: smp@csn.net (Steve Passe) Date: Tue, 22 Apr 1997 01:57:59 -0400 (EDT) Cc: smp@freebsd.org X-Mailer: ELM [version 2.4ME+ PL31 (25)] 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 --- Make/Model of motherboard: ASUS P/I-P65UP5 with C-P6ND CPU card --- Http links to manufacturer and/or board info: http://www.asus.com.tw/ http://www.asus.com.tw/Products/SPEC/P6/pi-p65up5.html http://www.asus.com/ http://www.asus.com/products/specs/mb/P65UP5-spec.asp --- SMP kernel works [yes/no]: yes --- APIC_IO works [yes/no]: yes --- Special #defines/options needed: Make sure you enable MP spec version 1.4 in the BIOS --- Comments: It's a pretty cool board -- 8 SIMM slots, up to 512MB RAM, and 5 PCI slots. According to the docs, you can't use SIMMS with more than about 24 DRAM chips on them, so composite 64MB SIMMs are out. (i.e. 32 or 36 chip 64MB SIMMs aren't guaranteed to work) The 5th slot is the same as the fourth, wiring/interrupt-wise, so make sure that if you use those slots the cards work okay sharing interrupts. In general that shouldn't be a problem, though. The CPUs reside on a daughtercard that plugs into the motherboard. You can get either a dual Pentium daughtercard with the Triton II chipset, or a dual Pentium Pro daughtercard with the Natoma chipset. Ken -- Kenneth Merry ken@ulc199.residence.gatech.edu Disclaimer: I don't speak for GTRI, GT, or Elvis. From owner-freebsd-smp Tue Apr 22 02:45:14 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id CAA04681 for smp-outgoing; Tue, 22 Apr 1997 02:45:14 -0700 (PDT) Received: from nlsystems.com (nlsys.demon.co.uk [158.152.125.33]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id CAA04676 for ; Tue, 22 Apr 1997 02:45:11 -0700 (PDT) Received: from herring.nlsystems.com (herring.nlsystems.com [10.0.0.2]) by nlsystems.com (8.8.5/8.8.5) with SMTP id KAA29971; Tue, 22 Apr 1997 10:45:07 +0100 (BST) Date: Tue, 22 Apr 1997 10:45:07 +0100 (BST) From: Doug Rabson To: Steve Passe cc: smp@freebsd.org Subject: Re: Rogue board classification In-Reply-To: <199704220203.UAA13431@Ilsa.StevesCafe.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Mon, 21 Apr 1997, Steve Passe wrote: > Hi, > > >> this option informs the kernel that the motherboard MP table incorrectly > >> states that the 8254 timer is connected to the IO APIC. > >> it replaces the #define in smptests.h: FAKE_8254_NC > > > >That did it! I added SMP_TIMER_NC to my config and I am now up and > >running with the SuperMicro P6DNE machine. > > I need a show of hands: > > who has a SuperMicro P6DNE board running SMP *with* APIC_IO? > if so, did you have to use FAKE_8254_NC (or SMP_TIMER_NC) to get it working? I have one and I had to use SMP_TIMER_NC to get it working. -- Doug Rabson Mail: dfr@nlsystems.com Nonlinear Systems Ltd. Phone: +44 181 951 1891 From owner-freebsd-smp Tue Apr 22 05:03:51 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id FAA11004 for smp-outgoing; Tue, 22 Apr 1997 05:03:51 -0700 (PDT) Received: from cais.cais.com (root@cais.com [199.0.216.4]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id FAA10999 for ; Tue, 22 Apr 1997 05:03:49 -0700 (PDT) Received: from earth.mat.net (root@earth.mat.net [205.252.122.1]) by cais.cais.com (8.8.5/8.7.3) with SMTP id IAA23325; Tue, 22 Apr 1997 08:03:47 -0400 (EDT) Received: from Journey2.mat.net (journey2.mat.net [205.252.122.116]) by earth.mat.net (8.6.12/8.6.12) with SMTP id IAA28349; Tue, 22 Apr 1997 08:03:45 -0400 Date: Tue, 22 Apr 1997 08:03:15 -0400 (EDT) From: Chuck Robey To: Steve Passe cc: smp@freebsd.org Subject: Re: hardware list In-Reply-To: <199704220454.WAA14074@Ilsa.StevesCafe.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Mon, 21 Apr 1997, Steve Passe wrote: > Hi, > > I'm updating the list of known working hardware. Please take a moment > and fill out the following form: > > ------------------------------------ cut -------------------------------------- > --- > Make/Model of motherboard: Tyan Titan II > --- > Http links to manufacturer and/or board info: http://www.tyan.com > --- > SMP kernel works [yes/no]: Yes > --- > APIC_IO works [yes/no]: Yes > --- > Special #defines/options needed: None > --- > Comments: > ------------------------------------ cut -------------------------------------- > -- > Steve Passe | powered by > smp@csn.net | Symmetric MultiProcessor FreeBSD > > > > ----------------------------+----------------------------------------------- Chuck Robey | Interests include any kind of voice or data chuckr@eng.umd.edu | communications topic, C programming, and Unix. 9120 Edmonston Ct #302 | Greenbelt, MD 20770 | I run Journey2 and picnic, both FreeBSD (301) 220-2114 | version 3.0 current -- and great FUN! ----------------------------+----------------------------------------------- From owner-freebsd-smp Tue Apr 22 06:30:56 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id GAA14858 for smp-outgoing; Tue, 22 Apr 1997 06:30:56 -0700 (PDT) Received: from babe.globecomm.net (babe.globecomm.net [207.51.48.8]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id GAA14853 for ; Tue, 22 Apr 1997 06:30:54 -0700 (PDT) Received: from warp.starnets.ro (warp.starnets.ro [193.226.124.33]) by babe.globecomm.net (8.8.5/8.8.0) with SMTP id JAA14329; Tue, 22 Apr 1997 09:30:44 -0400 (EDT) Message-ID: <335CBC8A.4044@earthling.net> Date: Tue, 22 Apr 1997 16:26:34 +0300 From: Penisoara Adrian Reply-To: ady@earthling.net X-Mailer: Mozilla 3.01Gold (Win95; I) MIME-Version: 1.0 To: Steve Passe CC: smp@freebsd.org Subject: Re: hardware list References: Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk --- Make/Model of motherboard: Tyan Tomcat III S1563D --- Http links to manufacturer and/or board info: http://www.tyan.com --- SMP kernel works [yes/no]: Yes --- APIC_IO works [yes/no]: Yes --- Special #defines/options needed: None From owner-freebsd-smp Tue Apr 22 06:35:24 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id GAA15010 for smp-outgoing; Tue, 22 Apr 1997 06:35:24 -0700 (PDT) Received: from intercore.com (num1sun.intercore.com [199.181.243.1]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id GAA15005 for ; Tue, 22 Apr 1997 06:35:22 -0700 (PDT) Received: (robin@localhost) by intercore.com (8.7.1/8.6.4) id JAA18829; Tue, 22 Apr 1997 09:35:00 -0400 (EDT) Message-Id: <199704221335.JAA18829@intercore.com> Date: Tue, 22 Apr 1997 09:34:59 -0400 From: robin@intercore.com (Robin Cutshaw) To: smp@csn.net (Steve Passe) Cc: smp@freebsd.org Subject: Re: hardware list In-Reply-To: <199704220454.WAA14074@Ilsa.StevesCafe.com>; from Steve Passe on Apr 21, 1997 22:54:57 -0600 References: <199704220454.WAA14074@Ilsa.StevesCafe.com> X-Mailer: Mutt 0.47 Mime-Version: 1.0 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Steve Passe writes: > > I'm updating the list of known working hardware. Please take a moment > and fill out the following form: > You would probably get a larger response if an smp-snapshot were cut (hint hint). :-) I haven't been tracking -current since it was no longer useful with smp. I'm running the last -current snapshot that worked with the smp kernel. robin -- ---- Robin Cutshaw internet: robin@interlabs.com robin@intercore.com Internet Labs, Inc. BellNet: 404-817-9787 "Time is just one damn thing after another" -- PBS/Nova ---- -- From owner-freebsd-smp Tue Apr 22 10:25:25 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA26599 for smp-outgoing; Tue, 22 Apr 1997 10:25:25 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA26593; Tue, 22 Apr 1997 10:25:22 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id LAA16301; Tue, 22 Apr 1997 11:25:04 -0600 (MDT) Message-Id: <199704221725.LAA16301@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Keith Mitchell NIS cc: scsi@freebsd.org, smp@freebsd.org Subject: Re: Freezes/Reboots with -current ahc driver In-reply-to: Your message of "Tue, 22 Apr 1997 09:14:06 EDT." <199704221314.JAA22747@weenix.guru.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 11:25:03 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > I just upgraded my 2.2-STABLE system (from around April 1) to 3.0-current > (as of April 21) to gain use of the SMP stuff. > > Now, I am experiancing system freezes and reboots during the > nightly backup. No error messages ever appear from what I can tell. > The little SCSI light doesn;t even stay solidly lit when the system > freezes. I didn't have any problems with the 2.2-STABLE system. > > I am only using SCB paging. Tagged queuing has never worked with my > Micropolis 4221W. I just get all kinds of timeouts with tht option > on. > > Has anyone else seen anything similar?? details please. what backup tool are you using when it crashes? are any NFS mounted partitions involved? are you using APIC_IO? is ddb installed in your kernel, if not please add. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Apr 22 10:32:26 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA27208 for smp-outgoing; Tue, 22 Apr 1997 10:32:26 -0700 (PDT) Received: from tacitus.globecomm.net (tacitus.globecomm.net [207.51.48.7]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA27198 for ; Tue, 22 Apr 1997 10:32:23 -0700 (PDT) Received: from warp.starnets.ro (warp.starnets.ro [193.226.124.33]) by tacitus.globecomm.net (8.8.5/8.8.0) with SMTP id NAA24463 for ; Tue, 22 Apr 1997 13:32:14 -0400 (EDT) Message-ID: <335CF51A.6C26@earthling.net> Date: Tue, 22 Apr 1997 20:27:54 +0300 From: Penisoara Adrian Reply-To: ady@earthling.net X-Mailer: Mozilla 3.01Gold (Win95; I) MIME-Version: 1.0 To: smp@FreeBSD.org Subject: Possible typo in sys sources ? Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi I got a nasty error when I tried to compile a kernel cvsup'ed today: - CVSup'd a "sys-src release=smp" kernel - checkout sys & renamed in sys-MP - made 'config ADYSMP' in i386/conf - 'make depend' in ../../compile/ADYSMP - make and complains about an undefined variable (xitp) in ../../kern/init_main.c line 180. Stop. - edited ../../kern/init_main.c and in line 180 changed from "*sipp = *xitp" to "*sipp = *xipp" (it's in a bubble sort) - again made "config ADYSMP" - make depend && make works OK Now it may be very possible to be a disk error because I had some problems today with an IDE disk (I use a SCSI one for root); I'll make another clean cvsup tomorrow. I hope you'll excuse me if I was wrong; it's just that tomorrow I have big plans and I want to be prepared... Ady (@earthling.net) From owner-freebsd-smp Tue Apr 22 10:38:17 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA27641 for smp-outgoing; Tue, 22 Apr 1997 10:38:17 -0700 (PDT) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA27633 for ; Tue, 22 Apr 1997 10:38:07 -0700 (PDT) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id TAA13209; Tue, 22 Apr 1997 19:15:38 +0200 (MET DST) Received: (from andreas@localhost) by klemm.gtn.com (8.8.5/8.8.2) id TAA04368; Tue, 22 Apr 1997 19:14:40 +0200 (CEST) Message-ID: <19970422191440.65411@klemm.gtn.com> Date: Tue, 22 Apr 1997 19:14:40 +0200 From: Andreas Klemm To: Steve Passe Cc: smp@FreeBSD.org Subject: Re: hardware list References: <199704220454.WAA14074@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 In-Reply-To: <199704220454.WAA14074@Ilsa.StevesCafe.com>; from Steve Passe on Mon, Apr 21, 1997 at 10:54:57PM -0600 X-Disclaimer: A free society is one where it is safe to be unpopular X-Operating-System: FreeBSD 2.2-STABLE Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk --- Make/Model of motherboard: Tyan Titan Pro ATX (S1668ATX) BIOS Version 3.03 --- Http links to manufacturer and/or board info: http://www.tyan.com/html/s1668.html --- SMP kernel works [yes/no]: yes --- APIC_IO works [yes/no]: yes --- Special #defines/options needed: no, only needed options SMP options APIC_IO options SMP_INVLTLB --- Comments: 5 PCI Slots 3 ISA Slots (1 shared) 8 SIMM Sockets -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-smp Tue Apr 22 10:45:44 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA28052 for smp-outgoing; Tue, 22 Apr 1997 10:45:44 -0700 (PDT) Received: from critter.dk.tfs.com (phk.cybercity.dk [195.8.129.17]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA28042; Tue, 22 Apr 1997 10:45:36 -0700 (PDT) Received: from critter (localhost [127.0.0.1]) by critter.dk.tfs.com (8.8.5/8.8.5) with ESMTP id TAA03513; Tue, 22 Apr 1997 19:44:35 +0200 (CEST) To: ady@earthling.net cc: smp@FreeBSD.org From: Poul-Henning Kamp Subject: Re: Possible typo in sys sources ? In-reply-to: Your message of "Tue, 22 Apr 1997 20:27:54 +0300." <335CF51A.6C26@earthling.net> Date: Tue, 22 Apr 1997 19:44:35 +0200 Message-ID: <3511.861731075@critter> Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk In message <335CF51A.6C26@earthling.net>, Penisoara Adrian writes: >Hi > - edited ../../kern/init_main.c and in line 180 changed from "*sipp = >*xitp" to "*sipp = *xipp" (it's in a bubble sort) We have qsort() in the kernel, replace it wholesale... -- Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. whois: [PHK] | phk@tfs.com TRW Financial Systems, Inc. Power and ignorance is a disgusting cocktail. From owner-freebsd-smp Tue Apr 22 10:45:58 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA28077 for smp-outgoing; Tue, 22 Apr 1997 10:45:58 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.vis.net.uk [194.207.134.1]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA27882 for ; Tue, 22 Apr 1997 10:42:46 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.vis.net.uk [194.207.134.1]) by bagpuss.visint.co.uk (8.7.5/8.7.3) with SMTP id SAA24872; Tue, 22 Apr 1997 18:48:14 +0100 (BST) Date: Tue, 22 Apr 1997 18:48:14 +0100 (BST) From: Stephen Roome To: Robin Cutshaw cc: Steve Passe , smp@freebsd.org Subject: Re: hardware list In-Reply-To: <199704221335.JAA18829@intercore.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Tue, 22 Apr 1997, Robin Cutshaw wrote: > You would probably get a larger response if an smp-snapshot were cut (hint > hint). :-) grovel. =) I've got two boxes here to install smp on, and this would make life for me slightly easier, for a start I could mirror things properly and get a wipe/reinstall going much faster. -- Steve Roome Technical Systems Manager, Vision Interactive Ltd. E: steve@visint.co.uk M: +44 (0) 976 241 342 T: +44 (0) 117 973 0597 F: +44 (0) 117 923 8522 From owner-freebsd-smp Tue Apr 22 10:54:27 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA28793 for smp-outgoing; Tue, 22 Apr 1997 10:54:27 -0700 (PDT) Received: from Campino.Informatik.RWTH-Aachen.DE (campino.Informatik.RWTH-Aachen.DE [137.226.116.240]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA28781 for ; Tue, 22 Apr 1997 10:54:19 -0700 (PDT) Received: from gilberto.physik.rwth-aachen.de (gilberto.physik.rwth-aachen.de [137.226.31.2]) by Campino.Informatik.RWTH-Aachen.DE (RBI-Z-5/8.6.12) with ESMTP id TAA18248 for ; Tue, 22 Apr 1997 19:54:52 +0200 (MET DST) Received: (from kuku@localhost) by gilberto.physik.rwth-aachen.de (8.8.5/8.6.9) id UAA13148 for freebsd-smp@freebsd.org; Tue, 22 Apr 1997 20:10:40 +0200 (MET DST) Date: Tue, 22 Apr 1997 20:10:40 +0200 (MET DST) From: Christoph Kukulies Message-Id: <199704221810.UAA13148@gilberto.physik.rwth-aachen.de> To: freebsd-smp@freebsd.org Subject: anyone go for a 4 CPU benchmark? Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk The ongoing rsacrack initiative shows some interesting CPU ratings on the so called bovine client. Look at http://www.vex.net/rsa/table.phtml and http://bovine.st.hmc.edu/ -- Chris Christoph P. U. Kukulies kuku@gil.physik.rwth-aachen.de From owner-freebsd-smp Tue Apr 22 10:55:03 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA28836 for smp-outgoing; Tue, 22 Apr 1997 10:55:03 -0700 (PDT) Received: from tacitus.globecomm.net (tacitus.globecomm.net [207.51.48.7]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA28819 for ; Tue, 22 Apr 1997 10:54:56 -0700 (PDT) Received: from warp.starnets.ro (warp.starnets.ro [193.226.124.33]) by tacitus.globecomm.net (8.8.5/8.8.0) with SMTP id NAA29615 for ; Tue, 22 Apr 1997 13:54:44 -0400 (EDT) Message-ID: <335CFA80.70F1@earthling.net> Date: Tue, 22 Apr 1997 20:50:56 +0300 From: Penisoara Adrian Reply-To: ady@earthling.net X-Mailer: Mozilla 3.01Gold (Win95; I) MIME-Version: 1.0 To: smp@FreeBSD.org Subject: AHA 2940AU (aic7xxx) safe options Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi, it's me again. I need to know which of the AHC_* options are safe in the kernel config file; I tried one kernel and I got big problems (wrong netstat output, core dumps and finally a nice cold reboot). I'm not sure that the system doesn't support AHC options but rather my partitions are ruined in consistency matter speaking. I have an Tyan Tomcat III with 2 Pentiums, 64Mb RAM @60ns, AHA2940AU PCI with an Quantum VP32170. Any hints are appreciated. Thanks Ady (@earthling.net) From owner-freebsd-smp Tue Apr 22 11:10:22 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA29787 for smp-outgoing; Tue, 22 Apr 1997 11:10:22 -0700 (PDT) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA29776 for ; Tue, 22 Apr 1997 11:10:01 -0700 (PDT) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id UAA16423 for smp@FreeBSD.ORG; Tue, 22 Apr 1997 20:00:26 +0200 (MET DST) Received: (from andreas@localhost) by klemm.gtn.com (8.8.5/8.8.2) id TAA06009; Tue, 22 Apr 1997 19:58:20 +0200 (CEST) Message-ID: <19970422195820.13904@klemm.gtn.com> Date: Tue, 22 Apr 1997 19:58:20 +0200 From: Andreas Klemm To: smp@FreeBSD.ORG Subject: smp cvs tree was deleted after last cvsup session Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 X-Disclaimer: A free society is one where it is safe to be unpopular X-Operating-System: FreeBSD 2.2-STABLE Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Is this ok, that my whole smp cvs tree vanished after my last cvsup update session ???? Andreas /// -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-smp Tue Apr 22 11:16:56 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA00260 for smp-outgoing; Tue, 22 Apr 1997 11:16:56 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA00255 for ; Tue, 22 Apr 1997 11:16:53 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id MAA16661; Tue, 22 Apr 1997 12:16:49 -0600 (MDT) Message-Id: <199704221816.MAA16661@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: ady@earthling.net cc: smp@freebsd.org Subject: Re: Possible typo in sys sources ? In-reply-to: Your message of "Tue, 22 Apr 1997 20:27:54 +0300." <335CF51A.6C26@earthling.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 12:16:49 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > Hi > > I got a nasty error when I tried to compile a kernel cvsup'ed today: > ... > and complains about an undefined variable (xitp) in > ../../kern/init_main.c line 180. Stop. > > - edited ../../kern/init_main.c and in line 180 changed from "*sipp = > *xitp" to "*sipp = *xipp" (it's in a bubble sort) > - again made "config ADYSMP" > - make depend && make works OK > > Now it may be very possible to be a disk error because I had some > problems today with an IDE disk (I use a SCSI one for root); I'll make > another clean cvsup tomorrow. checked my source, not damaged there. My guess is that your IDE disk added a bit to the 'p' making it a 't'. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Apr 22 11:18:39 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA00337 for smp-outgoing; Tue, 22 Apr 1997 11:18:39 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA00332 for ; Tue, 22 Apr 1997 11:18:36 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id MAA16673; Tue, 22 Apr 1997 12:18:31 -0600 (MDT) Message-Id: <199704221818.MAA16673@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Poul-Henning Kamp cc: ady@earthling.net, smp@freebsd.org Subject: Re: Possible typo in sys sources ? In-reply-to: Your message of "Tue, 22 Apr 1997 19:44:35 +0200." <3511.861731075@critter> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 12:18:30 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > In message <335CF51A.6C26@earthling.net>, Penisoara Adrian writes: > >Hi > > > - edited ../../kern/init_main.c and in line 180 changed from "*sipp = > >*xitp" to "*sipp = *xipp" (it's in a bubble sort) > > We have qsort() in the kernel, replace it wholesale... for the record, this has nothing to do with the SMP source tree, the bubble sort is in the main 3.0-current tree also. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Apr 22 11:18:30 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA00323 for smp-outgoing; Tue, 22 Apr 1997 11:18:30 -0700 (PDT) Received: from ceylon.informatik.uni-rostock.de (ceylon.informatik.uni-rostock.de [139.30.5.237]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA00317 for ; Tue, 22 Apr 1997 11:18:27 -0700 (PDT) Received: from donau.informatik.uni-rostock.de (donau [139.30.7.135]) by ceylon.informatik.uni-rostock.de (8.8.5/8.8.5/relay2.1) with ESMTP id UAA00464 for ; Tue, 22 Apr 1997 20:18:18 +0200 Received: (from gunther@localhost) by donau.informatik.uni-rostock.de (8.8.5/8.8.5/fin1.16) id UAA07790 for smp@FreeBSD.ORG; Tue, 22 Apr 1997 20:18:16 +0200 (MET DST) Date: Tue, 22 Apr 1997 20:18:16 +0200 (MET DST) From: Gunther Hipper Message-Id: <199704221818.UAA07790@donau.informatik.uni-rostock.de> To: smp@FreeBSD.ORG Subject: Re: smp cvs tree was deleted after last cvsup session Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Content-MD5: QZVg/VJ3kNIykpHyA/6Oaw== Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > > Is this ok, that my whole smp cvs tree vanished after my last cvsup > update session ???? > > Andreas /// I just wanted to do an update, too, but I thought it was my mistake. But the last time my scripts were okay, so it is possibly a fault on cvsup.freebsd.org ;-) Gunther From owner-freebsd-smp Tue Apr 22 11:26:32 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA00899 for smp-outgoing; Tue, 22 Apr 1997 11:26:32 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA00893 for ; Tue, 22 Apr 1997 11:26:28 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id MAA16720; Tue, 22 Apr 1997 12:26:23 -0600 (MDT) Message-Id: <199704221826.MAA16720@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: ady@earthling.net cc: smp@FreeBSD.org Subject: Re: AHA 2940AU (aic7xxx) safe options In-reply-to: Your message of "Tue, 22 Apr 1997 20:50:56 +0300." <335CFA80.70F1@earthling.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 12:26:23 -0600 Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi, > Hi, it's me again. > > I need to know which of the AHC_* options are safe in the kernel > config file; I tried one kernel and I got big problems (wrong netstat > output, core dumps and finally a nice cold reboot). I'm not sure that > the system doesn't support AHC options but rather my partitions are > ruined in consistency matter speaking. the last time I tried playing with them I successfully used: options AHC_TAGENABLE options AHC_SCBPAGING_ENABLE options AHC_ALLOW_MEMIO I don't currently use any of them as I need to keep non-SMP things as stable as possible so I can zero in on the SMP specific bugs. Stated another way, trying to track -current/scsi as to which option is working with which controller/disk is prone to my missing something and needlessly chasing an otherwise known problem. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Apr 22 11:41:02 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA02019 for smp-outgoing; Tue, 22 Apr 1997 11:41:02 -0700 (PDT) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA02014 for ; Tue, 22 Apr 1997 11:41:00 -0700 (PDT) Received: from fast.cs.utah.edu by cs.utah.edu (8.8.4/utah-2.21-cs) id MAA29860; Tue, 22 Apr 1997 12:40:55 -0600 (MDT) Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id MAA09006; Tue, 22 Apr 1997 12:40:53 -0600 Date: Tue, 22 Apr 1997 12:40:53 -0600 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199704221840.MAA09006@fast.cs.utah.edu> To: andreas@klemm.gtn.com, smp@FreeBSD.ORG Subject: Re: smp cvs tree was deleted after last cvsup session Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > >Is this ok, that my whole smp cvs tree vanished after my last cvsup >update session ???? > > Andreas /// > Mine dissapeared this morning too -- and I can't get it back. Kevin From owner-freebsd-smp Tue Apr 22 12:00:03 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA03436 for smp-outgoing; Tue, 22 Apr 1997 12:00:03 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA03393 for ; Tue, 22 Apr 1997 11:59:58 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id MAA16883; Tue, 22 Apr 1997 12:59:56 -0600 (MDT) Message-Id: <199704221859.MAA16883@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: smp@freebsd.org cc: Andreas Klemm , Gunther Hipper , vanmaren@fast.cs.utah.edu (Kevin Van Maren), John Polstra Subject: Re: smp cvs tree was deleted after last cvsup session In-reply-to: Your message of "Tue, 22 Apr 1997 19:58:20 +0200." <19970422195820.13904@klemm.gtn.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 12:59:56 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, 3 bummers so far: - > Is this ok, that my whole smp cvs tree vanished after my last cvsup > update session ???? - > I just wanted to do an update, too, but I thought it was my mistake. > But the last time my scripts were okay, so it is possibly a fault > on cvsup.freebsd.org ;-) - > Mine dissapeared this morning too -- and I can't get it back. earlier today on the cvs-commit list: >The cut-over has taken place and freefall is now the system which was >built from the donations of so many kind freebsd supporters (check 'em >out at http://www.freebsd.org/handbook/donors.html) - a P6/200 with >128MB of memory and 12GB of disk storage. > >The old freefall (the P5/90) is now "hub.freebsd.org" - a machine >dedicated to email and other tasks which formerly bogged down our >development work and we are very happy to see on another machine! ;-) > >cvsupd will probably not be available on freefall for a little while >longer; we need to transition it away from "hub" where it moved along >with everything else first. Please let us know if you encounter any >other problems. then later: >I've installed cvsupd on the new freefall, and it seems to be >working OK. Please let me know if you find any problems with it. > >John P. --- I currently am backing up my cvssmp tree in preparation for doing a test. I will let you know what happens. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Apr 22 12:05:34 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA03746 for smp-outgoing; Tue, 22 Apr 1997 12:05:34 -0700 (PDT) Received: from austin.polstra.com (austin.polstra.com [206.213.73.10]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA03741 for ; Tue, 22 Apr 1997 12:05:31 -0700 (PDT) Received: from austin.polstra.com (jdp@localhost) by austin.polstra.com (8.8.5/8.8.5) with ESMTP id MAA05601; Tue, 22 Apr 1997 12:05:26 -0700 (PDT) Message-Id: <199704221905.MAA05601@austin.polstra.com> To: Steve Passe cc: smp@freebsd.org, Andreas Klemm , Gunther Hipper , vanmaren@fast.cs.utah.edu (Kevin Van Maren) Subject: Re: smp cvs tree was deleted after last cvsup session In-reply-to: Your message of "Tue, 22 Apr 1997 12:59:56 MDT." <199704221859.MAA16883@Ilsa.StevesCafe.com> References: <199704221859.MAA16883@Ilsa.StevesCafe.com> Date: Tue, 22 Apr 1997 12:05:26 -0700 From: John Polstra Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Sorry, it has already been fixed. There was a brief window on the new freefall when /home/smp was empty, causing CVSup to make yours empty too. I didn't realize it at first -- I checked that the directories were there, but didn't see that they were empty. Unfortunately, a couple of the mirrors also picked up the changes. I'm sorry for the inconvenience. If you want to test it safely before you decide whether you trust it again, specify a destination directory after the supfile, as described in the cvsup manual page. John -- John Polstra jdp@polstra.com John D. Polstra & Co., Inc. Seattle, Washington USA "Self-knowledge is always bad news." -- John Barth From owner-freebsd-smp Tue Apr 22 12:07:09 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA03849 for smp-outgoing; Tue, 22 Apr 1997 12:07:09 -0700 (PDT) Received: from weenix.guru.org (kmitch@phantasma.bevc.blacksburg.va.us [198.82.200.65]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA03795; Tue, 22 Apr 1997 12:06:03 -0700 (PDT) Received: (from kmitch@localhost) by weenix.guru.org (8.8.5/8.8.5) id PAA02398; Tue, 22 Apr 1997 15:05:51 -0400 (EDT) From: Keith Mitchell Message-Id: <199704221905.PAA02398@weenix.guru.org> Subject: Re: Freezes/Reboots with -current ahc driver In-Reply-To: <199704221725.LAA16301@Ilsa.StevesCafe.com> from Steve Passe at "Apr 22, 97 11:25:03 am" To: smp@csn.net (Steve Passe) Date: Tue, 22 Apr 1997 15:05:51 -0400 (EDT) Cc: gibbs@freebsd.org, smp@freebsd.org, scsi@freebsd.org X-Mailer: ELM [version 2.4ME+ PL30 (25)] 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 > what backup tool are you using when it crashes? I am using amanda 2.3.0.4 as the backup program which in turn uses dump. None of the drives are mounted via NFS. I do have APIC_IO turned on. After I turned on the comconsole and ddb stuff I found out that it was panicing (it looks like in the SMP stuff). The controller card is a 3940UW. I did have toi patch the mp_machdep.c file for the PCI-PCI bridge. The panic message is: apicIPI is stuck panic(cpu#0): boot() called on cpu#0 What should I look for in DDB?? -- Keith Mitchell Head Administrator: acm.vt.edu Email: kmitch@weenix.guru.org PGP key available upon request http://weenix.guru.org/~kmitch Address and URL (c) 1997 Keith Mitchell - All Rights Reserved Unauthorized use or duplication prohibited From owner-freebsd-smp Tue Apr 22 12:28:23 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA08833 for smp-outgoing; Tue, 22 Apr 1997 12:28:23 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA08744 for ; Tue, 22 Apr 1997 12:28:12 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id NAA17034; Tue, 22 Apr 1997 13:28:05 -0600 (MDT) Message-Id: <199704221928.NAA17034@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: John Polstra cc: smp@freebsd.org, Andreas Klemm , Gunther Hipper , vanmaren@fast.cs.utah.edu (Kevin Van Maren) Subject: Re: smp cvs tree was deleted after last cvsup session In-reply-to: Your message of "Tue, 22 Apr 1997 12:05:26 PDT." <199704221905.MAA05601@austin.polstra.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 13:28:05 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > Sorry, it has already been fixed. There was a brief window on the > new freefall when /home/smp was empty, causing CVSup to make yours > empty too. I didn't realize it at first -- I checked that the > directories were there, but didn't see that they were empty. > Unfortunately, a couple of the mirrors also picked up the changes. > I'm sorry for the inconvenience. > > If you want to test it safely before you decide whether you trust it > again, specify a destination directory after the supfile, as > described in the cvsup manual page. looks like its OK now, I first tested both freefall and cvsup against my (copy of) existing cvssmp tree. in both cases cvsup completed without adding any files (expected as I was already in sync) and the tree was uncorrupted. I then made an empty directory and tried it on cvsup, it completed without any apparent error. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Apr 22 12:37:45 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA11673 for smp-outgoing; Tue, 22 Apr 1997 12:37:45 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.vis.net.uk [194.207.134.1]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA11081 for ; Tue, 22 Apr 1997 12:35:25 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.vis.net.uk [194.207.134.1]) by bagpuss.visint.co.uk (8.7.5/8.7.3) with SMTP id UAA27151; Tue, 22 Apr 1997 20:41:09 +0100 (BST) Date: Tue, 22 Apr 1997 20:41:09 +0100 (BST) From: Stephen Roome To: Steve Passe cc: smp@freebsd.org Subject: Re: hardware list In-Reply-To: <199704220454.WAA14074@Ilsa.StevesCafe.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk This isn't really an unusual configuration (same as yours?), but it works like a dream, so much so that I've 'requesitioned' it for 'destruction testing'. Aka playing quake with linux compatibility. > ------------------------------------ cut -------------------------------------- > Make/Model of motherboard: Gigabyte GA 586 DX, Rev. 3B > Http links to manufacturer and/or board info: http://www.gigabyte.com.tw/ > SMP kernel works [yes/no]: yes > APIC_IO works [yes/no]: yes > Special #defines/options needed: none used, works fine. > Comments: got some more information and the output from "hint" on the machine which is at: http://wakko.visint.co.uk/ I'm still not sure why my P166 desktop machine beats the pants off it on this hint test though ? -- Steve Roome Technical Systems Manager, Vision Interactive Ltd. E: steve@visint.co.uk M: +44 (0) 976 241 342 T: +44 (0) 117 973 0597 F: +44 (0) 117 923 8522 From owner-freebsd-smp Tue Apr 22 12:38:05 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA11803 for smp-outgoing; Tue, 22 Apr 1997 12:38:05 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA11694; Tue, 22 Apr 1997 12:37:49 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id NAA17103; Tue, 22 Apr 1997 13:36:25 -0600 (MDT) Message-Id: <199704221936.NAA17103@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Keith Mitchell cc: gibbs@freebsd.org, smp@freebsd.org, scsi@freebsd.org Subject: Re: Freezes/Reboots with -current ahc driver In-reply-to: Your message of "Tue, 22 Apr 1997 15:05:51 EDT." <199704221905.PAA02398@weenix.guru.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 13:36:25 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > > what backup tool are you using when it crashes? > > I am using amanda 2.3.0.4 as the backup program which in turn uses > dump. None of the drives are mounted via NFS. > > I do have APIC_IO turned on. > > After I turned on the comconsole and ddb stuff I found out that it was > panicing (it looks like in the SMP stuff). The controller card is a > 3940UW. I did have toi patch the mp_machdep.c file for the PCI-PCI > bridge. > > The panic message is: > > apicIPI is stuck > panic(cpu#0): > > boot() called on cpu#0 > > What should I look for in DDB?? you are hitting the known "APIC_IO/heavy IO deadlock" problem. I'll think more about a solution. In the meantime you could try a non_APIC_IO kernel, that should solve the problem for now... -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Apr 22 13:24:54 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id NAA01130 for smp-outgoing; Tue, 22 Apr 1997 13:24:54 -0700 (PDT) Received: from bacall.lodgenet.com (bacall.lodgenet.com [205.138.147.242]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id NAA01117 for ; Tue, 22 Apr 1997 13:24:52 -0700 (PDT) Received: (from mail@localhost) by bacall.lodgenet.com (8.6.12/8.6.12) id PAA10325; Tue, 22 Apr 1997 15:24:42 -0500 Received: from garbo.lodgenet.com(204.124.123.250) by bacall via smap (V1.3) id sma010310; Tue Apr 22 15:24:24 1997 Received: from jake.lodgenet.com ([10.0.11.30]) by garbo.lodgenet.com (8.6.12/8.6.9) with ESMTP id PAA13127; Tue, 22 Apr 1997 15:22:55 -0500 Received: from jake.lodgenet.com (localhost.lodgenet.com [127.0.0.1]) by jake.lodgenet.com (8.8.5/8.6.12) with ESMTP id PAA07357; Tue, 22 Apr 1997 15:24:21 -0500 (CDT) Message-Id: <199704222024.PAA07357@jake.lodgenet.com> X-Mailer: exmh version 2.0gamma 1/27/96 To: Steve Passe cc: smp@freebsd.org Subject: Re: hardware list In-reply-to: Your message of "Mon, 21 Apr 1997 22:54:57 MDT." <199704220454.WAA14074@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 15:24:20 -0500 From: "Eric L. Hernes" Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >--- >Make/Model of motherboard: AMI Titan-II, PCI/EISA > >--- >Http links to manufacturer and/or board info: http://www.ami.com/motherboards/archives.html > >--- >SMP kernel works [yes/no]: Yes >--- >APIC_IO works [yes/no]: Yes >--- >Special #defines/options needed: nope. >--- >Comments: This board is pretty old, but seems ok. The post lite2 works the best I've seen on it. eric. -- erich@rrnet.com http://rrnet.com/~erich erich@freebsd.org http://www.freebsd.org/~erich erich@lodgenet.com From owner-freebsd-smp Tue Apr 22 13:29:16 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id NAA01669 for smp-outgoing; Tue, 22 Apr 1997 13:29:16 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA01663 for ; Tue, 22 Apr 1997 13:29:13 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id OAA18733; Tue, 22 Apr 1997 14:29:03 -0600 (MDT) Message-Id: <199704222029.OAA18733@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: "Eric L. Hernes" cc: smp@freebsd.org Subject: Re: hardware list In-reply-to: Your message of "Tue, 22 Apr 1997 15:24:20 CDT." <199704222024.PAA07357@jake.lodgenet.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 14:29:03 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > >Comments: > > This board is pretty old, but seems ok. The post lite2 works the > best I've seen on it. I'm not sure of exact numbers, since it varies on a loaded system, but it seems like the latest src with the vm changes has shaved 6-7 seconds off my kernel compile times. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Apr 22 13:35:04 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id NAA02072 for smp-outgoing; Tue, 22 Apr 1997 13:35:04 -0700 (PDT) Received: from bacall.lodgenet.com (bacall.lodgenet.com [205.138.147.242]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id NAA02047 for ; Tue, 22 Apr 1997 13:34:57 -0700 (PDT) Received: (from mail@localhost) by bacall.lodgenet.com (8.6.12/8.6.12) id PAA10671; Tue, 22 Apr 1997 15:34:51 -0500 Received: from garbo.lodgenet.com(204.124.123.250) by bacall via smap (V1.3) id sma010656; Tue Apr 22 15:34:30 1997 Received: from jake.lodgenet.com ([10.0.11.30]) by garbo.lodgenet.com (8.6.12/8.6.9) with ESMTP id PAA13311; Tue, 22 Apr 1997 15:33:02 -0500 Received: from jake.lodgenet.com (localhost.lodgenet.com [127.0.0.1]) by jake.lodgenet.com (8.8.5/8.6.12) with ESMTP id PAA07575; Tue, 22 Apr 1997 15:34:28 -0500 (CDT) Message-Id: <199704222034.PAA07575@jake.lodgenet.com> X-Mailer: exmh version 2.0gamma 1/27/96 To: Steve Passe cc: "Eric L. Hernes" , smp@freebsd.org Subject: Re: hardware list In-reply-to: Your message of "Tue, 22 Apr 1997 14:29:03 MDT." <199704222029.OAA18733@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 15:34:28 -0500 From: "Eric L. Hernes" Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Steve Passe writes: >Hi, > >> >Comments: >> >> This board is pretty old, but seems ok. The post lite2 works the >> best I've seen on it. > >I'm not sure of exact numbers, since it varies on a loaded system, but it >seems like the latest src with the vm changes has shaved 6-7 seconds >off my kernel compile times. Yea, I've never gotten any numbers that are too pure, it seems I usually start another compile, or fire up netcrap, or somthing to blow the test all to hell ;-). The only problems I'm seeing seem vfork() related, and it (mis)behaves the same with the MP kernel as with the UP kernel, if that's any consolation ;-) > >-- >Steve Passe | powered by >smp@csn.net | Symmetric MultiProcessor FreeBSD > > eric. -- erich@rrnet.com http://rrnet.com/~erich erich@freebsd.org http://www.freebsd.org/~erich erich@lodgenet.com From owner-freebsd-smp Tue Apr 22 14:39:25 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id OAA07705 for smp-outgoing; Tue, 22 Apr 1997 14:39:25 -0700 (PDT) Received: from phaeton.artisoft.com (phaeton.Artisoft.COM [198.17.250.50]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id OAA07700 for ; Tue, 22 Apr 1997 14:39:22 -0700 (PDT) Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id OAA27462; Tue, 22 Apr 1997 14:36:14 -0700 From: Terry Lambert Message-Id: <199704222136.OAA27462@phaeton.artisoft.com> Subject: Re: Possible typo in sys sources ? To: smp@csn.net (Steve Passe) Date: Tue, 22 Apr 1997 14:36:14 -0700 (MST) Cc: phk@dk.tfs.com, ady@earthling.net, smp@freebsd.org In-Reply-To: <199704221818.MAA16673@Ilsa.StevesCafe.com> from "Steve Passe" at Apr 22, 97 12:18:30 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 > > > - edited ../../kern/init_main.c and in line 180 changed from "*sipp = > > >*xitp" to "*sipp = *xipp" (it's in a bubble sort) > > > > We have qsort() in the kernel, replace it wholesale... > > for the record, this has nothing to do with the SMP source tree, the bubble > sort is in the main 3.0-current tree also. Also for the record: 1) It's not a typo 2) You can replace it with qsort if you want to provide the compare function, but it's boot code, and is only ever executed once, so it's kind of a waste of time. 3) I'm not wure if a qsort would like to be unindexed; if not, it may not like the dirty way the original linkerset data is being rearranged in memory without benefit of a real array of pointers. Regards, 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 Apr 22 15:01:28 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id PAA09215 for smp-outgoing; Tue, 22 Apr 1997 15:01:28 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id PAA09210 for ; Tue, 22 Apr 1997 15:01:24 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id QAA19273 for ; Tue, 22 Apr 1997 16:01:22 -0600 (MDT) Message-Id: <199704222201.QAA19273@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: smp@freefall.freebsd.org Subject: new version of mptable Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 16:01:22 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, I just placed a new version of mptable.c on the web page: http://www.freebsd.org/~fsmp/SMP/mptable/mptable.c this version documents the most recent set of SMP kernel options in its output, including warnings about the rogue motherboards. For those new to freeBSD SMP, mptable is a userland program that extract's your SMP motherboard's MP table for use in configuring your kernel. See the SMP web page for details. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Apr 22 19:17:28 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id TAA26053 for smp-outgoing; Tue, 22 Apr 1997 19:17:28 -0700 (PDT) Received: from main.gbdata.com (USR2-1.detnet.com [207.113.12.44]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id TAA26042; Tue, 22 Apr 1997 19:17:24 -0700 (PDT) Received: (from gclarkii@localhost) by main.gbdata.com (8.8.5/8.8.5) id VAA02617; Tue, 22 Apr 1997 21:17:10 -0500 (CDT) From: Gary Clark II Message-Id: <199704230217.VAA02617@main.gbdata.com> Subject: Re: Freezes/Reboots with -current ahc driver To: smp@csn.net (Steve Passe) Date: Tue, 22 Apr 1997 21:17:10 -0500 (CDT) Cc: kmitch@weenix.guru.org, scsi@freebsd.org, smp@freebsd.org In-Reply-To: <199704221725.LAA16301@Ilsa.StevesCafe.com> from Steve Passe at "Apr 22, 97 11:25:03 am" X-Mailer: ELM [version 2.4ME+ PL22 (25)] 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 Steve Passe wrote: > Hi, > > > I just upgraded my 2.2-STABLE system (from around April 1) to 3.0-current > > (as of April 21) to gain use of the SMP stuff. > > > > Now, I am experiancing system freezes and reboots during the > > nightly backup. No error messages ever appear from what I can tell. > > The little SCSI light doesn;t even stay solidly lit when the system > > freezes. I didn't have any problems with the 2.2-STABLE system. > > > > I am only using SCB paging. Tagged queuing has never worked with my > > Micropolis 4221W. I just get all kinds of timeouts with tht option > > on. > > > > Has anyone else seen anything similar?? > I don't belive that this is a SMP problem. I'm running the same current here and am seeing random reboots (not panics) 1-4 times a day. I'm running on a 486DX4-100, 24MB and NO SMP. > details please. > > what backup tool are you using when it crashes? > > are any NFS mounted partitions involved? > > are you using APIC_IO? > > is ddb installed in your kernel, if not please add. > > > -- > Steve Passe | powered by > smp@csn.net | Symmetric MultiProcessor FreeBSD > Gary -- Gary Clark II (N5VMF) | I speak only for myself and "maybe" my company gclarkii@GBData.COM | Member of the FreeBSD Doc Team Providing Internet and ISP startups - http://WWW.GBData.com for information FreeBSD FAQ at ftp://ftp.FreeBSD.ORG/pub/FreeBSD/docs/FAQ.latin1 From owner-freebsd-smp Tue Apr 22 19:32:39 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id TAA27085 for smp-outgoing; Tue, 22 Apr 1997 19:32:39 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id TAA27079; Tue, 22 Apr 1997 19:32:36 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id UAA20177; Tue, 22 Apr 1997 20:32:24 -0600 (MDT) Message-Id: <199704230232.UAA20177@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Gary Clark II cc: kmitch@weenix.guru.org, scsi@freebsd.org, smp@freebsd.org Subject: Re: Freezes/Reboots with -current ahc driver In-reply-to: Your message of "Tue, 22 Apr 1997 21:17:10 CDT." <199704230217.VAA02617@main.gbdata.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Apr 1997 20:32:24 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > > > I just upgraded my 2.2-STABLE system (from around April 1) to 3.0-current > > > (as of April 21) to gain use of the SMP stuff. > > > > > > Now, I am experiancing system freezes and reboots during the > > > nightly backup. No error messages ever appear from what I can tell. > > > ... > > I don't belive that this is a SMP problem. I'm running the same current > here and am seeing random reboots (not panics) 1-4 times a day. > I'm running on a 486DX4-100, 24MB and NO SMP. For the record, after DDB was added to the SMP kernel we demonstrated that the problem in this case is SMP, specifically the apicIPI() related deadlock. So this proves that my cheap bandaid doesn't solve the problem... I've got my thinking cap on, but for now I've suggested the user switch to a NON APIC_IO kernel. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Apr 22 19:48:06 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id TAA28130 for smp-outgoing; Tue, 22 Apr 1997 19:48:06 -0700 (PDT) Received: from main.gbdata.com (USR2-1.detnet.com [207.113.12.44]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id TAA28041; Tue, 22 Apr 1997 19:48:00 -0700 (PDT) Received: (from gclarkii@localhost) by main.gbdata.com (8.8.5/8.8.5) id VAA02748; Tue, 22 Apr 1997 21:47:54 -0500 (CDT) From: Gary Clark II Message-Id: <199704230247.VAA02748@main.gbdata.com> Subject: Re: Freezes/Reboots with -current ahc driver To: smp@csn.net (Steve Passe) Date: Tue, 22 Apr 1997 21:47:54 -0500 (CDT) Cc: kmitch@weenix.guru.org, scsi@freebsd.org, smp@freebsd.org In-Reply-To: <199704230232.UAA20177@Ilsa.StevesCafe.com> from Steve Passe at "Apr 22, 97 08:32:24 pm" X-Mailer: ELM [version 2.4ME+ PL22 (25)] 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 Steve Passe wrote: > Hi, > > > > > I just upgraded my 2.2-STABLE system (from around April 1) to 3.0-current > > > > (as of April 21) to gain use of the SMP stuff. > > > > > > > > Now, I am experiancing system freezes and reboots during the > > > > nightly backup. No error messages ever appear from what I can tell. > > > > ... > > > > I don't belive that this is a SMP problem. I'm running the same current > > here and am seeing random reboots (not panics) 1-4 times a day. > > I'm running on a 486DX4-100, 24MB and NO SMP. > Ohhhh..... Then there are other problems in the latest current. I may have to downgrade to what I was running then (pre-lite snap). I can't run DDB here due to the fact that I have a SUN 19" monitor and no way to see regular VGA output...:( > For the record, after DDB was added to the SMP kernel we demonstrated that the > problem in this case is SMP, specifically the apicIPI() related deadlock. > So this proves that my cheap bandaid doesn't solve the problem... > I've got my thinking cap on, but for now I've suggested the user switch to > a NON APIC_IO kernel. > > -- > Steve Passe | powered by > smp@csn.net | Symmetric MultiProcessor FreeBSD > Gary -- Gary Clark II (N5VMF) | I speak only for myself and "maybe" my company gclarkii@GBData.COM | Member of the FreeBSD Doc Team Providing Internet and ISP startups - http://WWW.GBData.com for information FreeBSD FAQ at ftp://ftp.FreeBSD.ORG/pub/FreeBSD/docs/FAQ.latin1 From owner-freebsd-smp Tue Apr 22 22:04:04 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id WAA06317 for smp-outgoing; Tue, 22 Apr 1997 22:04:04 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id WAA06293 for ; Tue, 22 Apr 1997 22:03:47 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id NAA00663; Wed, 23 Apr 1997 13:00:58 +0800 (WST) Message-Id: <199704230500.NAA00663@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Stephen Roome cc: Robin Cutshaw , Steve Passe , smp@freebsd.org Subject: Re: hardware list In-reply-to: Your message of "Tue, 22 Apr 1997 18:48:14 +0100." Date: Wed, 23 Apr 1997 13:00:58 +0800 From: Peter Wemm Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Stephen Roome wrote: > On Tue, 22 Apr 1997, Robin Cutshaw wrote: > > You would probably get a larger response if an smp-snapshot were cut (hint > > hint). :-) > > grovel. =) You'll probably get your wish (or something better) sooner than expected.. Cheers, -Peter From owner-freebsd-smp Tue Apr 22 22:42:45 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id WAA08279 for smp-outgoing; Tue, 22 Apr 1997 22:42:45 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id WAA08274 for ; Tue, 22 Apr 1997 22:42:42 -0700 (PDT) From: Steve Passe Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id WAA01226 for freebsd-smp; Tue, 22 Apr 1997 22:42:35 -0700 (PDT) Date: Tue, 22 Apr 1997 22:42:35 -0700 (PDT) Message-Id: <199704230542.WAA01226@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/conf LINT Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/22 22:42:35 Modified: i386/conf LINT Log: added more descriptive text. added info on rogue hardware. Revision Changes Path 1.4 +38 -4 sys/i386/conf/LINT From owner-freebsd-smp Wed Apr 23 00:50:11 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id AAA14162 for smp-outgoing; Wed, 23 Apr 1997 00:50:11 -0700 (PDT) Received: from mpress.com (mpress.com [208.138.29.130]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id AAA14157 for ; Wed, 23 Apr 1997 00:50:08 -0700 (PDT) Received: (qmail 26363 invoked by uid 100); 23 Apr 1997 07:49:45 -0000 Message-ID: <19970423004945.15230@mpress.com> Date: Wed, 23 Apr 1997 00:49:45 -0700 From: Brian Litzinger To: freebsd-smp@freebsd.org Subject: Tyan Titan-Pro ATX S1668 no more? or changing? Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I apologize if this in inapproprate for this list. I thought potential purchasers of the Tyan S1668 might be interested in this heresay. I stopped by Fry's Electronics in San Jose Wednesday, and tried to buy a Tyan Titan-Pro ATX S1668 motherboard. They was a place in the shelf for them, but there were no S1668s, S1662s or other of the Tyan high end motherboards. Where the boards would have been was a sign saying something along the lines of: We're not out of Tyan [product] just ask for a sales person. So I did. He informed me that the people from the head office had come buy and taken them all. I asked if there were any at the other stores. He wondered off and came back about 5 minutes later. He said he looked in the computer and there were none in any of the Fry's stores anywhere, including the new store in Sacramento. He then said that Fry's did not expect to get anymore, but to expect the new version in about a week based on the [I forgot] chipset, which included support for the new [this and that]. Among this and that he included the K6 processor. I was not aware that the K6 had support for SMP, but then this was just a sales droid. Basically, it would seem new versions of their motherboards are coming out with a new chipset, and some will support the K6. -- Brian Litzinger brian@mediacity.com From owner-freebsd-smp Wed Apr 23 01:06:09 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id BAA15050 for smp-outgoing; Wed, 23 Apr 1997 01:06:09 -0700 (PDT) Received: from cypher.net (black@zen.pratt.edu [205.232.115.155]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id BAA15045 for ; Wed, 23 Apr 1997 01:06:05 -0700 (PDT) Received: (from black@localhost) by cypher.net (8.8.5/8.7.1) id EAA14771; Wed, 23 Apr 1997 04:04:40 -0400 Date: Wed, 23 Apr 1997 04:04:39 -0400 (EDT) From: Ben Black To: Brian Litzinger cc: smp@freebsd.org Subject: Re: Tyan Titan-Pro ATX S1668 no more? or changing? In-Reply-To: <19970423004945.15230@mpress.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk well, given that the PS/2 port and second serial port on my machine don't work, i don't think a recall is out of the question. as for K6, well, it has full MESI cache cohereceny for SMP. whether it will be supported in a P6 board is unlikely since K6 is Pentium pin compatible. On Wed, 23 Apr 1997, Brian Litzinger wrote: > I apologize if this in inapproprate for this list. > > I thought potential purchasers of the Tyan S1668 might be > interested in this heresay. > > I stopped by Fry's Electronics in San Jose Wednesday, and tried > to buy a Tyan Titan-Pro ATX S1668 motherboard. > > They was a place in the shelf for them, but there were no S1668s, > S1662s or other of the Tyan high end motherboards. > > Where the boards would have been was a sign saying something along the > lines of: > > We're not out of Tyan [product] just ask for a sales person. > > So I did. He informed me that the people from the head office > had come buy and taken them all. I asked if there were any at > the other stores. > > He wondered off and came back about 5 minutes later. He said he > looked in the computer and there were none in any of the Fry's > stores anywhere, including the new store in Sacramento. > > He then said that Fry's did not expect to get anymore, but to > expect the new version in about a week based on the [I forgot] > chipset, which included support for the new [this and that]. > > Among this and that he included the K6 processor. I was not > aware that the K6 had support for SMP, but then this was just > a sales droid. > > Basically, it would seem new versions of their motherboards are > coming out with a new chipset, and some will support the K6. > > -- > Brian Litzinger > brian@mediacity.com > From owner-freebsd-smp Wed Apr 23 04:55:07 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id EAA25979 for smp-outgoing; Wed, 23 Apr 1997 04:55:07 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.vis.net.uk [194.207.134.1]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id EAA25972 for ; Wed, 23 Apr 1997 04:55:02 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.vis.net.uk [194.207.134.1]) by bagpuss.visint.co.uk (8.7.5/8.7.3) with SMTP id NAA09161; Wed, 23 Apr 1997 13:02:51 +0100 (BST) Date: Wed, 23 Apr 1997 13:02:51 +0100 (BST) From: Stephen Roome To: Steve Passe cc: "Eric L. Hernes" , smp@freebsd.org Subject: Re: hardware list In-Reply-To: <199704222029.OAA18733@Ilsa.StevesCafe.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Tue, 22 Apr 1997, Steve Passe wrote: > Hi, > > > >Comments: > > > > This board is pretty old, but seems ok. The post lite2 works the > > best I've seen on it. > > I'm not sure of exact numbers, since it varies on a loaded system, but it > seems like the latest src with the vm changes has shaved 6-7 seconds > off my kernel compile times. What sort of kernel compile times should be expected, with my last compile make -j8 it took 3 minutes and 48 seconds for a Generic kernel with the sysv stuff for X, and none of the drivers I'm not using. (i.e. one net card a 2940 and 2 processors, nothing much else but 1 com port for a mouse) and make -j16 took 3 minutes 19 seconds on the same kernel. (both booted from this stripped down minimal kernel) So, are these good times then ? (the source was supped down on saturday ontop of a 3.0-970209-SNAP) -- Steve Roome Technical Systems Manager, Vision Interactive Ltd. E: steve@visint.co.uk M: +44 (0) 976 241 342 T: +44 (0) 117 973 0597 F: +44 (0) 117 923 8522 From owner-freebsd-smp Wed Apr 23 08:37:38 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id IAA05706 for smp-outgoing; Wed, 23 Apr 1997 08:37:38 -0700 (PDT) Received: from tacitus.globecomm.net (tacitus.globecomm.net [207.51.48.7]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id IAA05701 for ; Wed, 23 Apr 1997 08:37:36 -0700 (PDT) Received: from w3.starnets.ro ([193.226.124.34]) by tacitus.globecomm.net (8.8.5/8.8.0) with SMTP id LAA16828; Wed, 23 Apr 1997 11:37:25 -0400 (EDT) Message-ID: <335E2BC7.55A9@earthling.net> Date: Wed, 23 Apr 1997 18:33:27 +0300 From: Penisoara Adrian Reply-To: ady@earthling.net X-Mailer: Mozilla 3.01Gold (Win95; I) MIME-Version: 1.0 To: Steve Passe CC: freebsd-smp@FreeBSD.org Subject: Re: AHA 2940AU (aic7xxx) safe options References: <199704221826.MAA16720@Ilsa.StevesCafe.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Steve Passe wrote: > > Hi, > > > Hi, it's me again. > > > > I need to know which of the AHC_* options are safe in the kernel > > config file; I tried one kernel and I got big problems (wrong netstat > > output, core dumps and finally a nice cold reboot). I'm not sure that > > the system doesn't support AHC options but rather my partitions are > > ruined in consistency matter speaking. > > the last time I tried playing with them I successfully used: > > options AHC_TAGENABLE > options AHC_SCBPAGING_ENABLE > options AHC_ALLOW_MEMIO > Meaning everything should be OK from the SMP side of view, right ? I'll repost that question to the CURRENT list anyway, just to be sure and to learn something... Thanks. Ady (@earthling.net) From owner-freebsd-smp Wed Apr 23 09:41:44 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id JAA09042 for smp-outgoing; Wed, 23 Apr 1997 09:41:44 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA09037 for ; Wed, 23 Apr 1997 09:41:42 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id KAA22762; Wed, 23 Apr 1997 10:41:37 -0600 (MDT) Message-Id: <199704231641.KAA22762@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: ady@earthling.net cc: freebsd-smp@FreeBSD.org Subject: Re: AHA 2940AU (aic7xxx) safe options In-reply-to: Your message of "Wed, 23 Apr 1997 18:33:27 +0300." <335E2BC7.55A9@earthling.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 23 Apr 1997 10:41:37 -0600 Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi, > > the last time I tried playing with them I successfully used: > > > > options AHC_TAGENABLE > > options AHC_SCBPAGING_ENABLE > > options AHC_ALLOW_MEMIO > > > Meaning everything should be OK from the SMP side of view, right ? > I'll repost that question to the CURRENT list anyway, just to be sure > and to learn something... correct, none of them are an SMP specific issue, if they work for UP they should work for SMP, and visa-versa. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Wed Apr 23 09:52:01 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id JAA09560 for smp-outgoing; Wed, 23 Apr 1997 09:52:01 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA09541 for ; Wed, 23 Apr 1997 09:51:59 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id KAA22820; Wed, 23 Apr 1997 10:51:46 -0600 (MDT) Message-Id: <199704231651.KAA22820@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Stephen Roome cc: smp@freebsd.org Subject: Re: hardware list In-reply-to: Your message of "Wed, 23 Apr 1997 13:02:51 BST." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 23 Apr 1997 10:51:46 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > What sort of kernel compile times should be expected, with my last compile > > make -j8 it took 3 minutes and 48 seconds for a Generic kernel with > the sysv stuff for X, and none of the drivers I'm not using. > (i.e. one net card a 2940 and 2 processors, nothing much else but 1 com > port for a mouse) > > and make -j16 took 3 minutes 19 seconds on the same > kernel. > > So, are these good times then ? they're better than I got from my dual P5-133 with slow SCSI disk: make -j8 4min 20sec for a fairly dramatic speedup add this line to your /etc/make.conf file: COPTFLAGS= -pipe -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Wed Apr 23 09:57:22 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id JAA09910 for smp-outgoing; Wed, 23 Apr 1997 09:57:22 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA09902 for ; Wed, 23 Apr 1997 09:57:12 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id KAA22849; Wed, 23 Apr 1997 10:57:06 -0600 (MDT) Message-Id: <199704231657.KAA22849@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Brian Litzinger cc: freebsd-smp@freebsd.org Subject: Re: Tyan Titan-Pro ATX S1668 no more? or changing? In-reply-to: Your message of "Wed, 23 Apr 1997 00:49:45 PDT." <19970423004945.15230@mpress.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 23 Apr 1997 10:57:05 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > I apologize if this in inapproprate for this list. > > I thought potential purchasers of the Tyan S1668 might be > interested in this heresay. I think it is very appropriate. An MP system is a big purchase for most of us and any info that can help is appreciated. --- > I stopped by Fry's Electronics in San Jose Wednesday, and tried > to buy a Tyan Titan-Pro ATX S1668 motherboard. > > They was a place in the shelf for them, but there were no S1668s, > S1662s or other of the Tyan high end motherboards. > ... > He then said that Fry's did not expect to get anymore, but to > expect the new version in about a week based on the [I forgot] > chipset, which included support for the new [this and that]. > > Among this and that he included the K6 processor. I was not > aware that the K6 had support for SMP, but then this was just > a sales droid. It would be nice if someone could call Fry's (it would be LD for me) home office and pursue this for concrete facts. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Wed Apr 23 10:02:07 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA10216 for smp-outgoing; Wed, 23 Apr 1997 10:02:07 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA10211 for ; Wed, 23 Apr 1997 10:02:02 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id LAA22880; Wed, 23 Apr 1997 11:01:38 -0600 (MDT) Message-Id: <199704231701.LAA22880@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Ben Black cc: Brian Litzinger , smp@freebsd.org Subject: Re: Tyan Titan-Pro ATX S1668 no more? or changing? In-reply-to: Your message of "Wed, 23 Apr 1997 04:04:39 EDT." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 23 Apr 1997 11:01:38 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > as for K6, well, it has full MESI cache cohereceny for SMP. whether it > will be supported in a P6 board is unlikely since K6 is Pentium pin > compatible. and every report I've seen says the current K6 doesn't have an OPIC (Open Programmable Interrupt Controller, AMD/Cyrix answer to APIC) on it. So none of the dual boards, P5 or P6 could run dual K6 CPUs. And they're not going to retrofit these boards with a new chipset, so they would have to toss them, or sell them in some other market. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Wed Apr 23 10:34:47 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA11794 for smp-outgoing; Wed, 23 Apr 1997 10:34:47 -0700 (PDT) Received: from critter.dk.tfs.com ([140.145.230.252]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA11789 for ; Wed, 23 Apr 1997 10:34:45 -0700 (PDT) Received: from critter (localhost [127.0.0.1]) by critter.dk.tfs.com (8.8.5/8.8.5) with ESMTP id TAA01530 for ; Wed, 23 Apr 1997 19:33:19 +0200 (CEST) To: smp@freebsd.org Subject: Intel PR440FX motherboard anybody ? From: Poul-Henning Kamp Date: Wed, 23 Apr 1997 19:33:19 +0200 Message-ID: <1528.861816799@critter> Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I'm considering buying one of these with two PP200/256K chips, anybody know anything about them good or bad ? http://channel.intel.com/business/ibp/BOARDS/PR440FX.HTM -- Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. whois: [PHK] | phk@tfs.com TRW Financial Systems, Inc. Future will arrive by its own means, progress not so. From owner-freebsd-smp Wed Apr 23 11:01:26 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA13457 for smp-outgoing; Wed, 23 Apr 1997 11:01:26 -0700 (PDT) Received: from who.cdrom.com (who.cdrom.com [204.216.27.3]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA13452 for ; Wed, 23 Apr 1997 11:01:24 -0700 (PDT) Received: from cypher.net (black@zen.pratt.edu [205.232.115.155]) by who.cdrom.com (8.8.5/8.6.11) with ESMTP id LAA21042 for ; Wed, 23 Apr 1997 11:01:23 -0700 (PDT) Received: (from black@localhost) by cypher.net (8.8.5/8.7.1) id NAA25241; Wed, 23 Apr 1997 13:58:28 -0400 Date: Wed, 23 Apr 1997 13:58:28 -0400 (EDT) From: Ben Black To: Poul-Henning Kamp cc: smp@freebsd.org Subject: Re: Intel PR440FX motherboard anybody ? In-Reply-To: <1528.861816799@critter> 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 think these boards are great (be sure to get the version with integrated fast ethernet). a friend of mine bought one on my suggestion and has not been disappointed running NT and OpenBSD. b3n On Wed, 23 Apr 1997, Poul-Henning Kamp wrote: > > I'm considering buying one of these with two PP200/256K chips, anybody > know anything about them good or bad ? > > http://channel.intel.com/business/ibp/BOARDS/PR440FX.HTM > > -- > Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. > http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. > whois: [PHK] | phk@tfs.com TRW Financial Systems, Inc. > Future will arrive by its own means, progress not so. > From owner-freebsd-smp Wed Apr 23 11:09:54 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA13920 for smp-outgoing; Wed, 23 Apr 1997 11:09:54 -0700 (PDT) Received: from daffy-duck.cs.washington.edu (daffy-duck.cs.washington.edu [128.95.2.11]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA13915 for ; Wed, 23 Apr 1997 11:09:52 -0700 (PDT) From: mef@cs.washington.edu Received: (mef@localhost) by daffy-duck.cs.washington.edu (8.7.2/7.2ws+) id LAA23034; Wed, 23 Apr 1997 11:09:50 -0700 (PDT) Date: Wed, 23 Apr 1997 11:09:50 -0700 (PDT) Message-Id: <199704231809.LAA23034@daffy-duck.cs.washington.edu> To: phk@dk.tfs.com CC: smp@freebsd.org In-reply-to: <1528.861816799@critter> (message from Poul-Henning Kamp on Wed, 23 Apr 1997 19:33:19 +0200) Subject: Re: Intel PR440FX motherboard anybody ? Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Poul-Henning, We have two systems that use that particular motherboard. I believe the code name for the board is "buckeye". We just recently installed FreeBSD and had to deal with two minor problems: 1) needed to turn on "options SMP_TIMER_NC" 2) in the advanced chipset configuration needed to change MPS version from 1.1 to 1.4, and enable "Direct PCI Intro to I/O APIC". Can't really comment on the quality of these systems, as I have nothing to compare with. Nor have we completed the installation to run X and other stuff. Marc http://www.cs.washington.edu/homes/mef From: Poul-Henning Kamp Date: Wed, 23 Apr 1997 19:33:19 +0200 I'm considering buying one of these with two PP200/256K chips, anybody know anything about them good or bad ? http://channel.intel.com/business/ibp/BOARDS/PR440FX.HTM From owner-freebsd-smp Wed Apr 23 12:02:21 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA17184 for smp-outgoing; Wed, 23 Apr 1997 12:02:21 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.vis.net.uk [194.207.134.1]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA17176 for ; Wed, 23 Apr 1997 12:02:17 -0700 (PDT) Received: from bagpuss.visint.co.uk (bagpuss.vis.net.uk [194.207.134.1]) by bagpuss.visint.co.uk (8.7.5/8.7.3) with SMTP id UAA14534; Wed, 23 Apr 1997 20:10:06 +0100 (BST) Date: Wed, 23 Apr 1997 20:10:06 +0100 (BST) From: Stephen Roome To: Steve Passe cc: freebsd-smp@freebsd.org Subject: Re: hardware list In-Reply-To: <199704231651.KAA22820@Ilsa.StevesCafe.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Wed, 23 Apr 1997, Steve Passe wrote: > Hi, > > What sort of kernel compile times should be expected, with my last compile > > > > make -j8 it took 3 minutes and 48 seconds for a Generic kernel with > > the sysv stuff for X, and none of the drivers I'm not using. > > (i.e. one net card a 2940 and 2 processors, nothing much else but 1 com > > port for a mouse) > > > > and make -j16 took 3 minutes 19 seconds on the same > > kernel. > > > > So, are these good times then ? > > they're better than I got from my dual P5-133 with slow SCSI disk: > make -j8 4min 20sec > > for a fairly dramatic speedup add this line to your /etc/make.conf file: > > COPTFLAGS= -pipe (Oh dear, you've got me going on the 'benchmark your computer' thing again) I have this at the moment CFLAGS=-O6 -pipe -m486 #COPTFLAGS=-O -pipe notice this is commented out. HAVE_FPU=yes right now, and that's what the last two compiles ran under, I'd be surprised though if your disk is slower than this Quantum Fireball here. with iozone 51 I get: IOZONE performance measurements: 2894335 bytes/second for writing the file 4024164 bytes/second for reading the file That's one Quantum Fireball 3.5 series disk, which isn't much good by my standards. Besides, I haven't mounted it async,noatime yet, I'm just testing these speed as a plain drive.. I'll try freaky mount options later =! (I'll be adding a 2gb seagate hawk as well soon.) Anyway, I just chucked COMPAT_LINUX in as well and this is what I get ------ CFLAGS =-06 -pipe -m486 COPTFLAGS commented out of make.conf, HAVE_FPU=yes Wed Apr 23 19:12:59 BST 1997 start time = 55 second make depend Wed Apr 23 19:13:54 BST 1997 end of make depend = 3 minutes 36 seconds for make -j8 Wed Apr 23 19:17:30 BST 1997 end of make -j8 ----- This was interesting so I put the COPTFLAGS back in the make.conf and tried again. This time: ----- CFLAGS =-O6 -pipe -m486 COPTFLAGS = -O -pipe HAVE_FPU =yes Wed Apr 23 19:24:50 BST 1997 start make = 51 second make depend Wed Apr 23 19:25:41 BST 1997 end of make depend = 3 minutes 24 seconds for make -j8 Wed Apr 23 19:29:05 BST 1997 end of make -j8 Not a huge improvement, only -slightly- (worth it?) better. ----- Now, this (a make -j16) is interesting though: CFLAGS =-O6 -pipe -m486 COPTFLAGS=-O -pipe HAVE_FPU=yes Wed Apr 23 19:34:14 BST 1997 start make = 1 minute 1 second for a make depend Wed Apr 23 19:35:05 BST 1997 end of make depend = 3 minutes 27 second for make -j16 Wed Apr 23 19:38:33 BST 1997 -j16 doesn't seem to make any difference ? I can't find anything to say make doesn't accept more than 8 jobs max.. So I wondered what -j64 would do !? I assume that for a machine with 512MB of memory -jBIGNUMBER would be good.. Anyway, I'm trying these things out, if you have some more interesting tests please let me know! This is from a make -j64, obviously the -j64 happened, and was too much for this machine on memory (can't easily check this while timing it.) ----- Wed Apr 23 19:41:43 BST 1997 start make = 52 seconds for the make depend Wed Apr 23 19:42:35 BST 1997 end make depend = 4 minutes 42 seconds for a make -j64 Wed Apr 23 19:47:17 BST 1997 ----- I'm gonna write a script that just does this with as many different settings and see if I get the improvements I expect. (could do some nice graphs perhaps.) Then it'll be obivous where too little memory becomes the major factor and where disk access is slowing it down much. (Although it won't be tonight as I'm going to leave my other 4 FreeBSD machines running scripts to get random files (quickly!) through httpd from this server to see if I can tweak the settings for and number of httpd's to run!) Just for fun make -j200 took 53 secs for make depend, 5 min 50 secs for the make =) (mmm maybe it's not memeory slowing this down?) Perhaps make should have a -J option saying start as many processes as possible without getting the swap space usage to increase, and with some limit on the amount of process swapping that ends up happening. Steve Roome (Anyone interested in a unix benchmark site or can point me at one?) -- Steve Roome Technical Systems Manager, Vision Interactive Ltd. E: steve@visint.co.uk M: +44 (0) 976 241 342 T: +44 (0) 117 973 0597 F: +44 (0) 117 923 8522 From owner-freebsd-smp Wed Apr 23 12:06:52 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA17415 for smp-outgoing; Wed, 23 Apr 1997 12:06:52 -0700 (PDT) Received: from critter.dk.tfs.com (phk.cybercity.dk [195.8.129.17]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA17402; Wed, 23 Apr 1997 12:06:42 -0700 (PDT) Received: from critter (localhost [127.0.0.1]) by critter.dk.tfs.com (8.8.5/8.8.5) with ESMTP id VAA00619; Wed, 23 Apr 1997 21:05:44 +0200 (CEST) To: mef@cs.washington.edu cc: phk@dk.tfs.com, smp@freebsd.org From: Poul-Henning Kamp Subject: Re: Intel PR440FX motherboard anybody ? In-reply-to: Your message of "Wed, 23 Apr 1997 11:09:50 PDT." <199704231809.LAA23034@daffy-duck.cs.washington.edu> Date: Wed, 23 Apr 1997 21:05:43 +0200 Message-ID: <617.861822343@critter> Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk In message <199704231809.LAA23034@daffy-duck.cs.washington.edu>, mef@cs.washing ton.edu writes: >Poul-Henning, > >We have two systems that use that particular motherboard. I believe >the code name for the board is "buckeye". We just recently installed >FreeBSD and had to deal with two minor problems: nope, "Providence" is what Intel goes to great lengths to explain that it is not called. -- Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. whois: [PHK] | phk@tfs.com TRW Financial Systems, Inc. Power and ignorance is a disgusting cocktail. From owner-freebsd-smp Wed Apr 23 14:33:09 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id OAA24696 for smp-outgoing; Wed, 23 Apr 1997 14:33:09 -0700 (PDT) Received: from mitra.pgt.mpt.gov.br ([200.130.0.1]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id OAA24688 for ; Wed, 23 Apr 1997 14:33:04 -0700 (PDT) Received: from support.pgt.mpt.gov.br (support.pgt.mpt.gov.br [200.130.0.2]) by mitra.pgt.mpt.gov.br (8.7.6/8.7.3) with SMTP id SAA16692 for ; Wed, 23 Apr 1997 18:44:30 -0300 (EST) Received: by support.pgt.mpt.gov.br with Microsoft Mail id <01BC5014.D29B6AA0@support.pgt.mpt.gov.br>; Wed, 23 Apr 1997 18:33:22 -0300 Message-ID: <01BC5014.D29B6AA0@support.pgt.mpt.gov.br> From: Lucas Cotta To: "smp@freebsd.org" Subject: reults of mptable Date: Wed, 23 Apr 1997 18:33:16 -0300 Encoding: 208 TEXT Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Results of my machine with p166 dual processor , next p200 dual processor ======================================================================== ======= MPTable, version 2.0.6 looking for EBDA pointer @ 0x040e, found, searching EBDA @ 0x0009fc00 searching CMOS 'top of mem' @ 0x0009f800 (638K) searching default 'top of mem' @ 0x0009fc00 (639K) searching BIOS @ 0x000f0000 MP FPS found in BIOS @ physical addr: 0x000fdbe0 ------------------------------------------------------------------------ ------- MP Floating Pointer Structure: location: BIOS physical address: 0x000fdbe0 signature: '_MP_' length: 16 bytes version: 1.1 checksum: 0x4d mode: Virtual Wire ------------------------------------------------------------------------ ------- MP Config Table Header: physical address: 0x0009fd50 signature: 'PCMP' base table length: 252 version: 1.4 checksum: 0x03 OEM ID: 'ALR ' Product ID: '10010 EISA ' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 23 local APIC address: 0xfee00000 extended table length: 56 extended table checksum: 193 ------------------------------------------------------------------------ ------- MP Config Base Table Entries: -- Processors: APIC ID Version State Family Model Step Flags 0 0x10 BSP, usable 5 2 12 0x03bf 1 0x10 AP, usable 5 2 12 0x03bf -- Bus: Bus ID Type 0 PCI 1 EISA -- I/O APICs: APIC ID Version State Address 2 0x11 usable 0xfec00000 -- I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT active-hi edge 1 0 2 0 INT conforms conforms 1 1 2 1 INT conforms conforms 1 0 2 2 INT conforms conforms 1 3 2 3 INT conforms conforms 1 4 2 4 INT conforms conforms 1 5 2 5 INT conforms conforms 1 6 2 6 INT conforms conforms 1 7 2 7 INT conforms conforms 1 8 2 8 INT conforms conforms 1 9 2 9 INT conforms conforms 1 10 2 10 INT conforms conforms 1 11 2 11 INT conforms conforms 1 12 2 12 INT conforms conforms 1 13 2 13 INT conforms conforms 1 14 2 14 INT conforms conforms 1 15 2 15 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT active-hi edge 1 0 255 0 NMI active-hi edge 0 0:A 255 1 ------------------------------------------------------------------------ ------- MP Config Extended Table Entries: -- bus ID: 0 address type: memory address address base: 0x0 address range: 0x0 -- bus ID: 0 address type: I/O address address base: 0x0 address range: 0x10000 -- bus ID: 0 address modifier: add predefined range: 0x00000000-- bus ID: 0 address modifier: add predefined range: 0x00000001 ------------------------------------------------------------------------ ------- # SMP kernel config file options: options SMP # Symmetric MultiProcessor Kernel options APIC_IO # Symmetric (APIC) I/O options NCPU=2 # number of CPUs options NBUS=2 # number of busses options NAPIC=1 # number of IO APICs options NINTR$ # number of INTs options SMP_INVLTLB # #options SMP_PRIVPAGES # BROKEN, DO NOT use! #options SMP_AUTOSTART # BROKEN, DO NOT use! #options SERIAL_DEBUG # com port debug output ------------------------------------------------------------------------ ------- dmesg output: Copyright (c) 1992-1996 FreeBSD Inc. Copyright (c) 1982, 1986, 1989, 1991, 1993 The Regents of the University of California. All rights reserved. FreeBSD 2.2.1-RELEASE #0: Tue Apr 1 15:30:07 EST 1997 CPU: Pentium (166.19-MHz 586-class CPU) Origin = "GenuineIntel" Id = 0x52c Stepping_ Features=0x3bf real memory = 33554432 (32768K bytes) avail memory = 30031872 (29328K bytes) eisa0: Probing for devices on the EISA bus Probing for devices on PCI bus 0: chip0 rev 3 on pci0:0 chip1 rev 21 on pci0:7:0 pci0:8: vendor=0x10ad, device=0x0105, class=storage (ide) int a irq 14 [no driver assigned] vga0 rev 0 int a irq 9 on pci0:17 vx0 <3COM 3C590 Etherlink III PCI> rev 0 int a irq 11 on pci0:19 utp/aui/bnc[*utp*] address 00:a0:24:78:02:48 ahc0 rev 0 int a irq 10 on pci0:20 ahc0: aic7880 Wide Channel, SCSI Id=7, 16 SCBs ahc0 waiting for scsi devices to settle (ahc0:0:0): "SEAGATE ST32550W 0021" type 0 fixed SCSI 2 sd0(ahc0:0:0): Direct-Access 2047MB (4194058 512 byte sectors) (ahc0:5:0): "PLEXTOR CD-ROM PX-6XCS 2.05" type 5 removable SCSI 2 cd0(ahc0:5:0): CD-ROM can't get the size Probing for devices on the ISA bus: sc0 at 0x60-0x6f irq 1 on motherboard sc0: VGA color <16 virtual consoles, flags=0x0> ed0 not found at 0x280 ed1 not found at 0x300 fe0 not found at 0x300 sio0 at 0x3f8-0x3ff irq 4 on isa sio0: type 16550A sio1 at 0x2f8-0x2ff irq 3 on isa sio1: type 16550A sio2: disabled, not probed. sio3: disabled, not probed. lpt0 at 0x378-0x37f irq 7 on isa lpt0: Interrupt-driven port lp0: TCP/IP capable interface lpt1 not found at 0xffffffff mse0 not found at 0x23c psm0: disabled, not probed. fdc0 at 0x3f0-0x3f7 irq 6 drq 2 on isa fdc0: NEC 72065B fd0: 1.44MB 3.5in wdc0 not found at 0x1f0 wdc1 not found at 0x170 bt0 not found at 0x330 uha0 not found at 0x330 aha0 not found at 0x330 aic0 not found at 0x340 nca0 not found at 0x1f88 nca1 not found at 0x350 sea0 not found wt0 not found at 0x300 mcd0 not found at 0x300 matcdc0 not found at 0x230 scd0 not found at 0x230 ie0 not found at 0x360 ep0 not found at 0x300 ex0 not found at 0x300 ix0 not found at 0x300 le0 not found at 0x300 lnc0 not found at 0x280 ze0 not found at 0x300 zp0 not found at 0x300 npx0 on motherboard npx0: INT 16 interface apm0: disabled, not probed. changing root device to sd0a ======================================================================== ======= Abracos Lucas Cotta - cotta@pgt.mpt.gov.br From owner-freebsd-smp Wed Apr 23 15:57:27 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id PAA28909 for smp-outgoing; Wed, 23 Apr 1997 15:57:27 -0700 (PDT) Received: from mail.vlsi.fi (CnTzjVsKJoyG5sEoTSwzuxnmRLbQZo5J@mail.vlsi.fi [195.74.10.147]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id PAA28904 for ; Wed, 23 Apr 1997 15:57:24 -0700 (PDT) Received: (from smap@localhost) by mail.vlsi.fi (8.7.6/8.7.3) id BAA03048; Thu, 24 Apr 1997 01:57:11 +0300 (EET DST) Received: from vlsi1.vlsi.fi(193.64.2.2) by mail.vlsi.fi via smap (V1.3) id sma003044; Thu Apr 24 01:56:48 1997 Received: from layout.vlsi.fi by vlsi1.vlsi.fi with ESMTP (1.37.109.16/16.2) id AA193856207; Thu, 24 Apr 1997 01:56:47 +0300 Received: by layout.vlsi.fi (1.37.109.15/16.2) id AA131766207; Thu, 24 Apr 1997 01:56:47 +0300 Date: Thu, 24 Apr 1997 01:56:47 +0300 Message-Id: <199704232256.AA131766207@layout.vlsi.fi> From: Ville Eerola To: Poul-Henning Kamp Cc: smp@freebsd.org Subject: Re: Intel PR440FX motherboard anybody ? In-Reply-To: <1528.861816799@critter> References: <1528.861816799@critter> X-Mailer: VM Version 5.93 (beta) under GNU Emacs 19.29.6 Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Poul-Henning Kamp writes: > > I'm considering buying one of these with two PP200/256K chips, anybody > know anything about them good or bad ? I have one with single PP200/256K. I have the version including all the options: fast ethernet, Adaptec 7880 ultra-wide SCSI, and sound. I have been very satisfied so far. The system is very stable running FreeBSD 2.2-STABLE. I have been building world and releases all over again... The sound hardware is working (not great) with stock FreeBSD drivers. I think that the commercial OSS might have better support for the Crystal chip it is uning. In general everything has worked without any hassles. There are a few caveats, however: The SCSI bus on the motherboard is WIDE ONLY (It included a wide SCSI cable with external SCSI connector, which was nice). I had to buy an adapter (abt. USD50) for my old narrow SCSI disks. Also I haven so far found any documentation how to raise the clock multipliers for overclocking at 233MHz... (Any hints, anubody?) Also there has been some talk of requirements of using "options SMP_TIMER_NC" with current SMP code. I just out of curiosity ran the mptable program and it claimed MP 1.4 support... Regards, Ville -- Ville.Eerola@vlsi.fi VLSI Solution Oy Tel:+358 3 3165579 Hermiankatu 6-8 C Fax:+358 3 3165220 FIN-33720 Tampere, Finland From owner-freebsd-smp Wed Apr 23 16:32:02 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id QAA00400 for smp-outgoing; Wed, 23 Apr 1997 16:32:02 -0700 (PDT) Received: from news.quick.net (donegan@news.quick.net [207.212.170.1]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id QAA00380 for ; Wed, 23 Apr 1997 16:32:00 -0700 (PDT) Received: (from donegan@localhost) by news.quick.net (8.8.5/8.6.9) id QAA08242; Wed, 23 Apr 1997 16:31:53 -0700 (PDT) Date: Wed, 23 Apr 1997 16:31:52 -0700 (PDT) From: "Steven P. Donegan" To: smp@freebsd.org Subject: Tyan Tomcat/FreeBSD 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 have a Tyan Tomcat with dual processors (at this moment in UP mode). The board recognises 128M of EDO RAM, FreeBSD only sees 64M - any assist would be appreciated here as I have another 128M burning a hole in my pocket :-) Also, any assist in regaining CVSup would be appreciated - freefall.freebsd.org seems to have stopped allowing anon ftp right at the critical moment for me - installing 3.0-CURRENT (completely clean) and now wanting to go to SMP via cvsup... TIA Steven P. Donegan donegan@quick.net From owner-freebsd-smp Wed Apr 23 16:36:53 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id QAA00651 for smp-outgoing; Wed, 23 Apr 1997 16:36:53 -0700 (PDT) Received: from mpress.com (mpress.com [208.138.29.130]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id QAA00645 for ; Wed, 23 Apr 1997 16:36:51 -0700 (PDT) Received: (qmail 3626 invoked by uid 100); 23 Apr 1997 23:36:27 -0000 Message-ID: <19970423163627.27791@mpress.com> Date: Wed, 23 Apr 1997 16:36:27 -0700 From: Brian Litzinger To: freebsd-smp@freebsd.org Subject: The disappearing Tyan Titan-Pro ATX S1668 Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I called Tyan (is a local call) and talked to their sales department. I also noticed something new on their website today: 'Something great is coming May 7th' but they don't tell you anything about it. Basically they didn't want to say anything and refered me to a distributor. I talked to their local distributor who said that yes Tyan has a new line of Motherboards coming out in the next few weeks. She said that among other things there would be support for the Pentium Pro II. (but again this was a sales droid). She did not know if the S1668/S1662 would continue or be replaced. She said that she would be getting together some information about the new products and faxing them to me. It sounded though like I would not be getting anything till May 7th. However, as I mentioned in another posting, Fry's Electronics has removed all high end Tyan MBs from their stores and said the new one's would be arriving in a week. -- Brian Litzinger brian@mediacity.com From owner-freebsd-smp Wed Apr 23 16:40:40 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id QAA00857 for smp-outgoing; Wed, 23 Apr 1997 16:40:40 -0700 (PDT) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id QAA00850 for ; Wed, 23 Apr 1997 16:40:37 -0700 (PDT) Received: from fast.cs.utah.edu by cs.utah.edu (8.8.4/utah-2.21-cs) id RAA08252; Wed, 23 Apr 1997 17:40:32 -0600 (MDT) Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id RAA22021; Wed, 23 Apr 1997 17:40:32 -0600 Date: Wed, 23 Apr 1997 17:40:32 -0600 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199704232340.RAA22021@fast.cs.utah.edu> To: donegan@quick.net, smp@freebsd.org Subject: Re: Tyan Tomcat/FreeBSD Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Add this option to your config file: options "MAXMEM=262144" That makes FreeBSD look for 256MB :) Kevin From owner-freebsd-smp Wed Apr 23 16:46:40 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id QAA01031 for smp-outgoing; Wed, 23 Apr 1997 16:46:40 -0700 (PDT) Received: from mpress.com (mpress.com [208.138.29.130]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id QAA01025 for ; Wed, 23 Apr 1997 16:46:37 -0700 (PDT) Received: (qmail 3834 invoked by uid 100); 23 Apr 1997 23:46:14 -0000 Message-ID: <19970423164614.12120@mpress.com> Date: Wed, 23 Apr 1997 16:46:14 -0700 From: Brian Litzinger To: freebsd-smp@freebsd.org Subject: more on Tyan motherboard changes Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Perhaps the following is what all the silence is about: -- Brian Litzinger brian@mediacity.com MILPITAS, CA, (April 18, 1997) -- TYAN Computer, a leading developer of system boards and add-in cards, today announced the Talon AT, a high performance dual Pentium Pro I2O system board. The Talon AT will give a significant Input/Output performance boost to servers and other high-end computer systems. The new motherboard, which is upgradable from one to two processors and allows you to choose a wide range of Pentium Pro processor speeds and types (150-200MHz with 256K/512K cache), will ship in May. TYAN's Talon AT utilizes Intel's newest and fastest Pentium Pro chipset, the 440FX PCIset. It has eight PCI slots (four bus master and four I2O-compliant) and three ISA slots, which allows room for PCI expansion and support for older cards. This full size (13"x12") AT board includes eight 72-pin SIMM sockets with support for a maximum of 1GB EDO or FPM DRAM. The Talon AT features Intel's i960 I2O processor with Wind River Systems' IxWorks RT Operating System installed to implement the I2O architecture. I2O is a new architecture that is being promoted by Intel and others to improve I/O performance by offloading I/O interruptions to free the server's CPU for applications processing. TYAN is a member of the I2O SIG which is spearheading the development of the standard. Novell, Microsoft, and The Santa Cruz Operation are among those developing I2O compliant upgrades to their operating systems. "The Talon AT motherboard is positioned to the mid-range server and high-end computer systems user. It demonstrates TYAN's commitment to delivering leading edge technology in order to give our customers a competitive advantage," said TYAN President Larry Barber. Other standard features of the Talon AT include a new LM78 sensor chip, which protects the system from overheating and provides a server-level system monitoring with on-board alarms for voltage, fan and heat; an on-board switching voltage regulator; and on-board PCI EIDE. It also has Super I/O for maximum performance, enabling it to utilize a wide variety of hard disks, CD-ROMs, modems and other peripherals. TYAN offers a choice of Award or AMI Plug 'n' Play Flash BIOS. The Talon AT is backed by a two year warranty. [promo stuff deleted] From owner-freebsd-smp Wed Apr 23 17:02:34 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id RAA01711 for smp-outgoing; Wed, 23 Apr 1997 17:02:34 -0700 (PDT) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id RAA01706 for ; Wed, 23 Apr 1997 17:02:31 -0700 (PDT) Received: from fast.cs.utah.edu by cs.utah.edu (8.8.4/utah-2.21-cs) id SAA08657; Wed, 23 Apr 1997 18:02:27 -0600 (MDT) Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id SAA22792; Wed, 23 Apr 1997 18:02:27 -0600 Date: Wed, 23 Apr 1997 18:02:27 -0600 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199704240002.SAA22792@fast.cs.utah.edu> To: brian@mpress.com, freebsd-smp@freebsd.org Subject: Re: more on Tyan motherboard changes Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >Perhaps the following is what all the silence is about: -- No...I don't hink so. THe I2O motherboard was on Tyan's page *before* the ``wait until May 7th'' message (and it is still there). SuperMicro also makes a I2O board. Kevin From owner-freebsd-smp Wed Apr 23 17:06:06 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id RAA01886 for smp-outgoing; Wed, 23 Apr 1997 17:06:06 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id RAA01878 for ; Wed, 23 Apr 1997 17:06:03 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id SAA24132; Wed, 23 Apr 1997 18:05:56 -0600 (MDT) Message-Id: <199704240005.SAA24132@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: mef@cs.washington.edu cc: phk@dk.tfs.com, smp@freebsd.org Subject: Re: Intel PR440FX motherboard anybody ? In-reply-to: Your message of "Wed, 23 Apr 1997 11:09:50 PDT." <199704231809.LAA23034@daffy-duck.cs.washington.edu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 23 Apr 1997 18:05:56 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > 1) needed to turn on "options SMP_TIMER_NC" I would be interested to know if this is still true with the latest code. My last changes should make this only necessary if the motherboard lies about the timer/APIC connection. The MP table I have on file for this board shows it properly declaring the missing connection, and thus the software should work without explicitly declaring it via SMP_TIMER_NC (with the latest code, this is a recent change). -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Wed Apr 23 17:09:34 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id RAA02013 for smp-outgoing; Wed, 23 Apr 1997 17:09:34 -0700 (PDT) Received: from intercore.com (num1sun.intercore.com [199.181.243.1]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id RAA02006 for ; Wed, 23 Apr 1997 17:09:31 -0700 (PDT) Received: (robin@localhost) by intercore.com (8.7.1/8.6.4) id UAA24198; Wed, 23 Apr 1997 20:09:06 -0400 (EDT) Message-Id: <199704240009.UAA24198@intercore.com> Date: Wed, 23 Apr 1997 20:09:05 -0400 From: robin@intercore.com (Robin Cutshaw) To: smp@csn.net (Steve Passe) Cc: smp@FreeBSD.Org Subject: Re: hardware list In-Reply-To: <199704231651.KAA22820@Ilsa.StevesCafe.com>; from Steve Passe on Apr 23, 1997 10:51:46 -0600 References: <199704231651.KAA22820@Ilsa.StevesCafe.com> X-Mailer: Mutt 0.47 Mime-Version: 1.0 Sender: owner-smp@FreeBSD.Org X-Loop: FreeBSD.org Precedence: bulk Steve Passe writes: > > they're better than I got from my dual P5-133 with slow SCSI disk: > make -j8 4min 20sec > I got the latest up on a dell poweredge dual P133. It's slower than the previous cut that I was running. I use a massive build/package of the X11R6/XFree86 tree as my benchmark. Old build stats: Start Mon Apr 14 16:17:21 EDT 1997 Start-build Mon Apr 14 16:25:23 EDT 1997 End-build Mon Apr 14 19:03:46 EDT 1997 Start-install Mon Apr 14 19:05:11 EDT 1997 End-install Mon Apr 14 19:16:49 EDT 1997 Start-bindist Mon Apr 14 19:19:59 EDT 1997 End Mon Apr 14 19:22:20 EDT 1997 Latest build stats: Start Wed Apr 23 08:40:51 EDT 1997 Start-build Wed Apr 23 08:49:03 EDT 1997 End-build Wed Apr 23 12:00:04 EDT 1997 Start-install Wed Apr 23 12:01:32 EDT 1997 End-install Wed Apr 23 12:15:08 EDT 1997 Start-bindist Wed Apr 23 12:19:03 EDT 1997 End Wed Apr 23 12:21:48 EDT 1997 Almost 35 minutes slower... robin -- ---- Robin Cutshaw internet: robin@interlabs.com robin@intercore.com Internet Labs, Inc. BellNet: 404-817-9787 "Time is just one damn thing after another" -- PBS/Nova ---- -- From owner-freebsd-smp Wed Apr 23 17:14:21 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id RAA02347 for smp-outgoing; Wed, 23 Apr 1997 17:14:21 -0700 (PDT) Received: from caliban.dihelix.com (caliban.dihelix.com [198.180.136.138]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id RAA02334 for ; Wed, 23 Apr 1997 17:14:12 -0700 (PDT) Received: (from langfod@localhost) by caliban.dihelix.com (8.8.5/8.8.3) id OAA05988; Wed, 23 Apr 1997 14:13:46 -1000 (HST) Message-Id: <199704240013.OAA05988@caliban.dihelix.com> Subject: Re: more on Tyan motherboard changes In-Reply-To: <19970423164614.12120@mpress.com> from Brian Litzinger at "Apr 23, 97 04:46:14 pm" To: brian@mpress.com (Brian Litzinger) Date: Wed, 23 Apr 1997 14:13:46 -1000 (HST) Cc: freebsd-smp@freebsd.org From: "David Langford" X-blank-line: This space intentionaly left blank. X-Mailer: ELM [version 2.4ME+ PL31 (25)] 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 >TYAN's Talon AT utilizes Intel's newest and fastest Pentium Pro chipset, >the 440FX PCIset. It has eight PCI slots (four bus master and four >I2O-compliant) and three ISA slots, which allows room for PCI expansion >and support for older cards. This full size (13"x12") AT board includes >eight 72-pin SIMM sockets with support for a maximum of 1GB EDO or FPM >DRAM. > >The Talon AT features Intel's i960 I2O processor with Wind River >Systems' IxWorks RT Operating System installed to implement the I2O >architecture. I2O is a new architecture that is being promoted by Intel >and others to improve I/O performance by offloading I/O interruptions >to free the server's CPU for applications processing. TYAN is a member >of the I2O SIG which is spearheading the development of the standard. >Novell, Microsoft, and The Santa Cruz Operation are among those >developing I2O compliant upgrades to their operating systems. Boy this sounds like IBM's older RT machines. With the virtual machines and such. Or is this more like Sequents I/O system (where all I/O goes through a special board and get bottleneck there instead. >on-board switching voltage regulator; and on-board PCI EIDE. It also has >Super I/O for maximum performance, enabling it to utilize a wide variety Did they mean it has super I/O or "Super I/O(TM)" ? And what would that mean. Interesting. -David Langford langfod@dihelix.com From owner-freebsd-smp Wed Apr 23 17:45:42 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id RAA03807 for smp-outgoing; Wed, 23 Apr 1997 17:45:42 -0700 (PDT) Received: from news.quick.net (donegan@news.quick.net [207.212.170.1]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id RAA03802 for ; Wed, 23 Apr 1997 17:45:40 -0700 (PDT) Received: (from donegan@localhost) by news.quick.net (8.8.5/8.6.9) id RAA09741; Wed, 23 Apr 1997 17:45:29 -0700 (PDT) Date: Wed, 23 Apr 1997 17:45:28 -0700 (PDT) From: "Steven P. Donegan" To: Kevin Van Maren cc: smp@freebsd.org Subject: Re: Tyan Tomcat/FreeBSD In-Reply-To: <199704232340.RAA22021@fast.cs.utah.edu> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Wed, 23 Apr 1997, Kevin Van Maren wrote: > Add this option to your config file: > options "MAXMEM=262144" > > That makes FreeBSD look for 256MB :) > > Kevin > Thanks all - quite a few replies in real-time on this! Will adjust and re-boot and hopefully be back on-line with SMP tonight... Steven P. Donegan donegan@quick.net From owner-freebsd-smp Wed Apr 23 18:17:48 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id SAA05427 for smp-outgoing; Wed, 23 Apr 1997 18:17:48 -0700 (PDT) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id SAA05422 for ; Wed, 23 Apr 1997 18:17:46 -0700 (PDT) Received: from fast.cs.utah.edu by cs.utah.edu (8.8.4/utah-2.21-cs) id TAA10014; Wed, 23 Apr 1997 19:17:44 -0600 (MDT) Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id TAA24702; Wed, 23 Apr 1997 19:17:43 -0600 Date: Wed, 23 Apr 1997 19:17:43 -0600 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199704240117.TAA24702@fast.cs.utah.edu> To: smp@freebsd.org Subject: AMI BIOS on Titan PRO Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I burned the S1668 AMI BIOS from Tyan's site into a EPROM, and the AMI BIOS booted! Not only that, but the mptable correctly listed all the PCI bridges and adapters. Much better than the Award BIOS which only listed 4 of the 5 PCI slots, and didn't deal with bridges at all in the mptable. I'm sending the outputs to Steve -- contact me if you want a copy too. Kevin From owner-freebsd-smp Wed Apr 23 18:48:43 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id SAA07349 for smp-outgoing; Wed, 23 Apr 1997 18:48:43 -0700 (PDT) Received: from cais.cais.com (root@cais.com [199.0.216.4]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id SAA07343 for ; Wed, 23 Apr 1997 18:48:41 -0700 (PDT) Received: from earth.mat.net (root@earth.mat.net [205.252.122.1]) by cais.cais.com (8.8.5/8.7.3) with SMTP id VAA19302; Wed, 23 Apr 1997 21:48:33 -0400 (EDT) Received: from Journey2.mat.net (journey2.mat.net [205.252.122.116]) by earth.mat.net (8.6.12/8.6.12) with SMTP id VAA17377; Wed, 23 Apr 1997 21:48:31 -0400 Date: Wed, 23 Apr 1997 21:47:52 -0400 (EDT) From: Chuck Robey To: Kevin Van Maren cc: smp@freebsd.org Subject: Re: AMI BIOS on Titan PRO In-Reply-To: <199704240117.TAA24702@fast.cs.utah.edu> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Wed, 23 Apr 1997, Kevin Van Maren wrote: > I burned the S1668 AMI BIOS from Tyan's site into a EPROM, > and the AMI BIOS booted! Not only that, but the mptable > correctly listed all the PCI bridges and adapters. Much > better than the Award BIOS which only listed 4 of the 5 PCI > slots, and didn't deal with bridges at all in the mptable. > > I'm sending the outputs to Steve -- contact me if you want > a copy too. Absolutely, please tell me what I can pay for it, include shipping, I appreciate this! If it's convenient for you, include 2nd day air prices, ok? If it isn't, I appreciate what you're offering, I'll take it any way you darn well please to give it. Do you know how it responds to smp? Could you send your mptable and configfile to me? Thanks. > > Kevin > > ----------------------------+----------------------------------------------- Chuck Robey | Interests include any kind of voice or data chuckr@eng.umd.edu | communications topic, C programming, and Unix. 9120 Edmonston Ct #302 | Greenbelt, MD 20770 | I run Journey2 and picnic, both FreeBSD (301) 220-2114 | version 3.0 current -- and great FUN! ----------------------------+----------------------------------------------- From owner-freebsd-smp Wed Apr 23 20:31:20 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id UAA12576 for smp-outgoing; Wed, 23 Apr 1997 20:31:20 -0700 (PDT) Received: from abby.skypoint.net (abby.skypoint.net [199.86.32.252]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id UAA12571 for ; Wed, 23 Apr 1997 20:31:18 -0700 (PDT) Received: (from uucp@localhost) by abby.skypoint.net (8.8.5/alexis 2.7) with UUCP id WAA03628; Wed, 23 Apr 1997 22:31:02 -0500 (CDT) Received: (from bruce@localhost) by zuhause.mn.org (8.8.5/8.8.5) id WAA00560; Wed, 23 Apr 1997 22:00:53 -0500 (CDT) Date: Wed, 23 Apr 1997 22:00:53 -0500 (CDT) Message-Id: <199704240300.WAA00560@zuhause.mn.org> From: Bruce Albrecht To: Ben Black Cc: Brian Litzinger , smp@freebsd.org Subject: Re: Tyan Titan-Pro ATX S1668 no more? or changing? In-Reply-To: References: <19970423004945.15230@mpress.com> X-Mailer: VM 6.22 under 19.15p2 XEmacs Lucid Mime-Version: 1.0 (generated by tm-edit 7.106) Content-Type: text/plain; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Ben Black writes: > well, given that the PS/2 port and second serial port on my machine don't > work, i don't think a recall is out of the question. I just received an ATX-1668 last friday, and I'm not having any problems with the PS/2 ports or the second serial port. I did have problems with memory until I changed some of the chipset settings, though. From owner-freebsd-smp Wed Apr 23 20:31:26 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id UAA12583 for smp-outgoing; Wed, 23 Apr 1997 20:31:26 -0700 (PDT) Received: from abby.skypoint.net (abby.skypoint.net [199.86.32.252]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id UAA12578 for ; Wed, 23 Apr 1997 20:31:24 -0700 (PDT) Received: (from uucp@localhost) by abby.skypoint.net (8.8.5/alexis 2.7) with UUCP id WAA03641 for freebsd-smp@freebsd.org; Wed, 23 Apr 1997 22:31:23 -0500 (CDT) Received: (from bruce@localhost) by zuhause.mn.org (8.8.5/8.8.5) id WAA00582; Wed, 23 Apr 1997 22:17:33 -0500 (CDT) Date: Wed, 23 Apr 1997 22:17:33 -0500 (CDT) Message-Id: <199704240317.WAA00582@zuhause.mn.org> From: Bruce Albrecht To: freebsd-smp@freebsd.org Subject: FPU emulation still required? X-Mailer: VM 6.22 under 19.15p2 XEmacs Lucid Mime-Version: 1.0 (generated by tm-edit 7.106) Content-Type: text/plain; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Now that I've finally received my dual CPU ATX 1668, I'd like to get SMP up and running. I noticed that some of the messages from the beginning of the year said that FPU emulation was required because the FPU registers weren't being saved properly. Is this still true? If so, what sort of performance hit is there? From owner-freebsd-smp Wed Apr 23 20:35:22 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id UAA12764 for smp-outgoing; Wed, 23 Apr 1997 20:35:22 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id UAA12759 for ; Wed, 23 Apr 1997 20:35:20 -0700 (PDT) From: Steve Passe Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id UAA12478 for freebsd-smp; Wed, 23 Apr 1997 20:35:05 -0700 (PDT) Date: Wed, 23 Apr 1997 20:35:05 -0700 (PDT) Message-Id: <199704240335.UAA12478@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/i386 mp_machdep.c sys/i386/include smptests.h sys/i386/isa vector.s Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/23 20:35:05 Modified: i386/i386 mp_machdep.c i386/include smptests.h i386/isa vector.s Log: A bolder attempt to cure the apicIPI / SMP_INVLTLB deadlock: Xfastipi32, new inline function in vector.s Xfastipi32 is registered directly via setidt() at vector ICU+32, ie. in a APIC bucket of higher priority than the other INTs. This means that apicIPI shouldn't block for lack of buffer space. Note that for the first cut register_intr(), etc. are skipped. This can be restored later once the concept is proven. Because of the masking etc. that breaks when we go beyond the 32nd bit position I skipped that for now... Xfastipi32 DOES NOT get the mplock, it flushes the TLB, EOIs the APIC, irets. If anyone sees a potenrtial problem here please speak up. To enable uncomment "#define XFAST_IPI32" in i386/include/smptests.h. Revision Changes Path 1.41 +18 -1 sys/i386/i386/mp_machdep.c 1.10 +7 -1 sys/i386/include/smptests.h 1.40 +25 -0 sys/i386/isa/vector.s From owner-freebsd-smp Wed Apr 23 21:35:08 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id VAA14901 for smp-outgoing; Wed, 23 Apr 1997 21:35:08 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id VAA14892 for ; Wed, 23 Apr 1997 21:35:03 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id WAA01042; Wed, 23 Apr 1997 22:34:57 -0600 (MDT) Message-Id: <199704240434.WAA01042@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Bruce Albrecht cc: freebsd-smp@freebsd.org Subject: Re: FPU emulation still required? In-reply-to: Your message of "Wed, 23 Apr 1997 22:17:33 CDT." <199704240317.WAA00582@zuhause.mn.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 23 Apr 1997 22:34:57 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > Now that I've finally received my dual CPU ATX 1668, I'd like to get > SMP up and running. I noticed that some of the messages from the > beginning of the year said that FPU emulation was required because the > FPU registers weren't being saved properly. Is this still true? If > so, what sort of performance hit is there? although some people don't yet have a "warm fuzzy feeling" for the FPU code it does appear to be working. The main problem was identified as a missing lock release. float should be fine now... There is a current list of bugs at: http://www.freebsd.org/~fsmp/SMP/bugs.html -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Wed Apr 23 21:36:34 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id VAA14973 for smp-outgoing; Wed, 23 Apr 1997 21:36:34 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id VAA14968 for ; Wed, 23 Apr 1997 21:36:31 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id WAA01054; Wed, 23 Apr 1997 22:36:19 -0600 (MDT) Message-Id: <199704240436.WAA01054@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Keith Mitchell cc: cr@jcmax.com, smp@freebsd.org Subject: Re: Freezes/Reboots with -current ahc driver In-reply-to: Your message of "Tue, 22 Apr 1997 15:05:51 EDT." <199704221905.PAA02398@weenix.guru.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 23 Apr 1997 22:36:19 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, I just committed new code for the apicIPI/SMP_INVLTLB deadlock problem. Not sure if its reached the cvs mirror yet, but if you sup you should get a new vector.s, mp_machdep.c and smptests.h. uncomment the XFAST_IPI32 define in smptests.h and build. please let me know how this works. --- Keith, did you try running with APIC_IO turned off yet? did it help? this test should be run with APIC_IO ON... -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Wed Apr 23 23:16:52 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id XAA18575 for smp-outgoing; Wed, 23 Apr 1997 23:16:52 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id XAA18570 for ; Wed, 23 Apr 1997 23:16:51 -0700 (PDT) From: Peter Wemm Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id XAA13022 for freebsd-smp; Wed, 23 Apr 1997 23:16:35 -0700 (PDT) Date: Wed, 23 Apr 1997 23:16:35 -0700 (PDT) Message-Id: <199704240616.XAA13022@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/i386 mpapic.c Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk peter 97/04/23 23:16:35 Modified: i386/i386 mpapic.c Log: Delete some #if 0 code that I wrote while trying to figure out what EISA did. (EISA interrupts are "converted" to isa-style hi-edge trigger interrupts by the level/polarity converter gadget regardless of what the mptable says) Revision Changes Path 1.29 +12 -56 sys/i386/i386/mpapic.c From owner-freebsd-smp Thu Apr 24 08:12:51 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id IAA10863 for smp-outgoing; Thu, 24 Apr 1997 08:12:51 -0700 (PDT) Received: from mail0.iij.ad.jp (mail0.iij.ad.jp [202.232.2.113]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id IAA10858 for ; Thu, 24 Apr 1997 08:12:48 -0700 (PDT) Received: from uucp2.iij.ad.jp (uucp2.iij.ad.jp [202.232.2.202]) by mail0.iij.ad.jp (8.8.5+2.7Wbeta5/3.5Wpl4-MAIL) with SMTP id AAA13148 for ; Fri, 25 Apr 1997 00:12:46 +0900 (JST) Received: (from uucp@localhost) by uucp2.iij.ad.jp (8.6.12+2.4W/3.3W9-UUCP) with UUCP id AAA22864 for freebsd-smp@FreeBSD.org; Fri, 25 Apr 1997 00:12:46 +0900 Received: from tyd1.tydfam.iijnet.or.jp (tyd1.tydfam.iijnet.or.jp [192.168.1.2]) by tydfam.iijnet.or.jp (8.8.5/3.4W2-uucp) with ESMTP id UAA00574 for ; Thu, 24 Apr 1997 20:56:18 +0900 (JST) Received: from localhost.tydfam.iijnet.or.jp (localhost.tydfam.iijnet.or.jp [127.0.0.1]) by tyd1.tydfam.iijnet.or.jp (8.8.5/3.4Wnomx) with SMTP id UAA14270 for ; Thu, 24 Apr 1997 20:56:18 +0900 (JST) Message-Id: <199704241156.UAA14270@tyd1.tydfam.iijnet.or.jp> X-Authentication-Warning: tyd1.tydfam.iijnet.or.jp: localhost.tydfam.iijnet.or.jp [127.0.0.1] didn't use HELO protocol To: freebsd-smp@FreeBSD.org Subject: Success Report X-Mailer: Mew version 1.55 on Emacs 19.34.2, Mule 2.3 Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Date: Thu, 24 Apr 1997 20:56:18 +0900 From: Takeshi Yamada Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi! I darely not repeat the Hardware List as it is already reported, ASUS P/I-P65UP5 & C-P6ND. It works!! It has been working for 3 days without any trouble. I thank you all your great job. Followings are what I have with recent mptable (mptable -verbose -dmesg). =============================================================================== MPTable, version 2.0.7 looking for EBDA pointer @ 0x040e, NOT found searching CMOS 'top of mem' @ 0x0009fc00 (639K) searching BIOS @ 0x000f0000 MP FPS found in BIOS @ physical addr: 0x000f60b0 ------------------------------------------------------------------------------- MP Floating Pointer Structure: location: BIOS physical address: 0x000f60b0 signature: '_MP_' length: 16 bytes version: 1.4 checksum: 0x8b mode: Virtual Wire ------------------------------------------------------------------------------- MP Config Table Header: physical address: 0x000f5caa signature: 'PCMP' base table length: 252 version: 1.4 checksum: 0x8c OEM ID: 'OEM00000' Product ID: 'PROD00000000' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 23 local APIC address: 0xfee00000 extended table length: 0 extended table checksum: 0 ------------------------------------------------------------------------------- MP Config Base Table Entries: -- Processors: APIC ID Version State Family Model Step Flags 1 0x11 BSP, usable 6 1 7 0xfbff 0 0x11 AP, usable 6 1 7 0xfbff -- Bus: Bus ID Type 0 PCI 1 PCI 2 ISA -- I/O APICs: APIC ID Version State Address 2 0x11 usable 0xfec00000 -- I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 2 0 2 0 INT conforms conforms 2 1 2 1 INT conforms conforms 2 0 2 2 INT conforms conforms 2 3 2 3 INT conforms conforms 2 4 2 4 INT conforms conforms 2 5 2 5 INT conforms conforms 2 6 2 6 INT conforms conforms 2 7 2 7 INT conforms conforms 2 8 2 8 INT conforms conforms 2 9 2 9 INT conforms conforms 2 14 2 14 INT active-lo level 0 9:A 2 19 INT active-lo level 0 10:A 2 18 INT active-lo level 1 4:A 2 16 INT active-lo level 1 5:A 2 17 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT active-hi edge 2 0 255 0 NMI active-hi edge 2 0 255 1 ------------------------------------------------------------------------------- # SMP kernel config file options: options SMP # Symmetric MultiProcessor Kernel # Recommended: options APIC_IO # Symmetric (APIC) I/O options SMP_INVLTLB # both APIC_IO/SMP_INVLTBL required # Optional (built-in defaults will work in most cases): options NCPU=2 # number of CPUs options NBUS=3 # number of busses options NAPIC=1 # number of IO APICs options NINTR=24 # number of INTs # Currently broken: #options SMP_PRIVPAGES # BROKEN, DO NOT use! #options SMP_AUTOSTART # BROKEN, DO NOT use! # Rogue hardware: # # Tyan Tomcat II: #options SMP_TIMER_NC # # # SuperMicro P6DNE: #options SMP_TIMER_NC # ------------------------------------------------------------------------------- dmesg output: Copyright (c) 1992-1997 FreeBSD Inc. Copyright (c) 1982, 1986, 1989, 1991, 1993 The Regents of the University of California. All rights reserved. FreeBSD 3.0-SMP #0: Thu Apr 24 20:33:40 JST 1997 ken@tyd0.tydfam.iijnet.or.jp:/usr/src/sys-MP/compile/SMPTYD FreeBSD/SMP: Multiprocessor motherboard cpu0 (BSP): apic id: 1, version: 0x00040011 cpu1 (AP): apic id: 0, version: 0x00040011 io0 (APIC): apic id: 2, version: 0x00170011 CPU: Pentium Pro (686-class CPU) Origin = "GenuineIntel" Id = 0x617 Stepping=7 Features=0xfbff,MTRR,PGE,MCA,CMOV> real memory = 67108864 (65536K bytes) Physical memory hole(s): avail memory = 63750144 (62256K bytes) bdevsw_add_generic: adding D_DISK flag for device 15 Probing for devices on PCI bus 0: chip0 rev 2 on pci0:0:0 chip1 rev 1 on pci0:1:0 chip2 rev 0 on pci0:1:1 fxp0 rev 1 int a irq 19 on pci0:9:0 Freeing (NOT implimented) irq 15 for ISA cards. fxp0: Ethernet address 00:a0:c9:04:9a:61 de0 rev 32 int a irq 18 on pci0:10:0 Freeing (NOT implimented) irq 12 for ISA cards. de0: 21140A [10-100Mb/s] pass 2.0 de0: address 00:40:05:31:4c:15 de0: enabling 100baseTX port chip3 rev 2 on pci0:12:0 Probing for devices on PCI bus 1: ahc0 rev 0 int a irq 16 on pci1:4:0 Freeing (NOT implimented) irq 11 for ISA cards. ahc0: aic7880 Channel A, SCSI Id=7, 16/255 SCBs ahc0: waiting for scsi devices to settle scbus0 at ahc0 bus 0 ahc0: target 0 Tagged Queuing Device sd0 at scbus0 target 0 lun 0 sd0: type 0 fixed SCSI 2 sd0: Direct-Access 2049MB (4197405 512 byte sectors) sd0: with 4177 cyls, 8 heads, and an average 125 sectors/track ahc0: target 5 Tagged Queuing Device sd1 at scbus0 target 5 lun 0 sd1: type 0 fixed SCSI 2 sd1: Direct-Access 2049MB (4197405 512 byte sectors) sd1: with 4177 cyls, 8 heads, and an average 125 sectors/track ahc1 rev 0 int a irq 17 on pci1:5:0 Freeing (NOT implimented) irq 10 for ISA cards. ahc1: aic7880 Channel B, SCSI Id=7, 16/255 SCBs ahc1: waiting for scsi devices to settle scbus1 at ahc1 bus 0 ahc1: target 0 Tagged Queuing Device sd2 at scbus1 target 0 lun 0 sd2: type 0 fixed SCSI 2 sd2: Direct-Access 2049MB (4197405 512 byte sectors) sd2: with 4177 cyls, 8 heads, and an average 125 sectors/track ahc1: target 1 Tagged Queuing Device sd3 at scbus1 target 1 lun 0 sd3: type 0 fixed SCSI 2 sd3: Direct-Access 2049MB (4197405 512 byte sectors) sd3: with 4177 cyls, 8 heads, and an average 125 sectors/track st0 at scbus1 target 3 lun 0 st0: type 1 removable SCSI 2 st0: Sequential-Access density code 0x13, drive empty Probing for devices on the ISA bus: sc0 at 0x60-0x6f irq 1 on motherboard sc0: VGA color <16 virtual consoles, flags=0x0> lpt0 at 0x378-0x37f irq 9 on isa lpt0: Interrupt-driven port lp0: TCP/IP capable interface psm0 not found at 0x60 sio0 at 0x3f8-0x3ff irq 4 on isa sio1 at 0x2f8-0x2ff irq 3 on isa sio2 not found at 0x3e8 sio3 not found at 0x2e8 pca0 on motherboard pca0: PC speaker audio driver fdc0 at 0x3f0-0x3f7 irq 6 drq 2 on isa fdc0: NEC 72065B fd0: 1.44MB 3.5in npx0 on motherboard npx0: INT 16 interface sctarg0 at scbus255 target 255 lun 255 sctarg0: type 0 fixed SCSI 0 sctarg0: Processor Target Enabled INTs: 1, 2, 3, 4, 6, 8, 9, 16, 17, 18, 19, imen: 0x00f0fca1 ccd0-3: Concatenated disk drivers SMP: All idle procs online. SMP: Starting 1st AP! SMP: AP CPU #1 LAUNCHED!! Starting Scheduling... SMP: TADA! CPU #1 made it into the scheduler!. SMP: All 2 CPU's are online! =============================================================================== From owner-freebsd-smp Thu Apr 24 12:53:22 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA27027 for smp-outgoing; Thu, 24 Apr 1997 12:53:22 -0700 (PDT) Received: from babe.globecomm.net (babe.globecomm.net [207.51.48.8]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA27022 for ; Thu, 24 Apr 1997 12:53:20 -0700 (PDT) Received: from w3.starnets.ro ([193.226.124.34]) by babe.globecomm.net (8.8.5/8.8.0) with SMTP id PAA09600 for ; Thu, 24 Apr 1997 15:53:10 -0400 (EDT) Message-ID: <335FB93A.2D2D@earthling.net> Date: Thu, 24 Apr 1997 22:49:14 +0300 From: Penisoara Adrian Reply-To: ady@earthling.net X-Mailer: Mozilla 3.01Gold (Win95; I) MIME-Version: 1.0 To: freebsd-smp@FreeBSD.org Subject: The false typo & SMP kernel problem Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi! Steve was right, that what I reported as a typo was in fact a disk error (or maybe a network error, who knows ?). Still, I'm facing again with ps,netstat,etc. problems when I compile a SMP kernel from the new cvsup'ed smp-sys tree. Please note that I had a working and stable SMP kernel from an older cvsup tree (I think 1 Apr 97). Even WORSE: copied the GENERIC file and just made slight adjustements for my system (like disabling other SCSI controllers/Network cards than mine) and with NO SMP options and the same result: #ps ps: proc size mismatch (17280 total, 632 chunks) #netstat ??? netstat: kvm_read: Bad address [....] [ totally wrong output ] [....] # For now I'll try the older stable tree. Strange is that I had exactly the same kind of problems each time I tried the current SMP source tree. Ady (@earthling.net) From owner-freebsd-smp Thu Apr 24 13:23:55 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id NAA28787 for smp-outgoing; Thu, 24 Apr 1997 13:23:55 -0700 (PDT) Received: from phaeton.artisoft.com (phaeton.Artisoft.COM [198.17.250.50]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id NAA28777 for ; Thu, 24 Apr 1997 13:23:51 -0700 (PDT) Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id NAA01896; Thu, 24 Apr 1997 13:20:47 -0700 From: Terry Lambert Message-Id: <199704242020.NAA01896@phaeton.artisoft.com> Subject: Re: The false typo & SMP kernel problem To: ady@earthling.net Date: Thu, 24 Apr 1997 13:20:46 -0700 (MST) Cc: freebsd-smp@FreeBSD.org In-Reply-To: <335FB93A.2D2D@earthling.net> from "Penisoara Adrian" at Apr 24, 97 10:49:14 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 > Even WORSE: copied the GENERIC file and just made slight adjustements > for my system (like disabling other SCSI controllers/Network cards than > mine) and with NO SMP options and the same result: > #ps > ps: proc size mismatch (17280 total, 632 chunks) > #netstat > ??? > netstat: kvm_read: Bad address > [....] > [ totally wrong output ] > [....] The kernel structure sizes have changed, and kernel data is exported (via libkvm) as an interface. You will need to recompile /sys/libkern and /usr/src/lib/libkvm, and potentially all utilities like 'ps', 'w', 'netstat', 'ifconfig', 'vmstat', etc. which rely on likkvm. If you have just moved to 3.x from a 2.x kernel, then you will have to rebuild libc as well to get the popen changes and the newgetvfsbyname() system call used by mount and similar utilities. Before you do this, you will need to rebuild crt0.o so that the set_startup_locale (or something like that) crap doesn't bite you, and that means rebuilding all the compilation tools to rebuild ld to rebuild crt0. This takes about twice as much disk as it used to because the way the GNU stuff has been moved around to contrib (as if it weren't under GPL now, or some such nonsense). Then you will need to rebuild mount, etc., so that it calls the new calls. There are instructions on www.freebsd.org in the -current list archives. Bletch. Yuck. Bletch. Phthhhhhhtp. Regards, 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 Thu Apr 24 20:12:19 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id UAA20063 for smp-outgoing; Thu, 24 Apr 1997 20:12:19 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id UAA20056 for ; Thu, 24 Apr 1997 20:12:18 -0700 (PDT) From: Steve Passe Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id UAA20268 for freebsd-smp; Thu, 24 Apr 1997 20:11:55 -0700 (PDT) Date: Thu, 24 Apr 1997 20:11:55 -0700 (PDT) Message-Id: <199704250311.UAA20268@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/kern init_smp.c sys/i386/i386 autoconf.c mp_machdep.c mpapic.c mpboot.s pmap.c sys/i386/isa clock.c icu.h sys/i386/include mpapic.h smp.h smpasm.h smptests.h Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/24 20:11:54 Modified: kern init_smp.c i386/include mpapic.h smp.h smpasm.h smptests.h i386/isa clock.c icu.h Log: cleanup for the merge. Revision Changes Path 1.46 +2 -2 sys/kern/init_smp.c 1.12 +66 -66 sys/i386/include/mpapic.h 1.27 +27 -27 sys/i386/include/smp.h 1.8 +3 -3 sys/i386/include/smpasm.h 1.11 +2 -2 sys/i386/include/smptests.h 1.18 +8 -8 sys/i386/isa/clock.c 1.16 +9 -9 sys/i386/isa/icu.h Modified: i386/i386 autoconf.c mp_machdep.c mpapic.c mpboot.s pmap.c Log: cleanup for the merge. mp_machdep contains fix for mis-numbered PCI bus when only 1 PCI bus exists. Revision Changes Path 1.16 +2 -2 sys/i386/i386/autoconf.c 1.42 +340 -265 sys/i386/i386/mp_machdep.c 1.30 +92 -92 sys/i386/i386/mpapic.c 1.18 +9 -9 sys/i386/i386/mpboot.s 1.38 +5 -4 sys/i386/i386/pmap.c From owner-freebsd-smp Thu Apr 24 21:34:43 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id VAA22944 for smp-outgoing; Thu, 24 Apr 1997 21:34:43 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id VAA22930 for ; Thu, 24 Apr 1997 21:34:41 -0700 (PDT) From: Steve Passe Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id VAA20515 for freebsd-smp; Thu, 24 Apr 1997 21:34:18 -0700 (PDT) Date: Thu, 24 Apr 1997 21:34:18 -0700 (PDT) Message-Id: <199704250434.VAA20515@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/include smptests.h Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/24 21:34:18 Modified: i386/include smptests.h Log: opps, the XFAST_IPI32 define was left uncommented, now back where it belongs. (however I do want people to test it, need to know if it fixes/breaks anything) Revision Changes Path 1.12 +2 -2 sys/i386/include/smptests.h From owner-freebsd-smp Fri Apr 25 01:01:30 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id BAA00944 for smp-outgoing; Fri, 25 Apr 1997 01:01:30 -0700 (PDT) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id BAA00937 for ; Fri, 25 Apr 1997 01:01:26 -0700 (PDT) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id JAA23451; Fri, 25 Apr 1997 09:15:24 +0200 (MET DST) Received: (from andreas@localhost) by klemm.gtn.com (8.8.5/8.8.2) id IAA01380; Fri, 25 Apr 1997 08:58:37 +0200 (CEST) Message-ID: <19970425085837.57898@klemm.gtn.com> Date: Fri, 25 Apr 1997 08:58:37 +0200 From: Andreas Klemm To: Chuck Robey Cc: Kevin Van Maren , smp@FreeBSD.org Subject: Re: AMI BIOS on Titan PRO References: <199704240117.TAA24702@fast.cs.utah.edu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 In-Reply-To: ; from Chuck Robey on Wed, Apr 23, 1997 at 09:47:52PM -0400 X-Disclaimer: A free society is one where it is safe to be unpopular X-Operating-System: FreeBSD 3.0-CURRENT Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Wed, Apr 23, 1997 at 09:47:52PM -0400, Chuck Robey wrote: > On Wed, 23 Apr 1997, Kevin Van Maren wrote: > > > I burned the S1668 AMI BIOS from Tyan's site into a EPROM, > > and the AMI BIOS booted! Not only that, but the mptable > > correctly listed all the PCI bridges and adapters. Much > > better than the Award BIOS which only listed 4 of the 5 PCI > > slots, and didn't deal with bridges at all in the mptable. > > > > I'm sending the outputs to Steve -- contact me if you want > > a copy too. > > Absolutely, please tell me what I can pay for it, include shipping, I > appreciate this! If it's convenient for you, include 2nd day air prices, > ok? If it isn't, I appreciate what you're offering, I'll take it any way > you darn well please to give it. > > Do you know how it responds to smp? Could you send your mptable and > configfile to me? Thanks. Why do you want an extra EPROM ? The BIOS is flashable or do you recommend getting an extra EPROM to have a working Award as "fallback" BIOS in case of trouble ??? -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-smp Fri Apr 25 05:11:32 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id FAA10697 for smp-outgoing; Fri, 25 Apr 1997 05:11:32 -0700 (PDT) Received: from cais.cais.com (root@cais.com [199.0.216.4]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id FAA10692 for ; Fri, 25 Apr 1997 05:11:30 -0700 (PDT) Received: from earth.mat.net (root@earth.mat.net [205.252.122.1]) by cais.cais.com (8.8.5/8.7.3) with SMTP id IAA13439; Fri, 25 Apr 1997 08:11:27 -0400 (EDT) Received: from Journey2.mat.net (journey2.mat.net [205.252.122.116]) by earth.mat.net (8.6.12/8.6.12) with SMTP id IAA28902; Fri, 25 Apr 1997 08:11:25 -0400 Date: Fri, 25 Apr 1997 08:11:03 -0400 (EDT) From: Chuck Robey To: Andreas Klemm cc: Kevin Van Maren , smp@FreeBSD.org Subject: Re: AMI BIOS on Titan PRO In-Reply-To: <19970425085837.57898@klemm.gtn.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Fri, 25 Apr 1997, Andreas Klemm wrote: > On Wed, Apr 23, 1997 at 09:47:52PM -0400, Chuck Robey wrote: > > On Wed, 23 Apr 1997, Kevin Van Maren wrote: > > > > > I burned the S1668 AMI BIOS from Tyan's site into a EPROM, > > > and the AMI BIOS booted! Not only that, but the mptable > > > correctly listed all the PCI bridges and adapters. Much > > > better than the Award BIOS which only listed 4 of the 5 PCI > > > slots, and didn't deal with bridges at all in the mptable. > > > > > > I'm sending the outputs to Steve -- contact me if you want > > > a copy too. > > > > Absolutely, please tell me what I can pay for it, include shipping, I > > appreciate this! If it's convenient for you, include 2nd day air prices, > > ok? If it isn't, I appreciate what you're offering, I'll take it any way > > you darn well please to give it. > > > > Do you know how it responds to smp? Could you send your mptable and > > configfile to me? Thanks. > > Why do you want an extra EPROM ? The BIOS is flashable or do you > recommend getting an extra EPROM to have a working Award as > "fallback" BIOS in case of trouble ??? I contacted the source, Acme, and they said it would cost only $15, so I went that way. I am not especially anxious to do the flash route because of the stories I've heard about flash failure. If you get that problem, your Motherboard is basically toast, and $15 spent to avoid that seems like a fantastic bargain. BTW, my post above was meant to be private, and it wasn't until after I'd sent it that it occurred to me that there had to be something else involved, because it meant getting something for nothing. I don't want to do that, I just want to fix a problem I presently have. > > -- > andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH > Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de > pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< > ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< > > ----------------------------+----------------------------------------------- Chuck Robey | Interests include any kind of voice or data chuckr@eng.umd.edu | communications topic, C programming, and Unix. 9120 Edmonston Ct #302 | Greenbelt, MD 20770 | I run Journey2 and picnic, both FreeBSD (301) 220-2114 | version 3.0 current -- and great FUN! ----------------------------+----------------------------------------------- From owner-freebsd-smp Fri Apr 25 05:47:09 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id FAA12695 for smp-outgoing; Fri, 25 Apr 1997 05:47:09 -0700 (PDT) Received: from caleche.kecl.ntt.co.jp (elysium.kecl.ntt.co.jp [129.60.192.193]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id FAA12686 for ; Fri, 25 Apr 1997 05:47:05 -0700 (PDT) Received: from localhost by caleche.kecl.ntt.co.jp (8.8.5/kecl2.0/r8v7-M2-nishio) with ESMTP id VAA00491; Fri, 25 Apr 1997 21:46:45 +0900 (JST) To: freebsd-smp@FreeBSD.org Subject: Tyan ATX1668 problem -- success Mime-Version: 1.0 X-Mailer: Mew version 1.54 on Emacs 19.34.1, Mule 2.3 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-Id: <19970425214645B.nishio@elysium.kecl.ntt.co.jp> Date: Fri, 25 Apr 1997 21:46:45 +0900 From: NISHIO Shuichi X-Dispatcher: impost version 0.95+ (Nov. 26, 1996) Lines: 82 Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hello, Early in this month, I asked about the problem with the 5th PCI slot on Tyan S1668, which was not recognized correctly when using APIC_IO. Someone (Mr. Steve Passe ? I've lost most of my mails due to disk crashes) sent me a patch to fix this, but I could not try this until last Sunday. This is the suggested fix in i386/i386/mp_machdep.c --- start --- #define TYAN_S1668_ROGUE #if defined( TYAN_S1668_ROGUE ) /** NOTE: this might be some other #, we are guessing... */ #define TYAN_S1668_SLOT5_IRQ 16 int get_pci_apic_irq( int pciBus, int pciDevice, int pciInt ) { int intr; if ( (pciBus == 0) && (pciDevice == 10) ){ return TYAN_S1668_SLOT5_IRQ; } #else int get_pci_apic_irq( int pciBus __attribute__ ((unused)), int pciDevice, int pciInt ) { int intr; #endif /** * FIXME: how do we associate a SPECIFIC PCI bus with a unique bus ID??? */ --- end --- So, last Sunday, I cvsup'ed the SMP code and the entire current, did a 'make World', and tried the SMP kernel with this fix and APIC_IO. I tried defining TYAN_S1668_SLOT5_IRQ as 16 and 20, but only as 16 did the 5th PCI card (DEC FastEtherworks) got recognized. (16 is the one for the 1st slot) However, there still was some problems. 1. /bin/ps -a sometimes freezes sometimes, when I tried to see root processes with 'ps -a', it just freezes. The system keeps on running, but I couldn't kill the 'ps' process. 2. panic on heavy traffic This could be easily reproduced by transfering large files simultaneously on 2 network interfaces using ftp or NFS. (this system is connected to one 10BaseT and one 100BaseTX net) I also experienced crashes on dumping filesystems to DAT, but this might be due to the problem with the AIC driver. Last evening, I tried a kernel with XFAST_IPI32 defined (and also the latest current), and these problems seems to go away: I tried making kernel with -j8 'put'ting a 180MB file from FreeBSD to SGI O2 on 100BaseTX 'get'ting a 60MB file from O2 to FreeBSD dumping /home to DAT simultaneously, but it went through, without going panic. Additionaly, I don't know why, but the network transfer rate seems to have raised to 55Mb/s after defining XFAST_IPI32, from 45Mb/s with the previous kernel. So, in summary, the recent fix including XFAST_IPI32 seems to be working very fine here. Thank you very much. Nishio Shuichi From owner-freebsd-smp Fri Apr 25 07:17:04 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id HAA17915 for smp-outgoing; Fri, 25 Apr 1997 07:17:04 -0700 (PDT) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id HAA17910 for ; Fri, 25 Apr 1997 07:17:03 -0700 (PDT) Received: from fast.cs.utah.edu by cs.utah.edu (8.8.4/utah-2.21-cs) id IAA17096; Fri, 25 Apr 1997 08:17:00 -0600 (MDT) Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id IAA15451; Fri, 25 Apr 1997 08:17:00 -0600 Date: Fri, 25 Apr 1997 08:17:00 -0600 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199704251417.IAA15451@fast.cs.utah.edu> To: freebsd-smp@FreeBSD.org Subject: Re: AMI BIOS on Titan PRO Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Since several people have sent requests, I'm forwarding the mptable outputs to the list -- delete them if they don't interest you. Also, let me elaborate a little on the AMI BIOS. The Titan Pro (S1662/S1668) shipps with the Award BIOS in most cases. Recently an AMI BIOS became available. However, it is not possible to Flash an AMI BIOS over an Award BIOS (well, it might be `possible'). The AMI BIOS has apparently CORRECT mptable entries for ALL the PCI devices in the system (including the ubiquitious `slot 5'). Kevin From owner-freebsd-smp Fri Apr 25 07:20:09 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id HAA18070 for smp-outgoing; Fri, 25 Apr 1997 07:20:09 -0700 (PDT) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id HAA18065 for ; Fri, 25 Apr 1997 07:20:07 -0700 (PDT) Received: from fast.cs.utah.edu by cs.utah.edu (8.8.4/utah-2.21-cs) id IAA17136; Fri, 25 Apr 1997 08:20:05 -0600 (MDT) Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id IAA15561; Fri, 25 Apr 1997 08:20:04 -0600 Date: Fri, 25 Apr 1997 08:20:04 -0600 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199704251420.IAA15561@fast.cs.utah.edu> To: freebsd-smp@FreeBSD.org Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk =============================================================================== MPTable, version 2.0.4 looking for EBDA pointer @ 0x040e, found, searching EBDA @ 0x0009fc00 searching CMOS 'top of mem' @ 0x0009e800 (634K) searching default 'top of mem' @ 0x0009fc00 (639K) searching BIOS @ 0x000f0000 MP FPS found in BIOS @ physical addr: 0x000fb100 ------------------------------------------------------------------------------- MP Floating Pointer Structure: location: BIOS physical address: 0x000fb100 signature: '_MP_' length: 16 bytes version: 1.1 checksum: 0xf7 mode: Virtual Wire ------------------------------------------------------------------------------- MP Config Table Header: physical address: 0x000f5d40 signature: 'PCMP' base table length: 276 version: 1.1 checksum: 0x04 OEM ID: 'INTEL ' Product ID: '440FX ' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 26 local APIC address: 0xfee00000 extended table length: 0 extended table checksum: 0 ------------------------------------------------------------------------------- MP Config Base Table Entries: -- Processors: APIC ID Version State Family Model Step Flags 1 0x11 BSP, usable 6 1 6 0xfbff 0 0x11 AP, usable 6 1 6 0xfbff -- Bus: Bus ID Type 0 PCI 1 ISA -- I/O APICs: APIC ID Version State Address 2 0x11 usable 0xfec00000 -- I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 1 0 2 0 INT conforms conforms 1 1 2 1 INT conforms conforms 1 0 2 2 INT conforms conforms 1 3 2 3 INT conforms conforms 1 4 2 4 INT conforms conforms 1 5 2 5 INT conforms conforms 1 6 2 6 INT conforms conforms 1 7 2 7 INT active-hi edge 1 8 2 8 INT conforms conforms 1 9 2 9 INT conforms conforms 1 10 2 10 INT conforms conforms 1 11 2 11 INT conforms conforms 1 12 2 12 INT conforms conforms 1 13 2 13 INT conforms conforms 1 14 2 14 INT conforms conforms 1 15 2 15 INT active-lo level 0 12:A 2 18 INT active-lo level 0 11:A 2 19 SMI conforms conforms 1 0 2 23 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 0 0:A 255 0 NMI conforms conforms 0 0:A 255 1 ------------------------------------------------------------------------------- # SMP kernel config file options: options SMP # Symmetric MultiProcessor Kernel #options APIC_IO # Symmetric (APIC) I/O options NCPU=2 # number of CPUs options NBUS=2 # number of busses options NAPIC=1 # number of IO APICs options NINTR=19 # number of INTs =============================================================================== From owner-freebsd-smp Fri Apr 25 07:20:12 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id HAA18080 for smp-outgoing; Fri, 25 Apr 1997 07:20:12 -0700 (PDT) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id HAA18072 for ; Fri, 25 Apr 1997 07:20:10 -0700 (PDT) Received: from fast.cs.utah.edu by cs.utah.edu (8.8.4/utah-2.21-cs) id IAA17142; Fri, 25 Apr 1997 08:20:08 -0600 (MDT) Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id IAA15569; Fri, 25 Apr 1997 08:20:07 -0600 Date: Fri, 25 Apr 1997 08:20:07 -0600 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199704251420.IAA15569@fast.cs.utah.edu> To: freebsd-smp@FreeBSD.org Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk =============================================================================== MPTable, version 2.0.4 looking for EBDA pointer @ 0x040e, found, searching EBDA @ 0x0009fc00 searching CMOS 'top of mem' @ 0x0009e800 (634K) searching default 'top of mem' @ 0x0009fc00 (639K) searching BIOS @ 0x000f0000 MP FPS found in BIOS @ physical addr: 0x000fb100 ------------------------------------------------------------------------------- MP Floating Pointer Structure: location: BIOS physical address: 0x000fb100 signature: '_MP_' length: 16 bytes version: 1.1 checksum: 0x17 mode: Virtual Wire ------------------------------------------------------------------------------- MP Config Table Header: physical address: 0x000f5d20 signature: 'PCMP' base table length: 308 version: 1.1 checksum: 0xa7 OEM ID: 'INTEL ' Product ID: '440FX ' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 30 local APIC address: 0xfee00000 extended table length: 0 extended table checksum: 0 ------------------------------------------------------------------------------- MP Config Base Table Entries: -- Processors: APIC ID Version State Family Model Step Flags 1 0x11 BSP, usable 6 1 6 0xfbff 0 0x11 AP, usable 6 1 6 0xfbff -- Bus: Bus ID Type 0 PCI 1 PCI 2 PCI 3 PCI 4 ISA -- I/O APICs: APIC ID Version State Address 2 0x11 usable 0xfec00000 -- I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 4 0 2 0 INT conforms conforms 4 1 2 1 INT conforms conforms 4 0 2 2 INT conforms conforms 4 3 2 3 INT conforms conforms 4 4 2 4 INT conforms conforms 4 5 2 5 INT conforms conforms 4 6 2 6 INT conforms conforms 4 7 2 7 INT active-hi edge 4 8 2 8 INT conforms conforms 4 9 2 9 INT conforms conforms 4 10 2 10 INT conforms conforms 4 11 2 11 INT conforms conforms 4 12 2 12 INT conforms conforms 4 13 2 13 INT conforms conforms 4 14 2 14 INT conforms conforms 4 15 2 15 INT active-lo level 0 12:A 2 18 INT active-lo level 3 7:A 2 19 INT active-lo level 0 11:A 2 19 SMI conforms conforms 4 0 2 23 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 0 0:A 255 0 NMI conforms conforms 0 0:A 255 1 ------------------------------------------------------------------------------- # SMP kernel config file options: options SMP # Symmetric MultiProcessor Kernel #options APIC_IO # Symmetric (APIC) I/O options NCPU=2 # number of CPUs options NBUS=5 # number of busses options NAPIC=1 # number of IO APICs options NINTR=20 # number of INTs ===============================================================================  From owner-freebsd-smp Fri Apr 25 07:20:22 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id HAA18097 for smp-outgoing; Fri, 25 Apr 1997 07:20:22 -0700 (PDT) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id HAA18088 for ; Fri, 25 Apr 1997 07:20:19 -0700 (PDT) Received: from fast.cs.utah.edu by cs.utah.edu (8.8.4/utah-2.21-cs) id IAA17153; Fri, 25 Apr 1997 08:20:17 -0600 (MDT) Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id IAA15585; Fri, 25 Apr 1997 08:20:16 -0600 Date: Fri, 25 Apr 1997 08:20:16 -0600 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199704251420.IAA15585@fast.cs.utah.edu> To: freebsd-smp@FreeBSD.org Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk =============================================================================== MPTable, version 2.0.4 looking for EBDA pointer @ 0x040e, found, searching EBDA @ 0x0009fc00 searching CMOS 'top of mem' @ 0x0009e800 (634K) searching default 'top of mem' @ 0x0009fc00 (639K) searching BIOS @ 0x000f0000 MP FPS found in BIOS @ physical addr: 0x000fb100 ------------------------------------------------------------------------------- MP Floating Pointer Structure: location: BIOS physical address: 0x000fb100 signature: '_MP_' length: 16 bytes version: 1.1 checksum: 0xe7 mode: Virtual Wire ------------------------------------------------------------------------------- MP Config Table Header: physical address: 0x000f5d50 signature: 'PCMP' base table length: 264 version: 1.1 checksum: 0xe6 OEM ID: 'INTEL ' Product ID: '440FX ' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 26 local APIC address: 0xfee00000 extended table length: 0 extended table checksum: 0 ------------------------------------------------------------------------------- MP Config Base Table Entries: -- Processors: APIC ID Version State Family Model Step Flags 1 0x11 BSP, usable 6 1 6 0xfbff -- Bus: Bus ID Type 0 PCI 1 ISA -- I/O APICs: APIC ID Version State Address 2 0x11 usable 0xfec00000 -- I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 1 0 2 0 INT conforms conforms 1 1 2 1 INT conforms conforms 1 0 2 2 INT conforms conforms 1 3 2 3 INT conforms conforms 1 4 2 4 INT conforms conforms 1 5 2 5 INT conforms conforms 1 6 2 6 INT conforms conforms 1 7 2 7 INT active-hi edge 1 8 2 8 INT conforms conforms 1 9 2 9 INT conforms conforms 1 10 2 10 INT conforms conforms 1 11 2 11 INT conforms conforms 1 12 2 12 INT conforms conforms 1 13 2 13 INT conforms conforms 1 14 2 14 INT conforms conforms 1 15 2 15 INT active-lo level 0 14:A 2 16 INT active-lo level 0 10:A 2 16 INT active-lo level 0 11:A 2 19 SMI conforms conforms 1 0 2 23 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 0 0:A 255 0 NMI conforms conforms 0 0:A 255 1 ------------------------------------------------------------------------------- # SMP kernel config file options: options SMP # Symmetric MultiProcessor Kernel #options APIC_IO # Symmetric (APIC) I/O options NCPU=1 # number of CPUs options NBUS=2 # number of busses options NAPIC=1 # number of IO APICs options NINTR=20 # number of INTs =============================================================================== From owner-freebsd-smp Fri Apr 25 07:20:20 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id HAA18092 for smp-outgoing; Fri, 25 Apr 1997 07:20:20 -0700 (PDT) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id HAA18082 for ; Fri, 25 Apr 1997 07:20:17 -0700 (PDT) Received: from fast.cs.utah.edu by cs.utah.edu (8.8.4/utah-2.21-cs) id IAA17148; Fri, 25 Apr 1997 08:20:13 -0600 (MDT) Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id IAA15577; Fri, 25 Apr 1997 08:20:13 -0600 Date: Fri, 25 Apr 1997 08:20:13 -0600 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199704251420.IAA15577@fast.cs.utah.edu> To: freebsd-smp@FreeBSD.org Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk =============================================================================== MPTable, version 2.0.4 looking for EBDA pointer @ 0x040e, found, searching EBDA @ 0x0009fc00 searching CMOS 'top of mem' @ 0x0009e800 (634K) searching default 'top of mem' @ 0x0009fc00 (639K) searching BIOS @ 0x000f0000 MP FPS found in BIOS @ physical addr: 0x000fb100 ------------------------------------------------------------------------------- MP Floating Pointer Structure: location: BIOS physical address: 0x000fb100 signature: '_MP_' length: 16 bytes version: 1.1 checksum: 0xe7 mode: Virtual Wire ------------------------------------------------------------------------------- MP Config Table Header: physical address: 0x000f5d50 signature: 'PCMP' base table length: 264 version: 1.1 checksum: 0xdf OEM ID: 'INTEL ' Product ID: '440FX ' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 26 local APIC address: 0xfee00000 extended table length: 0 extended table checksum: 0 ------------------------------------------------------------------------------- MP Config Base Table Entries: -- Processors: APIC ID Version State Family Model Step Flags 1 0x11 BSP, usable 6 1 6 0xfbff -- Bus: Bus ID Type 0 PCI 1 ISA -- I/O APICs: APIC ID Version State Address 2 0x11 usable 0xfec00000 -- I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 1 0 2 0 INT conforms conforms 1 1 2 1 INT conforms conforms 1 0 2 2 INT conforms conforms 1 3 2 3 INT conforms conforms 1 4 2 4 INT conforms conforms 1 5 2 5 INT conforms conforms 1 6 2 6 INT conforms conforms 1 7 2 7 INT active-hi edge 1 8 2 8 INT conforms conforms 1 9 2 9 INT conforms conforms 1 10 2 10 INT conforms conforms 1 11 2 11 INT conforms conforms 1 12 2 12 INT conforms conforms 1 13 2 13 INT conforms conforms 1 14 2 14 INT conforms conforms 1 15 2 15 INT active-lo level 0 13:A 2 17 INT active-lo level 0 12:A 2 18 INT active-lo level 0 11:A 2 19 SMI conforms conforms 1 0 2 23 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 0 0:A 255 0 NMI conforms conforms 0 0:A 255 1 ------------------------------------------------------------------------------- # SMP kernel config file options: options SMP # Symmetric MultiProcessor Kernel #options APIC_IO # Symmetric (APIC) I/O options NCPU=1 # number of CPUs options NBUS=2 # number of busses options NAPIC=1 # number of IO APICs options NINTR=20 # number of INTs ===============================================================================  From owner-freebsd-smp Fri Apr 25 08:21:15 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id IAA22092 for smp-outgoing; Fri, 25 Apr 1997 08:21:15 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id IAA22077 for ; Fri, 25 Apr 1997 08:21:11 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id JAA07978; Fri, 25 Apr 1997 09:18:41 -0600 (MDT) Message-Id: <199704251518.JAA07978@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: NISHIO Shuichi cc: freebsd-smp@freebsd.org Subject: Re: Tyan ATX1668 problem -- success In-reply-to: Your message of "Fri, 25 Apr 1997 21:46:45 +0900." <19970425214645B.nishio@elysium.kecl.ntt.co.jp> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Fri, 25 Apr 1997 09:18:41 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > So, last Sunday, I cvsup'ed the SMP code and the entire current, did a > 'make World', and tried the SMP kernel with this fix and APIC_IO. > ... > However, there still was some problems. > > 1. /bin/ps -a sometimes freezes > ... > 2. panic on heavy traffic > ... > I also experienced crashes on dumping filesystems to DAT, but this > might be due to the problem with the AIC driver. > > Last evening, I tried a kernel with XFAST_IPI32 defined (and also the > latest current), and these problems seems to go away: > I tried > making kernel with -j8 > 'put'ting a 180MB file from FreeBSD to SGI O2 on 100BaseTX > 'get'ting a 60MB file from O2 to FreeBSD > dumping /home to DAT > > simultaneously, but it went through, without going panic. > > Additionaly, I don't know why, but the network transfer rate seems to > have raised to 55Mb/s after defining XFAST_IPI32, from 45Mb/s with the > previous kernel. > > So, in summary, the recent fix including XFAST_IPI32 seems to be > working very fine here. This is indeed good news! I would like to thank everyone who helped with this one, especially Cyrus, who spent many hours identifying the exact cause of the problem. I would also like anyone not running a 'critical' system to enable XFAST_IPI32 in smptest.h so I can hear that "it doesn't break anything here" a few times b4 making it mainline. As to the improved performance, this is because we are taking a big hit on all those TLB invalidations (has to be done), and the old method was competing for the kernel lock each time. The new method goes right for it without the lock. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Fri Apr 25 08:50:05 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id IAA23581 for smp-outgoing; Fri, 25 Apr 1997 08:50:05 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id IAA23550 for ; Fri, 25 Apr 1997 08:49:57 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id XAA25776; Fri, 25 Apr 1997 23:47:07 +0800 (WST) Message-Id: <199704251547.XAA25776@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Steve Passe cc: NISHIO Shuichi , freebsd-smp@freebsd.org Subject: Re: Tyan ATX1668 problem -- success In-reply-to: Your message of "Fri, 25 Apr 1997 09:18:41 CST." <199704251518.JAA07978@Ilsa.StevesCafe.com> Date: Fri, 25 Apr 1997 23:47:06 +0800 From: Peter Wemm Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Steve Passe wrote: > As to the improved performance, this is because we are taking a big hit on > all those TLB invalidations (has to be done), and the old method was competin g > for the kernel lock each time. The new method goes right for it without the > lock. No.. The old method wasn't fetching the kernel lock either.. I suspect that the speedup was because the old method was using the generic IPI_INTR() handler which was set up for calling C code, while the new one is a cut down version that doesn't have as much overhead. (Incidently, the new one doesn't show up on the vmstat interrupt counts) Cheers, -Peter From owner-freebsd-smp Fri Apr 25 09:09:11 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id JAA24331 for smp-outgoing; Fri, 25 Apr 1997 09:09:11 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA24326 for ; Fri, 25 Apr 1997 09:09:10 -0700 (PDT) From: Steve Passe Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id JAA26103 for freebsd-smp; Fri, 25 Apr 1997 09:08:42 -0700 (PDT) Date: Fri, 25 Apr 1997 09:08:42 -0700 (PDT) Message-Id: <199704251608.JAA26103@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/i386 mpapic.c Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/25 09:08:42 Modified: i386/i386 mpapic.c Log: fixed damage to define caused by style cleanup. Revision Changes Path 1.31 +4 -4 sys/i386/i386/mpapic.c From owner-freebsd-smp Fri Apr 25 09:15:32 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id JAA24549 for smp-outgoing; Fri, 25 Apr 1997 09:15:32 -0700 (PDT) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA24542 for ; Fri, 25 Apr 1997 09:15:29 -0700 (PDT) Received: from fast.cs.utah.edu by cs.utah.edu (8.8.4/utah-2.21-cs) id KAA19519; Fri, 25 Apr 1997 10:14:07 -0600 (MDT) Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id KAA25683; Fri, 25 Apr 1997 10:13:44 -0600 Date: Fri, 25 Apr 1997 10:13:44 -0600 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199704251613.KAA25683@fast.cs.utah.edu> To: peter@spinner.dialix.com, smp@csn.net Subject: Re: Tyan ATX1668 problem -- success Cc: freebsd-smp@freebsd.org, nishio@caleche.kecl.ntt.co.jp Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >(Incidently, >the new one doesn't show up on the vmstat interrupt counts) systat won't list 6000+ interrupts per second anymore? bummer. Kevin From owner-freebsd-smp Fri Apr 25 09:51:14 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id JAA26585 for smp-outgoing; Fri, 25 Apr 1997 09:51:14 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA26568 for ; Fri, 25 Apr 1997 09:51:07 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id KAA08348; Fri, 25 Apr 1997 10:50:50 -0600 (MDT) Message-Id: <199704251650.KAA08348@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Greg Shaffer cc: Chuck Robey , "Jordan K. Hubbard" , freebsd-smp@freebsd.org Subject: Re: SMP CTM Deltas In-reply-to: Your message of "Fri, 25 Apr 1997 09:10:32 PDT." <199704251610.JAA24657@intrepid.leaky.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Fri, 25 Apr 1997 10:50:50 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > I have been following the recent events smp mailing list and decided that > it is time to update my SMP machine to a post Lite2 baseline but I am having > trouble finding the CTM deltas. I used to get them off of freefall/spatter > but I can't get into either of them. Freefall won't let anonymous users in > and spatter does not exist. Do you know where I can get the CTM deltas for > the SMP kernel? Chuck reported this problem several days ago, who can fix it? -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Fri Apr 25 10:14:28 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA27809 for smp-outgoing; Fri, 25 Apr 1997 10:14:28 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA27800; Fri, 25 Apr 1997 10:14:19 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id BAA26769; Sat, 26 Apr 1997 01:13:02 +0800 (WST) Message-Id: <199704251713.BAA26769@spinner.DIALix.COM> X-Mailer: exmh version 2.0gamma 1/27/96 To: Steve Passe cc: Greg Shaffer , Chuck Robey , "Jordan K. Hubbard" , freebsd-smp@freebsd.org, phk@freebsd.org Subject: Re: SMP CTM Deltas In-reply-to: Your message of "Fri, 25 Apr 1997 10:50:50 CST." <199704251650.KAA08348@Ilsa.StevesCafe.com> Date: Sat, 26 Apr 1997 01:13:02 +0800 From: Peter Wemm Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Steve Passe wrote: > Hi, > > > I have been following the recent events smp mailing list and decided that > > it is time to update my SMP machine to a post Lite2 baseline but I am havin g > > trouble finding the CTM deltas. I used to get them off of freefall/spatter > > but I can't get into either of them. Freefall won't let anonymous users in > > and spatter does not exist. Do you know where I can get the CTM deltas for > > the SMP kernel? > > Chuck reported this problem several days ago, who can fix it? I really don't know either.. The last I had anything to do with ctm was when it was all being generated on freefall. Since then, pkh(?) moved it (I think) to spatter, and that's all I know. If spatter doesn't exist anymore, I don't have any idea what's happening with it. > -- > Steve Passe | powered by > smp@csn.net | Symmetric MultiProcessor FreeBSD > Cheers, -Peter From owner-freebsd-smp Fri Apr 25 10:33:41 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA29090 for smp-outgoing; Fri, 25 Apr 1997 10:33:41 -0700 (PDT) Received: from critter.dk.tfs.com ([140.145.230.252]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA29038; Fri, 25 Apr 1997 10:33:22 -0700 (PDT) Received: from critter (localhost [127.0.0.1]) by critter.dk.tfs.com (8.8.5/8.8.5) with ESMTP id TAA00391; Fri, 25 Apr 1997 19:31:37 +0200 (CEST) To: Steve Passe cc: Greg Shaffer , Chuck Robey , "Jordan K. Hubbard" , freebsd-smp@freebsd.org From: Poul-Henning Kamp Subject: Re: SMP CTM Deltas In-reply-to: Your message of "Fri, 25 Apr 1997 10:50:50 MDT." <199704251650.KAA08348@Ilsa.StevesCafe.com> Date: Fri, 25 Apr 1997 19:31:37 +0200 Message-ID: <389.861989497@critter> Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk In message <199704251650.KAA08348@Ilsa.StevesCafe.com>, Steve Passe writes: >Hi, > >> I have been following the recent events smp mailing list and decided that >> it is time to update my SMP machine to a post Lite2 baseline but I am having >> trouble finding the CTM deltas. I used to get them off of freefall/spatter >> but I can't get into either of them. Freefall won't let anonymous users in >> and spatter does not exist. Do you know where I can get the CTM deltas for >> the SMP kernel? > >Chuck reported this problem several days ago, who can fix it? Unfortunately most of my freebsd time is in offline mode right now, so I do not even know what the stat of it is. Rich didn't want to take on the cvs-smp and cvs-gnats and after the recent shuffles on freefall I'm totally lost. Sorry... -- Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. whois: [PHK] | phk@tfs.com TRW Financial Systems, Inc. Power and ignorance is a disgusting cocktail. From owner-freebsd-smp Fri Apr 25 10:37:52 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA29334 for smp-outgoing; Fri, 25 Apr 1997 10:37:52 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA29325 for ; Fri, 25 Apr 1997 10:37:48 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id LAA08547; Fri, 25 Apr 1997 11:36:32 -0600 (MDT) Message-Id: <199704251736.LAA08547@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Peter Wemm cc: NISHIO Shuichi , freebsd-smp@freebsd.org Subject: Re: Tyan ATX1668 problem -- success In-reply-to: Your message of "Fri, 25 Apr 1997 23:47:06 +0800." <199704251547.XAA25776@spinner.DIALix.COM> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Fri, 25 Apr 1997 11:36:32 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > Steve Passe wrote: > > As to the improved performance, this is because we are taking a big hit on > > all those TLB invalidations (has to be done), and the old method was competin > g > > for the kernel lock each time. The new method goes right for it without the > > lock. > > No.. The old method wasn't fetching the kernel lock either.. I suspect > that the speedup was because the old method was using the generic > IPI_INTR() handler which was set up for calling C code, while the new one > is a cut down version that doesn't have as much overhead. (Incidently, > the new one doesn't show up on the vmstat interrupt counts) your correct, no lock contention. after looking it over for awhile I'm convinced we want to keep the action in the mainline code, ie NOT call the C routine. Still not sure whether we want to put statistics back in. I'm afraid it will take more work than is justified at this point. The world believes that there are ONLY 32 INT sources, starting @ ICU_LEN, and densely packed thru the folowing 32 positions. I would vote for delaying the restoration of statistics till the re-write of the INT stuff. --- Now that it works I can remove the ipi_hits counter, am I correct in believing that the load of %ds with the kernel selector will still be necessary to address the apic[] for the EOI? -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Fri Apr 25 11:23:50 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA02582 for smp-outgoing; Fri, 25 Apr 1997 11:23:50 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA02577 for ; Fri, 25 Apr 1997 11:23:49 -0700 (PDT) From: Peter Wemm Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id LAA26416 for freebsd-smp; Fri, 25 Apr 1997 11:23:20 -0700 (PDT) Date: Fri, 25 Apr 1997 11:23:20 -0700 (PDT) Message-Id: <199704251823.LAA26416@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/i386 pmap.c Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk peter 97/04/25 11:23:20 Modified: i386/i386 pmap.c Log: Zap two extra calls to smp_invltlb.. It was called via invlpg() above. Revision Changes Path 1.39 +1 -8 sys/i386/i386/pmap.c From owner-freebsd-smp Fri Apr 25 11:37:42 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA03588 for smp-outgoing; Fri, 25 Apr 1997 11:37:42 -0700 (PDT) Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.19]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA03583 for ; Fri, 25 Apr 1997 11:37:39 -0700 (PDT) Received: (from bde@localhost) by godzilla.zeta.org.au (8.8.5/8.6.9) id EAA09113; Sat, 26 Apr 1997 04:35:09 +1000 Date: Sat, 26 Apr 1997 04:35:09 +1000 From: Bruce Evans Message-Id: <199704251835.EAA09113@godzilla.zeta.org.au> To: peter@spinner.dialix.com, smp@csn.net Subject: Re: Tyan ATX1668 problem -- success Cc: freebsd-smp@freebsd.org, nishio@caleche.kecl.ntt.co.jp Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >Now that it works I can remove the ipi_hits counter, am I correct in believing >that the load of %ds with the kernel selector will still be necessary to >address the apic[] for the EOI? No, you can access everything using %ss in assembler - you pay for loading %ss for traps to inner privilege whether you want to or not. However, prefixes may cost a cycle or two, so it is better to load %ds if you want to do more than a few memory accesses. Bruce From owner-freebsd-smp Fri Apr 25 11:54:38 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA04327 for smp-outgoing; Fri, 25 Apr 1997 11:54:38 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA04322 for ; Fri, 25 Apr 1997 11:54:35 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id MAA08905; Fri, 25 Apr 1997 12:54:09 -0600 (MDT) Message-Id: <199704251854.MAA08905@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Bruce Evans cc: peter@spinner.dialix.com, freebsd-smp@freebsd.org, nishio@caleche.kecl.ntt.co.jp Subject: Re: Tyan ATX1668 problem -- success In-reply-to: Your message of "Sat, 26 Apr 1997 04:35:09 +1000." <199704251835.EAA09113@godzilla.zeta.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Fri, 25 Apr 1997 12:54:09 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Bruce, > >Now that it works I can remove the ipi_hits counter, am I correct in believing > >that the load of %ds with the kernel selector will still be necessary to > >address the apic[] for the EOI? > > No, you can access everything using %ss in assembler - you pay for loading > %ss for traps to inner privilege whether you want to or not. However, > prefixes may cost a cycle or two, so it is better to load %ds if you > want to do more than a few memory accesses. excuse my asm ignorance, what would this convert to with your suggested technique? _Xfastipi32: pushl %eax movl %cr3, %eax movl %eax, %cr3 pushl %ds movl $KDSEL,%eax movl %ax,%ds movl _apic_base, %eax movl $0, APIC_EOI(%eax) popl %ds popl %eax iret _apic_base is actually a set of memory-mapped registers in the local APIC of the CPU, NOT general memory. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Fri Apr 25 12:31:10 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA06534 for smp-outgoing; Fri, 25 Apr 1997 12:31:10 -0700 (PDT) Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.19]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA06524 for ; Fri, 25 Apr 1997 12:31:04 -0700 (PDT) Received: (from bde@localhost) by godzilla.zeta.org.au (8.8.5/8.6.9) id FAA10469; Sat, 26 Apr 1997 05:29:39 +1000 Date: Sat, 26 Apr 1997 05:29:39 +1000 From: Bruce Evans Message-Id: <199704251929.FAA10469@godzilla.zeta.org.au> To: bde@zeta.org.au, smp@csn.net Subject: Re: Tyan ATX1668 problem -- success Cc: freebsd-smp@freebsd.org, nishio@caleche.kecl.ntt.co.jp, peter@spinner.dialix.com Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >> No, you can access everything using %ss in assembler - you pay for loading >> %ss for traps to inner privilege whether you want to or not. However, >> prefixes may cost a cycle or two, so it is better to load %ds if you >> want to do more than a few memory accesses. > >excuse my asm ignorance, what would this convert to with your suggested >technique? Deleted the commented out lines and add the lines marked `!'. _Xfastipi32: pushl %eax movl %cr3, %eax movl %eax, %cr3 # pushl %ds # movl $KDSEL,%eax # movl %ax,%ds ! ss movl _apic_base, %eax ! ss movl $0, APIC_EOI(%eax) # popl %ds popl %eax iret >_apic_base is actually a set of memory-mapped registers in the local >APIC of the CPU, NOT general memory. This shouldn't affect the addressing. Bruce From owner-freebsd-smp Fri Apr 25 20:58:53 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id UAA02868 for smp-outgoing; Fri, 25 Apr 1997 20:58:53 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id UAA02863 for ; Fri, 25 Apr 1997 20:58:50 -0700 (PDT) From: Peter Wemm Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id UAA02006 for freebsd-smp; Fri, 25 Apr 1997 20:58:49 -0700 (PDT) Date: Fri, 25 Apr 1997 20:58:49 -0700 (PDT) Message-Id: <199704260358.UAA02006@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/isa icu.h Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk peter 97/04/25 20:58:49 Modified: i386/isa icu.h Log: Indent added code to be consistant with the rest Revision Changes Path 1.17 +8 -8 sys/i386/isa/icu.h From owner-freebsd-smp Fri Apr 25 21:00:50 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id VAA02989 for smp-outgoing; Fri, 25 Apr 1997 21:00:50 -0700 (PDT) Received: from weenix.guru.org (kmitch@phantasma.bevc.blacksburg.va.us [198.82.200.65]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id VAA02983 for ; Fri, 25 Apr 1997 21:00:46 -0700 (PDT) Received: (from kmitch@localhost) by weenix.guru.org (8.8.5/8.8.5) id AAA01060; Sat, 26 Apr 1997 00:00:41 -0400 (EDT) Date: Sat, 26 Apr 1997 00:00:41 -0400 (EDT) From: Keith Mitchell Message-Id: <199704260400.AAA01060@weenix.guru.org> To: smp@csn.net (Steve Passe) Cc: smp@freebsd.org Subject: Re: Freezes/Reboots with -current ahc driver X-Newsreader: TIN [UNIX 1.3 unoff BETA release 970124] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 8bit Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > Not sure if its reached the cvs mirror yet, but if you sup you should get > a new vector.s, mp_machdep.c and smptests.h. uncomment the XFAST_IPI32 > define in smptests.h and build. please let me know how this works. > --- > Keith, > did you try running with APIC_IO turned off yet? did it help? > this test should be run with APIC_IO ON... Steve, Turning off APIC_IO solved the problem. The XFAST_IPI32 also seems to fix the problem. I have only tested it once or twice with a backup but it seems like it is going to work. -- Keith Mitchell Head Administrator: acm.vt.edu Email: kmitch@weenix.guru.org PGP key available upon request http://weenix.guru.org/~kmitch Address and URL (c) 1997 Keith Mitchell - All Rights Reserved Unauthorized use or duplication prohibited From owner-freebsd-smp Fri Apr 25 21:20:19 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id VAA04141 for smp-outgoing; Fri, 25 Apr 1997 21:20:19 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id VAA04134 for ; Fri, 25 Apr 1997 21:20:16 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id WAA10589; Fri, 25 Apr 1997 22:20:11 -0600 (MDT) Message-Id: <199704260420.WAA10589@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Keith Mitchell cc: smp@freebsd.org Subject: Re: Freezes/Reboots with -current ahc driver In-reply-to: Your message of "Sat, 26 Apr 1997 00:00:41 EDT." <199704260400.AAA01060@weenix.guru.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Fri, 25 Apr 1997 22:20:11 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > > Keith, > > did you try running with APIC_IO turned off yet? did it help? > > this test should be run with APIC_IO ON... > > Steve, > > Turning off APIC_IO solved the problem. The XFAST_IPI32 also seems to fix > the problem. I have only tested it once or twice with a backup but it > seems like it is going to work. thanx, yours is the second report of success from the 3 users known to have the problem. I will make XFAST_IPI32 default in the next set of changes. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Fri Apr 25 21:42:26 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id VAA05112 for smp-outgoing; Fri, 25 Apr 1997 21:42:26 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id VAA05106 for ; Fri, 25 Apr 1997 21:42:24 -0700 (PDT) From: Peter Wemm Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id VAA10790 for freebsd-smp; Fri, 25 Apr 1997 21:42:23 -0700 (PDT) Date: Fri, 25 Apr 1997 21:42:23 -0700 (PDT) Message-Id: <199704260442.VAA10790@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/i386 identcpu.c locore.s machdep.c swtch.s sys/kern kern_fork.c sys/sys kernel.h sys/i386/isa npx.c sys/pci pci.c pcireg.h Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk peter 97/04/25 21:42:23 Modified: i386/i386 identcpu.c locore.s machdep.c swtch.s i386/isa npx.c kern kern_fork.c pci pci.c pcireg.h sys kernel.h Log: Merge in -current 970425 onto mainline. The ELF kernel stuff isn't complete for the smp case. Revision Changes Path 1.7 +9 -4 sys/i386/i386/identcpu.c 1.37 +5 -5 sys/i386/i386/locore.s 1.40 +7 -1 sys/i386/i386/machdep.c 1.38 +2 -2 sys/i386/i386/swtch.s 1.18 +13 -8 sys/i386/isa/npx.c 1.12 +1 -1 sys/kern/kern_fork.c 1.10 +19 -10 sys/pci/pci.c 1.8 +2 -1 sys/pci/pcireg.h 1.16 +20 -2 sys/sys/kernel.h From owner-freebsd-smp Fri Apr 25 22:53:48 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id WAA07524 for smp-outgoing; Fri, 25 Apr 1997 22:53:48 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id WAA07515 for ; Fri, 25 Apr 1997 22:53:42 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id XAA11003; Fri, 25 Apr 1997 23:52:39 -0600 (MDT) Message-Id: <199704260552.XAA11003@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Peter Wemm cc: freebsd-smp@FreeBSD.org Subject: Re: panic: 8254 redirect impossible.. In-reply-to: Your message of "Sat, 26 Apr 1997 13:01:09 +0800." <199704260501.NAA00297@spinner.DIALix.COM> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Fri, 25 Apr 1997 23:52:39 -0600 Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi, I recently commited a version of mp_machdep.c that introduces a bug that may cause a panic during boot with the message: 8254 redirect impossible here's a patch to remove it IF it bites you: *** mp_machdep.c~ Thu Apr 24 21:11:27 1997 --- mp_machdep.c Fri Apr 25 23:46:34 1997 *************** *** 603,609 **** --- 603,611 ---- static int nintrs; + #if defined(FIX_MP_TABLE_WORKS) static void fix_mp_table __P((void)); + #endif /* FIX_MP_TABLE_WORKS */ static void processor_entry __P((proc_entry_ptr entry, int* cpu)); static void io_apic_entry __P((io_apic_entry_ptr entry, int* apic)); *************** *** 739,752 **** --- 741,757 ---- /* record # of IO APICs found */ nintrs = intr; + #if defined(FIX_MP_TABLE_WORKS) /* post scan cleanup */ fix_mp_table(); + #endif /* FIX_MP_TABLE_WORKS */ /* report fact that its NOT a default configuration */ return 0; } + #if defined(FIX_MP_TABLE_WORKS) /* * parse an Intel MP specification table */ *************** *** 816,822 **** } } } ! /* * --- 821,827 ---- } } } ! #endif /* FIX_MP_TABLE_WORKS */ /* * *************** *** 1020,1026 **** --- 1025,1033 ---- for (intr = 0; intr < nintrs; ++intr) /* search each record */ if ((INTTYPE(intr) == 0) + #if defined(FIX_MP_TABLE_WORKS) && (SRCBUSID(intr) == pciBus) + #endif /* FIX_MP_TABLE_WORKS */ && (SRCBUSDEVICE(intr) == pciDevice) && (SRCBUSLINE(intr) == pciInt)) /* a candidate IRQ */ if (apic_int_is_bus_type( intr, PCI )) /* check bus match */ -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Fri Apr 25 22:58:05 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id WAA07609 for smp-outgoing; Fri, 25 Apr 1997 22:58:05 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id WAA07604 for ; Fri, 25 Apr 1997 22:58:03 -0700 (PDT) From: Peter Wemm Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id WAA12329 for freebsd-smp; Fri, 25 Apr 1997 22:58:02 -0700 (PDT) Date: Fri, 25 Apr 1997 22:58:02 -0700 (PDT) Message-Id: <199704260558.WAA12329@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/i386 mp_machdep.c mpapic.c Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk peter 97/04/25 22:58:02 Modified: i386/i386 mp_machdep.c mpapic.c Log: KNF police Revision Changes Path 1.43 +1036 -1093sys/i386/i386/mp_machdep.c 1.32 +462 -485 sys/i386/i386/mpapic.c From owner-freebsd-smp Fri Apr 25 23:17:36 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id XAA08058 for smp-outgoing; Fri, 25 Apr 1997 23:17:36 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id XAA08053 for ; Fri, 25 Apr 1997 23:17:35 -0700 (PDT) From: Peter Wemm Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id XAA12383 for freebsd-smp; Fri, 25 Apr 1997 23:17:33 -0700 (PDT) Date: Fri, 25 Apr 1997 23:17:33 -0700 (PDT) Message-Id: <199704260617.XAA12383@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/i386 mp_machdep.c Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk peter 97/04/25 23:17:33 Modified: i386/i386 mp_machdep.c Log: #if out the fix_mp_table as per Steve's suggestion Revision Changes Path 1.44 +9 -1 sys/i386/i386/mp_machdep.c From owner-freebsd-smp Fri Apr 25 23:18:41 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id XAA08072 for smp-outgoing; Fri, 25 Apr 1997 23:18:41 -0700 (PDT) Received: from nyx.pr.mcs.net (nyx.pr.mcs.net [204.95.55.81]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id XAA08067 for ; Fri, 25 Apr 1997 23:18:39 -0700 (PDT) Received: from nyx.pr.mcs.net (localhost [127.0.0.1]) by nyx.pr.mcs.net (8.8.5/8.8.5) with ESMTP id BAA00411 for ; Sat, 26 Apr 1997 01:18:13 -0500 (CDT) Message-Id: <199704260618.BAA00411@nyx.pr.mcs.net> X-Mailer: exmh version 1.6.9 8/22/96 To: smp@freebsd.org Subject: Gigabyte 586DX problem... Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 26 Apr 1997 01:18:12 -0500 From: Chris Csanady Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk When I try to boot a current kernel with or without XFAST_IPI32, I get the following.. APIC missing RTC connection Then it panics. Any clue whats wrong here? Or am I the only one.. --Chris Csanady From owner-freebsd-smp Fri Apr 25 23:23:11 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id XAA08228 for smp-outgoing; Fri, 25 Apr 1997 23:23:11 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id XAA08223 for ; Fri, 25 Apr 1997 23:23:09 -0700 (PDT) From: Peter Wemm Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id XAA12425 for freebsd-smp; Fri, 25 Apr 1997 23:23:08 -0700 (PDT) Date: Fri, 25 Apr 1997 23:23:08 -0700 (PDT) Message-Id: <199704260623.XAA12425@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/pci pci.c pcibus.h Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk peter 97/04/25 23:23:07 Modified: pci pci.c pcibus.h Log: Minor attack from the style police Revision Changes Path 1.11 +3 -3 sys/pci/pci.c 1.8 +1 -1 sys/pci/pcibus.h From owner-freebsd-smp Fri Apr 25 23:37:39 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id XAA08801 for smp-outgoing; Fri, 25 Apr 1997 23:37:39 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id XAA08796 for ; Fri, 25 Apr 1997 23:37:37 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id AAA11265; Sat, 26 Apr 1997 00:37:30 -0600 (MDT) Message-Id: <199704260637.AAA11265@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Chris Csanady cc: smp@freebsd.org Subject: Re: Gigabyte 586DX problem... In-reply-to: Your message of "Sat, 26 Apr 1997 01:18:12 CDT." <199704260618.BAA00411@nyx.pr.mcs.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 26 Apr 1997 00:37:30 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > When I try to boot a current kernel with or without XFAST_IPI32, > I get the following.. > > APIC missing RTC connection > > Then it panics. Any clue whats wrong here? Or am I the only one.. my fault, sent mail about 15 minutes ago with the patch. in that mail I said the error would say: 254 redirect impossible you hit the same bug, just that yours fails in an ISA probe, the other an EISA probe... sorry..... -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Fri Apr 25 23:41:47 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id XAA08887 for smp-outgoing; Fri, 25 Apr 1997 23:41:47 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id XAA08882 for ; Fri, 25 Apr 1997 23:41:42 -0700 (PDT) From: Peter Wemm Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id XAA12624 for freebsd-smp; Fri, 25 Apr 1997 23:41:41 -0700 (PDT) Date: Fri, 25 Apr 1997 23:41:41 -0700 (PDT) Message-Id: <199704260641.XAA12624@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/include apic.h ipl.h mpapic.h smp.h spl.h sys/i386/isa icu.h icu.s if_ze.c isa.c isa_device.h npx.c sio.c vector.s sys/i386/i386 microtime.s mplock.s pmap.c swtch.s Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk peter 97/04/25 23:41:40 Modified: i386/i386 microtime.s mplock.s pmap.c swtch.s i386/include apic.h ipl.h mpapic.h smp.h spl.h i386/isa icu.h icu.s if_ze.c isa.c isa_device.h npx.c sio.c vector.s Log: A visit from the KNF whitespace SWAT police.. Revision Changes Path 1.19 +2 -2 sys/i386/i386/microtime.s 1.16 +3 -3 sys/i386/i386/mplock.s 1.40 +1 -1 sys/i386/i386/pmap.c 1.39 +1 -1 sys/i386/i386/swtch.s 1.17 +2 -2 sys/i386/include/apic.h 1.9 +2 -2 sys/i386/include/ipl.h 1.13 +2 -2 sys/i386/include/mpapic.h 1.28 +5 -5 sys/i386/include/smp.h 1.11 +1 -1 sys/i386/include/spl.h 1.18 +1 -1 sys/i386/isa/icu.h 1.24 +8 -8 sys/i386/isa/icu.s 1.12 +3 -3 sys/i386/isa/if_ze.c 1.20 +10 -10 sys/i386/isa/isa.c 1.10 +4 -4 sys/i386/isa/isa_device.h 1.19 +10 -10 sys/i386/isa/npx.c 1.18 +1 -1 sys/i386/isa/sio.c 1.41 +17 -17 sys/i386/isa/vector.s From owner-freebsd-smp Sat Apr 26 00:01:04 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id AAA09411 for smp-outgoing; Sat, 26 Apr 1997 00:01:04 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id AAA09403 for ; Sat, 26 Apr 1997 00:01:00 -0700 (PDT) From: Steve Passe Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id AAA12739 for freebsd-smp; Sat, 26 Apr 1997 00:00:59 -0700 (PDT) Date: Sat, 26 Apr 1997 00:00:59 -0700 (PDT) Message-Id: <199704260700.AAA12739@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/i386 mp_machdep.c Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/26 00:00:58 Modified: i386/i386 mp_machdep.c Log: fixed my fix_mp_table() fubar. if this still breaks your kernel with a panic at boot, undefine: FIX_MP_TABLE_WORKS Revision Changes Path 1.45 +12 -10 sys/i386/i386/mp_machdep.c From owner-freebsd-smp Sat Apr 26 00:16:05 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id AAA09843 for smp-outgoing; Sat, 26 Apr 1997 00:16:05 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id AAA09837 for ; Sat, 26 Apr 1997 00:16:03 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id BAA11489; Sat, 26 Apr 1997 01:15:17 -0600 (MDT) Message-Id: <199704260715.BAA11489@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Chris Csanady cc: smp@freebsd.org Subject: Re: Gigabyte 586DX problem... In-reply-to: Your message of "Sat, 26 Apr 1997 01:18:12 CDT." <199704260618.BAA00411@nyx.pr.mcs.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 26 Apr 1997 01:15:17 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, I've committed a fix for this, but till I get feedback that I got it right I've left the defines around the code. If it still panics undefine: FIX_MP_TABLE_WORKS in sys/i386/i386/mp_machdep.c, near the top. if it works now let me know... -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Sat Apr 26 00:21:41 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id AAA09990 for smp-outgoing; Sat, 26 Apr 1997 00:21:41 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id AAA09977; Sat, 26 Apr 1997 00:21:27 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id PAA00318; Sat, 26 Apr 1997 15:21:21 +0800 (WST) Message-Id: <199704260721.PAA00318@spinner.DIALix.COM> To: Steve Passe cc: freebsd-smp@FreeBSD.org Subject: Re: cvs commit: sys/i386/i386 mp_machdep.c In-reply-to: Your message of "Sat, 26 Apr 1997 00:00:59 MST." <199704260700.AAA12739@freefall.freebsd.org> Date: Sat, 26 Apr 1997 15:21:21 +0800 From: Peter Wemm Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Steve Passe wrote: > fsmp 97/04/26 00:00:58 > > Modified: i386/i386 mp_machdep.c > Log: > fixed my fix_mp_table() fubar. > > if this still breaks your kernel with a panic at boot, undefine: > FIX_MP_TABLE_WORKS It.. umm.. still doesn't work for me... :-( Apr 26 15:16:47 spinner /kernel: Device configuration finished. Apr 26 15:16:47 spinner /kernel: Considering FFS root f/s. Apr 26 15:16:47 spinner /kernel: configure() finished. Apr 26 15:16:47 spinner /kernel: Linux-ELF exec handler installed Apr 26 15:16:47 spinner /kernel: APIC missing 8254 connection Apr 26 15:16:47 spinner /kernel: 8254 redirect impossible! Apr 26 15:16:47 spinner /kernel: panic (cpu#0): Cheers, -Peter From owner-freebsd-smp Sat Apr 26 00:24:25 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id AAA10092 for smp-outgoing; Sat, 26 Apr 1997 00:24:25 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id AAA10086 for ; Sat, 26 Apr 1997 00:24:23 -0700 (PDT) From: Steve Passe Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id AAA12984 for freebsd-smp; Sat, 26 Apr 1997 00:24:21 -0700 (PDT) Date: Sat, 26 Apr 1997 00:24:21 -0700 (PDT) Message-Id: <199704260724.AAA12984@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/include smptests.h Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/26 00:24:21 Modified: i386/include smptests.h Log: made the XFAST_IPI32 code default. Revision Changes Path 1.13 +3 -3 sys/i386/include/smptests.h From owner-freebsd-smp Sat Apr 26 00:28:07 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id AAA10171 for smp-outgoing; Sat, 26 Apr 1997 00:28:07 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id AAA10166 for ; Sat, 26 Apr 1997 00:28:05 -0700 (PDT) From: Steve Passe Received: (from fsmp@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id AAA13019 for freebsd-smp; Sat, 26 Apr 1997 00:28:03 -0700 (PDT) Date: Sat, 26 Apr 1997 00:28:03 -0700 (PDT) Message-Id: <199704260728.AAA13019@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/i386 mp_machdep.c Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk fsmp 97/04/26 00:28:03 Modified: i386/i386 mp_machdep.c Log: poo, undefine FIX_MP_TABLE_WORKS till I can get it right. Revision Changes Path 1.46 +2 -2 sys/i386/i386/mp_machdep.c From owner-freebsd-smp Sat Apr 26 00:30:05 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id AAA10241 for smp-outgoing; Sat, 26 Apr 1997 00:30:05 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id AAA10236 for ; Sat, 26 Apr 1997 00:30:02 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id BAA11570; Sat, 26 Apr 1997 01:29:45 -0600 (MDT) Message-Id: <199704260729.BAA11570@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Peter Wemm cc: freebsd-smp@FreeBSD.org Subject: Re: cvs commit: sys/i386/i386 mp_machdep.c In-reply-to: Your message of "Sat, 26 Apr 1997 15:21:21 +0800." <199704260721.PAA00318@spinner.DIALix.COM> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 26 Apr 1997 01:29:45 -0600 Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > It.. umm.. still doesn't work for me... :-( ok, its removed for now... -- Steve Passe | powered by smp@csn.net | FreeBSD From owner-freebsd-smp Sat Apr 26 00:44:43 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id AAA10775 for smp-outgoing; Sat, 26 Apr 1997 00:44:43 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id AAA10770 for ; Sat, 26 Apr 1997 00:44:37 -0700 (PDT) From: Peter Wemm Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id AAA13064 for freebsd-smp; Sat, 26 Apr 1997 00:44:35 -0700 (PDT) Date: Sat, 26 Apr 1997 00:44:35 -0700 (PDT) Message-Id: <199704260744.AAA13064@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/include pcb.h Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk peter 97/04/26 00:44:35 Modified: i386/include pcb.h Log: Since the pcb size has changed, we may as well stake out a claim on a few spare bytes for future requirements. This will reduce the number of times coredumps will become unreadable in the future. Revision Changes Path 1.13 +1 -0 sys/i386/include/pcb.h From owner-freebsd-smp Sat Apr 26 01:11:57 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id BAA11333 for smp-outgoing; Sat, 26 Apr 1997 01:11:57 -0700 (PDT) Received: from freefall.freebsd.org (freefall.cdrom.com [204.216.27.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id BAA11328 for ; Sat, 26 Apr 1997 01:11:55 -0700 (PDT) From: Peter Wemm Received: (from peter@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id BAA13240 for freebsd-smp; Sat, 26 Apr 1997 01:11:53 -0700 (PDT) Date: Sat, 26 Apr 1997 01:11:53 -0700 (PDT) Message-Id: <199704260811.BAA13240@freefall.freebsd.org> To: freebsd-smp@FreeBSD.org Subject: cvs commit: sys/i386/i386 machdep.c mp_machdep.c sys/i386/include mpapic.h smp.h sys/i386/isa clock.c isa.c Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk peter 97/04/26 01:11:53 Modified: i386/i386 machdep.c mp_machdep.c i386/include mpapic.h smp.h i386/isa clock.c isa.c Log: With more profuse apologies to Steve, another attack from the KNF police. Revision Changes Path 1.41 +1 -1 sys/i386/i386/machdep.c 1.47 +3 -3 sys/i386/i386/mp_machdep.c 1.14 +91 -86 sys/i386/include/mpapic.h 1.29 +6 -6 sys/i386/include/smp.h 1.19 +21 -24 sys/i386/isa/clock.c 1.21 +10 -10 sys/i386/isa/isa.c From owner-freebsd-smp Sat Apr 26 03:46:51 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id DAA18039 for smp-outgoing; Sat, 26 Apr 1997 03:46:51 -0700 (PDT) Received: from news1.gtn.com (news1.gtn.com [194.77.0.15]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id DAA18034 for ; Sat, 26 Apr 1997 03:46:46 -0700 (PDT) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id MAA06953; Sat, 26 Apr 1997 12:16:36 +0200 (MET DST) Received: (from andreas@localhost) by klemm.gtn.com (8.8.5/8.8.2) id LAA06863; Sat, 26 Apr 1997 11:14:50 +0200 (CEST) Message-ID: <19970426111449.53042@klemm.gtn.com> Date: Sat, 26 Apr 1997 11:14:49 +0200 From: Andreas Klemm To: Kevin Van Maren Cc: freebsd-smp@FreeBSD.org Subject: Re: AMI BIOS on Titan PRO References: <199704251417.IAA15451@fast.cs.utah.edu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 In-Reply-To: <199704251417.IAA15451@fast.cs.utah.edu>; from Kevin Van Maren on Fri, Apr 25, 1997 at 08:17:00AM -0600 X-Disclaimer: A free society is one where it is safe to be unpopular X-Operating-System: FreeBSD 3.0-CURRENT Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Fri, Apr 25, 1997 at 08:17:00AM -0600, Kevin Van Maren wrote: > > Also, let me elaborate a little on the AMI BIOS. > The Titan Pro (S1662/S1668) shipps with the Award BIOS > in most cases. Recently an AMI BIOS became available. > However, it is not possible to Flash an AMI BIOS over an ^^^^^^^^^^^^^^^^^^ > Award BIOS (well, it might be `possible'). ^^^^^^^^^^^^^^^^^^ Hi Kevin ! Why is it not possible, but might be possible ? Could you please explain that a little more in detail ? Andreas /// -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-smp Sat Apr 26 07:30:54 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id HAA23834 for smp-outgoing; Sat, 26 Apr 1997 07:30:54 -0700 (PDT) Received: from gargoyle.bazzle.com (gargoyle.bazzle.com [206.103.246.190]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id HAA23828 for ; Sat, 26 Apr 1997 07:30:50 -0700 (PDT) Received: from gargoyle.bazzle.com (gargoyle.bazzle.com [206.103.246.189]) by gargoyle.bazzle.com (8.8.5/8.6.12) with SMTP id KAA00398 for ; Sat, 26 Apr 1997 10:30:48 -0400 (EDT) Date: Sat, 26 Apr 1997 10:30:48 -0400 (EDT) From: "Eric J. Chet" To: freebsd-smp@freebsd.org Subject: XFAST_IPI32 Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hello A kernel as of Sat Apr 26 10:23:59 EDT 1997 is working for me now. I'm not seeing any "APIC Missing RTC connection" messages anymore. I did have to touch smptests.h because of a parse error. I have XFAST_IPI32 defined. The optimized code in mp_machdep.c didn't work for me, either version. This is on a GigaByte 586DX rev 2, mainboard. Thanks, Eric From owner-freebsd-smp Sat Apr 26 08:53:10 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id IAA26204 for smp-outgoing; Sat, 26 Apr 1997 08:53:10 -0700 (PDT) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id IAA26188 for ; Sat, 26 Apr 1997 08:52:16 -0700 (PDT) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id RAA27081 for smp@FreeBSD.org; Sat, 26 Apr 1997 17:31:41 +0200 (MET DST) Received: (from andreas@localhost) by klemm.gtn.com (8.8.5/8.8.2) id RAA14728; Sat, 26 Apr 1997 17:21:58 +0200 (CEST) Message-ID: <19970426172158.46581@klemm.gtn.com> Date: Sat, 26 Apr 1997 17:21:58 +0200 From: Andreas Klemm To: smp@FreeBSD.org Subject: compilation problems under -current of today Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 X-Disclaimer: A free society is one where it is safe to be unpopular X-Operating-System: FreeBSD 3.0-CURRENT Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk FreeBSD-current of today, fbsd-smp of today: Somebody other seen this ? My configuration ? Well a simple GENERIC kernel produced similar messages. make -ki cc -c -x assembler-with-cpp -DLOCORE -nostdinc -I- -I. -I../.. -I/usr/include -DTELES_HAS_MEMCPYB -DMD5 -DCOMPAT_43 -DNSWAPDEV=3 -DMFS -DFFS -DINET -DKERNEL ../../i386/i386/exception.s machine/smpasm.h: Assembler messages: machine/smpasm.h:28: Error: no such 386 instruction: `extern' machine/smpasm.h:31: Error: no such 386 instruction: `void' machine/smpasm.h:34: Error: no such 386 instruction: `extern' machine/smpasm.h:37: Error: no such 386 instruction: `void' machine/smpasm.h:38: Error: no such 386 instruction: `void' machine/smpasm.h:39: Error: no such 386 instruction: `void' machine/smpasm.h:42: Error: no such 386 instruction: `extern' machine/smpasm.h:43: Error: no such 386 instruction: `extern' machine/smpasm.h:44: Error: no such 386 instruction: `extern' machine/smpasm.h:45: Error: no such 386 instruction: `extern' machine/smpasm.h:46: Error: no such 386 instruction: `extern' machine/smpasm.h:47: Error: no such 386 instruction: `extern' machine/smpasm.h:48: Error: no such 386 instruction: `extern' machine/smpasm.h:49: Error: no such 386 instruction: `extern' machine/smpasm.h:50: Error: no such 386 instruction: `extern' machine/smpasm.h:51: Error: no such 386 instruction: `extern' machine/smpasm.h:52: Error: no such 386 instruction: `extern' machine/smpasm.h:53: Error: no such 386 instruction: `extern' machine/smpasm.h:54: Error: no such 386 instruction: `extern' machine/smpasm.h:55: Error: no such 386 instruction: `extern' machine/smpasm.h:56: Error: no such 386 instruction: `extern' machine/smpasm.h:57: Error: no such 386 instruction: `extern' machine/smpasm.h:58: Error: no such 386 instruction: `extern' machine/smpasm.h:61: Error: invalid character '_' in opcode machine/smpasm.h:62: Error: no such 386 instruction: `void' machine/smpasm.h:63: Error: no such 386 instruction: `void' machine/smpasm.h:64: Error: Ignoring junk '(int)' after expression machine/smpasm.h:64: Error: operands given don't match any known 386 instruction machine/smpasm.h:65: Error: Ignoring junk '(int)' after expression machine/smpasm.h:65: Error: operands given don't match any known 386 instruction machine/smpasm.h:66: Error: Ignoring junk '(int,int,int)' after expression machine/smpasm.h:66: Error: operands given don't match any known 386 instruction machine/smpasm.h:67: Error: Ignoring junk '(int)' after expression machine/smpasm.h:67: Error: operands given don't match any known 386 instruction machine/smpasm.h:68: Error: Ignoring junk '(int)' after expression machine/smpasm.h:68: Error: operands given don't match any known 386 instruction machine/smpasm.h:69: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:69: Error: operands given don't match any known 386 instruction machine/smpasm.h:70: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:70: Error: operands given don't match any known 386 instruction machine/smpasm.h:71: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:71: Error: operands given don't match any known 386 instruction machine/smpasm.h:72: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:72: Error: operands given don't match any known 386 instruction machine/smpasm.h:73: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:73: Error: operands given don't match any known 386 instruction machine/smpasm.h:74: Error: no such 386 instruction: `void' machine/smpasm.h:75: Error: no such 386 instruction: `void' machine/smpasm.h:77: Error: no such 386 instruction: `void' machine/smpasm.h:78: Error: no such 386 instruction: `void' machine/smpasm.h:82: Error: no such 386 instruction: `extern' machine/smpasm.h:87: Error: no such 386 instruction: `extern' machine/smpasm.h:91: Error: no such 386 instruction: `void' machine/smpasm.h:92: Error: Ignoring junk '(u_int,int,int)' after expression machine/smpasm.h:92: Error: operands given don't match any known 386 instruction machine/smpasm.h:93: Error: Ignoring junk '(int)' after expression machine/smpasm.h:93: Error: operands given don't match any known 386 instruction machine/smpasm.h:94: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:94: Error: operands given don't match any known 386 instruction machine/smpasm.h:95: Error: no such 386 instruction: `void' machine/smpasm.h:102: Error: no such 386 instruction: `void' machine/smpasm.h:103: Error: Ignoring junk '(void)' after expression machine/smpasm.h:103: Error: operands given don't match any known 386 instruction machine/smpasm.h:104: Error: no such 386 instruction: `void' machine/smpasm.h:107: Error: no such 386 instruction: `extern' machine/smpasm.h:108: Error: no such 386 instruction: `extern' machine/smpasm.h:111: Error: no such 386 instruction: `void' machine/smpasm.h:112: Error: no such 386 instruction: `void' machine/smpasm.h:126: Error: no such 386 instruction: `static' machine/smpasm.h:127: Error: invalid character '(' in opcode machine/smpasm.h:128: Error: invalid character '{' in opcode machine/smpasm.h:129: Error: no such 386 instruction: `return' machine/smpasm.h:130: Error: Rest of line ignored. First ignored character is `}'. ../../i386/i386/exception.s:272: Error: invalid character '(' in opcode ../../i386/isa/vector.s:399: Error: invalid character '(' in opcode ../../i386/isa/vector.s:400: Error: invalid character '(' in opcode ../../i386/isa/vector.s:401: Error: invalid character '(' in opcode ../../i386/isa/vector.s:402: Error: invalid character '(' in opcode ../../i386/isa/vector.s:403: Error: invalid character '(' in opcode ../../i386/isa/vector.s:404: Error: invalid character '(' in opcode ../../i386/isa/vector.s:405: Error: invalid character '(' in opcode ../../i386/isa/vector.s:406: Error: invalid character '(' in opcode ../../i386/isa/vector.s:407: Error: invalid character '(' in opcode ../../i386/isa/vector.s:408: Error: invalid character '(' in opcode ../../i386/isa/vector.s:409: Error: invalid character '(' in opcode ../../i386/isa/vector.s:410: Error: invalid character '(' in opcode ../../i386/isa/vector.s:411: Error: invalid character '(' in opcode ../../i386/isa/vector.s:412: Error: invalid character '(' in opcode ../../i386/isa/vector.s:413: Error: invalid character '(' in opcode ../../i386/isa/vector.s:414: Error: invalid character '(' in opcode ../../i386/isa/vector.s:416: Error: invalid character '(' in opcode ../../i386/isa/vector.s:417: Error: invalid character '(' in opcode ../../i386/isa/vector.s:418: Error: invalid character '(' in opcode ../../i386/isa/vector.s:419: Error: invalid character '(' in opcode ../../i386/isa/vector.s:420: Error: invalid character '(' in opcode ../../i386/isa/vector.s:421: Error: invalid character '(' in opcode ../../i386/isa/vector.s:422: Error: invalid character '(' in opcode ../../i386/isa/vector.s:423: Error: invalid character '(' in opcode ../../i386/isa/vector.s:425: Error: invalid character '(' in opcode ../../i386/isa/vector.s:426: Error: invalid character '(' in opcode ../../i386/isa/vector.s:427: Error: invalid character '(' in opcode ../../i386/isa/vector.s:428: Error: invalid character '(' in opcode ../../i386/isa/vector.s:429: Error: invalid character '(' in opcode ../../i386/isa/vector.s:430: Error: invalid character '(' in opcode ../../i386/isa/vector.s:431: Error: invalid character '(' in opcode ../../i386/isa/vector.s:432: Error: invalid character '(' in opcode ../../i386/isa/vector.s:433: Error: invalid character '(' in opcode ../../i386/isa/vector.s:434: Error: invalid character '(' in opcode ../../i386/isa/vector.s:435: Error: invalid character '(' in opcode ../../i386/isa/vector.s:436: Error: invalid character '(' in opcode ../../i386/isa/vector.s:437: Error: invalid character '(' in opcode ../../i386/isa/vector.s:438: Error: invalid character '(' in opcode ../../i386/isa/vector.s:439: Error: invalid character '(' in opcode ../../i386/isa/vector.s:440: Error: invalid character '(' in opcode ../../i386/isa/vector.s:442: Error: invalid character '(' in opcode ../../i386/isa/vector.s:443: Error: invalid character '(' in opcode ../../i386/isa/vector.s:444: Error: invalid character '(' in opcode ../../i386/isa/vector.s:445: Error: invalid character '(' in opcode ../../i386/isa/vector.s:446: Error: invalid character '(' in opcode ../../i386/isa/vector.s:447: Error: invalid character '(' in opcode ../../i386/isa/vector.s:448: Error: invalid character '(' in opcode ../../i386/isa/vector.s:449: Error: invalid character '(' in opcode *** Error code 1 (ignored) cc -c -x assembler-with-cpp -DLOCORE -nostdinc -I- -I. -I../.. -I/usr/include -DTELES_HAS_MEMCPYB -DMD5 -DCOMPAT_43 -DNSWAPDEV=3 -DMFS -DFFS -DINET -DKERNEL ../../i386/i386/mplock.s machine/smpasm.h: Assembler messages: machine/smpasm.h:28: Error: no such 386 instruction: `extern' machine/smpasm.h:31: Error: no such 386 instruction: `void' machine/smpasm.h:34: Error: no such 386 instruction: `extern' machine/smpasm.h:37: Error: no such 386 instruction: `void' machine/smpasm.h:38: Error: no such 386 instruction: `void' machine/smpasm.h:39: Error: no such 386 instruction: `void' machine/smpasm.h:42: Error: no such 386 instruction: `extern' machine/smpasm.h:43: Error: no such 386 instruction: `extern' machine/smpasm.h:44: Error: no such 386 instruction: `extern' machine/smpasm.h:45: Error: no such 386 instruction: `extern' machine/smpasm.h:46: Error: no such 386 instruction: `extern' machine/smpasm.h:47: Error: no such 386 instruction: `extern' machine/smpasm.h:48: Error: no such 386 instruction: `extern' machine/smpasm.h:49: Error: no such 386 instruction: `extern' machine/smpasm.h:50: Error: no such 386 instruction: `extern' machine/smpasm.h:51: Error: no such 386 instruction: `extern' machine/smpasm.h:52: Error: no such 386 instruction: `extern' machine/smpasm.h:53: Error: no such 386 instruction: `extern' machine/smpasm.h:54: Error: no such 386 instruction: `extern' machine/smpasm.h:55: Error: no such 386 instruction: `extern' machine/smpasm.h:56: Error: no such 386 instruction: `extern' machine/smpasm.h:57: Error: no such 386 instruction: `extern' machine/smpasm.h:58: Error: no such 386 instruction: `extern' machine/smpasm.h:61: Error: invalid character '_' in opcode machine/smpasm.h:62: Error: no such 386 instruction: `void' machine/smpasm.h:63: Error: no such 386 instruction: `void' machine/smpasm.h:64: Error: Ignoring junk '(int)' after expression machine/smpasm.h:64: Error: operands given don't match any known 386 instruction machine/smpasm.h:65: Error: Ignoring junk '(int)' after expression machine/smpasm.h:65: Error: operands given don't match any known 386 instruction machine/smpasm.h:66: Error: Ignoring junk '(int,int,int)' after expression machine/smpasm.h:66: Error: operands given don't match any known 386 instruction machine/smpasm.h:67: Error: Ignoring junk '(int)' after expression machine/smpasm.h:67: Error: operands given don't match any known 386 instruction machine/smpasm.h:68: Error: Ignoring junk '(int)' after expression machine/smpasm.h:68: Error: operands given don't match any known 386 instruction machine/smpasm.h:69: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:69: Error: operands given don't match any known 386 instruction machine/smpasm.h:70: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:70: Error: operands given don't match any known 386 instruction machine/smpasm.h:71: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:71: Error: operands given don't match any known 386 instruction machine/smpasm.h:72: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:72: Error: operands given don't match any known 386 instruction machine/smpasm.h:73: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:73: Error: operands given don't match any known 386 instruction machine/smpasm.h:74: Error: no such 386 instruction: `void' machine/smpasm.h:75: Error: no such 386 instruction: `void' machine/smpasm.h:77: Error: no such 386 instruction: `void' machine/smpasm.h:78: Error: no such 386 instruction: `void' machine/smpasm.h:82: Error: no such 386 instruction: `extern' machine/smpasm.h:87: Error: no such 386 instruction: `extern' machine/smpasm.h:91: Error: no such 386 instruction: `void' machine/smpasm.h:92: Error: Ignoring junk '(u_int,int,int)' after expression machine/smpasm.h:92: Error: operands given don't match any known 386 instruction machine/smpasm.h:93: Error: Ignoring junk '(int)' after expression machine/smpasm.h:93: Error: operands given don't match any known 386 instruction machine/smpasm.h:94: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:94: Error: operands given don't match any known 386 instruction machine/smpasm.h:95: Error: no such 386 instruction: `void' machine/smpasm.h:102: Error: no such 386 instruction: `void' machine/smpasm.h:103: Error: Ignoring junk '(void)' after expression machine/smpasm.h:103: Error: operands given don't match any known 386 instruction machine/smpasm.h:104: Error: no such 386 instruction: `void' machine/smpasm.h:107: Error: no such 386 instruction: `extern' machine/smpasm.h:108: Error: no such 386 instruction: `extern' machine/smpasm.h:111: Error: no such 386 instruction: `void' machine/smpasm.h:112: Error: no such 386 instruction: `void' machine/smpasm.h:126: Error: no such 386 instruction: `static' machine/smpasm.h:127: Error: invalid character '(' in opcode machine/smpasm.h:128: Error: invalid character '{' in opcode machine/smpasm.h:129: Error: no such 386 instruction: `return' machine/smpasm.h:130: Error: Rest of line ignored. First ignored character is `}'. *** Error code 1 (ignored) cc -c -x assembler-with-cpp -DLOCORE -nostdinc -I- -I. -I../.. -I/usr/include -DTELES_HAS_MEMCPYB -DMD5 -DCOMPAT_43 -DNSWAPDEV=3 -DMFS -DFFS -DINET -DKERNEL ../../i386/i386/support.s machine/smpasm.h: Assembler messages: machine/smpasm.h:28: Error: no such 386 instruction: `extern' machine/smpasm.h:31: Error: no such 386 instruction: `void' machine/smpasm.h:34: Error: no such 386 instruction: `extern' machine/smpasm.h:37: Error: no such 386 instruction: `void' machine/smpasm.h:38: Error: no such 386 instruction: `void' machine/smpasm.h:39: Error: no such 386 instruction: `void' machine/smpasm.h:42: Error: no such 386 instruction: `extern' machine/smpasm.h:43: Error: no such 386 instruction: `extern' machine/smpasm.h:44: Error: no such 386 instruction: `extern' machine/smpasm.h:45: Error: no such 386 instruction: `extern' machine/smpasm.h:46: Error: no such 386 instruction: `extern' machine/smpasm.h:47: Error: no such 386 instruction: `extern' machine/smpasm.h:48: Error: no such 386 instruction: `extern' machine/smpasm.h:49: Error: no such 386 instruction: `extern' machine/smpasm.h:50: Error: no such 386 instruction: `extern' machine/smpasm.h:51: Error: no such 386 instruction: `extern' machine/smpasm.h:52: Error: no such 386 instruction: `extern' machine/smpasm.h:53: Error: no such 386 instruction: `extern' machine/smpasm.h:54: Error: no such 386 instruction: `extern' machine/smpasm.h:55: Error: no such 386 instruction: `extern' machine/smpasm.h:56: Error: no such 386 instruction: `extern' machine/smpasm.h:57: Error: no such 386 instruction: `extern' machine/smpasm.h:58: Error: no such 386 instruction: `extern' machine/smpasm.h:61: Error: invalid character '_' in opcode machine/smpasm.h:62: Error: no such 386 instruction: `void' machine/smpasm.h:63: Error: no such 386 instruction: `void' machine/smpasm.h:64: Error: Ignoring junk '(int)' after expression machine/smpasm.h:64: Error: operands given don't match any known 386 instruction machine/smpasm.h:65: Error: Ignoring junk '(int)' after expression machine/smpasm.h:65: Error: operands given don't match any known 386 instruction machine/smpasm.h:66: Error: Ignoring junk '(int,int,int)' after expression machine/smpasm.h:66: Error: operands given don't match any known 386 instruction machine/smpasm.h:67: Error: Ignoring junk '(int)' after expression machine/smpasm.h:67: Error: operands given don't match any known 386 instruction machine/smpasm.h:68: Error: Ignoring junk '(int)' after expression machine/smpasm.h:68: Error: operands given don't match any known 386 instruction machine/smpasm.h:69: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:69: Error: operands given don't match any known 386 instruction machine/smpasm.h:70: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:70: Error: operands given don't match any known 386 instruction machine/smpasm.h:71: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:71: Error: operands given don't match any known 386 instruction machine/smpasm.h:72: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:72: Error: operands given don't match any known 386 instruction machine/smpasm.h:73: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:73: Error: operands given don't match any known 386 instruction machine/smpasm.h:74: Error: no such 386 instruction: `void' machine/smpasm.h:75: Error: no such 386 instruction: `void' machine/smpasm.h:77: Error: no such 386 instruction: `void' machine/smpasm.h:78: Error: no such 386 instruction: `void' machine/smpasm.h:82: Error: no such 386 instruction: `extern' machine/smpasm.h:87: Error: no such 386 instruction: `extern' machine/smpasm.h:91: Error: no such 386 instruction: `void' machine/smpasm.h:92: Error: Ignoring junk '(u_int,int,int)' after expression machine/smpasm.h:92: Error: operands given don't match any known 386 instruction machine/smpasm.h:93: Error: Ignoring junk '(int)' after expression machine/smpasm.h:93: Error: operands given don't match any known 386 instruction machine/smpasm.h:94: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:94: Error: operands given don't match any known 386 instruction machine/smpasm.h:95: Error: no such 386 instruction: `void' machine/smpasm.h:102: Error: no such 386 instruction: `void' machine/smpasm.h:103: Error: Ignoring junk '(void)' after expression machine/smpasm.h:103: Error: operands given don't match any known 386 instruction machine/smpasm.h:104: Error: no such 386 instruction: `void' machine/smpasm.h:107: Error: no such 386 instruction: `extern' machine/smpasm.h:108: Error: no such 386 instruction: `extern' machine/smpasm.h:111: Error: no such 386 instruction: `void' machine/smpasm.h:112: Error: no such 386 instruction: `void' machine/smpasm.h:126: Error: no such 386 instruction: `static' machine/smpasm.h:127: Error: invalid character '(' in opcode machine/smpasm.h:128: Error: invalid character '{' in opcode machine/smpasm.h:129: Error: no such 386 instruction: `return' machine/smpasm.h:130: Error: Rest of line ignored. First ignored character is `}'. ../../i386/i386/support.s:627: Error: invalid character '(' in opcode ../../i386/i386/support.s:738: Error: invalid character '(' in opcode ../../i386/i386/support.s:747: Error: invalid character '(' in opcode ../../i386/i386/support.s:812: Error: invalid character '(' in opcode ../../i386/i386/support.s:850: Error: invalid character '(' in opcode ../../i386/i386/support.s:858: Error: invalid character '(' in opcode ../../i386/i386/support.s:1090: Error: invalid character '(' in opcode ../../i386/i386/support.s:1113: Error: invalid character '(' in opcode ../../i386/i386/support.s:1125: Error: invalid character '(' in opcode ../../i386/i386/support.s:1138: Error: invalid character '(' in opcode ../../i386/i386/support.s:1148: Error: invalid character '(' in opcode ../../i386/i386/support.s:1192: Error: invalid character '(' in opcode ../../i386/i386/support.s:1197: Error: invalid character '(' in opcode ../../i386/i386/support.s:1241: Error: invalid character '(' in opcode ../../i386/i386/support.s:1247: Error: invalid character '(' in opcode ../../i386/i386/support.s:1290: Error: invalid character '(' in opcode ../../i386/i386/support.s:1304: Error: invalid character '(' in opcode ../../i386/i386/support.s:1352: Error: invalid character '(' in opcode *** Error code 1 (ignored) cc -c -x assembler-with-cpp -DLOCORE -nostdinc -I- -I. -I../.. -I/usr/include -DTELES_HAS_MEMCPYB -DMD5 -DCOMPAT_43 -DNSWAPDEV=3 -DMFS -DFFS -DINET -DKERNEL ../../i386/i386/swtch.s machine/smpasm.h: Assembler messages: machine/smpasm.h:28: Error: no such 386 instruction: `extern' machine/smpasm.h:31: Error: no such 386 instruction: `void' machine/smpasm.h:34: Error: no such 386 instruction: `extern' machine/smpasm.h:37: Error: no such 386 instruction: `void' machine/smpasm.h:38: Error: no such 386 instruction: `void' machine/smpasm.h:39: Error: no such 386 instruction: `void' machine/smpasm.h:42: Error: no such 386 instruction: `extern' machine/smpasm.h:43: Error: no such 386 instruction: `extern' machine/smpasm.h:44: Error: no such 386 instruction: `extern' machine/smpasm.h:45: Error: no such 386 instruction: `extern' machine/smpasm.h:46: Error: no such 386 instruction: `extern' machine/smpasm.h:47: Error: no such 386 instruction: `extern' machine/smpasm.h:48: Error: no such 386 instruction: `extern' machine/smpasm.h:49: Error: no such 386 instruction: `extern' machine/smpasm.h:50: Error: no such 386 instruction: `extern' machine/smpasm.h:51: Error: no such 386 instruction: `extern' machine/smpasm.h:52: Error: no such 386 instruction: `extern' machine/smpasm.h:53: Error: no such 386 instruction: `extern' machine/smpasm.h:54: Error: no such 386 instruction: `extern' machine/smpasm.h:55: Error: no such 386 instruction: `extern' machine/smpasm.h:56: Error: no such 386 instruction: `extern' machine/smpasm.h:57: Error: no such 386 instruction: `extern' machine/smpasm.h:58: Error: no such 386 instruction: `extern' machine/smpasm.h:61: Error: invalid character '_' in opcode machine/smpasm.h:62: Error: no such 386 instruction: `void' machine/smpasm.h:63: Error: no such 386 instruction: `void' machine/smpasm.h:64: Error: Ignoring junk '(int)' after expression machine/smpasm.h:64: Error: operands given don't match any known 386 instruction machine/smpasm.h:65: Error: Ignoring junk '(int)' after expression machine/smpasm.h:65: Error: operands given don't match any known 386 instruction machine/smpasm.h:66: Error: Ignoring junk '(int,int,int)' after expression machine/smpasm.h:66: Error: operands given don't match any known 386 instruction machine/smpasm.h:67: Error: Ignoring junk '(int)' after expression machine/smpasm.h:67: Error: operands given don't match any known 386 instruction machine/smpasm.h:68: Error: Ignoring junk '(int)' after expression machine/smpasm.h:68: Error: operands given don't match any known 386 instruction machine/smpasm.h:69: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:69: Error: operands given don't match any known 386 instruction machine/smpasm.h:70: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:70: Error: operands given don't match any known 386 instruction machine/smpasm.h:71: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:71: Error: operands given don't match any known 386 instruction machine/smpasm.h:72: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:72: Error: operands given don't match any known 386 instruction machine/smpasm.h:73: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:73: Error: operands given don't match any known 386 instruction machine/smpasm.h:74: Error: no such 386 instruction: `void' machine/smpasm.h:75: Error: no such 386 instruction: `void' machine/smpasm.h:77: Error: no such 386 instruction: `void' machine/smpasm.h:78: Error: no such 386 instruction: `void' machine/smpasm.h:82: Error: no such 386 instruction: `extern' machine/smpasm.h:87: Error: no such 386 instruction: `extern' machine/smpasm.h:91: Error: no such 386 instruction: `void' machine/smpasm.h:92: Error: Ignoring junk '(u_int,int,int)' after expression machine/smpasm.h:92: Error: operands given don't match any known 386 instruction machine/smpasm.h:93: Error: Ignoring junk '(int)' after expression machine/smpasm.h:93: Error: operands given don't match any known 386 instruction machine/smpasm.h:94: Error: Ignoring junk '(int,int)' after expression machine/smpasm.h:94: Error: operands given don't match any known 386 instruction machine/smpasm.h:95: Error: no such 386 instruction: `void' machine/smpasm.h:102: Error: no such 386 instruction: `void' machine/smpasm.h:103: Error: Ignoring junk '(void)' after expression machine/smpasm.h:103: Error: operands given don't match any known 386 instruction machine/smpasm.h:104: Error: no such 386 instruction: `void' machine/smpasm.h:107: Error: no such 386 instruction: `extern' machine/smpasm.h:108: Error: no such 386 instruction: `extern' machine/smpasm.h:111: Error: no such 386 instruction: `void' machine/smpasm.h:112: Error: no such 386 instruction: `void' machine/smpasm.h:126: Error: no such 386 instruction: `static' machine/smpasm.h:127: Error: invalid character '(' in opcode machine/smpasm.h:128: Error: invalid character '{' in opcode machine/smpasm.h:129: Error: no such 386 instruction: `return' machine/smpasm.h:130: Error: Rest of line ignored. First ignored character is `}'. ../../i386/i386/swtch.s:263: Error: invalid character '(' in opcode ../../i386/i386/swtch.s:319: Error: invalid character '(' in opcode ../../i386/i386/swtch.s:351: Error: invalid character '(' in opcode ../../i386/i386/swtch.s:352: Error: invalid character '(' in opcode ../../i386/i386/swtch.s:364: Error: invalid character '(' in opcode ../../i386/i386/swtch.s:502: Error: invalid character '(' in opcode ../../i386/i386/swtch.s:529: Error: invalid character '(' in opcode ../../i386/i386/swtch.s:532: Error: invalid character '(' in opcode ../../i386/i386/swtch.s:533: Error: invalid character '(' in opcode ../../i386/i386/swtch.s:614: Error: invalid character '(' in opcode *** Error code 1 (ignored) sh ../../conf/newvers.sh BISDNSMP -DTELES_HAS_MEMCPYB -DMD5 -DCOMPAT_43 -DNSWAPDEV=3 -DMFS -DFFS -DINET cc -O -pipe -Wreturn-type -Wcomment -Wredundant-decls -Wimplicit -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -nostdinc -I- -I. -I../.. -I/usr/include -DTELES_HAS_MEMCPYB -DMD5 -DCOMPAT_43 -DNSWAPDEV=3 -DMFS -DFFS -DINET -DKERNEL -c vers.c loading kernel ld: exception.o: No such file or directory rearranging symbols symorder: kernel: No such file or directory size: kernel: No such file or directory chmod: kernel: No such file or directory *** Error code 1 (ignored) *** Error code 1 (ignored) -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-smp Sat Apr 26 09:13:16 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id JAA26912 for smp-outgoing; Sat, 26 Apr 1997 09:13:16 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA26904 for ; Sat, 26 Apr 1997 09:13:09 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id AAA00405; Sun, 27 Apr 1997 00:12:15 +0800 (WST) Message-Id: <199704261612.AAA00405@spinner.DIALix.COM> To: Andreas Klemm cc: smp@FreeBSD.org Subject: Re: compilation problems under -current of today In-reply-to: Your message of "Sat, 26 Apr 1997 17:21:58 +0200." <19970426172158.46581@klemm.gtn.com> Date: Sun, 27 Apr 1997 00:12:14 +0800 From: Peter Wemm Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Andreas Klemm wrote: > FreeBSD-current of today, fbsd-smp of today: > > Somebody other seen this ? My configuration ? > Well a simple GENERIC kernel produced similar messages. > > make -ki > > cc -c -x assembler-with-cpp -DLOCORE -nostdinc -I- -I. -I../.. -I/usr/include -DTELES_HAS_MEMCPYB -DMD5 -DCOMPAT_43 -DNSWAPDEV=3 -DMFS -DFFS -DINET -DKE RNEL ../../i386/i386/exception.s > machine/smpasm.h: Assembler messages: > machine/smpasm.h:28: Error: no such 386 instruction: `extern' [...] Err, something is busted somewhere.. smpasm.h shouldn't have any 'C' type keywords in it.. It should be mostly #defines.... And line 28 is a #define. Have you done this from a fresh 'config' run? Do you have the /sys symlink pointing to the right place? Have you looked at -current? The smp code just got merged! -Peter From owner-freebsd-smp Sat Apr 26 09:15:10 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id JAA27013 for smp-outgoing; Sat, 26 Apr 1997 09:15:10 -0700 (PDT) Received: from spinner.DIALix.COM (root@spinner.dialix.com [192.203.228.67]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA27004 for ; Sat, 26 Apr 1997 09:15:06 -0700 (PDT) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.5/8.8.5) with ESMTP id AAA00418 for ; Sun, 27 Apr 1997 00:14:55 +0800 (WST) Message-Id: <199704261614.AAA00418@spinner.DIALix.COM> To: smp@freebsd.org Subject: SMP code merged into -current as of a few hours ago! Date: Sun, 27 Apr 1997 00:14:54 +0800 From: Peter Wemm Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Just a 'heads up' in case anybody wasn't watching -current too closely.. I just merged the current smp code into the normal -current source. This should pretty much be the end of the '-current-is-out-of-sync' problems.. Cheers, -Peter From owner-freebsd-smp Sat Apr 26 10:10:51 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA28939 for smp-outgoing; Sat, 26 Apr 1997 10:10:51 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA28934 for ; Sat, 26 Apr 1997 10:10:48 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id LAA16333; Sat, 26 Apr 1997 11:10:15 -0600 (MDT) Message-Id: <199704261710.LAA16333@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Andreas Klemm cc: smp@FreeBSD.org Subject: Re: compilation problems under -current of today In-reply-to: Your message of "Sat, 26 Apr 1997 17:21:58 +0200." <19970426172158.46581@klemm.gtn.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 26 Apr 1997 11:10:14 -0600 Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi, --- >FreeBSD-current of today, fbsd-smp of today: > >Somebody other seen this ? My configuration ? >Well a simple GENERIC kernel produced similar messages. > ... as Peter just announced, SMP is now in the main 3.0-current tree!!! This morning I have successfully run an SMP kernel from the SMP tree as we have left it. I have also successfully run an SMP kernel built from the 3.0-current sys tree. It can rebuild itself without problems. Next I am going to cvsup 3.0-current and rebuild the world with the new SMP kernel... stay tuned. --- The SMP webpage now reflects the change in source trees. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Sat Apr 26 10:22:34 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA29483 for smp-outgoing; Sat, 26 Apr 1997 10:22:34 -0700 (PDT) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA29475 for ; Sat, 26 Apr 1997 10:22:31 -0700 (PDT) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.5/8.8.5) with ESMTP id LAA16382; Sat, 26 Apr 1997 11:21:10 -0600 (MDT) Message-Id: <199704261721.LAA16382@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: "Eric J. Chet" cc: freebsd-smp@freebsd.org Subject: Re: XFAST_IPI32 In-reply-to: Your message of "Sat, 26 Apr 1997 10:30:48 EDT." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 26 Apr 1997 11:21:10 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > A kernel as of Sat Apr 26 10:23:59 EDT 1997 is working for me now. > I'm not seeing any "APIC Missing RTC connection" messages anymore. I did > have to touch smptests.h because of a parse error. I have XFAST_IPI32 > defined. The optimized code in mp_machdep.c didn't work for me, > either version. This is on a GigaByte 586DX rev 2, mainboard. as mentioned earlier, the SMP tree in now part of 3.0-current. A lot of changes occurred last nite, I suspect you just grabbed an inconsistant set of sources. Re-cvsup from the main 3.0-current tree, the SMP tree is now FROZEN (I assume, Peter?). Rebuild and report if you still have any problems. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Sat Apr 26 15:15:49 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id PAA12554 for smp-outgoing; Sat, 26 Apr 1997 15:15:49 -0700 (PDT) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id PAA12533 for ; Sat, 26 Apr 1997 15:15:35 -0700 (PDT) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id AAA26294; Sun, 27 Apr 1997 00:01:32 +0200 (MET DST) Received: (from andreas@localhost) by klemm.gtn.com (8.8.5/8.8.2) id WAA25070; Sat, 26 Apr 1997 22:27:16 +0200 (CEST) Message-ID: <19970426222715.27571@klemm.gtn.com> Date: Sat, 26 Apr 1997 22:27:15 +0200 From: Andreas Klemm To: Peter Wemm Cc: smp@freebsd.org Subject: Re: SMP code merged into -current as of a few hours ago! References: <199704261614.AAA00418@spinner.DIALix.COM> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 In-Reply-To: <199704261614.AAA00418@spinner.DIALix.COM>; from Peter Wemm on Sun, Apr 27, 1997 at 12:14:54AM +0800 X-Disclaimer: A free society is one where it is safe to be unpopular X-Operating-System: FreeBSD 3.0-CURRENT Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Sun, Apr 27, 1997 at 12:14:54AM +0800, Peter Wemm wrote: > Just a 'heads up' in case anybody wasn't watching -current too closely.. > I just merged the current smp code into the normal -current source. > > This should pretty much be the end of the '-current-is-out-of-sync' > problems.. Hurray ! -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-smp Sat Apr 26 22:13:03 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id WAA28393 for smp-outgoing; Sat, 26 Apr 1997 22:13:03 -0700 (PDT) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id WAA28383 for ; Sat, 26 Apr 1997 22:12:59 -0700 (PDT) Received: from fast.cs.utah.edu by cs.utah.edu (8.8.4/utah-2.21-cs) id XAA25308; Sat, 26 Apr 1997 23:12:52 -0600 (MDT) Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id XAA20562; Sat, 26 Apr 1997 23:12:51 -0600 Date: Sat, 26 Apr 1997 23:12:51 -0600 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199704270512.XAA20562@fast.cs.utah.edu> To: andreas@klemm.gtn.com Subject: Re: AMI BIOS on Titan PRO Cc: freebsd-smp@FreeBSD.org Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > > Also, let me elaborate a little on the AMI BIOS. > > The Titan Pro (S1662/S1668) shipps with the Award BIOS > > in most cases. Recently an AMI BIOS became available. > > However, it is not possible to Flash an AMI BIOS over an > ^^^^^^^^^^^^^^^^^^ > > Award BIOS (well, it might be `possible'). > ^^^^^^^^^^^^^^^^^^ > > Hi Kevin ! > > Why is it not possible, but might be possible ? Could you please > explain that a little more in detail ? > > Andreas /// Well, it comes down more to a Software problem than a hardware one. Both BIOSes use the same Flash ROM. Both BIOSes are both stored in a 128k binary file that is written directly into the ROM. However, the AMI BIOS uses a flash routine IN the ROM, so you can not flash AMI BIOS with the AMI update utility since there isn't any support in the Award BIOS. The Award utility checks the checksum-equivelent to make sure the Award BIOS is intact, but of course, it isn't, since it is AMI BIOS. I hope this makes more sense. You can flash the BIOS if you can trick the utility (or write your own). Kevin