From owner-freebsd-smp Sun Jul 6 06:35:13 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id GAA22627 for smp-outgoing; Sun, 6 Jul 1997 06:35:13 -0700 (PDT) Received: from sv.compuland.com.br (sv.compuland.com.br [200.255.96.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id GAA22622 for ; Sun, 6 Jul 1997 06:35:07 -0700 (PDT) Received: from home (dial11.compuland.com.br [200.255.96.44]) by sv.compuland.com.br (8.8.6/8.8.6) with ESMTP id KAA25344; Sun, 6 Jul 1997 10:34:30 -0300 (EST) Message-Id: <199707061334.KAA25344@sv.compuland.com.br> From: "Helio Coelho Jr." To: Cc: Subject: help in two aspects Date: Sun, 6 Jul 1997 10:37:39 -0300 X-MSMail-Priority: Normal X-Priority: 3 X-Mailer: Microsoft Internet Mail 4.70.1161 MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi: I'm running current in a Asus Dual Pentium Pro Motherboard. It has 128mb memory, SMC ethernet, adaptec 2940AU and a quantum scsi HD. I wanted to make a full copy of the HD, so I added another Adaptec 2940UW and a Seagate Barracuda of 4gb. My idea was to exchange the disks, and in that way would be faster. I booted the machine, I've mounted the disk, copied all the stuff needed. At that moment, I shutdown the machine, removed the quantum and the 2940AU and restarted it again. It booted, just fine. When it reaches the 'Login: ' prompt, I got a panic, but the messages were so fast that I could not read !! It seems that the disk loose sync... I lost everything in this disk. I've returned the old components and everythyng was fine again. Just to be sure, I've repeated the experience, but now, I copied the disk to the the seagate but removed the big disk and it's 2940UW. I've rebooted, and I got the same panic again ! But now with the adaptec2940au and the quantum disk ! I turned off and on the machine again: this time it came back ! :) Fortunately this time I did not loose the contents of the disk... Anyone has an idea what happens or were I goofed ? :) Another thing I noticed: when I issue a 'shutdown now' and a 'halt' , sometimes I got a 'panic - shutdown not on CPU#0 - automatic reboot in 15 seconds' ... How can I avoid that ? How can I be sure that I'm on CPU#0 when halting ? ps -x ? :) Thanks a lot ! Regards, Helio. From owner-freebsd-smp Mon Jul 7 07:00:41 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id HAA13922 for smp-outgoing; Mon, 7 Jul 1997 07:00:41 -0700 (PDT) Received: from fang.cs.sunyit.edu (umji@fang.cs.sunyit.edu [192.52.220.66]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id HAA13914 for ; Mon, 7 Jul 1997 07:00:37 -0700 (PDT) Received: from localhost (umji@localhost) by fang.cs.sunyit.edu (8.7.6/8.7.3) with SMTP id KAA19311 for ; Mon, 7 Jul 1997 10:00:36 -0400 (EDT) Date: Mon, 7 Jul 1997 10:00:36 -0400 (EDT) From: Michael Imor To: freebsd-smp@freebsd.org Subject: subscribe Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk subscribe From owner-freebsd-smp Mon Jul 7 09:46:31 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id JAA22703 for smp-outgoing; Mon, 7 Jul 1997 09:46:31 -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 JAA22687 for ; Mon, 7 Jul 1997 09:46:19 -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 KAA20706; Mon, 7 Jul 1997 10:46:06 -0600 (MDT) Message-Id: <199707071646.KAA20706@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: "Helio Coelho Jr." cc: freebsd-smp@FreeBSD.ORG Subject: Re: help in two aspects In-reply-to: Your message of "Sun, 06 Jul 1997 10:37:39 -0300." <199707061334.KAA25344@sv.compuland.com.br> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 07 Jul 1997 10:46:05 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, > I'm running current in a Asus Dual Pentium Pro Motherboard. It has > 128mb memory, SMC ethernet, adaptec 2940AU and a quantum scsi HD. > ... > fine again. Just to be sure, I've repeated the experience, but now, I > copied > the disk to the the seagate but removed the big disk and it's 2940UW. I've > rebooted, and I got the same panic again ! But now with the adaptec2940au > and the quantum disk ! I turned off and on the machine again: this time it > came > back ! :) Fortunately this time I did not loose the contents of the > disk... > Anyone has an idea what happens or were I goofed ? :) no idea... --- > Another thing I noticed: when I issue a 'shutdown now' and a 'halt' , > sometimes I got > a 'panic - shutdown not on CPU#0 - automatic reboot in 15 seconds' ... How > can I avoid > that ? How can I be sure that I'm on CPU#0 when halting ? ps -x ? :) does it really say "panic"? it might say: "oops, I'm on cpu#1, I need to be on cpu#0!", but thats perfectly normal if you really requested a reboot/halt. Any 2 successive commands might run on different CPUs, there is no way (currently) to guarantee which CPU runs what, but as I said, in this case its not important. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Mon Jul 7 10:14:05 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA24539 for smp-outgoing; Mon, 7 Jul 1997 10:14:05 -0700 (PDT) Received: from sv.compuland.com.br (sv.compuland.com.br [200.255.96.21]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA24530 for ; Mon, 7 Jul 1997 10:13:59 -0700 (PDT) Received: from clpc1.compuland.com.br (clpc1.compuland.com.br [200.255.96.22]) by sv.compuland.com.br (8.8.6/8.8.6) with SMTP id OAA25997; Mon, 7 Jul 1997 14:12:17 -0300 (EST) Message-Id: <2.2.32.19970707171136.00c7a7f8@sv.compuland.com.br> X-Sender: helio@sv.compuland.com.br X-Mailer: Windows Eudora Pro Version 2.2 (32) Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Date: Mon, 07 Jul 1997 14:11:36 -0300 To: Steve Passe From: "Helio Coelho Jr." Subject: Re: help in two aspects Cc: freebsd-smp@freebsd.org Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >> Another thing I noticed: when I issue a 'shutdown now' and a 'halt' , >> sometimes I got >> a 'panic - shutdown not on CPU#0 - automatic reboot in 15 seconds' ... How >> can I avoid >> that ? How can I be sure that I'm on CPU#0 when halting ? ps -x ? :) > >does it really say "panic"? it might say: "oops, I'm on cpu#1, I need to be >on cpu#0!", but thats perfectly normal if you really requested a reboot/halt. >Any 2 successive commands might run on different CPUs, there is no way >(currently) to guarantee which CPU runs what, but as I said, in this case >its not important. Yes, it say 'panic' and 'automatic reboot in 15 seconds' :( Regards, Helio. From owner-freebsd-smp Mon Jul 7 10:39:31 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA26047 for smp-outgoing; Mon, 7 Jul 1997 10:39:31 -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 KAA26040 for ; Mon, 7 Jul 1997 10:39:25 -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 LAA20936; Mon, 7 Jul 1997 11:38:41 -0600 (MDT) Message-Id: <199707071738.LAA20936@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: "Helio Coelho Jr." cc: freebsd-smp@freebsd.org Subject: Re: help in two aspects In-reply-to: Your message of "Mon, 07 Jul 1997 14:11:36 -0300." <2.2.32.19970707171136.00c7a7f8@sv.compuland.com.br> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 07 Jul 1997 11:38:41 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > > >> Another thing I noticed: when I issue a 'shutdown now' and a 'halt' , > >> sometimes I got > >> a 'panic - shutdown not on CPU#0 - automatic reboot in 15 seconds' ... How > >> can I avoid > >> that ? How can I be sure that I'm on CPU#0 when halting ? ps -x ? :) > > > >does it really say "panic"? it might say: "oops, I'm on cpu#1, I need to be > >on cpu#0!", but thats perfectly normal if you really requested a reboot/halt. > >Any 2 successive commands might run on different CPUs, there is no way > >(currently) to guarantee which CPU runs what, but as I said, in this case > >its not important. > > Yes, it say 'panic' and 'automatic reboot in 15 seconds' :( I can't recreate it here, after the "shutdown now" messages I get: ------------------------------------- cut ------------------------------------- Enter pathname of shell or RETURN for sh: # halt boot() called on cpu#1 oops, I'm on cpu#1, I need to be on cpu#0! SMP: cpu#1 freezing syncing disks... done The operating system has halted. Please press any key to reboot. ------------------------------------- cut ------------------------------------- so I have no idea what your seeing... If you're not seeing disk corruption (or fsck running) when it reboots I wouldn't worry about it too much. Can anyone else report seeing this? -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Jul 8 11:05:55 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA29236 for smp-outgoing; Tue, 8 Jul 1997 11:05:55 -0700 (PDT) Received: from hutcs.cs.hut.fi (hutcs.cs.hut.fi [130.233.192.6]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA29230 for ; Tue, 8 Jul 1997 11:05:48 -0700 (PDT) Received: (from apl@localhost) by hutcs.cs.hut.fi (8.8.5/8.7.3) id VAA12256; Tue, 8 Jul 1997 21:05:45 +0300 (EET DST) Message-ID: <19970708210545.00117@hutcs.cs.hut.fi> Date: Tue, 8 Jul 1997 21:05:45 +0300 From: Antti-Pekka Liedes To: freebsd-smp@freebsd.org Subject: FreeBSD SMP on Soyo 5TH5? Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.73 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Has anyone got FreeBSD SMP to work on a Soyo 5TH5 board? I have one of these boards, equipped with two brand new pentiums (166 and 200MHz, currently running at only 100MHz), NCR SCSI-controller, SMC EtherPower 10/100, Matrox Millenium, and SB32 soundcard. I have tried several combinations of kernel options, each failing with quite a random looking results (the "best" result was to get both CPUs into the scheduler, but immediatly when the system began to run rc, I get a screen full of "I'm in cpu #1 and should be in #0" messages and panic). I'm not in FreeBSD right now, so I don't have dmesg or mptable output handy, but I can get those if needed to solve the problem. -- Antti-Pekka Liedes * apl@IRC apl@iki.fi * In two hells there's JMT 6 B 406 * apl@cs.hut.fi * one hell too many 02150 ESPOO * apl@apocalypse.tky.hut.fi * - Lucifer +358 - 9 - 468 3121 * +358 - 40 - 5873 593 * (in God's Army) From owner-freebsd-smp Tue Jul 8 11:40:22 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA01161 for smp-outgoing; Tue, 8 Jul 1997 11:40:22 -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 LAA01148 for ; Tue, 8 Jul 1997 11:40:10 -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 MAA24927; Tue, 8 Jul 1997 12:39:42 -0600 (MDT) Message-Id: <199707081839.MAA24927@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Antti-Pekka Liedes cc: freebsd-smp@FreeBSD.ORG Subject: Re: FreeBSD SMP on Soyo 5TH5? In-reply-to: Your message of "Tue, 08 Jul 1997 21:05:45 +0300." <19970708210545.00117@hutcs.cs.hut.fi> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 08 Jul 1997 12:39:41 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, > Has anyone got FreeBSD SMP to work on a Soyo 5TH5 board? I have one of > these boards, equipped with two brand new pentiums (166 and 200MHz, > currently running at only 100MHz), NCR SCSI-controller, SMC EtherPower why only 100? does the board show instability @ 166? --- > 10/100, Matrox Millenium, and SB32 soundcard. I have tried several > combinations of kernel options, each failing with quite a random looking > results (the "best" result was to get both CPUs into the scheduler, but > immediatly when the system began to run rc, I get a screen full of "I'm in > cpu #1 and should be in #0" messages and panic). I'm not in FreeBSD right > now, so I don't have dmesg or mptable output handy, but I can get those if > needed to solve the problem. We definately need both: do "mptable -dmesg > outfile" from a UP kernel. Do any messages PRECEED the "I'm in cpu #1 and should be in #0" messages? -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Tue Jul 8 12:24:30 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA03125 for smp-outgoing; Tue, 8 Jul 1997 12:24:30 -0700 (PDT) Received: from hutcs.cs.hut.fi (hutcs.cs.hut.fi [130.233.192.6]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA03114 for ; Tue, 8 Jul 1997 12:24:17 -0700 (PDT) Received: (from apl@localhost) by hutcs.cs.hut.fi (8.8.5/8.7.3) id WAA12888; Tue, 8 Jul 1997 22:24:05 +0300 (EET DST) Message-ID: <19970708222404.45819@hutcs.cs.hut.fi> Date: Tue, 8 Jul 1997 22:24:04 +0300 From: Antti-Pekka Liedes To: Steve Passe Cc: freebsd-smp@FreeBSD.ORG Subject: Re: FreeBSD SMP on Soyo 5TH5? References: <19970708210545.00117@hutcs.cs.hut.fi> <199707081839.MAA24927@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.73 In-Reply-To: <199707081839.MAA24927@Ilsa.StevesCafe.com>; from Steve Passe on Tue, Jul 08, 1997 at 12:39:41PM -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Tue, Jul 08, 1997 at 12:39:41PM -0600, Steve Passe wrote: > Hi, > > > Has anyone got FreeBSD SMP to work on a Soyo 5TH5 board? I have one of > > these boards, equipped with two brand new pentiums (166 and 200MHz, > > currently running at only 100MHz), NCR SCSI-controller, SMC EtherPower > > why only 100? does the board show instability @ 166? > No, I just had a 100MHz Pentium as one CPU earlier, and I just haven't configured the board for 166MHz yet. > --- > > 10/100, Matrox Millenium, and SB32 soundcard. I have tried several > > combinations of kernel options, each failing with quite a random looking > > results (the "best" result was to get both CPUs into the scheduler, but > > immediatly when the system began to run rc, I get a screen full of "I'm in > > cpu #1 and should be in #0" messages and panic). I'm not in FreeBSD right > > now, so I don't have dmesg or mptable output handy, but I can get those if > > needed to solve the problem. > > We definately need both: do "mptable -dmesg > outfile" from a UP kernel. > Do any messages PRECEED the "I'm in cpu #1 and should be in #0" messages? > I can't tell if anything preceeded the messages because they filled my screen way too fast. In the end there was a "timeout waiting for cpu #0" message, then failed disk sync and finally panic. Oh, I tried to change all IRQs to legacy ISA in BIOS, this produced different results: The kernel itself finished booting, in the end it said that both processors are in the scheduler. It did fscks from rc-files, but ifconfig caused a "page fault in kernel mode". Ok, I was using NT when I wrote my first mail, so I didn't have these, but here they are, I've tried exactly these kernel options as well as some other combinations, without much success. =============================================================================== MPTable, version 2.0.12 ------------------------------------------------------------------------------- MP Floating Pointer Structure: location: BIOS physical address: 0x000f0d20 signature: '_MP_' length: 16 bytes version: 1.1 checksum: 0x53 mode: Virtual Wire ------------------------------------------------------------------------------- MP Config Table Header: physical address: 0x000f0d34 signature: 'PCMP' base table length: 292 version: 1.1 checksum: 0xd5 OEM ID: 'OEM00000' Product ID: 'PROD00000000' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 28 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 0 0x11 BSP, usable 5 2 1 0x07bf 1 0x11 AP, usable 5 2 1 0x07bf -- Bus: Bus ID Type 0 ISA 1 PCI -- 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 0 0 2 0 INT conforms conforms 0 1 2 1 INT conforms conforms 0 0 2 2 INT conforms conforms 0 3 2 3 INT conforms conforms 0 4 2 4 INT conforms conforms 0 5 2 5 INT conforms conforms 0 6 2 6 INT conforms conforms 0 7 2 7 INT conforms conforms 0 8 2 8 INT conforms conforms 0 9 2 9 INT conforms conforms 0 10 2 10 INT conforms conforms 0 11 2 11 INT conforms conforms 0 12 2 12 INT conforms conforms 0 13 2 13 INT conforms conforms 0 14 2 14 INT conforms conforms 0 15 2 15 INT active-lo level 1 14:A 2 16 INT active-lo level 1 15:A 2 17 INT active-lo level 1 16:A 2 18 INT active-lo level 1 17:A 2 19 SMI conforms conforms 0 0 2 23 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT active-hi edge 0 0 255 0 NMI active-hi edge 0 0 255 1 ------------------------------------------------------------------------------- # SMP kernel config file options: # Required: options SMP # Symmetric MultiProcessor Kernel options APIC_IO # Symmetric (APIC) I/O # Useful: #options SMP_AUTOSTART # start the additional CPUs during boot # Optional (built-in defaults will work in most cases): #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 # 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-CURRENT #0: Tue Jul 8 16:28:11 EET DST 1997 apl@apocalypse.tky.hut.fi:/var/src/sys/compile/APOCALYPSE CPU: Pentium (99.65-MHz 586-class CPU) Origin = "GenuineIntel" Id = 0x52c Stepping=12 Features=0x3bf real memory = 67108864 (65536K bytes) Physical memory hole(s): avail memory = 63037440 (61560K bytes) DEVFS: ready for devices Probing for devices on PCI bus 0: chip0: rev 0x03 on pci0.0.0 chip1: rev 0x01 on pci0.7.0 chip2: rev 0x00 on pci0.7.1 vga0: rev 0x01 int a irq 9 on pci0.14.0 ncr0: rev 0x01 int a irq 9 on pci0.15.0 ncr0: waiting for scsi devices to settle scbus0 at ncr0 bus 0 scbus0 target 0 lun 0: 5.0 MB/s (200 ns, offset 8) sd0 at scbus0 target 0 lun 0 sd0: type 0 fixed SCSI 2 sd0: Direct-Access sd0: 10.0 MB/s (100 ns, offset 8) 522MB (1070496 512 byte sectors) sd1 at scbus0 target 5 lun 0 sd1: type 0 fixed SCSI 2 sd1: Direct-Access sd1: 10.0 MB/s (100 ns, offset 8) 3067MB (6281856 512 byte sectors) sd2 at scbus0 target 6 lun 0 sd2: type 0 fixed SCSI 2 sd2: Direct-Access sd2: 10.0 MB/s (100 ns, offset 8) 3067MB (6281856 512 byte sectors) de0: rev 0x20 int a irq 11 on pci0.17.0 de0: SMC 9334BDT 21140A [10-100Mb/s] pass 2.0 de0: address 00:00:c0:30:46:f9 Probing for devices on the ISA bus: sc0 at 0x60-0x6f irq 1 on motherboard sc0: VGA color <16 virtual consoles, flags=0x0> sio0 at 0x3f8-0x3ff irq 4 on isa sio0: type 16550A sio1 at 0x2f8-0x2ff irq 3 on isa sio1: type 16550A lpt0 at 0x378-0x37f irq 7 on isa lpt0: Interrupt-driven port lp0: TCP/IP capable interface psm0 at 0x60-0x64 irq 12 on motherboard psm0: device ID 0 fdc0 at 0x3f0-0x3f7 irq 6 drq 2 on isa fdc0: NEC 72065B fd0: 1.44MB 3.5in wdc0 at 0x1f0-0x1f7 irq 14 on isa wdc0: unit 1 (atapi): , removable, dma, iordy wcd0: 859/1375Kb/sec, 240Kb cache, audio play, 255 volume levels, ejectable tray wcd0: 120mm data disc loaded, unlocked sb0 at 0x220-0x22f irq 5 drq 1 on isa sb0: sbxvi0 at 0x220-0x22f irq 5 drq 5 on isa sbxvi0: sbmidi0 at 0x330-0x331 irq 5 on isa sbmidi0: npx0 on motherboard npx0: INT 16 interface DEVFS: ready to run ccd0-3: Concatenated disk drivers WARNING: / was not properly dismounted. de0: enabling 10baseT port =============================================================================== > -- > Steve Passe | powered by > smp@csn.net | Symmetric MultiProcessor FreeBSD > -- Antti-Pekka Liedes * apl@IRC apl@iki.fi * In two hells there's JMT 6 B 406 * apl@cs.hut.fi * one hell too many 02150 ESPOO * apl@apocalypse.tky.hut.fi * - Lucifer +358 - 9 - 468 3121 * +358 - 40 - 5873 593 * (in God's Army) From owner-freebsd-smp Wed Jul 9 08:21:30 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id IAA19177 for smp-outgoing; Wed, 9 Jul 1997 08:21:30 -0700 (PDT) Received: from hutcs.cs.hut.fi (hutcs.cs.hut.fi [130.233.192.6]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id IAA19167 for ; Wed, 9 Jul 1997 08:21:23 -0700 (PDT) Received: (from apl@localhost) by hutcs.cs.hut.fi (8.8.5/8.7.3) id SAA21073; Wed, 9 Jul 1997 18:21:21 +0300 (EET DST) Message-ID: <19970709182121.16683@hutcs.cs.hut.fi> Date: Wed, 9 Jul 1997 18:21:21 +0300 From: Antti-Pekka Liedes To: freebsd-smp@freebsd.org Subject: still problems with SMP, now with Tomcat III Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.73 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I changed my board from the Soyo 5TH5 to Tyan Tomcat IIID, but FreeBSD SMP kernel still fails. I tried my old SMP kernel and it produced a memory fault, page that's not present was tried to read in supervisor mode, process to cause this was ifconfig, again. I cvsup'd the very latest 3.0-current kernel, it caused the screen full of "I'm in cpu #1 and should be in #0" -errors, then "timeout waiting for cpu #0", and finally panic. My hardware includes the Tomcat motherboard, two brand new Pentium CPUs running at 166MHz, PCI cards Matrox Millenium, NCR SCSI-controller, and SMC EtherPower 10/100, and ISA PnP card Soundblaster 32. here's mptable -dmesg: =============================================================================== MPTable, version 2.0.12 ------------------------------------------------------------------------------- MP Floating Pointer Structure: location: BIOS physical address: 0x000fd320 signature: '_MP_' length: 16 bytes version: 1.1 checksum: 0x8d mode: Virtual Wire ------------------------------------------------------------------------------- MP Config Table Header: physical address: 0x000fd334 signature: 'PCMP' base table length: 228 version: 1.1 checksum: 0xeb OEM ID: 'OEM00000' Product ID: 'PROD00000000' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 20 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 0 0x11 BSP, usable 5 2 1 0x07bf 1 0x11 AP, usable 5 2 1 0x07bf -- Bus: Bus ID Type 0 ISA 1 PCI -- I/O APICs: APIC ID Version State Address 2 0x11 usable 0xfec00000 -- I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# INT conforms conforms 0 1 2 1 INT conforms conforms 0 0 2 2 INT conforms conforms 0 3 2 3 INT conforms conforms 0 4 2 4 INT conforms conforms 0 5 2 5 INT conforms conforms 0 6 2 6 INT conforms conforms 0 7 2 7 INT conforms conforms 0 8 2 8 INT conforms conforms 0 9 2 9 INT conforms conforms 0 10 2 10 INT conforms conforms 0 11 2 11 INT conforms conforms 0 12 2 12 INT conforms conforms 0 13 2 13 INT conforms conforms 0 14 2 14 INT conforms conforms 0 15 2 15 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ------------------------------------------------------------------------------- # SMP kernel config file options: # Required: options SMP # Symmetric MultiProcessor Kernel options APIC_IO # Symmetric (APIC) I/O # Useful: #options SMP_AUTOSTART # start the additional CPUs during boot # Optional (built-in defaults will work in most cases): #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 # 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-CURRENT #0: Sat Jul 5 19:55:23 EET DST 1997 zoot@apocalypse.tky.hut.fi:/var/src/sys/compile/APOCALYPSE CPU: Pentium (166.14-MHz 586-class CPU) Origin = "GenuineIntel" Id = 0x52c Stepping=12 Features=0x3bf real memory = 67108864 (65536K bytes) Physical memory hole(s): avail memory = 63045632 (61568K bytes) DEVFS: ready for devices Probing for devices on PCI bus 0: chip0: rev 0x03 on pci0.0.0 chip1: rev 0x01 on pci0.7.0 chip2: rev 0x00 on pci0.7.1 de0: rev 0x20 int a irq 9 on pci0.17.0 de0: SMC 9334BDT 21140A [10-100Mb/s] pass 2.0 de0: address 00:00:c0:30:46:f9 ncr0: rev 0x01 int a irq 9 on pci0.19.0 ncr0: waiting for scsi devices to settle scbus0 at ncr0 bus 0 scbus0 target 0 lun 0: 5.0 MB/s (200 ns, offset 8) sd0 at scbus0 target 0 lun 0 sd0: type 0 fixed SCSI 2 sd0: Direct-Access sd0: 10.0 MB/s (100 ns, offset 8) 522MB (1070496 512 byte sectors) sd1 at scbus0 target 5 lun 0 sd1: type 0 fixed SCSI 2 sd1: Direct-Access sd1: 10.0 MB/s (100 ns, offset 8) 3067MB (6281856 512 byte sectors) sd2 at scbus0 target 6 lun 0 sd2: type 0 fixed SCSI 2 sd2: Direct-Access sd2: 10.0 MB/s (100 ns, offset 8) 3067MB (6281856 512 byte sectors) vga0: rev 0x01 int a irq 11 on pci0.20.0 Probing for devices on the ISA bus: sc0 at 0x60-0x6f irq 1 on motherboard sc0: VGA color <16 virtual consoles, flags=0x0> sio0 at 0x3f8-0x3ff irq 4 on isa sio0: type 16550A sio1 at 0x2f8-0x2ff irq 3 on isa sio1: type 16550A lpt0 at 0x378-0x37f irq 7 on isa lpt0: Interrupt-driven port lp0: TCP/IP capable interface psm0 at 0x60-0x64 irq 12 on motherboard psm0: device ID 0 fdc0 at 0x3f0-0x3f7 irq 6 drq 2 on isa fdc0: NEC 72065B fd0: 1.44MB 3.5in wdc0 at 0x1f0-0x1f7 irq 14 on isa wdc0: unit 1 (atapi): , removable, dma, iordy wcd0: 859/1375Kb/sec, 240Kb cache, audio play, 255 volume levels, ejectable tray wcd0: 120mm data disc loaded, unlocked sb0 not found at 0x240 sbxvi0 not found sbmidi0 not found at 0x300 npx0 on motherboard npx0: INT 16 interface DEVFS: ready to run ccd0-3: Concatenated disk drivers de0: enabling 10baseT port =============================================================================== (oops, sb-devices aren't configured right in this kernel... they are correct in the SMP-kernels I've tried). -- Antti-Pekka Liedes * apl@IRC apl@iki.fi * In two hells there's JMT 6 B 406 * apl@cs.hut.fi * one hell too many 02150 ESPOO * apl@apocalypse.tky.hut.fi * - Lucifer +358 - 9 - 468 3121 * +358 - 40 - 5873 593 * (in God's Army) From owner-freebsd-smp Wed Jul 9 09:25:02 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id JAA22793 for smp-outgoing; Wed, 9 Jul 1997 09:25:02 -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 JAA22776 for ; Wed, 9 Jul 1997 09:24:50 -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 KAA29510; Wed, 9 Jul 1997 10:24:38 -0600 (MDT) Message-Id: <199707091624.KAA29510@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Antti-Pekka Liedes cc: freebsd-smp@FreeBSD.ORG Subject: Re: still problems with SMP, now with Tomcat III In-reply-to: Your message of "Wed, 09 Jul 1997 18:21:21 +0300." <19970709182121.16683@hutcs.cs.hut.fi> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 09 Jul 1997 10:24:37 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, >I changed my board from the Soyo 5TH5 to Tyan Tomcat IIID, but FreeBSD SMP >kernel still fails. I tried my old SMP kernel and it produced a memory >fault, page that's not present was tried to read in supervisor mode, >process to cause this was ifconfig, again. I cvsup'd the very latest >3.0-current kernel, it caused the screen full of "I'm in cpu #1 and should >be in #0" -errors, then "timeout waiting for cpu #0", and finally panic. try re-supping. I was checking in stuff yesterday, and lost network connectivity mid-stream, so there was a 5-6 hour timeslot where files were inconsistant. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Wed Jul 9 10:33:11 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA26447 for smp-outgoing; Wed, 9 Jul 1997 10:33:11 -0700 (PDT) Received: from hutcs.cs.hut.fi (hutcs.cs.hut.fi [130.233.192.6]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA26428 for ; Wed, 9 Jul 1997 10:32:56 -0700 (PDT) Received: (from apl@localhost) by hutcs.cs.hut.fi (8.8.5/8.7.3) id UAA22410; Wed, 9 Jul 1997 20:32:51 +0300 (EET DST) Message-ID: <19970709203250.19844@hutcs.cs.hut.fi> Date: Wed, 9 Jul 1997 20:32:50 +0300 From: Antti-Pekka Liedes To: Steve Passe Cc: freebsd-smp@FreeBSD.ORG Subject: Re: still problems with SMP, now with Tomcat III References: <19970709182121.16683@hutcs.cs.hut.fi> <199707091624.KAA29510@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.73 In-Reply-To: <199707091624.KAA29510@Ilsa.StevesCafe.com>; from Steve Passe on Wed, Jul 09, 1997 at 10:24:37AM -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Wed, Jul 09, 1997 at 10:24:37AM -0600, Steve Passe wrote: > Hi, > > >I changed my board from the Soyo 5TH5 to Tyan Tomcat IIID, but FreeBSD SMP > >kernel still fails. I tried my old SMP kernel and it produced a memory > >fault, page that's not present was tried to read in supervisor mode, > >process to cause this was ifconfig, again. I cvsup'd the very latest > >3.0-current kernel, it caused the screen full of "I'm in cpu #1 and should > >be in #0" -errors, then "timeout waiting for cpu #0", and finally panic. > > try re-supping. I was checking in stuff yesterday, and lost network > connectivity mid-stream, so there was a 5-6 hour timeslot where files were > inconsistant. > I just did a full cvsup, not a single file changed (except in ports). But FreeBSD SMP has been reported to work on Tomcat III, did someone break it or is it just me? I guess I'll remove the cards I can (SB32 and EtherPower) and try... > -- > Steve Passe | powered by > smp@csn.net | Symmetric MultiProcessor FreeBSD > -- Antti-Pekka Liedes * apl@IRC apl@iki.fi * In two hells there's JMT 6 B 406 * apl@cs.hut.fi * one hell too many 02150 ESPOO * apl@apocalypse.tky.hut.fi * - Lucifer +358 - 9 - 468 3121 * +358 - 40 - 5873 593 * (in God's Army) From owner-freebsd-smp Wed Jul 9 10:40:56 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA26845 for smp-outgoing; Wed, 9 Jul 1997 10:40:56 -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 KAA26836 for ; Wed, 9 Jul 1997 10:40:52 -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 LAA29844; Wed, 9 Jul 1997 11:40:29 -0600 (MDT) Message-Id: <199707091740.LAA29844@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Antti-Pekka Liedes cc: freebsd-smp@FreeBSD.ORG Subject: Re: still problems with SMP, now with Tomcat III In-reply-to: Your message of "Wed, 09 Jul 1997 20:32:50 +0300." <19970709203250.19844@hutcs.cs.hut.fi> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 09 Jul 1997 11:40:29 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, > > I just did a full cvsup, not a single file changed (except in ports). But > FreeBSD SMP has been reported to work on Tomcat III, did someone break it > or is it just me? I guess I'll remove the cards I can (SB32 and > EtherPower) and try... The general method is to remove every card you don't need for testing and boot a kernel built with SMP_GENERIC. No one with a tomcat III has reported problems recently... Another thing to try is resetting the BIOS settings to "SAFE" or whatever tyan calls the "conservative" defaults. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Wed Jul 9 10:53:07 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA27484 for smp-outgoing; Wed, 9 Jul 1997 10:53:07 -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 KAA27465 for ; Wed, 9 Jul 1997 10:52:43 -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 LAA29908; Wed, 9 Jul 1997 11:51:55 -0600 (MDT) Message-Id: <199707091751.LAA29908@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Antti-Pekka Liedes cc: freebsd-smp@FreeBSD.ORG Subject: Re: still problems with SMP, now with Tomcat III In-reply-to: Your message of "Wed, 09 Jul 1997 20:32:50 +0300." <19970709203250.19844@hutcs.cs.hut.fi> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 09 Jul 1997 11:51:54 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, I just compared your mptable output with that from a user reporting success, ie the one on the web page. There is a significant difference: yours: I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# INT conforms conforms 0 1 2 1 INT conforms conforms 0 0 2 2 INT conforms conforms 0 3 2 3 INT conforms conforms 0 4 2 4 INT conforms conforms 0 5 2 5 INT conforms conforms 0 6 2 6 INT conforms conforms 0 7 2 7 INT conforms conforms 0 8 2 8 INT conforms conforms 0 9 2 9 INT conforms conforms 0 10 2 10 INT conforms conforms 0 11 2 11 INT conforms conforms 0 12 2 12 INT conforms conforms 0 13 2 13 INT conforms conforms 0 14 2 14 INT conforms conforms 0 15 2 15 web page: I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT conforms conforms 0 0 2 0 ... INT active-lo level 1 20:A 2 16 INT active-lo level 1 19:A 2 17 INT active-lo level 1 18:A 2 18 INT active-lo level 1 17:A 2 19 SMI conforms conforms 0 0 2 23 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# ExtINT active-hi edge 0 0 255 0 NMI active-hi edge 0 0 255 1 ---- yours shows no sign of an APIC being available. Not only are the PCI entries NOT directed to APIC pins, but there are no SMI/ExtInt/NMI entries. I would look thru the BIOS for settings affecting the APIC, INTs, etc. Something along these lines is the cause of your trouble. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Wed Jul 9 13:06:56 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id NAA05035 for smp-outgoing; Wed, 9 Jul 1997 13:06:56 -0700 (PDT) Received: from hutcs.cs.hut.fi (hutcs.cs.hut.fi [130.233.192.6]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA05029 for ; Wed, 9 Jul 1997 13:06:51 -0700 (PDT) Received: (from apl@localhost) by hutcs.cs.hut.fi (8.8.5/8.7.3) id XAA23512; Wed, 9 Jul 1997 23:06:46 +0300 (EET DST) Message-ID: <19970709230646.19402@hutcs.cs.hut.fi> Date: Wed, 9 Jul 1997 23:06:46 +0300 From: Antti-Pekka Liedes To: Steve Passe Cc: freebsd-smp@FreeBSD.ORG Subject: Re: still problems with SMP, now with Tomcat III References: <19970709203250.19844@hutcs.cs.hut.fi> <199707091751.LAA29908@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.73 In-Reply-To: <199707091751.LAA29908@Ilsa.StevesCafe.com>; from Steve Passe on Wed, Jul 09, 1997 at 11:51:54AM -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Wed, Jul 09, 1997 at 11:51:54AM -0600, Steve Passe wrote: > Hi, > > I just compared your mptable output with that from a user reporting success, > ie the one on the web page. There is a significant difference: > [snap] > > ---- > yours shows no sign of an APIC being available. Not only are the PCI entries > NOT directed to APIC pins, but there are no SMI/ExtInt/NMI entries. > I would look thru the BIOS for settings affecting the APIC, INTs, etc. > Something along these lines is the cause of your trouble. > I didn't find anything in BIOS, however, my BIOS is quite old (07/14/96), because I need the NCR-support. Does anyone know how I could set up APIC? > -- > Steve Passe | powered by > smp@csn.net | Symmetric MultiProcessor FreeBSD > -- Antti-Pekka Liedes * apl@IRC apl@iki.fi * In two hells there's JMT 6 B 406 * apl@cs.hut.fi * one hell too many 02150 ESPOO * apl@apocalypse.tky.hut.fi * - Lucifer +358 - 9 - 468 3121 * +358 - 40 - 5873 593 * (in God's Army) From owner-freebsd-smp Wed Jul 9 20:59:04 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id UAA04772 for smp-outgoing; Wed, 9 Jul 1997 20:59:04 -0700 (PDT) Received: from icicle.winternet.com (adm@icicle.winternet.com [198.174.169.13]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id UAA04766 for ; Wed, 9 Jul 1997 20:59:00 -0700 (PDT) Received: (from adm@localhost) by icicle.winternet.com (8.7.5/8.7.5) id WAA16356 for ; Wed, 9 Jul 1997 22:58:42 -0500 (CDT) Posted-Date: Wed, 9 Jul 1997 22:58:42 -0500 (CDT) Received: from tundra.winternet.com(198.174.169.11) by icicle.winternet.com via smap (V2.0) id xma016044; Wed, 9 Jul 97 22:56:15 -0500 Received: from localhost (mestery@localhost) by tundra.winternet.com (8.8.4/8.8.4) with SMTP id WAA18551 for ; Wed, 9 Jul 1997 22:56:15 -0500 (CDT) X-Authentication-Warning: tundra.winternet.com: mestery owned process doing -bs Date: Wed, 9 Jul 1997 22:56:14 -0500 (CDT) From: Kyle Mestery To: smp@freebsd.org Subject: Question for SMP Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, I have been running SMP for about 1 month now, and I have a general question. I have noticed that certain programs, like mpg123 and netscape to be precise, only seem to run on CPU1 according to top. When I am in X, I have about 6 xterms open, netscape, and an mpg123 playing, and they both seem to stick to CPU1 while top moves between CPU0 and CPU1. Is this because CPU0 is the only one that can service interrupts? Or am I missing something? Kyle Mestery StorageTek's Network Systems Group 7600 Boone Ave. N., Brooklyn Park, MN 55428 mesteka@anubis.network.com, mestery@winternet.com From owner-freebsd-smp Thu Jul 10 05:02:34 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id FAA28507 for smp-outgoing; Thu, 10 Jul 1997 05:02:34 -0700 (PDT) Received: from hutcs.cs.hut.fi (hutcs.cs.hut.fi [130.233.192.6]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id FAA28502 for ; Thu, 10 Jul 1997 05:02:28 -0700 (PDT) Received: (from apl@localhost) by hutcs.cs.hut.fi (8.8.5/8.7.3) id PAA00289; Thu, 10 Jul 1997 15:02:26 +0300 (EET DST) Message-ID: <19970710150225.17993@hutcs.cs.hut.fi> Date: Thu, 10 Jul 1997 15:02:25 +0300 From: Antti-Pekka Liedes To: freebsd-smp@freebsd.org Subject: my bad (problems with Soyo 5TH5 and Tomcat III) Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.73 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Ok, my bad, didn't check my CPUs. They're both "VSU" meaning uniprocessor only :-/. -- Antti-Pekka Liedes * apl@IRC apl@iki.fi * In two hells there's JMT 6 B 406 * apl@cs.hut.fi * one hell too many 02150 ESPOO * apl@apocalypse.tky.hut.fi * - Lucifer +358 - 9 - 468 3121 * +358 - 40 - 5873 593 * (in God's Army) From owner-freebsd-smp Thu Jul 10 10:42:54 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA14308 for smp-outgoing; Thu, 10 Jul 1997 10:42:54 -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 KAA14299 for ; Thu, 10 Jul 1997 10:42:51 -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 LAA04203; Thu, 10 Jul 1997 11:42:42 -0600 (MDT) Message-Id: <199707101742.LAA04203@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Antti-Pekka Liedes cc: freebsd-smp@FreeBSD.ORG Subject: Re: my bad (problems with Soyo 5TH5 and Tomcat III) In-reply-to: Your message of "Thu, 10 Jul 1997 15:02:25 +0300." <19970710150225.17993@hutcs.cs.hut.fi> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Thu, 10 Jul 1997 11:42:41 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, > > Ok, my bad, didn't check my CPUs. They're both "VSU" meaning uniprocessor > only :-/. well, thats good news for me, I'm closing out this error report. thanx for letting us know, many people would have just quietly went away, leaving us thinking we have a problem of some sort... -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Thu Jul 10 10:50:27 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA14680 for smp-outgoing; Thu, 10 Jul 1997 10:50:27 -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 KAA14675 for ; Thu, 10 Jul 1997 10:50:25 -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 LAA04254; Thu, 10 Jul 1997 11:50:13 -0600 (MDT) Message-Id: <199707101750.LAA04254@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: Kyle Mestery cc: smp@FreeBSD.ORG Subject: Re: Question for SMP In-reply-to: Your message of "Wed, 09 Jul 1997 22:56:14 CDT." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Thu, 10 Jul 1997 11:50:13 -0600 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, > Hi, I have been running SMP for about 1 month now, and I have a general > question. I have noticed that certain programs, like mpg123 and netscape > to be precise, only seem to run on CPU1 according to top. When I am in X, > I have about 6 xterms open, netscape, and an mpg123 playing, and they both > seem to stick to CPU1 while top moves between CPU0 and CPU1. Is this > because CPU0 is the only one that can service interrupts? Or am I missing > something? I just discovered that CPU0 was the only on handling "mixed-mode" INTs, ie those from the timer when redirected by "options SMP_TIMER_NC", but otherwise they are handled by both CPUs. I just observed top with netscape running, it mostly uses CPU1, but sometimes uses CPU0. There may be some pattern where INTs are first sent to CPU0 if available, that stuff still needs alot of work. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD From owner-freebsd-smp Sat Jul 12 15:28:14 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id PAA22738 for smp-outgoing; Sat, 12 Jul 1997 15:28:14 -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 PAA22732 for ; Sat, 12 Jul 1997 15:28:10 -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 QAA16759 for ; Sat, 12 Jul 1997 16:28:08 -0600 (MDT) Message-Id: <199707122228.QAA16759@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0gamma 1/27/96 From: Steve Passe To: smp@freebsd.org Subject: APIC saga continues Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 12 Jul 1997 16:28:08 -0600 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, I have been beating my head on the wall the last 2 weeks trying to get APICs working for syncing CPUs. I think I finally see light at the end of the tunnel. But getting there I discovered more ugly 'features' of the APIC. Till now we have been using "mixed mode programming" where the 8259 PIC's INT output is routed thru the APIC and handled as an 'ExtInt' on those machines that don't route the 8254 to the APIC. This includes both machines that require "options SMP_TIMER_NC" and those which lack a line like: I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT# INT conforms conforms 0 0 2 2 in their mptable. It turns out that when you do this the 8254 timer INTs (or any INT from the 8259) are NOT reflected in the APIC IRR/ISR registers, and CANNOT be masked via the APIC TPR register/process priority scheme. This is unacceptable as we need this facility to direct INTs to those CPUs capable of handling them (and avoiding those that can't). As an example, when a CPU is blocked on a lock when in an INTerrupt routine, the IE flag is clear (INTs masked) so the CPU can't receive Xinvltlb and other important IPIs. By setting its TPR to a level that blocks hardware INTs, but allows IPIs, and then doing an STI, it can then receive the IPIs while ignoring the hardware INTs. BUT this all falls apart for the reasons described above concerning the failire of ExtInts to be restricted by IRR/ISR bits. --- Intel has a solution in: Intel486(TM) MicroProcessors and related Products, order #241731-002 pp 4-220 thru 4-302: 82489DX Advanced Programmable Interrupt Controller specifically see page 4-292: 824889DX/8259A DUAL MODE CONNECTION their solution for truly symmetric IO in this situation is: - program the 8259 to pass ONLY the DMA chaining INT - program the IO APIC to handle this as a regular (ie not 'ExtInt') input - abandon the 8254 timer, instead using the APIC's internal timer. --- When you abandon the 'ExtInt' mode, you cannot handle more than i 8259 INT as it no longer provides the vector, the APIC does. I believe that we don't want to abandon the 8254, but instead should abandon the DMA chaining INTs (who uses these anyways???) Then we can program in a similar way, but instead pass the 8254 INT thru as a regular INT. I have written test code that does this, and it seems to run nicely. I specifically trapped on the first timer INT and showed thru inspection of the APIC ISRs that the old 'ExtInt' method does indeed bypass the ISR bits, and that the Intel recommended 'non-ExtInt' method sets the ISR bit properly. SO I have alot of work ahead of me getting all my experiments cleaned up and into the main code tree, and the CPU sync code that I started 2 weeks ago in working shape now that I know what was biting me. But in the meantime we need to make a policy decision as to whether we can say bye-bye to the DMA chaining INTs. If I don't get thoughtful feedback on this I will just nmake an arbitrary desision (which I suspect to be axing the DMA INTs). I think the only situation needing them is non-busmaster EISA hardware that does DMA via the motherboard chipset DMA registers. Please correct me if I am wrong on this point. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD