From owner-freebsd-smp Sun Sep 20 01:53:20 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id BAA12114 for freebsd-smp-outgoing; Sun, 20 Sep 1998 01:53:20 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from spinner.netplex.com.au (spinner.netplex.com.au [202.12.86.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id BAA12107 for ; Sun, 20 Sep 1998 01:53:16 -0700 (PDT) (envelope-from peter@netplex.com.au) Received: from spinner.netplex.com.au (localhost [127.0.0.1]) by spinner.netplex.com.au (8.8.8/8.8.8/Spinner) with ESMTP id QAA05006; Sun, 20 Sep 1998 16:51:43 +0800 (WST) (envelope-from peter@spinner.netplex.com.au) Message-Id: <199809200851.QAA05006@spinner.netplex.com.au> X-Mailer: exmh version 2.0.2 2/24/98 To: John Hay cc: smp@FreeBSD.ORG Subject: Re: Only 50% idle with current -current? In-reply-to: Your message of "Sat, 19 Sep 1998 14:14:13 +0200." <199809191214.OAA25265@zibbi.mikom.csir.co.za> Date: Sun, 20 Sep 1998 16:51:41 +0800 From: Peter Wemm Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org John Hay wrote: > Hi, > > I have updated our one SMP box to the latest -current and now I see on top > that it doesn't go below 50% idle anymore. I'm doing a make release and > for a while ran two rc5's, but it still stayed at 50% idle. I remember > someone else also noticed it a few days ago. > > Anyone have any ideas? Yes, just try booting "-s" and go into single user mode to start with. Give a few commands, eg: 'sync; sync; sync', do a fsck if it's needed and then start multiuser.. If it then works as expected, then I suspect you are seeing a manifestation of a long running problem. I've found that SMP and/or ELF are unhappy at boot under SMP (and have been for 12 months). If I have /usr/libexec/getty dynamically linked and have more than a couple enabled in ttys, I get a lockup. The same happens if running rc5des/rc564 from the rc scripts if I don't go into single user and run a few commands first. At the time I hacked init(8) to do a couple of fork/exec's at startup and the problem went away. I don't understand what's going on and spent a fair while last year trying to figure it out. I'm pretty sure it's not ELF itself, it's just triggering something else. > John > -- > John Hay -- John.Hay@mikom.csir.co.za > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-smp" in the body of the message > Cheers, -Peter To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun Sep 20 13:19:57 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id NAA29709 for freebsd-smp-outgoing; Sun, 20 Sep 1998 13:19:57 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from mh2.cts.com (mh2.cts.com [209.68.192.68]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id NAA29703 for ; Sun, 20 Sep 1998 13:19:56 -0700 (PDT) (envelope-from panic@antix.org) Received: from antimatter (antimatter.cts.com [205.163.23.186]) by mh2.cts.com (8.8.7/8.8.5) with SMTP id NAA10696 for ; Sun, 20 Sep 1998 13:19:29 -0700 (PDT) Message-Id: <3.0.3.32.19980920131928.00bb9570@satan.antix.org> X-Sender: panic@satan.antix.org X-Mailer: QUALCOMM Windows Eudora Pro Version 3.0.3 (32) Date: Sun, 20 Sep 1998 13:19:28 -0700 To: freebsd-smp@FreeBSD.ORG From: Jason Beazell Subject: smp ?? Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 8bit X-MIME-Autoconverted: from quoted-printable to 8bit by hub.freebsd.org id NAA29704 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org What versions of Freebsd support smp? A friend of mine, and Freebsd user, tells me that there is a patch for 2.2.7, but I can't find it anywhere. Thanks, -Jason [TR] Col. Panic The /-----\   |----\ |      |    | Founder |      |----/ Webmaster |ech's |   \ evenge Postmaster Hostmaster "Out you demons of Stupidity!" http://www.antix.org quake.antix.org:27910 PureDM Mod quake.antix.org:27555 RA 2 quake.antix.org:27666 CTC To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun Sep 20 15:22:30 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id PAA21475 for freebsd-smp-outgoing; Sun, 20 Sep 1998 15:22:30 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from smtp04.primenet.com (smtp04.primenet.com [206.165.6.134]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id PAA21407 for ; Sun, 20 Sep 1998 15:22:13 -0700 (PDT) (envelope-from tlambert@usr04.primenet.com) Received: (from daemon@localhost) by smtp04.primenet.com (8.8.8/8.8.8) id PAA11103; Sun, 20 Sep 1998 15:21:44 -0700 (MST) Received: from usr04.primenet.com(206.165.6.204) via SMTP by smtp04.primenet.com, id smtpd011043; Sun Sep 20 15:21:41 1998 Received: (from tlambert@localhost) by usr04.primenet.com (8.8.5/8.8.5) id PAA03897; Sun, 20 Sep 1998 15:21:39 -0700 (MST) From: Terry Lambert Message-Id: <199809202221.PAA03897@usr04.primenet.com> Subject: Re: smp ?? To: panic@antix.org (Jason Beazell) Date: Sun, 20 Sep 1998 22:21:39 +0000 (GMT) Cc: freebsd-smp@FreeBSD.ORG In-Reply-To: <3.0.3.32.19980920131928.00bb9570@satan.antix.org> from "Jason Beazell" at Sep 20, 98 01:19:28 pm X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > What versions of Freebsd support smp? A friend of mine, and Freebsd user, > tells me that there is a patch for 2.2.7, but I can't find it anywhere. The initial work on SMP was done by Jack Vogel, of Sun Microsystems, who also did a SPARC port ofr FreeBSD 1.1.5. There is a patch available for 2.2.x-current, checked out as of 00:00 GMT 27 October 1995. I put some effort into updating this code to make it work with 2.2.x-current as of 21:06 06 June 1996, and it was the basis for the code that Peter Wemm and Steve Passe made work, and from which the current SMP code is derived. There is no intention to back-port the updated code to -stable; it could be done in perhaps 40 hours, but would require a good working knowledge of locor.s, the Intel 1.4 SMP specification, and (IMO) "vi' wiring in your medula oblogata to achive in that time frame. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun Sep 20 18:05:56 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id SAA19414 for freebsd-smp-outgoing; Sun, 20 Sep 1998 18:05:56 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from federation.addy.com (federation.addy.com [207.239.68.2]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id SAA19379 for ; Sun, 20 Sep 1998 18:05:44 -0700 (PDT) (envelope-from francisco@natserv.com) Received: from quisqueya.natserv.com (slip129-37-113-15.ny.us.ibm.net [129.37.113.15]) by federation.addy.com (8.8.5/8.6.12) with ESMTP id VAA15938; Sun, 20 Sep 1998 21:05:07 -0400 (EDT) Message-Id: <199809210105.VAA15938@federation.addy.com> X-Mailer: XFMail 1.3 [p0] on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <199809202221.PAA03897@usr04.primenet.com> Date: Sun, 20 Sep 1998 21:05:20 -0000 (GMT) Reply-To: francisco@natserv.com From: Francisco Reyes To: freebsd-smp@FreeBSD.ORG Subject: Re: smp ?? Cc: (Jason Beazell) Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >>Jason Beazell >> What versions of Freebsd support smp? A friend of mine, and Freebsd >> user, tells me that there is a patch for 2.2.7, but I can't find it > I put some effort into updating this code to make it work with > 2.2.x-current as of 21:06 06 June 1996, and it was the basis > for the code that Peter Wemm and Steve Passe made work, and > from which the current SMP code is derived. >Terry Lambert Jason, To add to what Terry wrote, FreeBSD 3.0 and forward will have SMP (or at least that is what I gather from all the posts). If you are just starting with FreeBSD use what you have till October when the first release of 3.X will be out. Then again maybe you like to hack and want to try to spend the estimated 40 hours to get it running on stable. :-) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun Sep 20 20:18:53 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id UAA10623 for freebsd-smp-outgoing; Sun, 20 Sep 1998 20:18:53 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from host.phc.igs.net (host.phc.igs.net [207.210.17.2]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id UAA10606 for ; Sun, 20 Sep 1998 20:18:32 -0700 (PDT) (envelope-from eagle@phc.igs.net) Received: from aa (st27.phc.igs.net [207.210.17.78]) by host.phc.igs.net (8.8.5/8.8.5) with SMTP id XAA09638 for ; Sun, 20 Sep 1998 23:23:42 -0400 (EDT) Date: Sun, 20 Sep 1998 23:23:42 -0400 (EDT) From: eagle Message-Id: <199809210323.XAA09638@host.phc.igs.net> To: undisclosed-recipients:; Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Sep 21 04:57:57 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id EAA23414 for freebsd-smp-outgoing; Mon, 21 Sep 1998 04:57:57 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from sunny.bahnhof.se (sunny.bahnhof.se [193.44.91.1]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id EAA23398; Mon, 21 Sep 1998 04:57:53 -0700 (PDT) (envelope-from chris@bahnhof.se) Received: from metro (metro.bahnhof.se [193.44.91.2]) by sunny.bahnhof.se (8.8.8+Sun/8.8.8) with SMTP id NAA16988; Mon, 21 Sep 1998 13:56:31 +0200 (MET DST) Date: Mon, 21 Sep 1998 13:56:59 +0200 (MET DST) From: Christopher Arnold X-Sender: chris@metro To: Terry Lambert cc: Jason Beazell , freebsd-smp@FreeBSD.ORG, freebsd-sparc@FreeBSD.ORG Subject: Re: smp ?? In-Reply-To: <199809202221.PAA03897@usr04.primenet.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sun, 20 Sep 1998, Terry Lambert wrote: > > What versions of Freebsd support smp? A friend of mine, and Freebsd user, > > tells me that there is a patch for 2.2.7, but I can't find it anywhere. > > The initial work on SMP was done by Jack Vogel, of Sun Microsystems, > who also did a SPARC port ofr FreeBSD 1.1.5. > Does this mean that we have an FreeBSD 1.1.5 that would boot on sparc? I guess this would contain usefull information about how to bootstrap an effort on getting an later version of FreeBSD running on SPARC. Does anyone have more info about the 1.1.5 SPARC port? /chris To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Sep 21 06:01:21 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id GAA02234 for freebsd-smp-outgoing; Mon, 21 Sep 1998 06:01:21 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from trinity.radio-do.de (trinity.Radio-do.de [193.101.164.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id GAA02215; Mon, 21 Sep 1998 06:01:14 -0700 (PDT) (envelope-from fn@trinity.radio-do.de) Received: (from fn@localhost) by trinity.radio-do.de (8.9.1/8.8.5/RADIO-1.1) id PAA00327; Mon, 21 Sep 1998 15:00:47 +0200 (CEST) Message-ID: <19980921150047.A315@radio-do.de> Date: Mon, 21 Sep 1998 15:00:47 +0200 From: Frank Nobis To: freebsd-smp@FreeBSD.ORG Cc: freebsd-current@FreeBSD.ORG Subject: Weired top display at smp current kernel from today Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Running a mkae world -j4 I noticed only 50% idle time during the make. Running just two programs whit a busy loop gives that output fron top last pid: 314; load averages: 1.84, 0.75, 0.30 14:55:17 45 processes: 3 running, 42 sleeping CPU states: 50.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 50.0% idle Mem: 7080K Active, 6332K Inact, 16M Wired, 100K Cache, 3457K Buf, 473M Free Swap: 199M Total, 199M Free PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND 308 fn 90 0 748K 236K RUN 1 1:36 50.00% 49.97% pig 310 fn 91 0 748K 236K RUN 1 0:57 49.18% 49.02% pig 311 fn 28 0 1568K 908K CPU1 1 0:00 0.00% 0.00% top Is this a bug in top? Can someone reproduce that? pig is simply 'for(;;) i++;' Regards Frank -- Frank Nobis Email: PGP AVAILABLE Landgrafenstr. 130 dg3dcn http://www.radio-do.de/~fn/ 44139 Dortmund Powered by FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Sep 21 07:19:03 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id HAA16696 for freebsd-smp-outgoing; Mon, 21 Sep 1998 07:19:03 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from door.barclayscapital.com (door.barclayscapital.com [194.205.158.2]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id HAA16684 for ; Mon, 21 Sep 1998 07:19:00 -0700 (PDT) (envelope-from Pierre.Dampure@barclayscapital.com) From: Pierre.Dampure@barclayscapital.com Received: (from mailman@localhost) by door.barclayscapital.com (8.8.8/8.8.7) id PAA08801 for ; Mon, 21 Sep 1998 15:16:29 +0100 (BST) Received: from gate.barclayscapital.net(194.205.158.68) by door.bzw.com via smap (V2.0) id xma008762; Mon, 21 Sep 98 15:16:19 +0100 Received: (from nobody@localhost) by gate.bzw.com (8.8.7/8.8.7) id PAA27605 for ; Mon, 21 Sep 1998 15:18:20 +0100 (BST) Received: from fwgw01-dmz(194.205.158.129) by gate.bzw.com via smap (V2.0) id xma027593; Mon, 21 Sep 98 15:18:19 +0100 Received: (from nobody@localhost) by fwgw01.ldn.bzwint.com (8.8.7/8.8.7) id PAA23910 for ; Mon, 21 Sep 1998 15:18:19 +0100 (BST) Received: from oplss0001.itops.ldn.bzwint.com(30.75.1.4) by fwgw01.ldn.bzwint.com via smap (V2.0) id xma023896; Mon, 21 Sep 98 15:18:17 +0100 Received: from nmb01gw01 (smtphost.ldn.bzwint.com [30.10.1.10]) by oplss0001.itops.ldn.bzwint.com (8.8.7/8.8.6) with SMTP id PAA03785 for ; Mon, 21 Sep 1998 15:16:59 +0100 (BST) Received: from EXMSMCON02.fmcs.ldn.bzwint.com (EXMSMCON02.fmcs.ldn.bzwint.com [30.81.1.2]) by nmb01gw01 (NTMail 3.02.13) with ESMTP id ua586762 for ; Mon, 21 Sep 1998 15:11:27 +0100 Received: from exintgw02.itops.ldn.bzwint.com (unverified [30.45.1.87]) by exmsmcon02 (Integralis SMTPRS 2.0.15) with ESMTP id ; Mon, 21 Sep 1998 15:06:59 +0100 Received: by exintgw02.itops.ldn.bzwint.com with Internet Mail Service (5.0.1460.8) id ; Mon, 21 Sep 1998 15:08:15 +0100 Message-Id: <711DCB8FB391D111B9DD00805F8BDDBAF7ED39@exips0019.itops.ldn.bzwint.com> To: fn@radio-do.de, freebsd-smp@FreeBSD.ORG Cc: freebsd-current@FreeBSD.ORG Subject: RE: Weired top display at smp current kernel from today Date: Mon, 21 Sep 1998 15:07:55 +0100 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.0.1460.8) Content-Type: text/plain Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Frank, Are you by any chance running an ELF version of X? I experienced pretty weird results over the past few days with and ELF X (built as per the port mods posted to the list): a make world running under X would basically bring the box to a halt, massive delays when typing characters on any of the other VTs, etc... this is on a box with 384Mb RAM, SMP w/PPro 200/512 and more than 256Mb free / no swap used, doing nothing else than the build. I'll be rebuilding the box tonight and verify whether this is still happening now that we have "official" XFree86 port mods. Best Regards, PY -----Original Message----- From: Frank Nobis [mailto:fn@radio-do.de] Sent: Monday, September 21, 1998 2:01 PM To: freebsd-smp@FreeBSD.ORG Cc: freebsd-current@FreeBSD.ORG Subject: Weired top display at smp current kernel from today Running a mkae world -j4 I noticed only 50% idle time during the make. Running just two programs whit a busy loop gives that output fron top last pid: 314; load averages: 1.84, 0.75, 0.30 14:55:17 45 processes: 3 running, 42 sleeping CPU states: 50.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 50.0% idle Mem: 7080K Active, 6332K Inact, 16M Wired, 100K Cache, 3457K Buf, 473M Free Swap: 199M Total, 199M Free PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND 308 fn 90 0 748K 236K RUN 1 1:36 50.00% 49.97% pig 310 fn 91 0 748K 236K RUN 1 0:57 49.18% 49.02% pig 311 fn 28 0 1568K 908K CPU1 1 0:00 0.00% 0.00% top Is this a bug in top? Can someone reproduce that? pig is simply 'for(;;) i++;' Regards Frank -- Frank Nobis Email: PGP AVAILABLE Landgrafenstr. 130 dg3dcn http://www.radio-do.de/~fn/ 44139 Dortmund Powered by FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message -------------------------------------------------------------------------------------- Internet communications are not secure and therefore the Barclays Group does not accept legal responsibility for the contents of this message. Any views or opinions presented are solely those of the author and do not necessarily represent those of the Barclays Group unless otherwise specifically stated. -------------------------------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Sep 21 08:34:52 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id IAA29730 for freebsd-smp-outgoing; Mon, 21 Sep 1998 08:34:52 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id IAA29691; Mon, 21 Sep 1998 08:34:35 -0700 (PDT) (envelope-from fbsd@Ilsa.StevesCafe.com) Received: from Ilsa.StevesCafe.com (localhost.StevesCafe.com [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.8/8.8.5) with ESMTP id JAA09435; Mon, 21 Sep 1998 09:30:29 -0600 (MDT) Message-Id: <199809211530.JAA09435@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0.2 2/24/98 From: Steve Passe To: Frank Nobis cc: freebsd-smp@FreeBSD.ORG, freebsd-current@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today In-reply-to: Your message of "Mon, 21 Sep 1998 15:00:47 +0200." <19980921150047.A315@radio-do.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 21 Sep 1998 09:30:29 -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hi, > Running a mkae world -j4 I noticed only 50% idle time during the make. > > Running just two programs whit a busy loop gives that output fron top > ... > Is this a bug in top? Can someone reproduce that? > > pig is simply 'for(;;) i++;' > --- idle system: last pid: 22688; load averages: 1.72, 1.18, 0.58 09:28:19 27 processes: 1 running, 26 sleeping CPU states: 0.2% user, 0.0% nice, 0.0% system, 0.0% interrupt, 99.8% idle Mem: 17M Active, 20M Inact, 50M Wired, 236M Cache, 7916K Buf, 180M Free Swap: 300M Total, 300M Free PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND 22688 root 28 0 1560K 892K CPU1 0 0:00 0.15% 0.04% top --- running two copies of pig: last pid: 22687; load averages: 1.30, 0.60, 0.27 09:25:16 29 processes: 3 running, 26 sleeping CPU states: 99.8% user, 0.0% nice, 0.2% system, 0.0% interrupt, 0.0% idle Mem: 18M Active, 20M Inact, 50M Wired, 236M Cache, 7916K Buf, 180M Free Swap: 300M Total, 300M Free PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND 22682 root 105 0 748K 240K RUN 0 0:48 99.32% 90.33% pig 22683 root 105 0 748K 240K CPU1 1 0:46 99.39% 89.45% pig --- This is with a system cvsup'ed midday yesterday. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Sep 21 10:40:21 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id KAA22445 for freebsd-smp-outgoing; Mon, 21 Sep 1998 10:40:21 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from trinity.radio-do.de (trinity.Radio-do.de [193.101.164.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id KAA22287; Mon, 21 Sep 1998 10:39:34 -0700 (PDT) (envelope-from fn@trinity.radio-do.de) Received: (from fn@localhost) by trinity.radio-do.de (8.9.1/8.8.5/RADIO-1.1) id TAA00607; Mon, 21 Sep 1998 19:39:02 +0200 (CEST) Message-ID: <19980921193902.A595@radio-do.de> Date: Mon, 21 Sep 1998 19:39:02 +0200 From: Frank Nobis To: Pierre.Dampure@barclayscapital.com, freebsd-smp@FreeBSD.ORG Cc: freebsd-current@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today References: <711DCB8FB391D111B9DD00805F8BDDBAF7ED39@exips0019.itops.ldn.bzwint.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i In-Reply-To: <711DCB8FB391D111B9DD00805F8BDDBAF7ED39@exips0019.itops.ldn.bzwint.com>; from Pierre.Dampure@barclayscapital.com on Mon, Sep 21, 1998 at 03:07:55PM +0100 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Mon, Sep 21, 1998 at 03:07:55PM +0100, Pierre.Dampure@barclayscapital.com wrote: > > Frank, > > Are you by any chance running an ELF version of X? I experienced pretty > weird results over the past few days with and ELF X (built as per the port > mods posted to the list): a make world running under X would basically bring > the box to a halt, massive delays when typing characters on any of the other > VTs, etc... this is on a box with 384Mb RAM, SMP w/PPro 200/512 and more > than 256Mb free / no swap used, doing nothing else than the build. I build an elf X11, but when doing my test the X server was not running. With X11 running I noticed small delays, but nothing really serious to worry about. The system I use has two 400Mhz PII with 512Mb physical RAM on an ASUS P2B-DS board. > I'll be rebuilding the box tonight and verify whether this is still > happening now that we have "official" XFree86 port mods. I will try this evening, too :-) -fn- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Sep 21 15:15:33 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id PAA24012 for freebsd-smp-outgoing; Mon, 21 Sep 1998 15:15:33 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from smtp04.primenet.com (smtp04.primenet.com [206.165.6.134]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id PAA23878; Mon, 21 Sep 1998 15:15:03 -0700 (PDT) (envelope-from tlambert@usr04.primenet.com) Received: (from daemon@localhost) by smtp04.primenet.com (8.8.8/8.8.8) id PAA24396; Mon, 21 Sep 1998 15:14:30 -0700 (MST) Received: from usr04.primenet.com(206.165.6.204) via SMTP by smtp04.primenet.com, id smtpd024290; Mon Sep 21 15:14:18 1998 Received: (from tlambert@localhost) by usr04.primenet.com (8.8.5/8.8.5) id PAA18188; Mon, 21 Sep 1998 15:14:14 -0700 (MST) From: Terry Lambert Message-Id: <199809212214.PAA18188@usr04.primenet.com> Subject: Re: smp ?? To: chris@bahnhof.se (Christopher Arnold) Date: Mon, 21 Sep 1998 22:14:14 +0000 (GMT) Cc: tlambert@primenet.com, panic@antix.org, freebsd-smp@FreeBSD.ORG, freebsd-sparc@FreeBSD.ORG In-Reply-To: from "Christopher Arnold" at Sep 21, 98 01:56:59 pm X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > > > What versions of Freebsd support smp? A friend of mine, and Freebsd user, > > > tells me that there is a patch for 2.2.7, but I can't find it anywhere. > > > > The initial work on SMP was done by Jack Vogel, of Sun Microsystems, > > who also did a SPARC port ofr FreeBSD 1.1.5. > > Does this mean that we have an FreeBSD 1.1.5 that would boot on sparc? It means Jack Vogel has a 1.1.5 that would boot on a SPARC. It was never committed to the FreeBSD repository, only partly because of the BSDI troubles that rendered 1.1.5 subject to controversy with USL. Part of it was also source tree organization changes that FreeBSD was unwilling to make at the time, to accommodate multiple architectures. > I guess this would contain usefull information about how to bootstrap an > effort on getting an later version of FreeBSD running on SPARC. You would be better of starting with NetBSD or OpenBSD at this time; the source code is closer to FreeBSD. > Does anyone have more info about the 1.1.5 SPARC port? You could always contact Jack directly. His email address is in the -hackers list archives; all you have to do is search for it. I expect that after the loaner SMP box that he had used for development was "repossesed", he gained a dislike for the FreeBSD community. 8-(. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Sep 21 23:15:47 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id XAA28483 for freebsd-smp-outgoing; Mon, 21 Sep 1998 23:15:47 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from host.phc.igs.net (host.phc.igs.net [207.210.17.2]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id XAA28464 for ; Mon, 21 Sep 1998 23:15:44 -0700 (PDT) (envelope-from eagle@phc.igs.net) Received: from aa (st01.phc.igs.net [207.210.17.52]) by host.phc.igs.net (8.8.5/8.8.5) with SMTP id CAA09169 for ; Tue, 22 Sep 1998 02:21:13 -0400 (EDT) Date: Tue, 22 Sep 1998 02:21:13 -0400 (EDT) From: eagle Message-Id: <199809220621.CAA09169@host.phc.igs.net> To: undisclosed-recipients:; Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Sep 22 00:36:35 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id AAA09822 for freebsd-smp-outgoing; Tue, 22 Sep 1998 00:36:35 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from trinity.radio-do.de (trinity.Radio-do.de [193.101.164.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id AAA09718; Tue, 22 Sep 1998 00:36:17 -0700 (PDT) (envelope-from fn@trinity.radio-do.de) Received: (from fn@localhost) by trinity.radio-do.de (8.9.1/8.8.5/RADIO-1.1) id JAA12524; Tue, 22 Sep 1998 09:35:51 +0200 (CEST) To: Pierre.Dampure@barclayscapital.com Cc: freebsd-smp@FreeBSD.ORG, freebsd-current@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today References: <711DCB8FB391D111B9DD00805F8BDDBAF7ED39@exips0019.itops.ldn.bzwint.com> <19980921193902.A595@radio-do.de> From: Frank Nobis Date: 22 Sep 1998 09:35:51 +0200 In-Reply-To: Frank Nobis's message of "Mon, 21 Sep 1998 19:39:02 +0200" Message-ID: Lines: 28 X-Mailer: Gnus v5.6.26/XEmacs 20.4 - "Emerald" Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org This is really strange. I did the last test in the afternoon, remote from work. I booted the maschine remote and did the test again. After some time - arounf one hour - I noticed that both pig processes are running at 50% cpu, but now th idle level was 0% and init was running on the other cpu with 100%. I stopped the pig's then and rebooted again when coming home. With the latest sources - cvsuped at midnight - but the same kernel, I did a make world and the strange top behaviour had just vanished. I have no idea why. su-2.01# time make -j4 buildworld>xxx real 43m47.956s user 38m5.671s sys 23m32.869s The "bad" make before took around 63 minutes. That seems to proof that before not both cpu's was full runnning. Regards Frank -- Frank Nobis Email: PGP AVAILABLE Landgrafenstr. 130 dg3dcn http://www.radio-do.de/~fn/ 44139 Dortmund Powered by SMP FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Sep 22 02:14:07 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id CAA23414 for freebsd-smp-outgoing; Tue, 22 Sep 1998 02:14:07 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from nlsystems.com (nlsys.demon.co.uk [158.152.125.33]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id CAA23290; Tue, 22 Sep 1998 02:13:37 -0700 (PDT) (envelope-from dfr@nlsystems.com) Received: from herring.nlsystems.com (herring.nlsystems.com [10.0.0.2]) by nlsystems.com (8.9.1/8.8.5) with SMTP id KAA10985; Tue, 22 Sep 1998 10:09:09 +0100 (BST) Date: Tue, 22 Sep 1998 10:09:09 +0100 (BST) From: Doug Rabson To: Pierre.Dampure@barclayscapital.com cc: fn@radio-do.de, freebsd-smp@FreeBSD.ORG, freebsd-current@FreeBSD.ORG Subject: RE: Weired top display at smp current kernel from today In-Reply-To: <711DCB8FB391D111B9DD00805F8BDDBAF7ED39@exips0019.itops.ldn.bzwint.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Mon, 21 Sep 1998 Pierre.Dampure@barclayscapital.com wrote: > > Frank, > > Are you by any chance running an ELF version of X? I experienced pretty > weird results over the past few days with and ELF X (built as per the port > mods posted to the list): a make world running under X would basically bring > the box to a halt, massive delays when typing characters on any of the other > VTs, etc... this is on a box with 384Mb RAM, SMP w/PPro 200/512 and more > than 256Mb free / no swap used, doing nothing else than the build. > > I'll be rebuilding the box tonight and verify whether this is still > happening now that we have "official" XFree86 port mods. Hey, I had this. I installed ELF XFree86 and it rewrote the /usr/X11R6/bin/X link to point at XF86_SVGA instead of my usual Xaccel. I decided to stay with XF86_SVGA for a few days for kicks but scrolling was so slow (the card is an 8Mb MGA Mill II) that I swapped back. I don't remember it being this slow last time I tried it and the MGA is supposed to be one of XFree86's faster servers :-(. It was acting as if it was a dumb framebuffer. -- Doug Rabson Mail: dfr@nlsystems.com Nonlinear Systems Ltd. Phone: +44 181 951 1891 Fax: +44 181 381 1039 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Sep 22 02:25:23 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id CAA25518 for freebsd-smp-outgoing; Tue, 22 Sep 1998 02:25:23 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from trinity.radio-do.de (trinity.Radio-do.de [193.101.164.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id CAA25401; Tue, 22 Sep 1998 02:24:35 -0700 (PDT) (envelope-from fn@trinity.radio-do.de) Received: (from fn@localhost) by trinity.radio-do.de (8.9.1/8.8.5/RADIO-1.1) id LAA12645; Tue, 22 Sep 1998 11:23:46 +0200 (CEST) Message-ID: <19980922112346.A12636@radio-do.de> Date: Tue, 22 Sep 1998 11:23:46 +0200 From: Frank Nobis To: Doug Rabson , Pierre.Dampure@barclayscapital.com Cc: freebsd-smp@FreeBSD.ORG, freebsd-current@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today References: <711DCB8FB391D111B9DD00805F8BDDBAF7ED39@exips0019.itops.ldn.bzwint.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i In-Reply-To: ; from Doug Rabson on Tue, Sep 22, 1998 at 10:09:09AM +0100 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Tue, Sep 22, 1998 at 10:09:09AM +0100, Doug Rabson wrote: > On Mon, 21 Sep 1998 Pierre.Dampure@barclayscapital.com wrote: > > > > > Frank, > > > > Are you by any chance running an ELF version of X? I experienced pretty > > weird results over the past few days with and ELF X (built as per the port > > mods posted to the list): a make world running under X would basically bring > > the box to a halt, massive delays when typing characters on any of the other > > VTs, etc... this is on a box with 384Mb RAM, SMP w/PPro 200/512 and more > > than 256Mb free / no swap used, doing nothing else than the build. > > > > I'll be rebuilding the box tonight and verify whether this is still > > happening now that we have "official" XFree86 port mods. > > Hey, I had this. I installed ELF XFree86 and it rewrote the > /usr/X11R6/bin/X link to point at XF86_SVGA instead of my usual Xaccel. I > decided to stay with XF86_SVGA for a few days for kicks but scrolling was > so slow (the card is an 8Mb MGA Mill II) that I swapped back. I don't > remember it being this slow last time I tried it and the MGA is supposed > to be one of XFree86's faster servers :-(. It was acting as if it was a > dumb framebuffer. That may be a difference. I'm running the Xaccel server. The Matrox g200 agp card is currently not supportted in XF86_SVGA. Regards Frank -- Frank Nobis Email: PGP AVAILABLE Landgrafenstr. 130 dg3dcn http://www.radio-do.de/~fn/ 44139 Dortmund Powered by SMP FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Sep 22 07:24:56 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id HAA10790 for freebsd-smp-outgoing; Tue, 22 Sep 1998 07:24:56 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from zibbi.mikom.csir.co.za (zibbi.mikom.csir.co.za [146.64.24.58]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id HAA10759 for ; Tue, 22 Sep 1998 07:24:48 -0700 (PDT) (envelope-from jhay@zibbi.mikom.csir.co.za) Received: (from jhay@localhost) by zibbi.mikom.csir.co.za (8.9.1/8.9.1) id QAA15764; Tue, 22 Sep 1998 16:23:06 +0200 (SAT) From: John Hay Message-Id: <199809221423.QAA15764@zibbi.mikom.csir.co.za> Subject: Re: Only 50% idle with current -current? In-Reply-To: <199809200851.QAA05006@spinner.netplex.com.au> from Peter Wemm at "Sep 20, 98 04:51:41 pm" To: peter@netplex.com.au (Peter Wemm) Date: Tue, 22 Sep 1998 16:23:06 +0200 (SAT) Cc: smp@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL32 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org This did it, by doing it like this I can get the persentage idle to below 50%...... But why??? John -- John Hay -- John.Hay@mikom.csir.co.za > John Hay wrote: > > Hi, > > > > I have updated our one SMP box to the latest -current and now I see on top > > that it doesn't go below 50% idle anymore. I'm doing a make release and > > for a while ran two rc5's, but it still stayed at 50% idle. I remember > > someone else also noticed it a few days ago. > > > > Anyone have any ideas? > > Yes, just try booting "-s" and go into single user mode to start with. > > Give a few commands, eg: 'sync; sync; sync', do a fsck if it's needed and > then start multiuser.. > > If it then works as expected, then I suspect you are seeing a > manifestation of a long running problem. > > I've found that SMP and/or ELF are unhappy at boot under SMP (and have > been for 12 months). If I have /usr/libexec/getty dynamically linked and > have more than a couple enabled in ttys, I get a lockup. The same happens > if running rc5des/rc564 from the rc scripts if I don't go into single user > and run a few commands first. > > At the time I hacked init(8) to do a couple of fork/exec's at startup and > the problem went away. I don't understand what's going on and spent a > fair while last year trying to figure it out. I'm pretty sure it's not > ELF itself, it's just triggering something else. > > > John > > -- > > John Hay -- John.Hay@mikom.csir.co.za > > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > > with "unsubscribe freebsd-smp" in the body of the message > > > > Cheers, > -Peter To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Sep 22 19:29:47 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id TAA01637 for freebsd-smp-outgoing; Tue, 22 Sep 1998 19:29:47 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id TAA01585; Tue, 22 Sep 1998 19:29:37 -0700 (PDT) (envelope-from smp@Ilsa.StevesCafe.com) Received: from Ilsa.StevesCafe.com (localhost.StevesCafe.com [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.8/8.8.5) with ESMTP id UAA15410; Tue, 22 Sep 1998 20:13:17 -0600 (MDT) Message-Id: <199809230213.UAA15410@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0.2 2/24/98 From: Steve Passe To: Peter Wemm cc: Frank Nobis , freebsd-smp@FreeBSD.ORG, freebsd-current@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today In-reply-to: Your message of "Wed, 23 Sep 1998 00:46:35 +0800." <199809221646.AAA08321@spinner.netplex.com.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 22 Sep 1998 20:13:17 -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Peter, > > PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND > > 22682 root 105 0 748K 240K RUN 0 0:48 99.32% 90.33% pig > > 22683 root 105 0 748K 240K CPU1 1 0:46 99.39% 89.45% pig > > > > --- > > This is with a system cvsup'ed midday yesterday. > > Running an ELF world? > > I used to see top showing itself on CPU0 or CPU1, with two processes in > "RUN" state and nothing else on the other CPU. Yes, (I think) I started with the 3.0-980917-SNAP and cvsuped on the 20th. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Sep 23 12:53:19 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id MAA02010 for freebsd-smp-outgoing; Wed, 23 Sep 1998 12:53:19 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from spinner.netplex.com.au (spinner.netplex.com.au [202.12.86.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id MAA01955; Wed, 23 Sep 1998 12:52:58 -0700 (PDT) (envelope-from peter@netplex.com.au) Received: from spinner.netplex.com.au (localhost [127.0.0.1]) by spinner.netplex.com.au (8.9.1/8.9.1/Spinner) with ESMTP id AAA08290; Wed, 23 Sep 1998 00:44:19 +0800 (WST) (envelope-from peter@spinner.netplex.com.au) Message-Id: <199809221644.AAA08290@spinner.netplex.com.au> X-Mailer: exmh version 2.0.2 2/24/98 To: Pierre.Dampure@barclayscapital.com cc: fn@radio-do.de, freebsd-smp@FreeBSD.ORG, freebsd-current@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today In-reply-to: Your message of "Mon, 21 Sep 1998 15:07:55 +0100." <711DCB8FB391D111B9DD00805F8BDDBAF7ED39@exips0019.itops.ldn.bzwint.com> Date: Wed, 23 Sep 1998 00:44:19 +0800 From: Peter Wemm Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Pierre.Dampure@barclayscapital.com wrote: > > Frank, > > Are you by any chance running an ELF version of X? I experienced pretty > weird results over the past few days with and ELF X (built as per the port > mods posted to the list): a make world running under X would basically bring > the box to a halt, massive delays when typing characters on any of the other > VTs, etc... this is on a box with 384Mb RAM, SMP w/PPro 200/512 and more > than 256Mb free / no swap used, doing nothing else than the build. Two things.. 1: There have been some clock tweaks in the last few days that might affect this. 2: Try (humor me :-) booting up into single user, running a few commands (eg: sync; sync; sync; fsck -p; ls) and then doing a ctrl-D to go into multi-user. If this (#2) is the key to making your system work properly, then you are seeing the same problem I've been unable to put a finger on for ages. None of the other SMP folks saw it, but only I was running ELF at the time. Somebody else (John Hay) mentioned that this fixes his problem, but it's not clear whether (or when) he's using elf. The annoying thing was that it appeared to be the combination of ELF executables and SMP that caused the problem. Also, having init spawn 12 /usr/libexec/getty processes would kill the system too. I had decided that it was something peculiar with my system that was causing this. If other people are seeing it now, I'll be greatly relieved to know that I wasn't imagining it. :-) (and also worried, because this is a show-stopper) Cheers, -Peter > Best Regards, > > > PY > > -----Original Message----- > From: Frank Nobis [mailto:fn@radio-do.de] > Sent: Monday, September 21, 1998 2:01 PM > To: freebsd-smp@FreeBSD.ORG > Cc: freebsd-current@FreeBSD.ORG > Subject: Weired top display at smp current kernel from today > > > Running a mkae world -j4 I noticed only 50% idle time during the make. > > Running just two programs whit a busy loop gives that output fron top > > last pid: 314; load averages: 1.84, 0.75, 0.30 > 14:55:17 > 45 processes: 3 running, 42 sleeping > CPU states: 50.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 50.0% > idle > Mem: 7080K Active, 6332K Inact, 16M Wired, 100K Cache, 3457K Buf, 473M Free > Swap: 199M Total, 199M Free > > PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND > 308 fn 90 0 748K 236K RUN 1 1:36 50.00% 49.97% pig > 310 fn 91 0 748K 236K RUN 1 0:57 49.18% 49.02% pig > 311 fn 28 0 1568K 908K CPU1 1 0:00 0.00% 0.00% top > > Is this a bug in top? Can someone reproduce that? > > pig is simply 'for(;;) i++;' > > Regards > Frank > > -- > Frank Nobis Email: PGP AVAILABLE > Landgrafenstr. 130 dg3dcn http://www.radio-do.de/~fn/ > 44139 Dortmund Powered by FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Sep 23 12:53:20 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id MAA02017 for freebsd-smp-outgoing; Wed, 23 Sep 1998 12:53:20 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from spinner.netplex.com.au (spinner.netplex.com.au [202.12.86.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id MAA01954; Wed, 23 Sep 1998 12:52:58 -0700 (PDT) (envelope-from peter@netplex.com.au) Received: from spinner.netplex.com.au (localhost [127.0.0.1]) by spinner.netplex.com.au (8.9.1/8.9.1/Spinner) with ESMTP id AAA08321; Wed, 23 Sep 1998 00:46:35 +0800 (WST) (envelope-from peter@spinner.netplex.com.au) Message-Id: <199809221646.AAA08321@spinner.netplex.com.au> X-Mailer: exmh version 2.0.2 2/24/98 To: Steve Passe cc: Frank Nobis , freebsd-smp@FreeBSD.ORG, freebsd-current@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today In-reply-to: Your message of "Mon, 21 Sep 1998 09:30:29 CST." <199809211530.JAA09435@Ilsa.StevesCafe.com> Date: Wed, 23 Sep 1998 00:46:35 +0800 From: Peter Wemm Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Steve Passe wrote: > Hi, > > Running a mkae world -j4 I noticed only 50% idle time during the make. > > > > Running just two programs whit a busy loop gives that output fron top > > ... > > Is this a bug in top? Can someone reproduce that? > > > > pig is simply 'for(;;) i++;' > > > > --- > running two copies of pig: > > last pid: 22687; load averages: 1.30, 0.60, 0.27 09:25: 16 > 29 processes: 3 running, 26 sleeping > CPU states: 99.8% user, 0.0% nice, 0.2% system, 0.0% interrupt, 0.0% idle > Mem: 18M Active, 20M Inact, 50M Wired, 236M Cache, 7916K Buf, 180M Free > Swap: 300M Total, 300M Free > > PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND > 22682 root 105 0 748K 240K RUN 0 0:48 99.32% 90.33% pig > 22683 root 105 0 748K 240K CPU1 1 0:46 99.39% 89.45% pig > > --- > This is with a system cvsup'ed midday yesterday. Running an ELF world? I used to see top showing itself on CPU0 or CPU1, with two processes in "RUN" state and nothing else on the other CPU. > -- > Steve Passe | powered by > smp@csn.net | Symmetric MultiProcessor FreeBSD Cheers, -Peter To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Sep 23 14:29:43 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id OAA19035 for freebsd-smp-outgoing; Wed, 23 Sep 1998 14:29:43 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from vision.vc3.com (vision.vc3.com [209.12.161.2]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id OAA19030 for ; Wed, 23 Sep 1998 14:29:41 -0700 (PDT) (envelope-from tatemj@vision.vc3.com) Received: from localhost (tatemj@localhost) by vision.vc3.com (8.8.7/8.8.5) with SMTP id RAA19768 for ; Wed, 23 Sep 1998 17:29:37 -0400 Date: Wed, 23 Sep 1998 17:29:37 -0400 (EDT) From: Jason Tatem To: freebsd-smp@FreeBSD.ORG Subject: Fatal trap 12 on startup Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I recently managed to score a dual PII 233 machine to play with until someone else needs it at my workplace, so I decided to give FreeBSD's SMP support a try. Installed using the 0520 snapshot, compiled SMP support into the kernel, and everything seemed real happy. System running nice and fast, etc. I went ahead and cvsup'd to the latest sources, rebuilt world, and rebuilt kernel using the same configuration file i had used to build the old SMP kernel. Everything compiled fine, no problems there. When I rebooted to load the new kernel, it produced the following message right at the point where it switches from white text to gray text: Fatal trap 12: page fault while in kernel mode mp_lock = 00000002; cpuid = 0; lapic.id = 01000000 stopped at _ffs_mountt 0x62 testb $0x1, 0x42(%eax) Anyone seen this before? I'm running the machine fine so far with new world and old kernel, but I do like to keep everything looking at the same page so to speak.... Thanks Jason To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Sep 23 21:58:35 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id VAA27787 for freebsd-smp-outgoing; Wed, 23 Sep 1998 21:58:35 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from zibbi.mikom.csir.co.za (zibbi.mikom.csir.co.za [146.64.24.58]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id VAA27744; Wed, 23 Sep 1998 21:58:18 -0700 (PDT) (envelope-from jhay@zibbi.mikom.csir.co.za) Received: (from jhay@localhost) by zibbi.mikom.csir.co.za (8.9.1/8.9.1) id GAA20856; Thu, 24 Sep 1998 06:54:51 +0200 (SAT) From: John Hay Message-Id: <199809240454.GAA20856@zibbi.mikom.csir.co.za> Subject: Re: Weired top display at smp current kernel from today In-Reply-To: <199809221644.AAA08290@spinner.netplex.com.au> from Peter Wemm at "Sep 23, 98 00:44:19 am" To: peter@netplex.com.au (Peter Wemm) Date: Thu, 24 Sep 1998 06:54:51 +0200 (SAT) Cc: Pierre.Dampure@barclayscapital.com, fn@radio-do.de, freebsd-smp@FreeBSD.ORG, freebsd-current@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL32 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > Pierre.Dampure@barclayscapital.com wrote: > > > > Frank, > > > > Are you by any chance running an ELF version of X? I experienced pretty > > weird results over the past few days with and ELF X (built as per the port > > mods posted to the list): a make world running under X would basically bring > > the box to a halt, massive delays when typing characters on any of the other > > VTs, etc... this is on a box with 384Mb RAM, SMP w/PPro 200/512 and more > > than 256Mb free / no swap used, doing nothing else than the build. > > Two things.. > > 1: There have been some clock tweaks in the last few days that might > affect this. > > 2: Try (humor me :-) booting up into single user, running a few commands > (eg: sync; sync; sync; fsck -p; ls) and then doing a ctrl-D to go into > multi-user. > > If this (#2) is the key to making your system work properly, then you are > seeing the same problem I've been unable to put a finger on for ages. > None of the other SMP folks saw it, but only I was running ELF at the time. > > Somebody else (John Hay) mentioned that this fixes his problem, but it's > not clear whether (or when) he's using elf. Yes I'm using elf. I never saw it before I changed to elf. Another way I found is to use an aout /sbin/init. These problems is on a dual 266MHz PII with onboard adaptec scsi. Last night I upgraded our dual 400Mhz PII with Intel N440BX motherboard (ncr scsi onboard) to elf and up to now it hasn't displayed the same problems, but then I haven't rebooted it too many times yet. John -- John Hay -- John.Hay@mikom.csir.co.za To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Sep 23 23:34:07 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id XAA08895 for freebsd-smp-outgoing; Wed, 23 Sep 1998 23:34:07 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from zibbi.mikom.csir.co.za (zibbi.mikom.csir.co.za [146.64.24.58]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id XAA08796; Wed, 23 Sep 1998 23:33:47 -0700 (PDT) (envelope-from jhay@zibbi.mikom.csir.co.za) Received: (from jhay@localhost) by zibbi.mikom.csir.co.za (8.9.1/8.9.1) id IAA22256; Thu, 24 Sep 1998 08:33:22 +0200 (SAT) From: John Hay Message-Id: <199809240633.IAA22256@zibbi.mikom.csir.co.za> Subject: Re: Weired top display at smp current kernel from today In-Reply-To: <199809240454.GAA20856@zibbi.mikom.csir.co.za> from John Hay at "Sep 24, 98 06:54:51 am" To: jhay@mikom.csir.co.za (John Hay) Date: Thu, 24 Sep 1998 08:33:22 +0200 (SAT) Cc: peter@netplex.com.au, freebsd-smp@FreeBSD.ORG, freebsd-current@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL32 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > > > > 2: Try (humor me :-) booting up into single user, running a few commands > > (eg: sync; sync; sync; fsck -p; ls) and then doing a ctrl-D to go into > > multi-user. > > > > If this (#2) is the key to making your system work properly, then you are > > seeing the same problem I've been unable to put a finger on for ages. > > None of the other SMP folks saw it, but only I was running ELF at the time. > > > > Somebody else (John Hay) mentioned that this fixes his problem, but it's > > not clear whether (or when) he's using elf. > > Yes I'm using elf. I never saw it before I changed to elf. Another way I > found is to use an aout /sbin/init. These problems is on a dual 266MHz PII > with onboard adaptec scsi. Last night I upgraded our dual 400Mhz PII with > Intel N440BX motherboard (ncr scsi onboard) to elf and up to now it hasn't > displayed the same problems, but then I haven't rebooted it too many times > yet. Correction, the dual 400Mhz PII also have the problem and booting with an aout /sbin/init solves it. Can there be something in the elf image loader missing or not initialized that effects things if the first process is elf? John -- John Hay -- John.Hay@mikom.csir.co.za To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Sep 23 23:58:25 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id XAA12742 for freebsd-smp-outgoing; Wed, 23 Sep 1998 23:58:25 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from silverback.gorilla.net (silverback.gorilla.net [208.128.8.1]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id XAA12719; Wed, 23 Sep 1998 23:58:23 -0700 (PDT) (envelope-from tom@gorilla.net) Received: from peeper.TOJ.org [208.143.84.52] by silverback.gorilla.net with ESMTP (SMTPD32-4.06) id AB6D8F00B4; Thu, 24 Sep 1998 01:49:17 CDT Received: (from tom@localhost) by peeper.TOJ.org (8.9.1/8.8.8) id BAA00828; Thu, 24 Sep 1998 01:53:01 -0500 (CDT) (envelope-from tom) Message-ID: <19980924015300.A807@TOJ.org> Date: Thu, 24 Sep 1998 01:53:00 -0500 From: Tom Jackson To: Peter Wemm , Pierre.Dampure@barclayscapital.com Cc: fn@radio-do.de, freebsd-smp@FreeBSD.ORG, freebsd-current@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today References: <711DCB8FB391D111B9DD00805F8BDDBAF7ED39@exips0019.itops.ldn.bzwint.com> <199809221644.AAA08290@spinner.netplex.com.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.93.2i In-Reply-To: <199809221644.AAA08290@spinner.netplex.com.au>; from Peter Wemm on Wed, Sep 23, 1998 at 12:44:19AM +0800 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hi Peter, I was really constipated about this on smp until I saw a posting from you and one by Mike Smith that told me others were having this problem. As discussed by Mike, people using a script in rc.d to fire up 2 rc5des's see this regular. X is not involved in this case. When I boot, and it happens about every other day including today, both rc5des's are running at 50/50 on one cpu and init is running 100 on the other. There is no login prompt so I have to login from another machine, comment out the rc5des starts and reboot. Then start the rc5des's manually. What's funny is this happens almost invariably every other day. Thinking about rebuilding world for today and see if it corrects itself. btw, I'm running ELF, no softupdates, on a asus p2l97-ds w 128 MB ecc RAM. I'll keep lurking and checking for yours or Mike's fix :) On Wed, Sep 23, 1998 at 12:44:19AM +0800, Peter Wemm wrote: > Pierre.Dampure@barclayscapital.com wrote: > > > > Frank, > > > > Are you by any chance running an ELF version of X? I experienced pretty > > weird results over the past few days with and ELF X (built as per the port > > mods posted to the list): a make world running under X would basically bring > > the box to a halt, massive delays when typing characters on any of the other > > VTs, etc... this is on a box with 384Mb RAM, SMP w/PPro 200/512 and more > > than 256Mb free / no swap used, doing nothing else than the build. > > Two things.. > > 1: There have been some clock tweaks in the last few days that might > affect this. > > 2: Try (humor me :-) booting up into single user, running a few commands > (eg: sync; sync; sync; fsck -p; ls) and then doing a ctrl-D to go into > multi-user. > > If this (#2) is the key to making your system work properly, then you are > seeing the same problem I've been unable to put a finger on for ages. > None of the other SMP folks saw it, but only I was running ELF at the time. > > Somebody else (John Hay) mentioned that this fixes his problem, but it's > not clear whether (or when) he's using elf. > > The annoying thing was that it appeared to be the combination of ELF > executables and SMP that caused the problem. Also, having init spawn 12 > /usr/libexec/getty processes would kill the system too. > > I had decided that it was something peculiar with my system that was > causing this. If other people are seeing it now, I'll be greatly relieved > to know that I wasn't imagining it. :-) (and also worried, because this > is a show-stopper) > > Cheers, > -Peter > > > Best Regards, > > > > > > PY > > > > -----Original Message----- > > From: Frank Nobis [mailto:fn@radio-do.de] > > Sent: Monday, September 21, 1998 2:01 PM > > To: freebsd-smp@FreeBSD.ORG > > Cc: freebsd-current@FreeBSD.ORG > > Subject: Weired top display at smp current kernel from today > > > > > > Running a mkae world -j4 I noticed only 50% idle time during the make. > > > > Running just two programs whit a busy loop gives that output fron top > > > > last pid: 314; load averages: 1.84, 0.75, 0.30 > > 14:55:17 > > 45 processes: 3 running, 42 sleeping > > CPU states: 50.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 50.0% > > idle > > Mem: 7080K Active, 6332K Inact, 16M Wired, 100K Cache, 3457K Buf, 473M Free > > Swap: 199M Total, 199M Free > > > > PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND > > 308 fn 90 0 748K 236K RUN 1 1:36 50.00% 49.97% pig > > 310 fn 91 0 748K 236K RUN 1 0:57 49.18% 49.02% pig > > 311 fn 28 0 1568K 908K CPU1 1 0:00 0.00% 0.00% top > > > > Is this a bug in top? Can someone reproduce that? > > > > pig is simply 'for(;;) i++;' > > > > Regards > > Frank > > > > -- > > Frank Nobis Email: PGP AVAILABLE > > Landgrafenstr. 130 dg3dcn http://www.radio-do.de/~fn/ > > 44139 Dortmund Powered by FreeBSD > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-smp" in the body of the message > -- Tom -- IMail Server for Windows NT. Evaluation version. Copyright (c) 1995-98 Ipswitch, Inc. http://www.ipswitch.com/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Sep 24 00:05:24 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id AAA13675 for freebsd-smp-outgoing; Thu, 24 Sep 1998 00:05:24 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from sos.freebsd.dk (sos.freebsd.dk [212.242.40.180]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id AAA13654; Thu, 24 Sep 1998 00:05:21 -0700 (PDT) (envelope-from sos@sos.freebsd.dk) Received: (from sos@localhost) by sos.freebsd.dk (8.9.1/8.9.1) id JAA05414; Thu, 24 Sep 1998 09:04:42 +0200 (CEST) (envelope-from sos) Message-Id: <199809240704.JAA05414@sos.freebsd.dk> Subject: Re: Weired top display at smp current kernel from today In-Reply-To: <199809240633.IAA22256@zibbi.mikom.csir.co.za> from John Hay at "Sep 24, 98 08:33:22 am" To: jhay@mikom.csir.co.za (John Hay) Date: Thu, 24 Sep 1998 09:04:42 +0200 (CEST) Cc: jhay@mikom.csir.co.za, peter@netplex.com.au, freebsd-smp@FreeBSD.ORG, freebsd-current@FreeBSD.ORG From: Søren Schmidt Reply-to: sos@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL38 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org In reply to John Hay who wrote: > > > > Yes I'm using elf. I never saw it before I changed to elf. Another way I > > found is to use an aout /sbin/init. These problems is on a dual 266MHz PII > > with onboard adaptec scsi. Last night I upgraded our dual 400Mhz PII with > > Intel N440BX motherboard (ncr scsi onboard) to elf and up to now it hasn't > > displayed the same problems, but then I haven't rebooted it too many times > > yet. > > Correction, the dual 400Mhz PII also have the problem and booting with an > aout /sbin/init solves it. > > Can there be something in the elf image loader missing or not initialized > that effects things if the first process is elf? Strange, I remeber Peter having this problem, but I've never seen it here on any of my SMP machines and still dont, wierd.... -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- Søren Schmidt (sos@FreeBSD.org) FreeBSD Core Team Even more code to hack -- will it ever end? .. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Sep 24 00:55:22 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id AAA19862 for freebsd-smp-outgoing; Thu, 24 Sep 1998 00:55:22 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from btp1da.phy.uni-bayreuth.de (btp1da.phy.uni-bayreuth.de [132.180.20.32]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id AAA19845; Thu, 24 Sep 1998 00:55:16 -0700 (PDT) (envelope-from werner@btp1da.phy.uni-bayreuth.de) Received: (from werner@localhost) by btp1da.phy.uni-bayreuth.de (8.8.8/8.7.3) id JAA27343; Thu, 24 Sep 1998 09:55:03 +0200 (MEST) Message-ID: X-Mailer: XFMail 1.3 [p0] on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <199809240704.JAA05414@sos.freebsd.dk> Date: Thu, 24 Sep 1998 09:55:03 +0200 (MEST) Organization: University of bayreuth From: Werner Griessl To: "S\xren Schmidt" Subject: Re: Weired top display at smp current kernel from today Cc: freebsd-current@FreeBSD.ORG, freebsd-smp@FreeBSD.ORG, peter@netplex.com.au, (John Hay) Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On 24-Sep-98 S\xren Schmidt wrote: > In reply to John Hay who wrote: >> > >> > Yes I'm using elf. I never saw it before I changed to elf. Another way I >> > found is to use an aout /sbin/init. These problems is on a dual 266MHz PII >> > with onboard adaptec scsi. Last night I upgraded our dual 400Mhz PII with >> > Intel N440BX motherboard (ncr scsi onboard) to elf and up to now it hasn't >> > displayed the same problems, but then I haven't rebooted it too many times >> > yet. >> >> Correction, the dual 400Mhz PII also have the problem and booting with an >> aout /sbin/init solves it. >> >> Can there be something in the elf image loader missing or not initialized >> that effects things if the first process is elf? > > Strange, I remeber Peter having this problem, but I've never seen it here > on any of my SMP machines and still dont, wierd.... > > > -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- > Søren Schmidt (sos@FreeBSD.org) FreeBSD Core Team > Even more code to hack -- will it ever end? > .. > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-smp" in the body of the message ---------------------------------- Had also this problem last friday after the change to elf and cam. Since Monday it's gone. Werner To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Sep 24 01:58:35 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id BAA27768 for freebsd-smp-outgoing; Thu, 24 Sep 1998 01:58:35 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from trinity.radio-do.de (trinity.Radio-do.de [193.101.164.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id BAA27747; Thu, 24 Sep 1998 01:58:31 -0700 (PDT) (envelope-from fn@trinity.radio-do.de) Received: (from fn@localhost) by trinity.radio-do.de (8.9.1/8.8.5/RADIO-1.1) id KAA08410; Thu, 24 Sep 1998 10:58:37 +0200 (CEST) Message-ID: <19980924105837.A8400@radio-do.de> Date: Thu, 24 Sep 1998 10:58:37 +0200 From: Frank Nobis To: freebsd-current@FreeBSD.ORG, freebsd-smp@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today References: <199809240704.JAA05414@sos.freebsd.dk> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i In-Reply-To: ; from Werner Griessl on Thu, Sep 24, 1998 at 09:55:03AM +0200 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Thu, Sep 24, 1998 at 09:55:03AM +0200, Werner Griessl wrote: > > On 24-Sep-98 S\xren Schmidt wrote: > > In reply to John Hay who wrote: > >> > > >> > Yes I'm using elf. I never saw it before I changed to elf. Another way I > >> > found is to use an aout /sbin/init. These problems is on a dual 266MHz PII > >> > with onboard adaptec scsi. Last night I upgraded our dual 400Mhz PII with > >> > Intel N440BX motherboard (ncr scsi onboard) to elf and up to now it hasn't > >> > displayed the same problems, but then I haven't rebooted it too many times > >> > yet. > >> > >> Correction, the dual 400Mhz PII also have the problem and booting with an > >> aout /sbin/init solves it. > >> > >> Can there be something in the elf image loader missing or not initialized > >> that effects things if the first process is elf? > > > > Strange, I remeber Peter having this problem, but I've never seen it here > > on any of my SMP machines and still dont, wierd.... I thought it was gone here, but... During a run of two cpu pigs and a top display with two times of 50% cpu usage and idle time again at 50% I suddenly have seen an init with 100% cpu and idle time now at 0%. This seems to be a good hint, when an aout init fixes that problem. Even after running in normal state, make -j4 world and idle tending to 0%, I have seen a fallback to the strange behaviour, but no boot in the meantime. There must be events that lets the system switch between those states. Regards Frank -- Frank Nobis Email: PGP AVAILABLE Landgrafenstr. 130 dg3dcn http://www.radio-do.de/~fn/ 44139 Dortmund Powered by SMP FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Sep 24 09:20:28 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id JAA25156 for freebsd-smp-outgoing; Thu, 24 Sep 1998 09:20:28 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from trinity.radio-do.de (trinity.Radio-do.de [193.101.164.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id JAA25133; Thu, 24 Sep 1998 09:20:19 -0700 (PDT) (envelope-from fn@trinity.radio-do.de) Received: (from fn@localhost) by trinity.radio-do.de (8.9.1/8.8.5/RADIO-1.1) id SAA09617; Thu, 24 Sep 1998 18:20:25 +0200 (CEST) Message-ID: <19980924182025.A9605@radio-do.de> Date: Thu, 24 Sep 1998 18:20:25 +0200 From: Frank Nobis To: freebsd-current@FreeBSD.ORG, freebsd-smp@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today References: <199809240704.JAA05414@sos.freebsd.dk> <19980924105837.A8400@radio-do.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i In-Reply-To: <19980924105837.A8400@radio-do.de>; from Frank Nobis on Thu, Sep 24, 1998 at 10:58:37AM +0200 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Thu, Sep 24, 1998 at 10:58:37AM +0200, Frank Nobis wrote: > > I thought it was gone here, but... I can now reproduce the problem, but yet don't understand why it happens. Running to pigs locally gives the expected result with 0% idle and both cpus running at 100%. Now i do the same via a telnet connection and voila, the bad thing(tm) is back! Regards Frank -- Frank Nobis Email: PGP AVAILABLE Landgrafenstr. 130 dg3dcn http://www.radio-do.de/~fn/ 44139 Dortmund Powered by SMP FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Sep 24 22:47:22 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id WAA02336 for freebsd-smp-outgoing; Thu, 24 Sep 1998 22:47:22 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from midten.fast.no (midten.fast.no [195.139.251.11]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id WAA02327; Thu, 24 Sep 1998 22:47:17 -0700 (PDT) (envelope-from tegge@fast.no) Received: from fast.no (IDENT:tegge@midten.fast.no [195.139.251.11]) by midten.fast.no (8.9.1/8.9.1) with ESMTP id HAA26153; Fri, 25 Sep 1998 07:43:51 +0200 (CEST) Message-Id: <199809250543.HAA26153@midten.fast.no> To: fn@radio-do.de Cc: freebsd-current@FreeBSD.ORG, freebsd-smp@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today From: Tor.Egge@fast.no In-Reply-To: Your message of "Thu, 24 Sep 1998 18:20:25 +0200" References: <19980924182025.A9605@radio-do.de> X-Mailer: Mew version 1.70 on Emacs 19.34.1 Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Date: Fri, 25 Sep 1998 07:43:46 +0200 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > On Thu, Sep 24, 1998 at 10:58:37AM +0200, Frank Nobis wrote: > > > > I thought it was gone here, but... > > I can now reproduce the problem, but yet don't understand why it happens. Replacing the aout /sbin/init with an elf /sbin/init seems to be sufficient to trigger this problem. Looking at mp_lock using gdb -k /kernel.gdb /dev/mem ... print/x mp_lock gave 0x1 or 0x1000001 with the aout /sbin/init, but 0x2 or 0x1000002 with the elf /sbin/init. This means that when a cpu returns to userland, mp_lock is still 0x1 or 0x1000001. Which blocks the other CPU until the CPU holding the giant kernel lock enters _idle. - Tor Egge To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Fri Sep 25 00:01:27 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id AAA11474 for freebsd-smp-outgoing; Fri, 25 Sep 1998 00:01:27 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from smtp01.primenet.com (smtp01.primenet.com [206.165.6.131]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id AAA11453; Fri, 25 Sep 1998 00:01:24 -0700 (PDT) (envelope-from tlambert@usr01.primenet.com) Received: (from daemon@localhost) by smtp01.primenet.com (8.8.8/8.8.8) id AAA07505; Fri, 25 Sep 1998 00:01:19 -0700 (MST) Received: from usr01.primenet.com(206.165.6.201) via SMTP by smtp01.primenet.com, id smtpd007481; Fri Sep 25 00:01:15 1998 Received: (from tlambert@localhost) by usr01.primenet.com (8.8.5/8.8.5) id AAA15964; Fri, 25 Sep 1998 00:01:09 -0700 (MST) From: Terry Lambert Message-Id: <199809250701.AAA15964@usr01.primenet.com> Subject: Re: Weired top display at smp current kernel from today To: Tor.Egge@fast.no Date: Fri, 25 Sep 1998 07:01:09 +0000 (GMT) Cc: fn@radio-do.de, freebsd-current@FreeBSD.ORG, freebsd-smp@FreeBSD.ORG In-Reply-To: <199809250543.HAA26153@midten.fast.no> from "Tor.Egge@fast.no" at Sep 25, 98 07:43:46 am X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > > On Thu, Sep 24, 1998 at 10:58:37AM +0200, Frank Nobis wrote: > > > > > > I thought it was gone here, but... > > > > I can now reproduce the problem, but yet don't understand why it happens. > > > Replacing the aout /sbin/init with an elf /sbin/init seems to be sufficient > to trigger this problem. I can't tell right now... has my mmap object size patch been committed, or not? I suspect that this has to do with the boundary page (the page containing both text and data that would have been padded to a page boundary under a.out). Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Fri Sep 25 12:54:36 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id MAA29199 for freebsd-smp-outgoing; Fri, 25 Sep 1998 12:54:36 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from magnet.geophysik.tu-freiberg.de (magnet.geophysik.tu-freiberg.de [139.20.128.6]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id MAA29184; Fri, 25 Sep 1998 12:54:23 -0700 (PDT) (envelope-from freebsd@magnet.geophysik.tu-freiberg.de) Received: (from freebsd@localhost) by magnet.geophysik.tu-freiberg.de (8.9.1/8.7.3) id VAA02617; Fri, 25 Sep 1998 21:50:02 +0200 (CEST) From: Holm Tiffe Message-Id: <199809251950.VAA02617@magnet.geophysik.tu-freiberg.de> Subject: AHA 2742T+CAM+SMP problems 2nd. try #2 To: freebsd-scsi@FreeBSD.ORG Date: Fri, 25 Sep 1998 21:50:01 +0200 (CEST) Cc: freebsd-smp@FreeBSD.ORG Reply-To: freebsd@magnet.geophysik.tu-freiberg.de X-Mailer: ELM [version 2.4ME+ PL26 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org More from my SMP problem: Today evening I have upgraded my src/sys to cvs-cur.4676 (cam_xpt.c version 1.13) and now I get the following with the new SMP kernel: SMP: AP CPU #1 Launched! ........................... here is a long pause with a stady lightening SCSI LED (probe9:ahc0:1:2:0): Sending SDTR! (what this means Scsi Device Target Reset ?) (probe9:ahc0:1:2:0): SCB 0x9 timed out in message in phase, SCSISIGI == 0xb6 SEQADDR == 0x15b SSTAT1 == 0x13 (probe9:ahc0:1:2:0): BDR message in message buffer Fatal trap 12: page fault while in kernel mode mp_lock = 01000002; cpuid = 1, lapicid = 01000000 fault virtual address = 0xb8 funkt code = supervisor read, page not present instruction pointer = 0x8:0xf0106a78 stack pointer = 0x10:0xff804cc4 frame pointer = 0x10:0xff805e04 code segment = base 0x0,limit 0xfffff, type 0x16 = DPL0; pres1, def32 1, gran 1 processor eflags = interrupt enabled, resume, IOPL=0 current process = Idle interrupt mask = cam <- SMP: XXX kernel type 12 trap, code=0 stopped at _xpt_set_transfer_settings+0xd8: -> testb $0x20,0xb8(%esi) trace: _xpt_set_transfer_settings(ff804e78,1) at _xpt_set_transfer_settings+0xd8 _xpt_async(200,f05acc40,ff804e78,ff804e78,f05acc40,1,f07b8000) at _xpt_async+0xb0 _ahc_set_syncrate(f07b8000,ff804f38,f05acc40,0,0,0,1,f07b8000,ff804f38,f05acc40,0,1) at ahc_set_syncrate+0x1de _ahc_handle_devreset() _ahc_handle_scsiint() _ahc_intr() .... this is shorted, pencil broken :-) this seams to be a NULL pointer reference in cam_xpt.c around line 5302 , maybe device->quirk is not jet initialized ? Holm PS: Changing the AHA 2742T to another (rev C) and changing the P5/90 CPU to a P5/100 has nothing changed. The SCSI bus hangs after the SMP: AP CPU #1 Launched line... -- ******************************************************************************* * Holm Tiffe holm@geophysik.tu-freiberg.de * * Freiberger Strasse 24 * * 09600 Kleinschirma, Germany Microsoft is not the Answer - * * Tel.: 49 3731 74233 Microsoft is the Question, * * UUCP: 49 3731 73719 unicorn!holm and the Answer is no ! * ******************************************************************************* To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Fri Sep 25 13:29:45 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id NAA06538 for freebsd-smp-outgoing; Fri, 25 Sep 1998 13:29:45 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from midten.fast.no (midten.fast.no [195.139.251.11]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id NAA06463; Fri, 25 Sep 1998 13:29:10 -0700 (PDT) (envelope-from tegge@fast.no) Received: from fast.no (IDENT:tegge@midten.fast.no [195.139.251.11]) by midten.fast.no (8.9.1/8.9.1) with ESMTP id WAA00593; Fri, 25 Sep 1998 22:24:59 +0200 (CEST) Message-Id: <199809252024.WAA00593@midten.fast.no> To: mike@smith.net.au Cc: fn@radio-do.de, freebsd-current@FreeBSD.ORG, freebsd-smp@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today From: Tor.Egge@fast.no In-Reply-To: Your message of "Thu, 24 Sep 1998 23:20:08 -0700" References: <199809250620.XAA00529@word.smith.net.au> X-Mailer: Mew version 1.70 on Emacs 19.34.1 Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Date: Fri, 25 Sep 1998 22:24:58 +0200 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > Sounds like a bug in the ELF image activator. It's possible that > something got bent when the corefile writing code went in (waves dead > poultry speculatively). It is a bug in cpu_fork(). pcb_mpnest should be initialized to 1. Index: vm_machdep.c =================================================================== RCS file: /home/ncvs/src/sys/i386/i386/vm_machdep.c,v retrieving revision 1.109 diff -u -r1.109 vm_machdep.c --- vm_machdep.c 1998/08/18 07:46:58 1.109 +++ vm_machdep.c 1998/09/25 20:22:52 @@ -636,6 +649,9 @@ * pcb2->pcb_onfault: cloned above (always NULL here?). */ +#ifdef SMP + pcb2->pcb_mpnest = 1; +#endif #ifdef VM86 /* * XXX don't copy the i/o pages. this should probably be fixed. - Tor Egge To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sat Sep 26 00:27:07 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id AAA02968 for freebsd-smp-outgoing; Sat, 26 Sep 1998 00:27:07 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from zibbi.mikom.csir.co.za (zibbi.mikom.csir.co.za [146.64.24.58]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id AAA02961; Sat, 26 Sep 1998 00:26:58 -0700 (PDT) (envelope-from jhay@zibbi.mikom.csir.co.za) Received: (from jhay@localhost) by zibbi.mikom.csir.co.za (8.9.1/8.9.1) id JAA06562; Sat, 26 Sep 1998 09:26:30 +0200 (SAT) From: John Hay Message-Id: <199809260726.JAA06562@zibbi.mikom.csir.co.za> Subject: Re: Weired top display at smp current kernel from today In-Reply-To: <199809252024.WAA00593@midten.fast.no> from "Tor.Egge@fast.no" at "Sep 25, 98 10:24:58 pm" To: Tor.Egge@fast.no Date: Sat, 26 Sep 1998 09:26:30 +0200 (SAT) Cc: freebsd-current@FreeBSD.ORG, freebsd-smp@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL32 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > > Sounds like a bug in the ELF image activator. It's possible that > > something got bent when the corefile writing code went in (waves dead > > poultry speculatively). > > It is a bug in cpu_fork(). > > pcb_mpnest should be initialized to 1. > > Index: vm_machdep.c > =================================================================== > RCS file: /home/ncvs/src/sys/i386/i386/vm_machdep.c,v > retrieving revision 1.109 > diff -u -r1.109 vm_machdep.c > --- vm_machdep.c 1998/08/18 07:46:58 1.109 > +++ vm_machdep.c 1998/09/25 20:22:52 > @@ -636,6 +649,9 @@ > * pcb2->pcb_onfault: cloned above (always NULL here?). > */ > > +#ifdef SMP > + pcb2->pcb_mpnest = 1; > +#endif > #ifdef VM86 > /* > * XXX don't copy the i/o pages. this should probably be fixed. > This fix it for me. ... This fix seems to be binary format neutral, so why didn't it happen with an aout /sbin/init? John -- John Hay -- John.Hay@mikom.csir.co.za To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sat Sep 26 03:09:48 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id DAA14465 for freebsd-smp-outgoing; Sat, 26 Sep 1998 03:09:48 -0700 (PDT) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from outmail.utsunomiya-u.ac.jp (outmail.utsunomiya-u.ac.jp [160.12.196.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id DAA14458; Sat, 26 Sep 1998 03:09:44 -0700 (PDT) (envelope-from yokota@zodiac.mech.utsunomiya-u.ac.jp) Received: from zodiac.mech.utsunomiya-u.ac.jp (IDENT:OustuushhoZ30BiKzXfr4nutht+ogGB8@zodiac.mech.utsunomiya-u.ac.jp [160.12.42.1]) by outmail.utsunomiya-u.ac.jp (8.9.1/8.9.1) with ESMTP id TAA01418; Sat, 26 Sep 1998 19:09:38 +0900 (JST) Received: from zodiac.mech.utsunomiya-u.ac.jp (zodiac.mech.utsunomiya-u.ac.jp [160.12.42.1]) by zodiac.mech.utsunomiya-u.ac.jp (8.7.6+2.6Wbeta7/3.4W/zodiac-May96) with ESMTP id TAA20805; Sat, 26 Sep 1998 19:10:43 +0900 (JST) Message-Id: <199809261010.TAA20805@zodiac.mech.utsunomiya-u.ac.jp> To: freebsd-smp@FreeBSD.ORG cc: jlemon@FreeBSD.ORG, yokota@zodiac.mech.utsunomiya-u.ac.jp Subject: VM86 on SMP Date: Sat, 26 Sep 1998 19:10:43 +0900 From: Kazutaka YOKOTA Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I compiled a SMP kernel with VM86. It appears that the kernel panics as soon as something makes a vm86 call. Example 1: Enable apm0, then the kernel panics while apm0 is probed. Trap 12 fault virtual address: 0xa00 fault code: superviser write vm86_prepcall() at vm86_prepcall+0x4a vm86_bioscall() at vm86_bioscall+0xe4 apmprobe() at apmprobe+0x3d movl %eax,0(%edx,0) at vm86_prepcall+0x4a Example 2: Boot the kernel without APM, then try to load the VESA LKM. The same panic at the same place. vm86_prepcall() at vm86_prepcall+0x4a vm86_bioscall() at vm86_bioscall+0xe4 But, this time it is the VESA LKM initialization routine which is calling VM86. The uniprocessor kernel has, of cource, no problems in the above situations. I think the fault is at the following line. We have a hardcoded address here: 0xa00, Is this address valid in SMP? vm86_prepcall(struct vm86frame vmf) { uintptr_t addr[] = { 0xA00, 0x1000 }; /* code, stack */ u_char intcall[] = { CLI, INTn, 0x00, STI, HLT }; if ((vmf.vmf_trapno & PAGE_MASK) <= 0xff) { /*interrupt call requested */ intcall[2] = (u_char)(vmf.vmf_trapno & 0xff); memcpy((void *)addr[0], (void *)intcall, sizeof(intcall)); ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ vmf.vmf_ip = addr[0]; vmf.vmf_cs = 0; } vmf.vmf_sp = addr[1] - 2; /* keep aligned */ vmf.kernel_es = vmf.kernel_ds = 0; vmf.vmf_ss = 0; vmf.vmf_eflags = PSL_VIF | PSL_VM | PSL_USER; vm86_initflags(&vmf); } Kazu To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message