From owner-freebsd-smp Sun Dec 21 04:34:52 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id EAA26673 for smp-outgoing; Sun, 21 Dec 1997 04:34:52 -0800 (PST) (envelope-from owner-freebsd-smp) Received: from frmug.org (frmug-gw.frmug.org [193.56.58.252]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id EAA26667 for ; Sun, 21 Dec 1997 04:34:47 -0800 (PST) (envelope-from roberto@keltia.freenix.fr) Received: (from uucp@localhost) by frmug.org (8.8.8/frmug-2.2/nospam) with UUCP id NAA06295 for freebsd-smp@FreeBSD.ORG; Sun, 21 Dec 1997 13:34:43 +0100 (CET) (envelope-from roberto@keltia.freenix.fr) Received: (from roberto@localhost) by keltia.freenix.fr (8.8.8/keltia-2.13/nospam) id NAA06097; Sun, 21 Dec 1997 13:23:45 +0100 (CET) (envelope-from roberto) Message-ID: <19971221132344.10742@keltia.freenix.fr> Date: Sun, 21 Dec 1997 13:23:44 +0100 From: Ollivier Robert To: freebsd-smp@freebsd.org Subject: Re: cpu monitor References: <3.0.1.32.19971220100029.04e194d0@sltic.com> <14562.882643029@time.cdrom.com> <199712210603.AAA00653@zuhause.mn.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.88 In-Reply-To: <199712210603.AAA00653@zuhause.mn.org>; from Bruce Albrecht on Sun, Dec 21, 1997 at 12:03:59AM -0600 X-Operating-System: FreeBSD 3.0-CURRENT ctm#3883 AMD-K6 MMX @ 208 MHz Sender: owner-freebsd-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk According to Bruce Albrecht: > It would be better to send any diffs for top to William LeFebvre > (wnl@groupsys.com), since he's the maintainer of top. Even the latest > version of top (3.5 beta 7) doesn't break it down by CPU for SMP > systems (at least not for FreeBSD or Solaris). The version of top shipped with HP-UX 10.20 does make a different display for multiple processors. I don't know if their modifications are public or not... -- Ollivier ROBERT -=- FreeBSD: The Power to Serve! -=- roberto@keltia.freenix.fr FreeBSD keltia.freenix.fr 3.0-CURRENT #19: Tue Dec 9 20:17:10 CET 1997 From owner-freebsd-smp Mon Dec 22 08:32:51 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id IAA03574 for smp-outgoing; Mon, 22 Dec 1997 08:32:51 -0800 (PST) (envelope-from owner-freebsd-smp) Received: from damon.com (root@damon.com [207.170.114.1]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id IAA03555; Mon, 22 Dec 1997 08:32:33 -0800 (PST) (envelope-from dap@damon.com) Received: (from dap@localhost) by damon.com (8.8.3/8.8.3) id KAA02374; Mon, 22 Dec 1997 10:32:19 -0600 (CST) From: Damon Anton Permezel Message-Id: <199712221632.KAA02374@damon.com> Subject: -current panics, possibly -smp related To: freebsd-smp@freebsd.org, freebsd-current@freebsd.org Date: Mon, 22 Dec 1997 10:32:18 -0600 (CST) X-Mailer: ELM [version 2.4ME+ PL22 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Yo! I just subscribed last nite, so forgive me if this has been discussed already. I have a P-II MP system, with one CPU (thats all they had in stock). When I boot the smp kernel, and run "make world", i have twice now panic()ed as follows. When rebooting on the non-smp kernel, I can run "make world" until I run out of disk space ;-). Here is a synopsis of the error: trap 12 mp_lock = 2 virt = deadc0ea fault = supervisor read, page not present procfs_exit + 0x18 cmpl %esi, 0xc(%ebx) ebx = deadc0de procfs_exit is just running the linked list: for (pfs = pfshead; pfs ; pfs = pfs->pfs_next) { if (pfs->pfs_pid == pid) vgone(PFSTOV(pfs)); I ran the list (the last time) and it appeared to terminate with 0. I say "appeared" because this was the first time I used this debugger, and it was 1am, after 2 margaritas, so in the light of day, I have no reason to believe myself. When it happens again, I will run the pfshead list and verify. This may be of interest (from the non-mp kernel boot): FreeBSD 3.0-971208-SNAP #0: Sun Dec 21 20:39:48 CST 1997 root@xylyl.damon.com:/usr/src/sys/compile/XYLYL CPU: Pentium Pro (233.86-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0x633 Stepping=3 Features=0x80fbff real memory = 134217728 (131072K bytes) avail memory = 128253952 (125248K bytes) Probing for devices on PCI bus 0: chip0: rev 0x03 on pci0.0.0 chip1: rev 0x03 on pci0.1.0 chip2: rev 0x01 on pci0.4.0 chip3: rev 0x01 int d irq 10 on pci0.4.2 chip4: rev 0x01 on pci0.4.3 ahc0: rev 0x00 int a irq 10 on pci0.6. From owner-freebsd-smp Mon Dec 22 08:59:21 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id IAA05745 for smp-outgoing; Mon, 22 Dec 1997 08:59:21 -0800 (PST) (envelope-from owner-freebsd-smp) Received: from cod.nosc.mil (root@cod.nosc.mil [128.49.4.5]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id IAA05738 for ; Mon, 22 Dec 1997 08:59:19 -0800 (PST) (envelope-from gshaffer@nosc.mil) Received: from [128.49.16.48] (aegis.nosc.mil [128.49.16.48]) by cod.nosc.mil (8.8.7/8.8.7) with ESMTP id IAA27080; Mon, 22 Dec 1997 08:58:57 -0800 (PST) X-Sender: gshaffer@cod.nosc.mil Message-Id: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Date: Mon, 22 Dec 1997 08:57:23 -0800 To: freebsd-smp@freebsd.org From: Greg Shaffer Subject: Tomcat IV and overclocked 166MMX Cc: gshaffer@cod.nosc.mil Sender: owner-freebsd-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I read some information this weekend on the ability to overclock a recent batch of 166MMX to 233Mhz (SL27-). I was just curious if anybody running FreeBSD might have tried this with the Tomcat IV board? Greg Shaffer From owner-freebsd-smp Mon Dec 22 18:48:45 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id SAA22363 for smp-outgoing; Mon, 22 Dec 1997 18:48:45 -0800 (PST) (envelope-from owner-freebsd-smp) Received: from picard.penw.com (picard.penw.com [207.149.143.101]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id SAA22339 for ; Mon, 22 Dec 1997 18:48:22 -0800 (PST) (envelope-from dennisg@penw.com) Received: from faq.penw.com (faq.penw.com [130.25.50.10]) by picard.penw.com (8.8.8/8.8.8) with SMTP id SAA08416 for ; Mon, 22 Dec 1997 18:48:16 -0800 (PST) Received: by localhost with Microsoft MAPI; Mon, 22 Dec 1997 18:48:15 -0800 Message-ID: <01BD0F0A.29895E80.dennisg@penw.com> From: dennisg To: "'freebsd-smp@freebsd.org'" Subject: Does GW2k GP6-300-2 support SMP? Date: Mon, 22 Dec 1997 18:48:14 -0800 Organization: Penwest Ltd. X-Mailer: Microsoft Internet E-mail/MAPI - 8.0.0.4211 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I have asked Gateway to research this but if, by chance, someone on this list knows: will FreeBSD's SMP work on the Gateway GP6-300-2? (I've pointed Gateway to the info on http://www.freebsd.org.) Sorry for the silly question. :) -dpg From owner-freebsd-smp Mon Dec 22 20:35:50 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id UAA29261 for smp-outgoing; Mon, 22 Dec 1997 20:35:50 -0800 (PST) (envelope-from owner-freebsd-smp) Received: from mailgate2.aist-nara.ac.jp (fse4.aist-nara.ac.jp [163.221.76.12]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id UAA29251 for ; Mon, 22 Dec 1997 20:35:45 -0800 (PST) (envelope-from takuya-k@is.aist-nara.ac.jp) Received: from ryo1123.aist-nara.ac.jp (ryo1123.aist-nara.ac.jp [163.221.150.32]) by mailgate2.aist-nara.ac.jp (8.8.5+2.7Wbeta5/3.5Wpl5/NAIST/GATE-2.2) with ESMTP id NAA20912 for ; Tue, 23 Dec 1997 13:35:34 +0900 (JST) Received: from ryo1123.aist-nara.ac.jp by ryo1123.aist-nara.ac.jp (8.8.8/2.7W-KASA/1.5) id EAA00654; Tue, 23 Dec 1997 04:35:01 GMT Message-Id: <199712230435.EAA00654@ryo1123.aist-nara.ac.jp> To: freebsd-smp@freebsd.org Subject: Mystery on clock. Date: Tue, 23 Dec 1997 13:35:01 +0900 From: Takuya Koumoto Sender: owner-freebsd-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, I found a strange behaver on smp system. My system is approximately 12/9 of 3.0-current running on a GA586DX with dual P5-133. % time dd if=/dev/zero of=/dev/null bs=1m count=1000 1000+0 records in 1000+0 records out 1048576000 bytes transferred in 10.211286 secs (102687948 bytes/sec) 9.873u 0.299s 0:10.21 99.5% 60+2218k 0+0io 0pf+0w % time dd if=/dev/zero of=/dev/null bs=10m count=100 100+0 records in 100+0 records out 1048576000 bytes transferred in 1.271951 secs (824383984 bytes/sec) 0.977u 0.309s 0:01.29 98.4% 62+20972k 0+0io 0pf+0w Actually, both consume about 12 seconds, but the case of bs=1m is not a problem. Problem is the case of bs=10m. Is it a known problem? Thanks, Takuya. ---