From owner-freebsd-hardware Sun Jun 1 01:58:16 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id BAA14175 for hardware-outgoing; Sun, 1 Jun 1997 01:58:16 -0700 (PDT) Received: from dfw-ix2.ix.netcom.com (dfw-ix2.ix.netcom.com [206.214.98.2]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id BAA14166; Sun, 1 Jun 1997 01:58:03 -0700 (PDT) Received: (from smap@localhost) by dfw-ix2.ix.netcom.com (8.8.4/8.8.4) id DAA01168; Sun, 1 Jun 1997 03:57:31 -0500 (CDT) Received: from sjx-ca25-02.ix.netcom.com(204.30.65.194) by dfw-ix2.ix.netcom.com via smap (V1.3) id sma001163; Sun Jun 1 03:57:14 1997 Received: (from asami@localhost) by blimp.mimi.com (8.8.5/8.6.9) id BAA27939; Sun, 1 Jun 1997 01:57:10 -0700 (PDT) Date: Sun, 1 Jun 1997 01:57:10 -0700 (PDT) Message-Id: <199706010857.BAA27939@blimp.mimi.com> To: roberto@keltia.freenix.fr CC: hardware@freebsd.org, kato@freebsd.org In-reply-to: <19970531191202.58857@keltia.freenix.fr> (message from Ollivier Robert on Sat, 31 May 1997 19:12:02 +0200) Subject: Re: Intel Pentium II released From: asami@cs.berkeley.edu (Satoshi Asami) Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk (Please don't remove Mr. Kato from CC:, I don't think he's on -hardware.) * I'm running it right now. I don't see any increase in speed and the two dd * tests gave the same numbers. I guess the ASUS BIOS has already put the K6 * in that mode... Is it possible to turn it OFF from the kernel? Then we can at least see if it makes any difference.... Satoshi From owner-freebsd-hardware Sun Jun 1 02:06:29 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id CAA14576 for hardware-outgoing; Sun, 1 Jun 1997 02:06:29 -0700 (PDT) Received: from mexico.brainstorm.eu.org (root@mexico.brainstorm.fr [193.56.58.253]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id CAA14569 for ; Sun, 1 Jun 1997 02:06:23 -0700 (PDT) Received: from brasil.brainstorm.eu.org (brasil.brainstorm.fr [193.56.58.33]) by mexico.brainstorm.eu.org (8.8.4/8.8.4) with ESMTP id LAA03580 for ; Sun, 1 Jun 1997 11:06:13 +0200 Received: (from uucp@localhost) by brasil.brainstorm.eu.org (8.8.4/8.6.12) with UUCP id LAA21542 for hardware@FreeBSD.ORG; Sun, 1 Jun 1997 11:05:58 +0200 Received: (from roberto@localhost) by keltia.freenix.fr (8.8.5/keltia-uucp-2.9) id KAA15454; Sun, 1 Jun 1997 10:49:55 +0200 (CEST) Message-ID: <19970601104955.42869@keltia.freenix.fr> Date: Sun, 1 Jun 1997 10:49:55 +0200 From: Ollivier Robert To: hardware@FreeBSD.ORG Subject: Re: Intel Pentium II released References: <19970531191202.58857@keltia.freenix.fr> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.67 In-Reply-To: ; from Mike Andrews on Sat, May 31, 1997 at 09:17:32PM -0400 X-Operating-System: FreeBSD 3.0-CURRENT ctm#3332 Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk According to Mike Andrews: > Which version of the ASUS P55T2P4 BIOS are y'all using? > 0203 (dated mid-May) is supposed to enable these K6 features... earlier > ones supposedly don't know anything about it. I'm using 2.03. When I got my K6, I went to take the 2.02 and found they have released 2.03 so I installed it. -- Ollivier ROBERT -=- FreeBSD: There are no limits -=- roberto@keltia.freenix.fr FreeBSD keltia.freenix.fr 3.0-CURRENT #10: Fri May 23 22:47:39 CEST 1997 From owner-freebsd-hardware Sun Jun 1 02:34:37 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id CAA15690 for hardware-outgoing; Sun, 1 Jun 1997 02:34:37 -0700 (PDT) Received: from mexico.brainstorm.eu.org (root@mexico.brainstorm.fr [193.56.58.253]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id CAA15660; Sun, 1 Jun 1997 02:34:23 -0700 (PDT) Received: from brasil.brainstorm.eu.org (brasil.brainstorm.fr [193.56.58.33]) by mexico.brainstorm.eu.org (8.8.4/8.8.4) with ESMTP id LAA03620; Sun, 1 Jun 1997 11:34:15 +0200 Received: (from uucp@localhost) by brasil.brainstorm.eu.org (8.8.4/8.6.12) with UUCP id LAA21864; Sun, 1 Jun 1997 11:33:57 +0200 Received: (from roberto@localhost) by keltia.freenix.fr (8.8.5/keltia-uucp-2.9) id LAA15704; Sun, 1 Jun 1997 11:29:30 +0200 (CEST) Message-ID: <19970601112930.36404@keltia.freenix.fr> Date: Sun, 1 Jun 1997 11:29:30 +0200 From: Ollivier Robert To: hardware@FreeBSD.ORG Cc: kato@FreeBSD.ORG Subject: Re: Intel Pentium II released References: <19970531191202.58857@keltia.freenix.fr> <199706010857.BAA27939@blimp.mimi.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.67 In-Reply-To: <199706010857.BAA27939@blimp.mimi.com>; from Satoshi Asami on Sun, Jun 01, 1997 at 01:57:10AM -0700 X-Operating-System: FreeBSD 3.0-CURRENT ctm#3332 Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk According to Satoshi Asami: > Is it possible to turn it OFF from the kernel? Then we can at least > see if it makes any difference.... A sysctl-controlled variable would be nice although I don"t see why anyone would want to run without this feature :-) Has anyone tried to use the MMX registers to "emulate" the FPU-based bcopy/bzero/copyin/out routines ? The K6 is said to be a fast MMX processor... I have no documentation on both the assembler syntax (well, maybe somewhere deeply buried) and the MMX registers so it is difficult for me to try it. -- Ollivier ROBERT -=- FreeBSD: There are no limits -=- roberto@keltia.freenix.fr FreeBSD keltia.freenix.fr 3.0-CURRENT #10: Fri May 23 22:47:39 CEST 1997 From owner-freebsd-hardware Sun Jun 1 03:20:16 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id DAA17051 for hardware-outgoing; Sun, 1 Jun 1997 03:20:16 -0700 (PDT) Received: from dfw-ix7.ix.netcom.com (dfw-ix7.ix.netcom.com [206.214.98.7]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id DAA16991; Sun, 1 Jun 1997 03:19:38 -0700 (PDT) Received: (from smap@localhost) by dfw-ix7.ix.netcom.com (8.8.4/8.8.4) id FAA19361; Sun, 1 Jun 1997 05:19:06 -0500 (CDT) Received: from sjx-ca25-02.ix.netcom.com(204.30.65.194) by dfw-ix7.ix.netcom.com via smap (V1.3) id sma019357; Sun Jun 1 05:18:40 1997 Received: (from asami@localhost) by blimp.mimi.com (8.8.5/8.6.9) id DAA28193; Sun, 1 Jun 1997 03:18:37 -0700 (PDT) Date: Sun, 1 Jun 1997 03:18:37 -0700 (PDT) Message-Id: <199706011018.DAA28193@blimp.mimi.com> To: roberto@keltia.freenix.fr CC: hardware@FreeBSD.ORG, kato@FreeBSD.ORG In-reply-to: <19970601112930.36404@keltia.freenix.fr> (message from Ollivier Robert on Sun, 1 Jun 1997 11:29:30 +0200) Subject: Re: Intel Pentium II released From: asami@cs.berkeley.edu (Satoshi Asami) Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk * A sysctl-controlled variable would be nice although I don"t see why anyone * would want to run without this feature :-) Actually, write allocate may not help or even hurt if you are copying large amount of data. If it is implemented the straightforward way, i.e., to read the rest of the bytes in the line when a write to a currently uncached memory ("read-before-writes"), those reads will be simply wasted as the rest of the line is going to be quickly overwritten by writes from the CPU. For this reason, we might even want to disable write caching entirely during a large memory copy (no need to keep them in cache if they are not going to be read again soon enough). * I have no documentation on both the assembler syntax (well, maybe somewhere * deeply buried) and the MMX registers so it is difficult for me to try it. Well, even if you know the assembler syntax, you need an assembler that understands it don't you. :) So, please take a look at PR gnu/3157. (The syntax is just like regular mov instructions anyway.) Also, you can get a sample test program from: ftp://stampede.cs.berkeley.edu/pub/bcopy/bcopy-960524.tar.gz as you probably don't want to change sys/i386/i386/support.s without making sure it works first. :) Satoshi From owner-freebsd-hardware Sun Jun 1 04:26:42 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id EAA18757 for hardware-outgoing; Sun, 1 Jun 1997 04:26:42 -0700 (PDT) Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.19]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id EAA18744; Sun, 1 Jun 1997 04:26:32 -0700 (PDT) Received: (from bde@localhost) by godzilla.zeta.org.au (8.8.5/8.6.9) id VAA19986; Sun, 1 Jun 1997 21:25:02 +1000 Date: Sun, 1 Jun 1997 21:25:02 +1000 From: Bruce Evans Message-Id: <199706011125.VAA19986@godzilla.zeta.org.au> To: asami@cs.berkeley.edu, roberto@keltia.freenix.fr Subject: Re: Intel Pentium II released Cc: hardware@FreeBSD.ORG, kato@FreeBSD.ORG Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > * A sysctl-controlled variable would be nice although I don"t see why anyone > * would want to run without this feature :-) > >Actually, write allocate may not help or even hurt if you are copying >large amount of data. If it is implemented the straightforward way, >i.e., to read the rest of the bytes in the line when a write to a >currently uncached memory ("read-before-writes"), those reads will be >simply wasted as the rest of the line is going to be quickly >overwritten by writes from the CPU. For this reason, we might even >want to disable write caching entirely during a large memory copy (no >need to keep them in cache if they are not going to be read again soon >enough). It does seem to be implemented in a straightforward way on P6/Natoma systems. This results in a about 2 times slowdown for the `dd if=/dev/zero of=/dev/null bs=1m' test and a 3/2 times slowdown for large bcopies. I tried setting the per-page cache disable bits in pmap_zero_page() and pmap_zero_page(). I couldn't see any effect on a P5 system. This is not surprising, since there is no write allocation on P5's. Note that pmap_zero_page() and pmap_copy_page() invalidate the caching for the pages after accessing them, so any write caching is harmful - cached data on other pages is discarded to make room, then the results of the write are discarded. Read caching is probably harmful except in the "i586-optimized" case which depends on it. >Well, even if you know the assembler syntax, you need an assembler >that understands it don't you. :) No :-). See wrmsr(). Bruce From owner-freebsd-hardware Sun Jun 1 10:33:31 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA28402 for hardware-outgoing; Sun, 1 Jun 1997 10:33:31 -0700 (PDT) Received: from kithrup.com (kithrup.com [205.179.156.40]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id KAA28397 for ; Sun, 1 Jun 1997 10:33:28 -0700 (PDT) Received: (from sef@localhost) by kithrup.com (8.6.8/8.6.6) id KAA29965; Sun, 1 Jun 1997 10:01:05 -0700 Date: Sun, 1 Jun 1997 10:01:05 -0700 From: Sean Eric Fagan Message-Id: <199706011701.KAA29965@kithrup.com> To: hardware@freebsd.org Subject: Re: Intel Pentium II released Newsgroups: kithrup.freebsd.hardware In-Reply-To: <19970601104955.42869.kithrup.freebsd.hardware@keltia.freenix.fr> References: ; from Mike Andrews on Sat, May 31, 1997 at 09:17:32PM -0400 Organization: Kithrup Enterprises, Ltd. Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk In article <19970601104955.42869.kithrup.freebsd.hardware@keltia.freenix.fr> you write: >According to Mike Andrews: >> Which version of the ASUS P55T2P4 BIOS are y'all using? >> 0203 (dated mid-May) is supposed to enable these K6 features... earlier >> ones supposedly don't know anything about it. >I'm using 2.03. When I got my K6, I went to take the 2.02 and found they >have released 2.03 so I installed it. I, on the other hand, have a revions 2. *board* -- and I'm told that I can't run the K6 as a result (base level being revision 3). I bought this board about a year ago, I think. Maybe a bit more. If anyone knows otherwise, that would be nice -- I would like to get a K6 instead of the P133 it currently has. From owner-freebsd-hardware Mon Jun 2 19:43:31 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id TAA28930 for hardware-outgoing; Mon, 2 Jun 1997 19:43:31 -0700 (PDT) Received: from george.lbl.gov (george-2.lbl.gov [131.243.2.12]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id TAA28872; Mon, 2 Jun 1997 19:40:38 -0700 (PDT) Received: (jin@localhost) by george.lbl.gov (8.6.10/8.6.5) id TAA16816; Mon, 2 Jun 1997 19:40:32 -0700 Date: Mon, 2 Jun 1997 19:40:32 -0700 From: "Jin Guojun[ITG]" Message-Id: <199706030240.TAA16816@george.lbl.gov> To: smp@csn.net Subject: Re: SMP (3.0-970527-SNAP) on dual pentium machines Cc: hardware@FreeBSD.ORG, smp@FreeBSD.ORG Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk } > I have two different dual pentium motherboards: } > 1) ASUS P/I-P65UP5 with C-P55T2D } > 2) TYAN S1563D } > } > neither of them really gets worked for SMP. Here is the testing result by } > using pthread library -lc_r: } > } > ----------------------- } > } > FreeBSD with single CPU: } > 60 /data/src: vfft mri.b128 > /dev/null } > 9.7u 0.1s 0:09.95 99.3% 97+11132k 0+0io 0pf+0w } > } > FreeBSD with dual CPU + pthread (failure SMP): } > 62 /data/src: vfft.mt < mri.b128 > /dev/null } > 9.5u 0.2s 0:09.83 99.1% 77+11822k 0+0io 0pf+0w } > } > } > ----------------------- } > } > Solaris 2.5.1.u8 with single CPU: } > 67 /home/data/src: vfft mri.b128 > /dev/null } > 12.0u 0.0s 0:13 87% 0+0k 0+0io 0pf+0w } > } > Solaris 2.5.1.u8 with dual CPU + thread (SMP): } > 69 /home/data/src: vfft.mt mri.b128 > /dev/null } > 12.0u 0.0s 0:07 168% 0+0k 0+0io 0pf+0w } > } > ----------------------- Actually, I had a mistake on testing of FreeBSD with dual CPU + pthread. The SMP /kernel.smp was not booted when doing above testing due to some problem. After trying different SMP options for SMP kernel, I still cannot make it work on these two motherboards. Both systems have page fault (12) after message: apm0: disabled, not probed. (cpu#0) panic: page fault ... The /sys/i386/conf/KSMP configuration file is attached at end of this message. } what you are demonstrating is the fact that we do not yet have kernel threads } working. The threads provided by our libc_r all run in one process, thus no } improvement in thruput for your test. } } Note that FreeBSD does much better (if I'm reading thse right) than Solaris } in the single CPU test. Once we have kernel threads we should also do } substantially better than Solaris in the MP test. Yes. What you read is the truth. In comparing BSD/OS, FreeBSD, Solaris.x86, FreeBSD has the best performance at most areas. That is the reason that we are working on FreeBSD for developing high end file server. It is appreciated if some one can tell me if above motherboards have been tested under FreeBSD 3.0. If not, what are the motherboards tested for SMP version? I do really like to run FreeBSD on some dual pentium (not P6) boxes. Thanks, -Jin From owner-freebsd-hardware Mon Jun 2 20:10:45 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id UAA29889 for hardware-outgoing; Mon, 2 Jun 1997 20:10:45 -0700 (PDT) Received: from asa1.asan.com (asa1.asan.com [206.20.111.11]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id UAA29884 for ; Mon, 2 Jun 1997 20:10:43 -0700 (PDT) Received: from ppp97.asan.com (ppp97.asan.com [206.20.111.97]) by asa1.asan.com (NTMail 3.02.13) with ESMTP id ca269726 for ; Mon, 2 Jun 1997 23:10:35 -0400 Message-Id: <3.0.1.32.19970602231043.00f8bffc@asan.com> X-Sender: bugtraq@asan.com X-Mailer: Windows Eudora Pro Version 3.0.1 (32) Date: Mon, 02 Jun 1997 23:10:43 -0400 To: Georges Arhodakis From: WaiKin Wong Subject: Re: DIP Switch Information Cc: freebsd-hardware@FreeBSD.ORG In-Reply-To: <199706021735.TAA08605@bach.ai.univ-paris8.fr> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk At 07:35 PM 6/2/97 +0200, Georges Arhodakis wrote: >Hi !, >I am looking for the DE201 EtherWorks Documentation. Specialy for the >DIP Switch of the NIC adapter. The adapter comes from Digital Equipment Corp. >Too many thanks. > >Giorgos ARHODAKIS > Guess what manufacturer has a web site with the documentation. ;) http://www.networks.digital.com/html/ethernet-adapters.html http://www.networks.digital.com/dr/nics/manuals/ http://www.networks.digital.com/dr/nics/manuals/de201-om.pdf From owner-freebsd-hardware Tue Jun 3 09:33:28 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id JAA07770 for hardware-outgoing; Tue, 3 Jun 1997 09:33:28 -0700 (PDT) Received: from dfw-ix8.ix.netcom.com (dfw-ix8.ix.netcom.com [206.214.98.8]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA07761 for ; Tue, 3 Jun 1997 09:33:24 -0700 (PDT) Received: (from smap@localhost) by dfw-ix8.ix.netcom.com (8.8.4/8.8.4) id LAA13954; Tue, 3 Jun 1997 11:31:55 -0500 (CDT) Received: from sil-wa2-19.ix.netcom.com(206.214.137.51) by dfw-ix8.ix.netcom.com via smap (V1.3) id sma013911; Tue Jun 3 11:30:33 1997 Message-ID: <339446BB.11D2@ix.netcom.com> Date: Tue, 03 Jun 1997 09:30:51 -0700 From: "Thomas D. Dean" Reply-To: tomdean@ix.netcom.com Organization: Home X-Mailer: Mozilla 3.01 (WinNT; I) MIME-Version: 1.0 To: Georges Arhodakis CC: freebsd-hardware@FreeBSD.ORG Subject: Re: DIP Switch Information References: <199706021735.TAA08605@bach.ai.univ-paris8.fr> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk look at http://www.networks.digital.com/dr/nics/manuals/ I believe all the DEC nic manuals are there. I saw a postscript and an Adobe version of the de201 manual. From owner-freebsd-hardware Wed Jun 4 06:35:05 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id GAA28192 for hardware-outgoing; Wed, 4 Jun 1997 06:35:05 -0700 (PDT) Received: from mail.nacamar.de (mail.nacamar.de [194.162.162.200]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id GAA28185 for ; Wed, 4 Jun 1997 06:35:02 -0700 (PDT) Received: from newsfeed (newsfeed.nacamar.de [194.162.162.196]) by mail.nacamar.de (8.8.5/8.8.5) with SMTP id PAA04796 for ; Wed, 4 Jun 1997 15:34:56 +0200 (CEST) Message-Id: <3.0.1.32.19970604153456.00cdee50@mail.nacamar.de> X-Sender: petzi@mail.nacamar.de X-Mailer: Windows Eudora Pro Version 3.0.1 (32) Date: Wed, 04 Jun 1997 15:34:56 +0200 To: hardware@freebsd.org From: Michael Beckmann Subject: SMC EtherPower 10/100 on 10BaseT network Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Greetings, I have obtained an SMC EtherPower 10/100 Rev. C Ethernet card with a Digital 21140-AE chip. When the system is booted, the link state on the 10BaseT hub is dropped. The card is switched to 100BaseTX mode. I searched the mailing list archives, but haven't found messages relevant to this issue. Anybody know how to force the card into 10BaseT mode ? Thanks, Michael From owner-freebsd-hardware Wed Jun 4 07:31:02 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id HAA00665 for hardware-outgoing; Wed, 4 Jun 1997 07:31:02 -0700 (PDT) Received: from mail.nacamar.de (mail.nacamar.de [194.162.162.200]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id HAA00653 for ; Wed, 4 Jun 1997 07:30:58 -0700 (PDT) Received: from newsfeed (newsfeed.nacamar.de [194.162.162.196]) by mail.nacamar.de (8.8.5/8.8.5) with SMTP id QAA08130 for ; Wed, 4 Jun 1997 16:30:56 +0200 (CEST) Message-Id: <3.0.1.32.19970604163056.00cb0650@mail.nacamar.de> X-Sender: petzi@mail.nacamar.de X-Mailer: Windows Eudora Pro Version 3.0.1 (32) Date: Wed, 04 Jun 1997 16:30:56 +0200 To: hardware@freebsd.org From: Michael Beckmann Subject: Re: SMC EtherPower 10/100 on 10BaseT network Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, I forgot to add that I run FreeBSD 2.2.2. Michael From owner-freebsd-hardware Wed Jun 4 08:54:31 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id IAA06210 for hardware-outgoing; Wed, 4 Jun 1997 08:54:31 -0700 (PDT) Received: from Campino.Informatik.RWTH-Aachen.DE (campino.Informatik.RWTH-Aachen.DE [137.226.116.240]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id IAA06202 for ; Wed, 4 Jun 1997 08:54:28 -0700 (PDT) Received: from gil.physik.rwth-aachen.de (gilberto.physik.rwth-aachen.de [137.226.31.2]) by Campino.Informatik.RWTH-Aachen.DE (RBI-Z-5/8.6.12) with ESMTP id RAA04733; Wed, 4 Jun 1997 17:54:31 +0200 (MET DST) Received: (from kuku@localhost) by gil.physik.rwth-aachen.de (8.8.5/8.6.9) id RAA03967; Wed, 4 Jun 1997 17:57:26 +0200 (MEST) Message-ID: <19970604175725.20973@gil.physik.rwth-aachen.de> Date: Wed, 4 Jun 1997 17:57:25 +0200 From: Christoph Kukulies To: Michael Beckmann Cc: hardware@FreeBSD.ORG Subject: Re: SMC EtherPower 10/100 on 10BaseT network References: <3.0.1.32.19970604153456.00cdee50@mail.nacamar.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69e In-Reply-To: <3.0.1.32.19970604153456.00cdee50@mail.nacamar.de>; from Michael Beckmann on Wed, Jun 04, 1997 at 03:34:56PM +0200 Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Wed, Jun 04, 1997 at 03:34:56PM +0200, Michael Beckmann wrote: > Greetings, > > I have obtained an SMC EtherPower 10/100 Rev. C Ethernet card with a > Digital 21140-AE chip. When the system is booted, the link state on the > 10BaseT hub is dropped. The card is switched to 100BaseTX mode. I searched > the mailing list archives, but haven't found messages relevant to this > issue. Anybody know how to force the card into 10BaseT mode ? Wasn't it to use the link2 vs. -link2 flag to the ifconfig command? > > Thanks, > > Michael -- -- Chris Christoph P. U. Kukulies kuku@gil.physik.rwth-aachen.de From owner-freebsd-hardware Wed Jun 4 10:17:17 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id KAA11383 for hardware-outgoing; Wed, 4 Jun 1997 10:17:17 -0700 (PDT) Received: from GndRsh.aac.dev.com (GndRsh.aac.dev.com [198.145.92.241]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id KAA11378 for ; Wed, 4 Jun 1997 10:17:14 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.8.5/8.7.3) id KAA18640; Wed, 4 Jun 1997 10:16:50 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199706041716.KAA18640@GndRsh.aac.dev.com> Subject: Re: SMC EtherPower 10/100 on 10BaseT network In-Reply-To: <3.0.1.32.19970604153456.00cdee50@mail.nacamar.de> from Michael Beckmann at "Jun 4, 97 03:34:56 pm" To: beckmann@nacamar.de (Michael Beckmann) Date: Wed, 4 Jun 1997 10:16:50 -0700 (PDT) Cc: hardware@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL25 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > Greetings, > > I have obtained an SMC EtherPower 10/100 Rev. C Ethernet card with a > Digital 21140-AE chip. When the system is booted, the link state on the I haven't seen the Rev C card with the 21140-AE chip yet, but you could try adding a ``-link2'' to your ifconfig statement which should force the card into 10BaseT mode. > 10BaseT hub is dropped. The card is switched to 100BaseTX mode. I searched > the mailing list archives, but haven't found messages relevant to this > issue. Anybody know how to force the card into 10BaseT mode ? Does the card report itself as an ``SMC9332BDT'' during the boot, or is it comming up as a generic 21140 card? Ie, can you send us the dmesg output for it? -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation, Inc. Reliable computers for FreeBSD From owner-freebsd-hardware Wed Jun 4 11:08:17 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA15517 for hardware-outgoing; Wed, 4 Jun 1997 11:08:17 -0700 (PDT) Received: from mail.nacamar.de (mail.nacamar.de [194.162.162.200]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA15506 for ; Wed, 4 Jun 1997 11:08:11 -0700 (PDT) Received: from newsfeed (newsfeed.nacamar.de [194.162.162.196]) by mail.nacamar.de (8.8.5/8.8.5) with SMTP id UAA13082; Wed, 4 Jun 1997 20:07:32 +0200 (CEST) Message-Id: <3.0.1.32.19970604200733.00ced4c0@mail.nacamar.de> X-Sender: petzi@mail.nacamar.de X-Mailer: Windows Eudora Pro Version 3.0.1 (32) Date: Wed, 04 Jun 1997 20:07:33 +0200 To: "Rodney W. Grimes" From: Michael Beckmann Subject: Re: SMC EtherPower 10/100 on 10BaseT network Cc: hardware@FreeBSD.ORG In-Reply-To: <199706041716.KAA18640@GndRsh.aac.dev.com> References: <3.0.1.32.19970604153456.00cdee50@mail.nacamar.de> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk >I haven't seen the Rev C card with the 21140-AE chip yet, but you >could try adding a ``-link2'' to your ifconfig statement which should >force the card into 10BaseT mode. After issuing ifconfig de0 -link2 on the command line, it said it was in 10BaseT mode, but still no link state. Hmm. >Does the card report itself as an ``SMC9332BDT'' during the boot, >or is it comming up as a generic 21140 card? Ie, can you send >us the dmesg output for it? de0 rev 34 int a irq 9 on pci0:100 mapreg[10] type=1 addr=0000f880 size=0080. mapreg[14] type=0 addr=fffbrc00 size=0080. reg16: ioaddr=0xf880 size=0x80 de0: 21140A [10-100Mb/s] pass 2.2 de0: address 00:e0:29:00:c0:0b de0: enabling 100baseTX port Cheers, Michael From owner-freebsd-hardware Wed Jun 4 11:55:42 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA20394 for hardware-outgoing; Wed, 4 Jun 1997 11:55:42 -0700 (PDT) Received: from GndRsh.aac.dev.com (GndRsh.aac.dev.com [198.145.92.241]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA20374 for ; Wed, 4 Jun 1997 11:55:37 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.8.5/8.7.3) id LAA19189; Wed, 4 Jun 1997 11:55:18 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199706041855.LAA19189@GndRsh.aac.dev.com> Subject: Re: SMC EtherPower 10/100 on 10BaseT network In-Reply-To: <3.0.1.32.19970604200733.00ced4c0@mail.nacamar.de> from Michael Beckmann at "Jun 4, 97 08:07:33 pm" To: beckmann@nacamar.de (Michael Beckmann) Date: Wed, 4 Jun 1997 11:55:18 -0700 (PDT) Cc: hardware@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL25 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > >I haven't seen the Rev C card with the 21140-AE chip yet, but you > >could try adding a ``-link2'' to your ifconfig statement which should > >force the card into 10BaseT mode. > > After issuing ifconfig de0 -link2 on the command line, it said it was in > 10BaseT mode, but still no link state. Hmm. > > >Does the card report itself as an ``SMC9332BDT'' during the boot, > >or is it comming up as a generic 21140 card? Ie, can you send > >us the dmesg output for it? > > de0 rev 34 int a irq 9 on pci0:100 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Arghhh... it appears as if they have made yet another change to the SMC cards that is causing us greif. From the above message your card is being identified as a Generic DC21140A card, probably assuming the old phy interface which is causing you greif. > mapreg[10] type=1 addr=0000f880 size=0080. > mapreg[14] type=0 addr=fffbrc00 size=0080. > reg16: ioaddr=0xf880 size=0x80 > de0: 21140A [10-100Mb/s] pass 2.2 > de0: address 00:e0:29:00:c0:0b ^^^^^^^^ Hummm.... this looks like a new OUI for SMC, you might try the following quick hack to if_de.c to see if it makes the card work. If it does I'll create a more appropriate patch... Index: if_de.c =================================================================== RCS file: /home/ncvs/src/sys/pci/if_de.c,v retrieving revision 1.54.2.5 diff -c -r1.54.2.5 if_de.c *** if_de.c 1997/04/20 05:21:34 1.54.2.5 --- if_de.c 1997/06/04 18:54:20 *************** *** 3289,3297 **** sc->tulip_boardsw = &tulip_21040_zx314_master_boardsw; sc->tulip_flags |= TULIP_SHAREDINTR; } ! } else if (sc->tulip_hwaddr[0] == TULIP_OUI_SMC_0 ! && sc->tulip_hwaddr[1] == TULIP_OUI_SMC_1 ! && sc->tulip_hwaddr[2] == TULIP_OUI_SMC_2) { tulip_identify_smc_nic(sc); } --- 3289,3297 ---- sc->tulip_boardsw = &tulip_21040_zx314_master_boardsw; sc->tulip_flags |= TULIP_SHAREDINTR; } ! } else if (sc->tulip_hwaddr[0] == 0x00 ! && sc->tulip_hwaddr[1] == 0xE0 ! && sc->tulip_hwaddr[2] == 0x29) { tulip_identify_smc_nic(sc); } -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation, Inc. Reliable computers for FreeBSD From owner-freebsd-hardware Wed Jun 4 11:59:29 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA20782 for hardware-outgoing; Wed, 4 Jun 1997 11:59:29 -0700 (PDT) Received: from mail.cdsnet.net (mail.cdsnet.net [204.118.244.5]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA20777 for ; Wed, 4 Jun 1997 11:59:21 -0700 (PDT) Received: from johndoe (1Cust30.Max13.Boston.MA.MS.UU.NET [153.35.75.158]) by mail.cdsnet.net (8.8.5/8.7.3) with SMTP id LAA13357; Wed, 4 Jun 1997 11:59:06 -0700 (PDT) Message-Id: <3.0.1.32.19970604145811.00b5cf28@ranier.altavista-software.com> X-Sender: 3ampop@ranier.altavista-software.com X-Mailer: Windows Eudora Pro Version 3.0.1 (32) Date: Wed, 04 Jun 1997 14:58:11 -0400 To: Michael Beckmann From: Matt Thomas Subject: Re: SMC EtherPower 10/100 on 10BaseT network Cc: hardware@freebsd.org In-Reply-To: <3.0.1.32.19970604153456.00cdee50@mail.nacamar.de> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk At 03:34 PM 6/4/97 +0200, you wrote: >Greetings, > >I have obtained an SMC EtherPower 10/100 Rev. C Ethernet card with a >Digital 21140-AE chip. When the system is booted, the link state on the >10BaseT hub is dropped. The card is switched to 100BaseTX mode. I searched >the mailing list archives, but haven't found messages relevant to this >issue. Anybody know how to force the card into 10BaseT mode ? Use the driver at http://www.3am-software.com/de-970603.tar.gz (or de-970513.tar.gz; the 970603 version has an improved transmit path which results in better performance). -- Matt Thomas Internet: matt@3am-software.com 3am Software Foundry WWW URL: http://www.3am-software.com/bio/matt.html Westford, MA Disclaimer: I disavow all knowledge of this message From owner-freebsd-hardware Wed Jun 4 12:11:04 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA22177 for hardware-outgoing; Wed, 4 Jun 1997 12:11:04 -0700 (PDT) Received: from mail.nacamar.de (mail.nacamar.de [194.162.162.200]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id MAA22157 for ; Wed, 4 Jun 1997 12:11:00 -0700 (PDT) Received: from newsfeed (newsfeed.nacamar.de [194.162.162.196]) by mail.nacamar.de (8.8.5/8.8.5) with SMTP id VAA14682; Wed, 4 Jun 1997 21:10:46 +0200 (CEST) Message-Id: <3.0.1.32.19970604211046.00cbe100@mail.nacamar.de> X-Sender: petzi@mail.nacamar.de X-Mailer: Windows Eudora Pro Version 3.0.1 (32) Date: Wed, 04 Jun 1997 21:10:46 +0200 To: Matt Thomas From: Michael Beckmann Subject: Re: SMC EtherPower 10/100 on 10BaseT network Cc: hardware@freebsd.org In-Reply-To: <3.0.1.32.19970604145811.00b5cf28@ranier.altavista-software .com> References: <3.0.1.32.19970604153456.00cdee50@mail.nacamar.de> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >Use the driver at http://www.3am-software.com/de-970603.tar.gz (or >de-970513.tar.gz; the 970603 version has an improved transmit path >which results in better performance). Thanks to a hint from Larry Baird, who pointed me to this driver, we made the card work in the mean time. We installed FreeBSD 2.2.2 on that box via ftp, using an SMC EtherPower 10. Then we made a new kernel with your driver. The 10/100 card worked out of the box with de-970513.tar.gz, we'll try the 970603 of course. Thanks a lot, Michael From owner-freebsd-hardware Wed Jun 4 12:49:23 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id MAA27651 for hardware-outgoing; Wed, 4 Jun 1997 12:49:23 -0700 (PDT) Received: from stingray.ivision.co.uk (stingray.ivision.co.uk [194.154.62.72]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id MAA27628 for ; Wed, 4 Jun 1997 12:49:16 -0700 (PDT) Received: from stingray.ivision.co.uk [194.154.62.72] by stingray.ivision.co.uk with smtp (Exim 0.53 #1) id E0wZM2w-0002wn-00; Wed, 4 Jun 1997 20:48:38 +0100 Date: Wed, 4 Jun 1997 20:48:38 +0100 (BST) From: Manar Hussain To: hardware@freebsd.org Subject: Network/graphics card Message-ID: Organisation: Internet Vision MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Is there somewehere with an kept up-to-date list of recommendations of what cards one is advised to get for decent performance/ease of use? What would the recommendation be on a 10/100 ethernet card + mid-level graphics card ? Cheers, Manar From owner-freebsd-hardware Wed Jun 4 13:22:04 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id NAA04606 for hardware-outgoing; Wed, 4 Jun 1997 13:22:04 -0700 (PDT) Received: from agora.rdrop.com (root@agora.rdrop.com [199.2.210.241]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA04597 for ; Wed, 4 Jun 1997 13:22:01 -0700 (PDT) Received: from mail.nacamar.de (mail.nacamar.de [194.162.162.200]) by agora.rdrop.com (8.8.5/8.8.5) with ESMTP id NAA20502 for ; Wed, 4 Jun 1997 13:21:49 -0700 (PDT) Received: from newsfeed (newsfeed.nacamar.de [194.162.162.196]) by mail.nacamar.de (8.8.5/8.8.5) with SMTP id WAA15480; Wed, 4 Jun 1997 22:20:14 +0200 (CEST) Message-Id: <3.0.1.32.19970604222015.00b0ade0@mail.nacamar.de> X-Sender: petzi@mail.nacamar.de X-Mailer: Windows Eudora Pro Version 3.0.1 (32) Date: Wed, 04 Jun 1997 22:20:15 +0200 To: "Rodney W. Grimes" From: Michael Beckmann Subject: Re: SMC EtherPower 10/100 on 10BaseT network Cc: hardware@FreeBSD.ORG In-Reply-To: <199706041855.LAA19189@GndRsh.aac.dev.com> References: <3.0.1.32.19970604200733.00ced4c0@mail.nacamar.de> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk At 11:55 04.06.97 -0700, Rodney W. Grimes wrote: >Hummm.... this looks like a new OUI for SMC, you might try the >following quick hack to if_de.c to see if it makes the card >work. If it does I'll create a more appropriate patch... The patch works. The link state does not go away any more when the kernel finds the card during boot. I applied it to a 2.2.1-RELEASE system. It even works when I take out the -link2 option to ifconfig. I will not be able to conduct any further tests with this specific card, because it is now integrated into a production system :-) Thanks, Michael From owner-freebsd-hardware Thu Jun 5 13:49:03 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id NAA06295 for hardware-outgoing; Thu, 5 Jun 1997 13:49:03 -0700 (PDT) Received: from apollo.netsonic.com (netsonic.com [207.250.84.2]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA06286 for ; Thu, 5 Jun 1997 13:48:57 -0700 (PDT) Received: from adam.netsonic.com (zeus.netsonic.com [207.250.84.25]) by apollo.netsonic.com (8.8.5/8.8.5) with SMTP id PAA19834 for ; Thu, 5 Jun 1997 15:47:59 -0500 (CDT) Message-Id: <3.0.32.19970605154815.00751a20@mail.netsonic.net> X-Sender: adam@mail.netsonic.net X-Mailer: Windows Eudora Pro Version 3.0 (32) Date: Thu, 05 Jun 1997 15:48:16 -0500 To: freebsd-hardware@freebsd.org From: NetSonic Subject: APC 650 and Config Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi all. Just curious how you fellow ISP people have your UPS Battery Systems configured for use? Are you running the System thru another box such as a Win95 box or are you able to get it configured to shutdown the system directly on the FreeBSD box? IF this is the case can you explain how this may be accomplished? Sorry for the amateur sound of this, but I am still pretty new at this FreeBSD stuff. I appreciate your help! Thanks Adam From owner-freebsd-hardware Fri Jun 6 13:35:31 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id NAA10247 for hardware-outgoing; Fri, 6 Jun 1997 13:35:31 -0700 (PDT) Received: from sparkie.gnofn.org (sparkie.gnofn.org [206.27.168.35]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA10240 for ; Fri, 6 Jun 1997 13:35:27 -0700 (PDT) Received: from sparkie.gnofn.org (sparkie.gnofn.org [206.27.168.35]) by sparkie.gnofn.org (8.7.Beta.10/8.7.Beta.10) with SMTP id PAA20089 for ; Fri, 6 Jun 1997 15:35:10 -0500 (CDT) Date: Fri, 6 Jun 1997 15:35:10 -0500 (CDT) From: Craig Johnston To: hardware@freebsd.org Subject: psm0 problems Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I'm using a Mousesystems optical mouse plugged into the ps/2 port of my ABIT IT5H mobo. Kernel is FreeBSD 2.2-stable cvsup'd yesterday, June 5. Problem is, when psm0 is enabled, I just hang at the check for it. I enabled the debugging info, I get this during boot: psm0: current command byte:0047 kbdio: new command byte:0054 (set controller...) kbdio: TEST_AUX_PORT status:0000 and then we hang. I had the same problem previously, but sometimes if I played with the mouse as the system came up I was able to get it detected and working fine. Apparently not so anymore. Any clues? regards, Craig. From owner-freebsd-hardware Fri Jun 6 14:40:51 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id OAA13972 for hardware-outgoing; Fri, 6 Jun 1997 14:40:51 -0700 (PDT) Received: from sparkie.gnofn.org (sparkie.gnofn.org [206.27.168.35]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id OAA13966 for ; Fri, 6 Jun 1997 14:40:40 -0700 (PDT) Received: from sparkie.gnofn.org (sparkie.gnofn.org [206.27.168.35]) by sparkie.gnofn.org (8.7.Beta.10/8.7.Beta.10) with SMTP id QAA27098 for ; Fri, 6 Jun 1997 16:40:30 -0500 (CDT) Date: Fri, 6 Jun 1997 16:40:30 -0500 (CDT) From: Craig Johnston To: hardware@freebsd.org Subject: poor memory bandwidth on ABIT IT5H rev 1.5 Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Interesting -- 2.2.2 on the ABIT with an AMD K5-PR166 gives a result of 60 megs/sec maximum via the naive memory bandwidth benchmark: dd if=/dev/zero of=/dev/null bs=1m count=100 while 2.2.2 on an Asus mobo (the HX one, t2p4? or something?) gives 86 meg/sec by the same benchmark. The ABIT board has EDO dram @60ns, the Asus FPM @ 60ns. Both kernels have 'flags 0x7' for npx0 -- as their slower (than intel) FPUs don't speed up memory moves. I'd be extremely interested in seeing your results for 2.2.2 with the K5 and the above flags on the ABIT and other motherboards. Anyone else have reason to believe the ABITs memory bandwidth sucks? -Craig From owner-freebsd-hardware Fri Jun 6 15:04:50 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id PAA15180 for hardware-outgoing; Fri, 6 Jun 1997 15:04:50 -0700 (PDT) Received: from george.lbl.gov (george-2.lbl.gov [131.243.2.12]) by hub.freebsd.org (8.8.5/8.8.5) with SMTP id PAA15172 for ; Fri, 6 Jun 1997 15:04:48 -0700 (PDT) Received: (jin@localhost) by george.lbl.gov (8.6.10/8.6.5) id PAA10932; Fri, 6 Jun 1997 15:04:45 -0700 Date: Fri, 6 Jun 1997 15:04:45 -0700 From: "Jin Guojun[ITG]" Message-Id: <199706062204.PAA10932@george.lbl.gov> To: craig@gnofn.org, hardware@FreeBSD.ORG Subject: Re: poor memory bandwidth on ABIT IT5H rev 1.5 Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > 2.2.2 on the ABIT with an AMD K5-PR166 gives a result of > 60 megs/sec maximum via the naive memory bandwidth benchmark: > dd if=/dev/zero of=/dev/null bs=1m count=100 > > while 2.2.2 on an Asus mobo (the HX one, t2p4? or something?) > gives 86 meg/sec by the same benchmark. Are they use same CPU? If not, I doubt it is the K5 problem. -Jin From owner-freebsd-hardware Fri Jun 6 15:22:39 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id PAA15869 for hardware-outgoing; Fri, 6 Jun 1997 15:22:39 -0700 (PDT) Received: from sparkie.gnofn.org (sparkie.gnofn.org [206.27.168.35]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id PAA15863 for ; Fri, 6 Jun 1997 15:22:32 -0700 (PDT) Received: from sparkie.gnofn.org (sparkie.gnofn.org [206.27.168.35]) by sparkie.gnofn.org (8.7.Beta.10/8.7.Beta.10) with SMTP id RAA01210 for ; Fri, 6 Jun 1997 17:22:17 -0500 (CDT) Date: Fri, 6 Jun 1997 17:22:17 -0500 (CDT) From: Craig Johnston To: hardware@FreeBSD.ORG Subject: Re: poor memory bandwidth on ABIT IT5H rev 1.5 In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Fri, 6 Jun 1997, Craig Johnston wrote: > > Interesting -- > > 2.2.2 on the ABIT with an AMD K5-PR166 gives a result of > 60 megs/sec maximum via the naive memory bandwidth benchmark: > dd if=/dev/zero of=/dev/null bs=1m count=100 > > while 2.2.2 on an Asus mobo (the HX one, t2p4? or something?) > gives 86 meg/sec by the same benchmark. Having to follow myself up because I was an idiot. The Asus board has an AMD K5-PR133, the ABIT a PR-166. So the slower cpu is on the board with the better performance to main memory. Could the 1.5 vs 1.75 multiplier for 133/166 respecitively be an issue? -Craig From owner-freebsd-hardware Sat Jun 7 02:33:36 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id CAA08354 for hardware-outgoing; Sat, 7 Jun 1997 02:33:36 -0700 (PDT) Received: from shadows.aeon.net (bsdhw@shadows.aeon.net [194.100.41.1]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id CAA08349 for ; Sat, 7 Jun 1997 02:33:32 -0700 (PDT) Received: (from bsdhw@localhost) by shadows.aeon.net (8.8.5/8.8.3) id MAA05112; Sat, 7 Jun 1997 12:32:34 +0300 (EET DST) From: mika ruohotie Message-Id: <199706070932.MAA05112@shadows.aeon.net> Subject: Re: poor memory bandwidth on ABIT IT5H rev 1.5 In-Reply-To: <199706062204.PAA10932@george.lbl.gov> from "Jin Guojun[ITG]" at "Jun 6, 97 03:04:45 pm" To: jin@george.lbl.gov (Jin Guojun[ITG]) Date: Sat, 7 Jun 1997 12:32:34 +0300 (EET DST) Cc: craig@gnofn.org, hardware@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL31 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > > 60 megs/sec maximum via the naive memory bandwidth benchmark: > > dd if=/dev/zero of=/dev/null bs=1m count=100 > > while 2.2.2 on an Asus mobo (the HX one, t2p4? or something?) > > gives 86 meg/sec by the same benchmark. gigabyte GA586HX512 p200 (both, onboard cache) beasty-boys# dd if=/dev/zero of=/dev/null bs=1m count=100 100+0 records in 100+0 records out 104857600 bytes transferred in 0.783996 secs (133747624 bytes/sec) beasty-boys# pluto# dd if=/dev/zero of=/dev/null bs=1m count=100 100+0 records in 100+0 records out 104857600 bytes transferred in 0.759968 secs (137976328 bytes/sec) pluto# cant be that much faster? (both running 2 weeks old 2.2-STABLE) even intel endeavor fx430 p133 gives (pipeline 512Kb CELP cache): shadows% dd if=/dev/zero of=/dev/null bs=1m count=100 100+0 records in 100+0 records out 104857600 bytes transferred in 0.953357 secs (109987761 bytes/sec) shadows% this is few days old 3.0-CURRENT mickey From owner-freebsd-hardware Sat Jun 7 13:34:48 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id NAA04622 for hardware-outgoing; Sat, 7 Jun 1997 13:34:48 -0700 (PDT) Received: from mag-net.com (mag-net.com [207.102.83.2]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA04617 for ; Sat, 7 Jun 1997 13:34:47 -0700 (PDT) Received: from mag-net.com (mag-net.com [207.102.83.2]) by mag-net.com (8.8.5/8.8.5) with SMTP id NAA10534 for ; Sat, 7 Jun 1997 13:34:25 -0700 (PDT) Date: Sat, 7 Jun 1997 13:34:25 -0700 (PDT) From: Rob Nelson To: freebsd-hardware@freebsd.org Subject: Sony SDT9000 DAT tape drive Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Does anybody have any experience with this drive? We are looking at purchasing a high capacity DAT drive. The speed and capacity of this drive makes it very attractive. It is SCSI-2 and native capacity is 12GB, will do 24GB with hardware compression using 125m tapes. Rob Nelson - System Administrator - Mag-Net Internet email: rob@mag-net.com voice: (250)564-6765 http://www.mag-net.com fax: (250)563-8752 smail: 2012 Pine St., Prince George, BC V2L 2C9, Canada