From owner-freebsd-hardware Sun Aug 19 0:11: 0 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id 33BB237B40C; Sun, 19 Aug 2001 00:10:54 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id E3D2A20F13; Sun, 19 Aug 2001 00:10:53 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <200108190658.f7J6wrS07021@mass.dis.org> Date: Sun, 19 Aug 2001 00:10:53 -0700 (PDT) From: Hodge Podge To: Mike Smith Subject: Re: 3ware stuff not ready for heavy duty useage Cc: mike.wentz@3ware.com, val@picturetrail.com, freebsd-hardware@freebsd.org Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 19-Aug-01 Mike Smith wrote: > > Firstly, I would like to thank Nicole for giving me a chance to offer her > some informed information and suggestions before going public with this > slam. I'm glad I was able to ... well, no, actually, I didn't hear jack > about this until now. Pity. Frankly I'm not sure what suggestions could do to help with this. The failures have been often enough across such a varied array of equipment that narrowing to one thing would be difficult at best. > >> OK.. I tried.. I really liked the 3ware stuff. At first all of our >> troubles seemed to be directly traceable to my usage of IBM DTLA drives. >> But now after replacing abt 16 IBM drives.. I am still dealing with the >> 3ware card droppin g out drives like rain. > > This is a known feature of the card; it will drop drives when the error > count for the drive gets too high. Typically, this only happens when you > have bad sectors on the drive; hitting a bad sector a few times a day > will eventually drive the error counter too high and drop the drive. > > I don't like it; I've been trying to talk 3ware out of it, but the real > fix is rather subjective. But just dropping the drive from the array seems to not be the answer. I mean hell, I had 3 hot spares... The final hot spare never even had a chance to pop in as two drives on the same plex dropped at once. > In your case, though, this doesn't look like the problem. I'd be very > suspicious of your data cabling (you are using the cables that came with > the controller, right?) and power supply. 10 drives is way more than > your average box can power, especially if you are working them hard. Yup, cables that were supplied by 3ware. In 3 2 or 3 different cases and power supplies. Each were 300 or 400 watt power supplies. > More details here would help narrow the problem down. > >> I have had it. There are no driver issues here, there is no FreeBSD issue >> here, its all 3ware and can IDE drives really take abuse at all like that in >> a database server or even a very busy picture server. > > They can, actually. Well just as I like Maxtor drives becouse (up till now) I have had little failures with them, I know others who hate them and claim they suck.. becouse their luck with them has been poor. Your Milage May Vary. > You know perfectly well that there are other people out there that aren't > having these problems beating these cards up. You know that 3ware and I > are both interested in fixing anything that's wrong. Thats nice, wanna come to AboveNet in San Jose tonight and join me? Maybe wake up some 3ware people and ask them to donate their weekend? I am the one having to deal with this stuff on a Saturday night, AGAIN! > So why are you crying in public about it, when you could be getting it > fixed? This doesn't do anyone any favours. 8( Becouse AGAIN my weekend is shot becouse of this. Our site is down and I am mad as hell and deeply frustrated. How can I have faith in something that has split in my face so many times? Nicole > Regards, > Mike > > -- > ... every activity meets with opposition, everyone who acts has his > rivals and unfortunately opponents also. But not because people want > to be opponents, rather because the tasks and relationships force > people to take different points of view. [Dr. Fritz Todt] > V I C T O R Y N O T V E N G E A N C E ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Sun Aug 19 0:26:53 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from sphinx.wuhjuhbuh.2y.net (syr-66-24-24-88.twcny.rr.com [66.24.24.88]) by hub.freebsd.org (Postfix) with ESMTP id D33B737B408 for ; Sun, 19 Aug 2001 00:26:50 -0700 (PDT) (envelope-from brian.szymanski@cornell.edu) Received: (from www@localhost) by sphinx.wuhjuhbuh.2y.net (8.11.4/8.10.1) id f7J7Qms02507 for freebsd-hardware@freebsd.org; Sun, 19 Aug 2001 03:26:48 -0400 (EDT) X-Authentication-Warning: sphinx.wuhjuhbuh.2y.net: www set sender to brian.szymanski@cornell.edu using -f To: freebsd-hardware@freebsd.org Subject: supported parallel port card? Message-ID: <998206008.3b7f6a3869039@wuhjuhbuh.2y.net> Date: Sun, 19 Aug 2001 03:26:48 -0400 (EDT) From: Brian Szymanski MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit User-Agent: IMP/PHP IMAP webmail program 2.2.6 X-Originating-IP: 192.168.1.5 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hiya, Please CC: me in any response. I need to install plip between two computers, one of which has a working parallel port and one of which does not. I tried to buy the digital research "drparepp1" card ($10), but looking at netstat -r output it appears that packets go out but not in. Actually I tried this with the cheaper digital research "bidirectional" card ($5), but received the same results. Since the lp(4) manpage says that bugs are plentiful with cheap parallel port cards, I'm wondering if someone can recommend a GOOD parallel port card that they have set up to WORK with plip? thanks for your time, Brian Szymanski bks10@cornell.edu brian.szymanski@cornell.edu To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Sun Aug 19 0:43: 2 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from sphinx.wuhjuhbuh.2y.net (syr-66-24-24-88.twcny.rr.com [66.24.24.88]) by hub.freebsd.org (Postfix) with ESMTP id A6DC937B403 for ; Sun, 19 Aug 2001 00:42:59 -0700 (PDT) (envelope-from brian.szymanski@cornell.edu) Received: (from www@localhost) by sphinx.wuhjuhbuh.2y.net (8.11.4/8.10.1) id f7J7guV10694; Sun, 19 Aug 2001 03:42:56 -0400 (EDT) X-Authentication-Warning: sphinx.wuhjuhbuh.2y.net: www set sender to brian.szymanski@cornell.edu using -f To: freebsd-hardware@freebsd.org Subject: supported parallel port card? Message-ID: <998206975.3b7f6dffe23c3@wuhjuhbuh.2y.net> Date: Sun, 19 Aug 2001 03:42:55 -0400 (EDT) From: Brian Szymanski Cc: "Me, myself, or I" MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit User-Agent: IMP/PHP IMAP webmail program 2.2.6 X-Originating-IP: 192.168.1.5 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I was wondering if anyone knew of a good parallel port card that will work with plip under freebsd 4.x on i386? Sorry if this message got thru more than once, I'm having email client issues... Thanks for reading, Brian Szymanski bks10@cornell.edu brian.szymanski@cornell.edu To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Sun Aug 19 0:43:25 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from sphinx.wuhjuhbuh.2y.net (syr-66-24-24-88.twcny.rr.com [66.24.24.88]) by hub.freebsd.org (Postfix) with ESMTP id 861AB37B410 for ; Sun, 19 Aug 2001 00:43:22 -0700 (PDT) (envelope-from brian.szymanski@cornell.edu) Received: (from www@localhost) by sphinx.wuhjuhbuh.2y.net (8.11.4/8.10.1) id f7J7hKj11004; Sun, 19 Aug 2001 03:43:20 -0400 (EDT) X-Authentication-Warning: sphinx.wuhjuhbuh.2y.net: www set sender to brian.szymanski@cornell.edu using -f To: freebsd-hardware@freebsd.org Subject: supported parallel port card? Message-ID: <998207000.3b7f6e1816188@wuhjuhbuh.2y.net> Date: Sun, 19 Aug 2001 03:43:20 -0400 (EDT) From: Brian Szymanski Cc: "Me, myself, or I" MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit User-Agent: IMP/PHP IMAP webmail program 2.2.6 X-Originating-IP: 192.168.1.5 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I was wondering if anyone knew of a good parallel port card that will work with plip under freebsd 4.x on i386? Sorry if this message got thru more than once, I'm having email client issues... Thanks for reading, Brian Szymanski bks10@cornell.edu brian.szymanski@cornell.edu To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Sun Aug 19 5:48:21 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from borja.sarenet.es (borja.sarenet.es [192.148.167.77]) by hub.freebsd.org (Postfix) with ESMTP id 63E9D37B419 for ; Sun, 19 Aug 2001 05:48:18 -0700 (PDT) (envelope-from borjamar@sarenet.es) Received: from there (localhost [127.0.0.1]) by borja.sarenet.es (8.11.3/8.11.3) with SMTP id f7JCm5F91609 for ; Sun, 19 Aug 2001 14:48:07 +0200 (CEST) (envelope-from borjamar@sarenet.es) Message-Id: <200108191248.f7JCm5F91609@borja.sarenet.es> Content-Type: text/plain; charset="iso-8859-1" From: Borja Marcos To: freebsd-hardware@freebsd.org Subject: Re: 3ware stuff not ready for heavy duty useage Date: Sun, 19 Aug 2001 14:48:05 +0200 X-Mailer: KMail [version 1.3] References: In-Reply-To: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Sunday 19 August 2001 09:10, you wrote: > Yup, cables that were supplied by 3ware. In 3 2 or 3 different cases > and power supplies. Each were 300 or 400 watt power supplies. Excuse me for stepping into the discussion, but I think this is an important issue: Which was the brand of the cases, power supplies and fans? How much did they cost? Nowadays the choice of a good case and power supply is as important as the choice of a good cabling, disks, etc. Regarding disks, I have seen whole batches of disks failing because of poor handling in one of the dealers. When you buy a disk it usually travels through a complex chain involving three or four dealers. It is crazy, and it is impossible to make sure that the disks have been properly handled all the time. One of the cures is to buy them from different dealers, and better with different manufacture dates. Borja. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Sun Aug 19 14:19:54 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id 4909837B403 for ; Sun, 19 Aug 2001 14:19:49 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id DA3E320F1A; Sun, 19 Aug 2001 14:19:48 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <200108191248.f7JCm5F91609@borja.sarenet.es> Date: Sun, 19 Aug 2001 14:19:48 -0700 (PDT) From: Hodge Podge To: Borja Marcos Subject: Re: 3ware stuff not ready for heavy duty useage-followup Cc: freebsd-hardware@freebsd.org, mike.wentz@3ware.com, val@picturetrail.com Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 19-Aug-01 Borja Marcos wrote: > On Sunday 19 August 2001 09:10, you wrote: > >> Yup, cables that were supplied by 3ware. In 3 2 or 3 different cases >> and power supplies. Each were 300 or 400 watt power supplies. > > Excuse me for stepping into the discussion, but I think this is an > important issue: Which was the brand of the cases, power supplies and > fans? How much did they cost? Nowadays the choice of a good case and power > supply is as important as the choice of a good cabling, disks, etc. One of the cases was from Silicon-rax and had a 300 watt power supply. The other cases were from (I think) acmemicro and one had a 300 watt power supply and the other a 400 watt power supply. (don't know the makes of any of the supplies. > Regarding disks, I have seen whole batches of disks failing because of > poor handling in one of the dealers. When you buy a disk it usually > travels through a complex chain involving three or four dealers. It is > crazy, and it is impossible to make sure that the disks have been properly > handled all the time. One of the cures is to buy them from different > dealers, and better with different manufacture dates. Here is my belife as far as the database server goes. Since a database server is constantly reading and writing to the same file or set of files contained within the same directory, this creates a lot of concentrated usage on one small area of the drive. IDE drives (by the words of someone at 3ware) do not have the error correctimg capabilites that SCSI drives do and are not able to recover as well when bad sectors are encountered. Since most IDE's are made with the average consumer in mind, they probobly cannot withstand the small area pounding of a database like server. If my boss is willing I would like to try an experiment using the type of drives used in my TIVO, which are supposed to be specially made for high usage applications. (a special model of quantum hard drives) It may be that using this type of drive is what is required. Our Raid 5 array server that died durring rdisting of data recovered after removing the power for a moment. Ctrl-alt-del did not do it nor did reset even though the computer bios reported the IRQ used by it, the 3ware Bios would not appear. So it seems that the 3ware card died or locked up perhaps. It showed 2 failed drives however and rebuilding failed twice. Now this morning (for me up till 4am) the server is dead again! Don't get me wrong, I want this stuff to work. The cost savings is no small thing, but reliability cannot be this way. The RAID 5 server was all new Maxtor 60 Gig drives and is less than a week old. Thats a pretty high failure rate so far. I want to work with 3ware to see if they can tell me why this is happening, but so far our luck has been pretty dismal. Having a raid array that seems to regularly drop 2 drives at once and cannot recover from a 2 drive failure seems like a very bad combination. Nicole > > Borja. > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-hardware" in the body of the message ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Mon Aug 20 2:13:56 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from ns.sphinx-corp.ru (v3m9.math.nsc.ru [193.125.180.205]) by hub.freebsd.org (Postfix) with ESMTP id 69D6737B401 for ; Mon, 20 Aug 2001 02:13:52 -0700 (PDT) (envelope-from od@ns.sphinx-corp.ru) Received: (from od@localhost) by ns.sphinx-corp.ru (8.11.5/8.11.5) id f7K9CdX99131 for freebsd-hardware@freebsd.org; Mon, 20 Aug 2001 16:12:40 +0700 (NOVST) (envelope-from od) Date: Mon, 20 Aug 2001 16:12:39 +0700 From: oleg dashevskii To: freebsd-hardware@freebsd.org Subject: USR PCI hardware modems Message-ID: <20010820161239.A67404@ns.sphinx-corp.ru> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hallo, Are $(subj)es supported by FreeBSD (namely, 4-STABLE)? These are not soft-modems, but rather hardware ones just emulating standard serial port on a PCI bus. /be9 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Mon Aug 20 9:30:30 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from msgbas1.cos.agilent.com (msgbas1x.cos.agilent.com [192.6.9.33]) by hub.freebsd.org (Postfix) with ESMTP id C4D6437B405 for ; Mon, 20 Aug 2001 09:30:26 -0700 (PDT) (envelope-from darrylo@soco.agilent.com) Received: from msgrel1.cos.agilent.com (msgrel1.cos.agilent.com [130.29.152.77]) by msgbas1.cos.agilent.com (Postfix) with ESMTP id 1334A1696; Mon, 20 Aug 2001 10:30:26 -0600 (MDT) Received: from mina.soco.agilent.com (mina.soco.agilent.com [141.121.54.157]) by msgrel1.cos.agilent.com (Postfix) with ESMTP id 246D63D4; Mon, 20 Aug 2001 10:30:22 -0600 (MDT) Received: from mina.soco.agilent.com (darrylo@localhost [127.0.0.1]) by mina.soco.agilent.com (8.9.3 (PHNE_22672)/8.9.3 SMKit7.1.1_Agilent) with ESMTP id JAA00644; Mon, 20 Aug 2001 09:30:16 -0700 (PDT) Message-Id: <200108201630.JAA00644@mina.soco.agilent.com> To: Hodge Podge Cc: freebsd-hardware@FreeBSD.ORG, mike.wentz@3ware.com Subject: Re: 3ware stuff not ready for heavy duty useage-followup Reply-To: Darryl Okahata In-Reply-To: Your message of "Sun, 19 Aug 2001 14:19:48 PDT." Mime-Version: 1.0 (generated by tm-edit 1.6) Content-Type: text/plain; charset=US-ASCII Date: Mon, 20 Aug 2001 09:30:16 -0700 From: Darryl Okahata Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hodge Podge wrote: > Our Raid 5 array server that died durring rdisting of data recovered after > removing the power for a moment. Ctrl-alt-del did not do it nor did reset eve > n > though the computer bios reported the IRQ used by it, the 3ware Bios would no > t > appear. So it seems that the 3ware card died or locked up perhaps. > It showed 2 failed drives however and rebuilding failed twice. Now this > morning (for me up till 4am) the server is dead again! This doesn't help Nicole, but I can say that I have seen (two) intermittent power-up lockups with an Escalade 6200 -- lockups that an hard reset will not help. I have to do a full power cycle (but the raid 1 array is fine). -- Darryl Okahata darrylo@soco.agilent.com DISCLAIMER: this message is the author's personal opinion and does not constitute the support, opinion, or policy of Agilent Technologies, or of the little green men that have been following him all day. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Mon Aug 20 9:45:10 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from alpha.public.smithconcepts.com (alpha.public.smithconcepts.com [205.245.53.214]) by hub.freebsd.org (Postfix) with ESMTP id 7C6C437B408 for ; Mon, 20 Aug 2001 09:45:05 -0700 (PDT) (envelope-from b.j.smith@ieee.org) Received: from ieee.org (localhost.public.smithconcepts.com [127.0.0.1]) by alpha.public.smithconcepts.com (8.9.3/8.9.3) with ESMTP id NAA22047; Mon, 20 Aug 2001 13:02:55 -0400 Message-ID: <3B813DD5.A86E2016@ieee.org> Date: Mon, 20 Aug 2001 12:41:57 -0400 From: Bryan-TheBS-Smith Organization: SmithConcepts, Inc. X-Mailer: Mozilla 4.77 [en] (X11; U; Linux 2.4.3-SGI_XFS_1.0.1 i686) X-Accept-Language: en MIME-Version: 1.0 To: Darryl Okahata Cc: Hodge Podge , freebsd-hardware@FreeBSD.ORG, mike.wentz@3ware.com Subject: Re: 3ware stuff not ready for heavy duty useage-followup References: <200108201630.JAA00644@mina.soco.agilent.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hodge Podge wrote: > Our Raid 5 array server that died durring rdisting of data > recovered after removing the power for a moment ... It > showed 2 failed drives however and rebuilding failed twice. Er, can you have 2 failed drives in a working RAID-5 array? Or am I missing something here? > This doesn't help Nicole, but I can say that I have seen > (two) intermittent power-up lockups with an Escalade 6200 > -- lockups that an hard reset will not help. I have to do > a full power cycle (but the raid 1 array is fine). I recently bought a 3Ware 6200. Before I did anything, I updated my firmware (with the late June release) and then created the RAID-0 array (two Maxtor 80GB drives). 0 problems so far at just under 2 months, I hope I continue to have none either. I'm now looking to buy a 4-channel and 8-channel card. I am on various lists (XFS, Linux, NFS, etc...) where people have had issues with 3Ware 6000-series cards with RAID-5 volumes, but no one is having issues with RAID-0, 1 or 0+1 (aka 10). Plus the RAID-5 write performance on the 6000-series is not optimal (although the 7000-series is supposed to change that). So I think I'm going to stick with RAID-0+1 for these drives, even if it means losing a 80-240GB in effective disk space verses RAID-5 (160GB instead of 240GB on the 4-channel, and 320GB instead of 560GB on the 8-channel). Any comments? I know this is a FreeBSD list, but I want to hear if anyone has any comments on this. -- TheBS P.S. My target platform is Linux -- specifically RedHat 7.1 + SGI's XFS 1.0.1 filesystem. I have been running XFS for over 6 months now without an error. I cannot consider any other JFS because I have NFS clients (and ReiserFS and JFS continue to have kNFSd issues), and I really want the ACL support of XFS for Samba/Windows as well (which rules out Ext3, which I love on kernel 2.2, but don't trust on kernel 2.4 yet). -- Bryan "TheBS" Smith mailto:b.j.smith@ieee.org chat:thebs413 Engineer Absolute Value Systems, Inc. http://www.linux-wlan.org President SmithConcepts, Inc. http://www.SmithConcepts.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Mon Aug 20 11:14:52 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id E3C1037B403 for ; Mon, 20 Aug 2001 11:14:47 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 393D520F10; Mon, 20 Aug 2001 11:14:46 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <3B813DD5.A86E2016@ieee.org> Date: Mon, 20 Aug 2001 11:14:46 -0700 (PDT) From: Hodge Podge To: Bryan-TheBS-Smith Subject: Re: 3ware stuff not ready for heavy duty useage-followup Cc: mike.wentz@3ware.com, freebsd-hardware@FreeBSD.ORG, Darryl Okahata Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 20-Aug-01 Bryan-TheBS-Smith wrote: > Hodge Podge wrote: >> Our Raid 5 array server that died durring rdisting of data >> recovered after removing the power for a moment ... It >> showed 2 failed drives however and rebuilding failed twice. > > Er, can you have 2 failed drives in a working RAID-5 array? Or am I > missing something here? I was assuming the presece of a hot spare. The failures I have been getting so far have been 1 drive fails.. the hot spare starts trying to kick in.. This taxes the other drive(s) and it (or some other) drive in the array (raid 5 or raid 10) fails before the hot spare even kicks in. > >> This doesn't help Nicole, but I can say that I have seen >> (two) intermittent power-up lockups with an Escalade 6200 >> -- lockups that an hard reset will not help. I have to do >> a full power cycle (but the raid 1 array is fine). > > I recently bought a 3Ware 6200. Before I did anything, I updated my > firmware (with the late June release) and then created the RAID-0 array > (two Maxtor 80GB drives). 0 problems so far at just under 2 months, I > hope I continue to have none either. I have a 3ware raid a well that so far has been A-ok. However it is not loaded much. The arrays so far have seemed ok, until loaded like a very busy server with lots of IO. SO far out of 4 servers attempted with the 3ware card.. not one has survived. Only my personal one which is obviosly less loaded. > > I'm now looking to buy a 4-channel and 8-channel card. I am on various > lists (XFS, Linux, NFS, etc...) where people have had issues with 3Ware > 6000-series cards with RAID-5 volumes, but no one is having issues with > RAID-0, 1 or 0+1 (aka 10). Plus the RAID-5 write performance on the > 6000-series is not optimal (although the 7000-series is supposed to > change that). So I think I'm going to stick with RAID-0+1 for these > drives, even if it means losing a 80-240GB in effective disk space > verses RAID-5 (160GB instead of 240GB on the 4-channel, and 320GB > instead of 560GB on the 8-channel). Yea.. Thats is my plan as well. Ideally I woudl prefer to have two servers.. mirroring each other in JBOD (so its a server mirror) But I am uncertain how to mirror the file systems thus far. However my boss has given up for now and we are going back to SCSI it seems. > > Any comments? I know this is a FreeBSD list, but I want to hear if > anyone has any comments on this. As I said before, I don't think it is a driver issue, or a FreeBSD issue, but more a, can IDE's take the abuse and how well can 3ware deal with the myriad of error reporing they told me is a problem with IDE drives. I have heard they wil soon have a way to remap around bad sectors on the fly, This would prevent them from having to drop the disk in the event of error reporting hopefully. Nicole > -- TheBS > > P.S. My target platform is Linux -- specifically RedHat 7.1 + SGI's XFS > 1.0.1 filesystem. I have been running XFS for over 6 months now without > an error. I cannot consider any other JFS because I have NFS clients > (and ReiserFS and JFS continue to have kNFSd issues), and I really want > the ACL support of XFS for Samba/Windows as well (which rules out Ext3, > which I love on kernel 2.2, but don't trust on kernel 2.4 yet). > > -- > Bryan "TheBS" Smith mailto:b.j.smith@ieee.org chat:thebs413 > Engineer Absolute Value Systems, Inc. http://www.linux-wlan.org > President SmithConcepts, Inc. http://www.SmithConcepts.com ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Mon Aug 20 17: 5:14 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from polaris.we.lc.ehu.es (polaris.we.lc.ehu.es [158.227.6.43]) by hub.freebsd.org (Postfix) with ESMTP id CAC6237B409 for ; Mon, 20 Aug 2001 17:05:08 -0700 (PDT) (envelope-from jose@we.lc.ehu.es) Received: from v-ger.we.lc.ehu.es (lxpx528.lx.ehu.es [158.227.27.174]) by polaris.we.lc.ehu.es (8.11.5/8.11.5) with ESMTP id f7L04pb27958; Tue, 21 Aug 2001 02:04:51 +0200 (MET DST) Received: (from jose@localhost) by v-ger.we.lc.ehu.es (8.11.3/8.11.3) id f7L04dY66969; Tue, 21 Aug 2001 02:04:39 +0200 (CEST) (envelope-from jose) Date: Tue, 21 Aug 2001 02:04:39 +0200 From: "Jose M. Alcaide" To: Bryan-TheBS-Smith Cc: Darryl Okahata , Hodge Podge , freebsd-hardware@FreeBSD.ORG, mike.wentz@3ware.com Subject: Re: 3ware stuff not ready for heavy duty useage-followup Message-ID: <20010821020439.A66366@v-ger.we.lc.ehu.es> Mail-Followup-To: Bryan-TheBS-Smith , Darryl Okahata , Hodge Podge , freebsd-hardware@FreeBSD.ORG, mike.wentz@3ware.com References: <200108201630.JAA00644@mina.soco.agilent.com> <3B813DD5.A86E2016@ieee.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i In-Reply-To: <3B813DD5.A86E2016@ieee.org>; from b.j.smith@ieee.org on Mon, Aug 20, 2001 at 12:41:57PM -0400 X-Operating-System: FreeBSD 4.3-RELEASE Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Mon, Aug 20, 2001 at 12:41:57PM -0400, Bryan-TheBS-Smith wrote: > > I recently bought a 3Ware 6200. Before I did anything, I updated my > firmware (with the late June release) and then created the RAID-0 array > (two Maxtor 80GB drives). 0 problems so far at just under 2 months, I > hope I continue to have none either. > > I'm now looking to buy a 4-channel and 8-channel card. I am on various > lists (XFS, Linux, NFS, etc...) where people have had issues with 3Ware > 6000-series cards with RAID-5 volumes, but no one is having issues with > RAID-0, 1 or 0+1 (aka 10). Plus the RAID-5 write performance on the > 6000-series is not optimal (although the 7000-series is supposed to > change that). So I think I'm going to stick with RAID-0+1 for these > drives, even if it means losing a 80-240GB in effective disk space > verses RAID-5 (160GB instead of 240GB on the 4-channel, and 320GB > instead of 560GB on the 8-channel). > > Any comments? I know this is a FreeBSD list, but I want to hear if > anyone has any comments on this. > I have a system with an Escalade 6200 and two IBM DTLA-307075 (75 GB) in a RAID-0 configuration. Also, I recently installed an Escalade 7410 on another system, this time with four DTLA-307075 attached in RAID-5 mode. No problems so far. Moreover, the RAID-5 performs quite well: -------Sequential Output-------- ---Sequential Input-- --Random-- -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks--- Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU 256 7996 18.9 8189 6.3 5743 5.2 28958 95.5 73159 44.2 1148.9 5.7 1024 7962 17.4 8006 6.2 5818 5.2 29244 95.5 70261 42.5 338.4 2.1 Obviously the write performance is not impressive, but it is a RAID-5. OTOH, the read throughput is *fast*. Cheers, JMA -- ****** Jose M. Alcaide // jose@we.lc.ehu.es // jmas@FreeBSD.org ****** ** "Beware of Programmers who carry screwdrivers" -- Leonard Brandwein ** To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Mon Aug 20 18:37:56 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id 2FC8A37B405 for ; Mon, 20 Aug 2001 18:37:52 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id D071020F1A; Mon, 20 Aug 2001 18:37:51 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <36F7B20351634E4FBFFE6C6A216B30D54CA8@ecx1.edifecs.com> Date: Mon, 20 Aug 2001 18:37:51 -0700 (PDT) From: Hodge Podge To: Michael VanLoon Subject: RE: 3ware stuff not ready for heavy duty useage-followup Cc: val@picturetrail.com, mike.wentz@3ware.com, freebsd-hardware@freebsd.org, Borja Marcos Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 20-Aug-01 Michael VanLoon wrote: > I seriously doubt the average 300W power supply is going to reliably power > your computer and that many disks. You might check into trying one of the > Enermax EG651P power supplies which would supply a much more stable amount > under heavy load. Other high-load power supplies might work as well. That > 400 might be OK, but quality construction is important too -- some cheap > generic 400 might not be any better than the others. Check with PC Power > and Cooling, SuperMicro, etc. for suitable power supplies. No, 300 watts is plenty. IDE's do not use as much current as SCSI drives and I have run more scsi drives than that on a 300W Power supply. Now I suppose it would depend on the amount of activity and the drives particular sensitivity, but that only makes the case more so in some ways. How much coddling do the IDE's need then? Nicole >> From: Hodge Podge [mailto:nicole@unixgirl.com] >> Sent: Sunday, August 19, 2001 2:20 PM >> >> On 19-Aug-01 Borja Marcos wrote: >> > On Sunday 19 August 2001 09:10, you wrote: >> > >> >> Yup, cables that were supplied by 3ware. In 3 2 or 3 >> different cases >> >> and power supplies. Each were 300 or 400 watt power supplies. >> > >> > Excuse me for stepping into the discussion, but I >> think this is an >> > important issue: Which was the brand of the cases, power >> supplies and >> > fans? How much did they cost? Nowadays the choice of a good >> case and power >> > supply is as important as the choice of a good cabling, disks, etc. >> >> One of the cases was from Silicon-rax and had a 300 watt >> power supply. The >> other cases were from (I think) acmemicro and one had a 300 >> watt power supply >> and the other a 400 watt power supply. (don't know the makes >> of any of the >> supplies. ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Mon Aug 20 19:34:22 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from msgbas1.cos.agilent.com (msgbas1x.cos.agilent.com [192.6.9.33]) by hub.freebsd.org (Postfix) with ESMTP id 549F137B408 for ; Mon, 20 Aug 2001 19:34:19 -0700 (PDT) (envelope-from darrylo@soco.agilent.com) Received: from msgrel1.cos.agilent.com (msgrel1.cos.agilent.com [130.29.152.77]) by msgbas1.cos.agilent.com (Postfix) with ESMTP id EAA0F1479; Mon, 20 Aug 2001 20:34:14 -0600 (MDT) Received: from mina.soco.agilent.com (mina.soco.agilent.com [141.121.54.157]) by msgrel1.cos.agilent.com (Postfix) with ESMTP id C5E7F2D5; Mon, 20 Aug 2001 20:34:08 -0600 (MDT) Received: from mina.soco.agilent.com (darrylo@localhost [127.0.0.1]) by mina.soco.agilent.com (8.9.3 (PHNE_22672)/8.9.3 SMKit7.1.1_Agilent) with ESMTP id TAA10412; Mon, 20 Aug 2001 19:34:08 -0700 (PDT) Message-Id: <200108210234.TAA10412@mina.soco.agilent.com> To: Bryan-TheBS-Smith Cc: freebsd-hardware@FreeBSD.ORG Subject: Re: 3ware stuff not ready for heavy duty useage-followup Reply-To: Darryl Okahata In-Reply-To: Your message of "Mon, 20 Aug 2001 12:41:57 EDT." <3B813DD5.A86E2016@ieee.org> Mime-Version: 1.0 (generated by tm-edit 1.6) Content-Type: text/plain; charset=US-ASCII Date: Mon, 20 Aug 2001 19:34:07 -0700 From: Darryl Okahata Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Bryan-TheBS-Smith wrote: > I recently bought a 3Ware 6200. Before I did anything, I updated my > firmware (with the late June release) and then created the RAID-0 array > (two Maxtor 80GB drives). 0 problems so far at just under 2 months, I > hope I continue to have none either. Gah. My stupidity factor is particularly high these days. The one thing I haven't done is upgrade the firmware .... ;-( -- Darryl Okahata darrylo@soco.agilent.com DISCLAIMER: this message is the author's personal opinion and does not constitute the support, opinion, or policy of Agilent Technologies, or of the little green men that have been following him all day. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Mon Aug 20 21:46:40 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from smtp1.sentex.ca (smtp1.sentex.ca [199.212.134.4]) by hub.freebsd.org (Postfix) with ESMTP id 1B72337B409 for ; Mon, 20 Aug 2001 21:46:37 -0700 (PDT) (envelope-from mike@sentex.net) Received: from chimp.simianscience.com (cage.simianscience.com [64.7.134.1]) by smtp1.sentex.ca (8.11.1/8.11.1) with SMTP id f7L4kUH25504 for ; Tue, 21 Aug 2001 00:46:31 -0400 (EDT) (envelope-from mike@sentex.net) From: Mike Tancsa To: freebsd-hardware@FreeBSD.ORG Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Tue, 21 Aug 2001 00:46:30 -0400 Message-ID: References: <3B813DD5.A86E2016@ieee.org> In-Reply-To: X-Mailer: Forte Agent 1.8/32.548 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: quoted-printable Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 20 Aug 2001 14:15:05 -0400, in sentex.lists.freebsd.hardware you = wrote: > > I have a 3ware raid a well that so far has been A-ok. However it is = not >loaded much. The arrays so far have seemed ok, until loaded like a very = busy >server with lots of IO.=20 > SO far out of 4 servers attempted with the 3ware card.. not one has = survived. >Only my personal one which is obviosly less loaded. I use a 4 port cards on my news server. 20Mb/s Usenet feed from Cidera coming in 24hrs a day and 2Mb/s going out for readers plus night time expires on DNEWS. I would call this fairly busy server in terms of IO. = No problems ever. The IDE drives are almost a year old and dont have = errors. The 4 drives are in 2 RAID 0 sets. > > As I said before, I don't think it is a driver issue, or a FreeBSD = issue, but >more a, can IDE's take the abuse and how well can 3ware deal with the = myriad of >error reporing they told me is a problem with IDE drives. > I have heard they wil soon have a way to remap around bad sectors on = the fly, >This would prevent them from having to drop the disk in the event of = error >reporting hopefully. Even with "cheap" IDE drives, I dont think you are going to see failures = on a weekly basis. This is rather odd. Like I said, I have been pounding the snot out of 4 of them in my news server as well as 2 13 gig drives on a busy squid box. I also have a 4 port RAID 10 box on a fairly busy Win2K box running MS SQL 7.=20 Perhaps its the 8 port card ? I have not used any of those. ---Mike Mike Tancsa (mdtancsa@sentex.net) =09 Sentex Communications Corp, =09 Waterloo, Ontario, Canada "Given enough time, 100 monkeys on 100 routers=20 could setup a national IP network." (KDW2) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Mon Aug 20 22:56:16 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from elitists.org (www.elitists.org [64.40.73.38]) by hub.freebsd.org (Postfix) with ESMTP id E81C537B409 for ; Mon, 20 Aug 2001 22:56:11 -0700 (PDT) (envelope-from freebsdlists@elitists.org) Received: from blah (64-40-88-202.pk.dsl.grics.net [64.40.88.202]) by elitists.org (Postfix) with SMTP id 0A2A5213; Tue, 21 Aug 2001 01:06:48 -0500 (CDT) Message-ID: <020401c12a06$67ef7040$6601a8c0@elitists.org> From: "F. Even" To: "Hodge Podge" , "Michael VanLoon" Cc: , , , "Borja Marcos" References: Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Tue, 21 Aug 2001 00:59:12 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.00.2615.200 X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2615.200 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I would be incliined to agree w/ Michael. After I saw the first couple of messages, I started thinking the same thing. I've seen systems w/ 4 IDE devs. get loaded down. 8 disks plus whatever else on that system is a LOT of devices sucking a lot of power. Dedicate a seperate PS for some of those drives, and see if that doesn't help out. Just saying that its "plenty" w/out trying does nothing to further this. ...and how much "coddling?" Hell....that is a LOT of devices there. You toss that much hardware in a box...you NEED power. Frank ----- Original Message ----- From: Hodge Podge To: Michael VanLoon Cc: ; ; ; Borja Marcos Sent: Monday, August 20, 2001 8:37 PM Subject: RE: 3ware stuff not ready for heavy duty useage-followup On 20-Aug-01 Michael VanLoon wrote: > I seriously doubt the average 300W power supply is going to reliably power > your computer and that many disks. You might check into trying one of the > Enermax EG651P power supplies which would supply a much more stable amount > under heavy load. Other high-load power supplies might work as well. That > 400 might be OK, but quality construction is important too -- some cheap > generic 400 might not be any better than the others. Check with PC Power > and Cooling, SuperMicro, etc. for suitable power supplies. No, 300 watts is plenty. IDE's do not use as much current as SCSI drives and I have run more scsi drives than that on a 300W Power supply. Now I suppose it would depend on the amount of activity and the drives particular sensitivity, but that only makes the case more so in some ways. How much coddling do the IDE's need then? Nicole >> From: Hodge Podge [mailto:nicole@unixgirl.com] >> Sent: Sunday, August 19, 2001 2:20 PM >> >> On 19-Aug-01 Borja Marcos wrote: >> > On Sunday 19 August 2001 09:10, you wrote: >> > >> >> Yup, cables that were supplied by 3ware. In 3 2 or 3 >> different cases >> >> and power supplies. Each were 300 or 400 watt power supplies. >> > >> > Excuse me for stepping into the discussion, but I >> think this is an >> > important issue: Which was the brand of the cases, power >> supplies and >> > fans? How much did they cost? Nowadays the choice of a good >> case and power >> > supply is as important as the choice of a good cabling, disks, etc. >> >> One of the cases was from Silicon-rax and had a 300 watt >> power supply. The >> other cases were from (I think) acmemicro and one had a 300 >> watt power supply >> and the other a 400 watt power supply. (don't know the makes >> of any of the >> supplies. ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 0: 6: 9 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from borja.sarenet.es (borja.sarenet.es [192.148.167.77]) by hub.freebsd.org (Postfix) with ESMTP id C040837B41A for ; Tue, 21 Aug 2001 00:06:05 -0700 (PDT) (envelope-from borjamar@sarenet.es) Received: from there (localhost [127.0.0.1]) by borja.sarenet.es (8.11.3/8.11.3) with SMTP id f7L75HV04414; Tue, 21 Aug 2001 09:05:18 +0200 (CEST) (envelope-from borjamar@sarenet.es) Message-Id: <200108210705.f7L75HV04414@borja.sarenet.es> Content-Type: text/plain; charset="iso-8859-1" From: Borja Marcos To: Hodge Podge , Michael VanLoon Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Tue, 21 Aug 2001 09:05:17 +0200 X-Mailer: KMail [version 1.3] Cc: val@picturetrail.com, mike.wentz@3ware.com, freebsd-hardware@freebsd.org, Borja Marcos References: In-Reply-To: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Tuesday 21 August 2001 03:37, Hodge Podge wrote: No, 300 watts is plenty. IDE's do not use as much current as SCSI drive= s > and I have run more scsi drives than that on a 300W Power supply. > > Now I suppose it would depend on the amount of activity and the drives > particular sensitivity, but that only makes the case more so in some wa= ys. > How much coddling do the IDE's need then? =09Have a look at the specifications and check the temperature after some= =20 hours. Modern, high-performance disks generate enormous amounts of heat. =09Borja. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 16:28:18 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id D719F37B40C for ; Tue, 21 Aug 2001 16:28:07 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 92C4720F19; Tue, 21 Aug 2001 16:28:07 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <200108210705.f7L75HV04414@borja.sarenet.es> Date: Tue, 21 Aug 2001 16:28:07 -0700 (PDT) From: Hodge Podge To: Borja Marcos Subject: Re: 3ware stuff not ready for heavy duty useage-followup Cc: freebsd-hardware@freebsd.org, mike.wentz@3ware.com, val@picturetrail.com, Michael VanLoon Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 21-Aug-01 Borja Marcos wrote: > On Tuesday 21 August 2001 03:37, Hodge Podge wrote: > No, 300 watts is plenty. IDE's do not use as much current as SCSI drives >> and I have run more scsi drives than that on a 300W Power supply. >> >> Now I suppose it would depend on the amount of activity and the drives >> particular sensitivity, but that only makes the case more so in some ways. >> How much coddling do the IDE's need then? > > Have a look at the specifications and check the temperature after some > hours. Modern, high-performance disks generate enormous amounts of heat. > > Well.. Gee who woulda thought? However, when you have 3 (4u) full size fans blowing air through the case across the drives, and its sitting right by an air outlet in the datacenter that is always 68deg or less. That is not the problem. Don't mean to be snippy.. But that is rather basic. I HATE poorly ventelated cases and I have lived through dealing with ones that were not. 99% of the time, the drive worked, The CPU or MB crapped out. Nicole > > Borja. ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 16:49:11 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id 6DD3737B410 for ; Tue, 21 Aug 2001 16:48:25 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 58A6D20F19; Tue, 21 Aug 2001 16:48:25 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <36F7B20351634E4FBFFE6C6A216B30D54CAA@ecx1.edifecs.com> Date: Tue, 21 Aug 2001 16:48:25 -0700 (PDT) From: Hodge Podge To: Michael VanLoon Subject: RE: 3ware stuff not ready for heavy duty useage-followup Cc: Borja Marcos , freebsd-hardware@freebsd.org, mike.wentz@3ware.com, val@picturetrail.com Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 21-Aug-01 Michael VanLoon wrote: >> From: Hodge Podge [mailto:nicole@unixgirl.com] >> Sent: Monday, August 20, 2001 6:38 PM >> >> On 20-Aug-01 Michael VanLoon wrote: >> > I seriously doubt the average 300W power supply is going to reliably > power >> > your computer and that many disks. You might check into trying one of > the >> > Enermax EG651P power supplies which would supply a much more stable > amount >> > under heavy load. Other high-load power supplies might work as well. > That >> > 400 might be OK, but quality construction is important too -- some cheap >> > generic 400 might not be any better than the others. Check with PC > Power >> > and Cooling, SuperMicro, etc. for suitable power supplies. >> >> No, 300 watts is plenty. IDE's do not use as much current as SCSI drives > and I >> have run more scsi drives than that on a 300W Power supply. >> >> Now I suppose it would depend on the amount of activity and the drives >> particular sensitivity, but that only makes the case more so in some ways. > How >> much coddling do the IDE's need then? > > Well yes and no. First it depends how much power your system itself is > pulling. Don't forget that AMD recommends a minimum of 300W power supply > for just your average desktop with only one or two drives. Intel chips suck > up less, but in some cases not significantly less. > > Now you may be right in some cases. I decided to go look at the Maxtor and > IBM sites. It seems under peak load, considering worst-case (highest > electrical running load) on eight drives (I think that was your biggest > set-up) you get a power draw of: > > Maxtor DiamondMax Plus 60: > 4.80 Amps at 12V > 4.40 Amps at 5V > > IBM 60GXP: > 5.36A at 12V > 3.92A at 5V > > These are for average load. I think Maxtor doesn't actually print true peak > because IBM's is quite a bit higher than these. At peak loads: > > IBM 60GXP: > 16.00A at 12V!! > 9.04A at 5V > > Remember that's 16A for the hard drives alone, not counting any other stuff > installed in your computer. > > Someone mentioned having problems with starting the system properly. Here's > maybe why... look at these spin-up currents: > > Maxtor DiamondMax Plus 60: > 23.60A at 12V!!! > 3.44A at 5V > > IBM 60GXP: > 16.00A at 12V!! > 6.4A at 5V > > > The quality Enermax power supplies are a good place to look for some > guidance on this. Remember that cheap no-name power supplies are typically > going to handle this worse than well-made ones will. Their 300W model > (EG301P) has a max output rating of 15A at 12V. This means that if all > eight drives try to spin up at once, you are over-loading the power supply. > This can result in startup errors. But even as indicated above, if all > eight drives are doing full seek traffic all at once, even that might push > you above the power supply ratings (16A on drives > 15A on power supply). > > And remember this is only the drives -- this doesn't count other stuff > drawing 12V inside your case. Since the CPU and motherboard circuitry use > the 3.3V and 5V taps, this likely will not crash your machine, but will > cause hard drive errors. > > Even Enermax's biggest power supply, the 550W unit (EG651P) is just barely > capable of providing enough power for simultaneous spin-up of all eight > Maxtor drives (23.6A on drives just barely < 24A from PS). And that's > assuming you don't have more than 0.4A draw on 12V from everything else in > your system. > > So your assumption, "300 watts is plenty," doesn't necessarily bear itself > out. Now if you use things like staggered spin-up, that will help alleviate > problems with every drive trying to suck down spin-up current at the same > time, but even with that, your full-load performance is just barely over the > limit of this particular power supply. Assuming "no, it's plenty" without > any real proof is an invitation to disaster in my book. I see.. So what you are saying is then that all those people who make and sell systems with that many HD's more or less are all asking for trouble? That all the scsi systems I have built or seen running similiarly and without errors anywere near this are just lucky? So you postulate that if I replace my 400 watt power supply with a 400 Watt "better" power supply, I will no longer have problems with the 3ware card under heavy loads? I know my boss is not sinking another dime into IDE stuff until proven safe. So.. Anyone have a power supply they belive will handle the load they can loan me for testing? I'm game? What would you say if I told you that the power supply in the case was an Enermax power supply? Nicole >> >> >> From: Hodge Podge [mailto:nicole@unixgirl.com] >> >> Sent: Sunday, August 19, 2001 2:20 PM >> >> >> >> On 19-Aug-01 Borja Marcos wrote: >> >> > On Sunday 19 August 2001 09:10, you wrote: >> >> > >> >> >> Yup, cables that were supplied by 3ware. In 3 2 or 3 >> >> different cases >> >> >> and power supplies. Each were 300 or 400 watt power supplies. >> >> > >> >> > Excuse me for stepping into the discussion, but I >> >> think this is an >> >> > important issue: Which was the brand of the cases, power >> >> supplies and >> >> > fans? How much did they cost? Nowadays the choice of a good >> >> case and power >> >> > supply is as important as the choice of a good cabling, >> disks, etc. >> >> >> >> One of the cases was from Silicon-rax and had a 300 watt >> >> power supply. The >> >> other cases were from (I think) acmemicro and one had a 300 >> >> watt power supply >> >> and the other a 400 watt power supply. (don't know the makes >> >> of any of the >> >> supplies. ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 17: 7:11 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from elitists.org (www.elitists.org [64.40.73.38]) by hub.freebsd.org (Postfix) with ESMTP id 3651F37B414 for ; Tue, 21 Aug 2001 17:06:39 -0700 (PDT) (envelope-from freebsdlists@elitists.org) Received: from blah (64-40-88-202.pk.dsl.grics.net [64.40.88.202]) by elitists.org (Postfix) with SMTP id 9C609213; Tue, 21 Aug 2001 19:17:13 -0500 (CDT) Message-ID: <03d801c12a9e$bab359c0$6601a8c0@elitists.org> From: "F. Even" To: "Hodge Podge" , "Michael VanLoon" Cc: , References: Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Tue, 21 Aug 2001 19:09:34 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.00.2615.200 X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2615.200 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Who sells systems w/ that many disks that is anemically underpowered? I have not seen them a'plenty. At least not without dual/redundant PS's. I can't fathom running that many devs. on a 300W PS, but it is probably a stretch even on a lone 400W, esp. if it has a lot of other devices, or a higher clocked chip w/ mounds of memory, those are all pieces that need power too. You are now talking about 400W, but you had mentioned trying this on a 300W before also...which is a ridiculous notion. I have a hard time believing that you have tossed SCSI systems together w/ 8 drives on them and functioning peripherals, on a 300W PS. If it worked great for you, well, great. Lucky. Don't count on that as being a good practice though. Fire up an old AT PS to just handle a few of the drives, and see if that doesn't help out. Frank ----- Original Message ----- From: Hodge Podge To: Michael VanLoon Cc: Borja Marcos ; ; ; Sent: Tuesday, August 21, 2001 6:48 PM Subject: RE: 3ware stuff not ready for heavy duty useage-followup I see.. So what you are saying is then that all those people who make and sell systems with that many HD's more or less are all asking for trouble? That all the scsi systems I have built or seen running similiarly and without errors anywere near this are just lucky? So you postulate that if I replace my 400 watt power supply with a 400 Watt "better" power supply, I will no longer have problems with the 3ware card under heavy loads? I know my boss is not sinking another dime into IDE stuff until proven safe. So.. Anyone have a power supply they belive will handle the load they can loan me for testing? I'm game? What would you say if I told you that the power supply in the case was an Enermax power supply? To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 17: 9:21 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from borja.sarenet.es (borja.sarenet.es [192.148.167.77]) by hub.freebsd.org (Postfix) with ESMTP id 533BD37B412 for ; Tue, 21 Aug 2001 17:09:16 -0700 (PDT) (envelope-from borjamar@sarenet.es) Received: from there (localhost [127.0.0.1]) by borja.sarenet.es (8.11.3/8.11.3) with SMTP id f7M08dV15753; Wed, 22 Aug 2001 02:08:39 +0200 (CEST) (envelope-from borjamar@sarenet.es) Message-Id: <200108220008.f7M08dV15753@borja.sarenet.es> Content-Type: text/plain; charset="iso-8859-1" From: Borja Marcos To: Hodge Podge , Borja Marcos Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Wed, 22 Aug 2001 02:08:39 +0200 X-Mailer: KMail [version 1.3] Cc: freebsd-hardware@freebsd.org, mike.wentz@3ware.com, val@picturetrail.com, Michael VanLoon References: In-Reply-To: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Wednesday 22 August 2001 01:28, Hodge Podge wrote: > Well.. Gee who woulda thought? > However, when you have 3 (4u) full size fans blowing air through the = case > across the drives, and its sitting right by an air outlet in the datace= nter > that is always 68deg or less. That is not the problem. =09;-) Just checking causes for a multiple drive failure ;-) (Other than = poor=20 handling by the dealer or a bad batch). =09Borja. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 17:18: 7 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from elitists.org (www.elitists.org [64.40.73.38]) by hub.freebsd.org (Postfix) with ESMTP id 9BD9437B40D for ; Tue, 21 Aug 2001 17:17:42 -0700 (PDT) (envelope-from freebsdlists@elitists.org) Received: from blah (64-40-88-202.pk.dsl.grics.net [64.40.88.202]) by elitists.org (Postfix) with SMTP id 193B9213; Tue, 21 Aug 2001 19:28:18 -0500 (CDT) Message-ID: <03f901c12aa0$461ca1a0$6601a8c0@elitists.org> From: "F. Even" To: , , "Hodge Podge" , "Borja Marcos" References: Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Tue, 21 Aug 2001 19:20:39 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.00.2615.200 X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2615.200 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I hope those fans are not hooked into that PS also. Talk about more power suck. ----- Original Message ----- From: Hodge Podge To: Borja Marcos Cc: ; ; ; Michael VanLoon Sent: Tuesday, August 21, 2001 6:28 PM Subject: Re: 3ware stuff not ready for heavy duty useage-followup On 21-Aug-01 Borja Marcos wrote: > On Tuesday 21 August 2001 03:37, Hodge Podge wrote: > No, 300 watts is plenty. IDE's do not use as much current as SCSI drives >> and I have run more scsi drives than that on a 300W Power supply. >> >> Now I suppose it would depend on the amount of activity and the drives >> particular sensitivity, but that only makes the case more so in some ways. >> How much coddling do the IDE's need then? > > Have a look at the specifications and check the temperature after some > hours. Modern, high-performance disks generate enormous amounts of heat. > > Well.. Gee who woulda thought? However, when you have 3 (4u) full size fans blowing air through the case across the drives, and its sitting right by an air outlet in the datacenter that is always 68deg or less. That is not the problem. Don't mean to be snippy.. But that is rather basic. I HATE poorly ventelated cases and I have lived through dealing with ones that were not. 99% of the time, the drive worked, The CPU or MB crapped out. Nicole > > Borja. ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 17:30:22 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id 5D40B37B410 for ; Tue, 21 Aug 2001 17:29:45 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 1FAF620F1A; Tue, 21 Aug 2001 17:29:45 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: Date: Tue, 21 Aug 2001 17:29:45 -0700 (PDT) From: Hodge Podge To: Mike Tancsa Subject: Re: 3ware stuff not ready for heavy duty useage-followup Cc: freebsd-hardware@FreeBSD.ORG Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 21-Aug-01 Mike Tancsa wrote: > On 20 Aug 2001 14:15:05 -0400, in sentex.lists.freebsd.hardware you wrote: > >> >> I have a 3ware raid a well that so far has been A-ok. However it is not >>loaded much. The arrays so far have seemed ok, until loaded like a very busy >>server with lots of IO. >> SO far out of 4 servers attempted with the 3ware card.. not one has >> survived. >>Only my personal one which is obviosly less loaded. > > I use a 4 port cards on my news server. 20Mb/s Usenet feed from Cidera > coming in 24hrs a day and 2Mb/s going out for readers plus night time > expires on DNEWS. I would call this fairly busy server in terms of IO. No > problems ever. The IDE drives are almost a year old and dont have errors. > The 4 drives are in 2 RAID 0 sets. > Yea.. Thats the strange part, I have had no problems with RAID 0 Only RAID 10 and RAID 5. >> >> As I said before, I don't think it is a driver issue, or a FreeBSD issue, >> but >>more a, can IDE's take the abuse and how well can 3ware deal with the myriad >>of >>error reporing they told me is a problem with IDE drives. >> I have heard they wil soon have a way to remap around bad sectors on the >> fly, >>This would prevent them from having to drop the disk in the event of error >>reporting hopefully. > > Even with "cheap" IDE drives, I dont think you are going to see failures on > a weekly basis. This is rather odd. Like I said, I have been pounding the > snot out of 4 of them in my news server as well as 2 13 gig drives on a > busy squid box. I also have a 4 port RAID 10 box on a fairly busy Win2K > box running MS SQL 7. Yea.. I think it also has to do with the size of the drive. As they keep putting more and more data into a smaller area, if you have a busy server, especially a database server were the same files are very active, I think that is were IDE's might really show their deficiancies. > Perhaps its the 8 port card ? I have not used any of those. Dunno. The more irritating thing is that with the last 8 port RAID 5 array, when one drive failed, it refused to rebuild to the hot spare. I tried twice and it failed twice then froze again :( Maybe it is the power supply issue, maybe there were enough drives and they and or the card or something is sensitive to any voltage spikes. If I can get the rebuild help from 3ware soon I hope to do some imperical testing on the failed database server to find out. I will run teh snot out of it and try to do a rebuild and monitor the voltages with a digital meter. I did some testing today and found it to be pretty stable even on bootup. Nicole > ---Mike > > Mike Tancsa (mdtancsa@sentex.net) > Sentex Communications Corp, > Waterloo, Ontario, Canada > "Given enough time, 100 monkeys on 100 routers > could setup a national IP network." (KDW2) > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-hardware" in the body of the message ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 17:37:40 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from beppo.feral.com (beppo.feral.com [192.67.166.79]) by hub.freebsd.org (Postfix) with ESMTP id 50BF637B40C for ; Tue, 21 Aug 2001 17:37:36 -0700 (PDT) (envelope-from mjacob@feral.com) Received: from wonky.feral.com (wonky.feral.com [192.67.166.7]) by beppo.feral.com (8.11.3/8.11.3) with ESMTP id f7M0bZI80667 for ; Tue, 21 Aug 2001 17:37:35 -0700 (PDT) (envelope-from mjacob@feral.com) Date: Tue, 21 Aug 2001 17:37:18 -0700 (PDT) From: Matthew Jacob Reply-To: To: Subject: looking for ia32 system that supports > 4GB memory and has 64 bit PCI Message-ID: <20010821170539.Q23686-100000@wonky.feral.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I'm looking for in Intel IA32 system that has 64 bit PCI slots and can support more than 4GB memory- it's time for me to start thinking about what 64 bit DAC PCI really means. My STL2 board only supports up to 4GB. I've grovelled around a bit on the Intel site, and don't see anything very helpful. I know that some of you are playing around with these systems now. What's available and workable? -matt To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 17:40:19 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id 70BFA37B40C for ; Tue, 21 Aug 2001 17:39:54 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 1C03920F1A; Tue, 21 Aug 2001 17:39:54 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: Date: Tue, 21 Aug 2001 17:39:54 -0700 (PDT) From: Hodge Podge To: Hodge Podge Subject: RE: 3ware stuff not ready for heavy duty useage- ATTN 3ware Cc: mike.wentz@3ware.com, freebsd-hardware@freebsd.org, Borja Marcos , Michael VanLoon , val@picturetrail.com Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org OK.. I have an Idea. Since 3ware is selling an 8 port card.. Ostensibly to be used with 8 devices in the system, do they have any reccoemndations? Have they done any empirical testing? I mean it sounds like a good idea to say .. hey if you are using our 8 port card with 8 drives better make sure you have X power supply rating etc in their manual? Can someone at 3ware do some testing if this hasn't been done? I will do what I can with what I have available, but obviosly their testing would be more highly regarded. I am willing to go to 3ware and do the testing with them if we can work something out. I think it would be a good idea. Also is there anyone currently using 8 drives in a system following this? What are you using? Nicole ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 17:59:43 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from cage.simianscience.com (cage.simianscience.com [64.7.134.1]) by hub.freebsd.org (Postfix) with ESMTP id D6B5437B410 for ; Tue, 21 Aug 2001 17:59:36 -0700 (PDT) (envelope-from mike@sentex.net) Received: (from root@localhost) by cage.simianscience.com (8.11.5/8.11.5) id f7M0xZn73540; Tue, 21 Aug 2001 20:59:35 -0400 (EDT) (envelope-from mike@sentex.net) Received: from chimp.sentex.net (fcage [192.168.0.2]) by cage.simianscience.com (8.11.5/8.11.5av) with ESMTP id f7M0xRM73531; Tue, 21 Aug 2001 20:59:31 -0400 (EDT) (envelope-from mike@sentex.net) Message-Id: <5.1.0.14.0.20010821205247.049785f0@192.168.0.12> X-Sender: mdtancsa@192.168.0.12 X-Mailer: QUALCOMM Windows Eudora Version 5.1 Date: Tue, 21 Aug 2001 20:59:26 -0400 To: Hodge Podge From: Mike Tancsa Subject: Re: 3ware stuff not ready for heavy duty useage-followup Cc: freebsd-hardware@freebsd.org In-Reply-To: References: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Virus-Scanned: by AMaViS perl-10 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org You didnt by chance change the Stripe size from the default of 64 did you? I remember doing this _once_ and it caused me no end of grief. Just looking at one of the production RAID10 boxes I have. Its a win2k server running MS-SQL... Pretty busy and very busy in bursts when billing for 10,000 users gets run twice a month. Its a 6400 card, Firmware 1.0043.003. BIOS is BEXX 1.04.00.009 It has been in service for some time now without any problems. I have a couple of RAID 10 devices on FreeBSD, but I dont have access to them right now to see which firmware they are running. ---Mike >---------------------------------------------------------------- -------------------------------------------------------------------- Mike Tancsa, tel +1 519 651 3400 Network Administration, mike@sentex.net Sentex Communications www.sentex.net Cambridge, Ontario Canada www.sentex.net/mike To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 18: 2:51 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id 35DEE37B415 for ; Tue, 21 Aug 2001 18:01:22 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 4A91620F1D; Tue, 21 Aug 2001 18:01:22 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 2 (High) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <36F7B20351634E4FBFFE6C6A216B30D54CAD@ecx1.edifecs.com> Date: Tue, 21 Aug 2001 18:01:22 -0700 (PDT) From: Hodge Podge To: Michael VanLoon Subject: RE: 3ware stuff not ready for heavy duty useage-followup Cc: val@picturetrail.com, mike.wentz@3ware.com, freebsd-hardware@freebsd.org, Borja Marcos Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 22-Aug-01 Michael VanLoon wrote: > Ignore physics if you want. I tend not to try to bend the laws of reality. > The numbers are in front of you: there are some conceivable situations where > you will over-load your power supply. It may not happen frequently, but it > can happen. Oh I don't doubt that at all. I used to be an engineering technician who had the fun task of taking what engineers said shoudl work.. on paper and making it work.. for real. > As someone else posted, if you're also running all those big fans off this > PS you're loading it further. Not that much, the fans are very efficiant. > You've been lucky in the past. You won't always be lucky. > It's funny how you say you've run these big servers in the past and they > worked all great with off-the shelf power supplies. Our biggest servers > have power supplies in them commonly twice the size of normal desktop > machines, and being proprietary (often redundant), I don't even know how > many watts they are, but you can bet they're more than 300. You might want to check. Quite often they are not. Have you seen the wattage on power suplies in 1 and 2U servers. Pretty damn small. > Note this isn't a SCSI/IDE issue. I'm one of the first people to suggest > you should just be running SCSI with a good hardware RAID controller for > most servers. However the rules remain there: too many disks with too small > a power supply = potential problems and hair-pulling. But you have to admit that something this repeatable on different systems seems damn odd. So far I have not seen one reply from anyone saying.. Yea I have a system like that that works fine. Only people with 4 port units or folks with small capacity drives. And therein is what I am saying. If you use drives that pack the density so high, they then would likely become more suseptable to any anomilies. > I'm honestly surprised people (myself included) are still trying to help you > when you won't take good advice, and bite the heads off people who try to > make suggestions. I'm not biting your head off, and I'm sorry you took it that way. I am mearly showing examples or reason how your reasoning might be wrong or not applicable in this case. I would like to point to 1 example server that has 13 Drives in it, and only 1 300 Watt power supply. http://www.rackable.com/index-productsST.php3?checkit=noflash They have sold quite a few of these units, they beat the snot out of them at Yahoo and Google, BUT they do not use them in RAID 5 or even RAID 10 as I have been. You would think that they would be having power supply issues, but apperantly they have not. This is but one example of why I think the power supply issue is not relevant, but perhaps as I stated in my last email.. perhaps is worth testing, especially by 3ware to make sure users have what is needed to use their card safely. Again I will state, I like the 3ware stuff, I wish I could use the 3ware stuff, I do not think it is a FreeBSD or Driver issue. But, when using RAID 10 or RAID 5 with these newer High Capacity drives, the 3ware card may not have enough error handling yet to be able to work well under heavy usage. Nicole > Good luck. Have fun. > >> From: Hodge Podge [mailto:nicole@unixgirl.com] >> Sent: Tuesday, August 21, 2001 4:48 PM >> >> On 21-Aug-01 Michael VanLoon wrote: >> >> From: Hodge Podge [mailto:nicole@unixgirl.com] >> >> Sent: Monday, August 20, 2001 6:38 PM >> >> >> >> On 20-Aug-01 Michael VanLoon wrote: >> >> > I seriously doubt the average 300W power supply is going >> to reliably >> > power >> >> > your computer and that many disks. You might check into >> trying one of >> > the >> >> > Enermax EG651P power supplies which would supply a much >> more stable >> > amount >> >> > under heavy load. Other high-load power supplies might >> work as well. >> > That >> >> > 400 might be OK, but quality construction is important >> too -- some cheap >> >> > generic 400 might not be any better than the others. >> Check with PC >> > Power >> >> > and Cooling, SuperMicro, etc. for suitable power supplies. >> >> >> >> No, 300 watts is plenty. IDE's do not use as much current >> as SCSI drives >> > and I >> >> have run more scsi drives than that on a 300W Power supply. >> >> >> >> Now I suppose it would depend on the amount of activity >> and the drives >> >> particular sensitivity, but that only makes the case more >> so in some ways. >> > How >> >> much coddling do the IDE's need then? >> > >> > Well yes and no. First it depends how much power your >> system itself is >> > pulling. Don't forget that AMD recommends a minimum of >> 300W power supply >> > for just your average desktop with only one or two drives. >> Intel chips suck >> > up less, but in some cases not significantly less. >> > >> > Now you may be right in some cases. I decided to go look >> at the Maxtor and >> > IBM sites. It seems under peak load, considering >> worst-case (highest >> > electrical running load) on eight drives (I think that was >> your biggest >> > set-up) you get a power draw of: >> > >> > Maxtor DiamondMax Plus 60: >> > 4.80 Amps at 12V >> > 4.40 Amps at 5V >> > >> > IBM 60GXP: >> > 5.36A at 12V >> > 3.92A at 5V >> > >> > These are for average load. I think Maxtor doesn't >> actually print true peak >> > because IBM's is quite a bit higher than these. At peak loads: >> > >> > IBM 60GXP: >> > 16.00A at 12V!! >> > 9.04A at 5V >> > >> > Remember that's 16A for the hard drives alone, not counting >> any other stuff >> > installed in your computer. >> > >> > Someone mentioned having problems with starting the system >> properly. Here's >> > maybe why... look at these spin-up currents: >> > >> > Maxtor DiamondMax Plus 60: >> > 23.60A at 12V!!! >> > 3.44A at 5V >> > >> > IBM 60GXP: >> > 16.00A at 12V!! >> > 6.4A at 5V >> > >> > >> > The quality Enermax power supplies are a good place to look for some >> > guidance on this. Remember that cheap no-name power >> supplies are typically >> > going to handle this worse than well-made ones will. Their >> 300W model >> > (EG301P) has a max output rating of 15A at 12V. This means >> that if all >> > eight drives try to spin up at once, you are over-loading >> the power supply. >> > This can result in startup errors. But even as indicated >> above, if all >> > eight drives are doing full seek traffic all at once, even >> that might push >> > you above the power supply ratings (16A on drives > 15A on >> power supply). >> > >> > And remember this is only the drives -- this doesn't count >> other stuff >> > drawing 12V inside your case. Since the CPU and >> motherboard circuitry use >> > the 3.3V and 5V taps, this likely will not crash your >> machine, but will >> > cause hard drive errors. >> > >> > Even Enermax's biggest power supply, the 550W unit (EG651P) >> is just barely >> > capable of providing enough power for simultaneous spin-up >> of all eight >> > Maxtor drives (23.6A on drives just barely < 24A from PS). >> And that's >> > assuming you don't have more than 0.4A draw on 12V from >> everything else in >> > your system. >> > >> > So your assumption, "300 watts is plenty," doesn't >> necessarily bear itself >> > out. Now if you use things like staggered spin-up, that >> will help alleviate >> > problems with every drive trying to suck down spin-up >> current at the same >> > time, but even with that, your full-load performance is >> just barely over the >> > limit of this particular power supply. Assuming "no, it's >> plenty" without >> > any real proof is an invitation to disaster in my book. >> >> I see.. So what you are saying is then that all those people >> who make and sell >> systems with that many HD's more or less are all asking for trouble? >> That all the scsi systems I have built or seen running >> similiarly and without >> errors anywere near this are just lucky? >> >> So you postulate that if I replace my 400 watt power supply >> with a 400 Watt >> "better" power supply, I will no longer have problems with >> the 3ware card under >> heavy loads? >> I know my boss is not sinking another dime into IDE stuff >> until proven >> safe. So.. Anyone have a power supply they belive will >> handle the load they >> can loan me for testing? I'm game? >> >> What would you say if I told you that the power supply in >> the case was an >> Enermax power supply? >> >> >> >> Nicole >> >> >> >> >> >> >> >> From: Hodge Podge [mailto:nicole@unixgirl.com] >> >> >> Sent: Sunday, August 19, 2001 2:20 PM >> >> >> >> >> >> On 19-Aug-01 Borja Marcos wrote: >> >> >> > On Sunday 19 August 2001 09:10, you wrote: >> >> >> > >> >> >> >> Yup, cables that were supplied by 3ware. In 3 2 or 3 >> >> >> different cases >> >> >> >> and power supplies. Each were 300 or 400 watt power supplies. >> >> >> > >> >> >> > Excuse me for stepping into the discussion, but I >> >> >> think this is an >> >> >> > important issue: Which was the brand of the cases, power >> >> >> supplies and >> >> >> > fans? How much did they cost? Nowadays the choice of a good >> >> >> case and power >> >> >> > supply is as important as the choice of a good cabling, >> >> disks, etc. >> >> >> >> >> >> One of the cases was from Silicon-rax and had a 300 watt >> >> >> power supply. The >> >> >> other cases were from (I think) acmemicro and one had a 300 >> >> >> watt power supply >> >> >> and the other a 400 watt power supply. (don't know the makes >> >> >> of any of the >> >> >> supplies. ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 18: 4:31 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from odin.wrath.net (068up241.chartermi.net [24.247.68.241]) by hub.freebsd.org (Postfix) with ESMTP id E6DD037B405 for ; Tue, 21 Aug 2001 18:02:00 -0700 (PDT) (envelope-from ircd@wrath.com) Received: from danrc ([192.168.1.2]) by odin.wrath.net with Microsoft SMTPSVC(5.0.2195.2966); Tue, 21 Aug 2001 21:08:43 -0400 Message-ID: <005101c12aa5$7dd36160$0201a8c0@fear.wrath.net> From: "Brian" To: Cc: References: <03d801c12a9e$bab359c0$6601a8c0@elitists.org> Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Tue, 21 Aug 2001 20:58:01 -0400 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.50.4133.2400 X-MimeOLE: Produced By Microsoft MimeOLE V5.50.4133.2400 X-OriginalArrivalTime: 22 Aug 2001 01:08:43.0276 (UTC) FILETIME=[FC877CC0:01C12AA6] Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org ----- Original Message ----- From: "F. Even" To: "Hodge Podge" ; "Michael VanLoon" Cc: ; Sent: Tuesday, August 21, 2001 8:09 PM Subject: Re: 3ware stuff not ready for heavy duty useage-followup > Who sells systems w/ that many disks that is anemically underpowered? I > have not seen them a'plenty. At least not without dual/redundant PS's. I > can't fathom running that many devs. on a 300W PS, but it is probably a > stretch even on a lone 400W, esp. if it has a lot of other devices, or a > higher clocked chip w/ mounds of memory, those are all pieces that need > power too. You are now talking about 400W, but you had mentioned trying > this on a 300W before also...which is a ridiculous notion. > > I have a hard time believing that you have tossed SCSI systems together w/ 8 > drives on them and functioning peripherals, on a 300W PS. If it worked > great for you, well, great. Lucky. Don't count on that as being a good > practice though. Fire up an old AT PS to just handle a few of the drives, > and see if that doesn't help out. I admit to being a dumb college kid. OK, the most energy I've ever seen a drive take is when it's powering up (common sense). I can't remember seeing a drive that required more than 3 amps to power up. 12v x 3a = 36 watts. A general rule of thumb is that the read/write power is half of that that takes to spin the disk up. So let's see, that would be 18 watts. 8 disks x 36 watts/disk ~ = 290 watts. So, she should be definitely safe with a 400 watt power supply. It should very much definitely handle it when running. Now, I've got a crappy 235watt power supply. It handles my six drives, my dual katmai p3-550's, a pair of dual fan cpu fans, and three fans. Sure, you can attempt to ridicule me for doing such things, but I shall ridicule you for being impractical. So I've got a question for Nicole since I haven't been watching the thread as closely as I should. Are the drives completely and utterly dead? Do they work as standalones in another machine? Do they stay spinning or do they just repeatedly spin up and down? I imagine you'd know that if they don't spin chances are the feet welded to the disk and heat got them and I remember that you were quite sure heat was not a factor. If you can't get them to work with a BSD machine and they do stay spun up, try sticking them in a 32bit windows machine and format them with NTFS4 or NTFS5 (it works sometimes, I haven't got the foggiest idea why). Can you run diagnostics on the disk with the software that the manufacturer of the disk supplies? Is there a cabling problem? I assume that all the cables are 80 conductor. What gauge wire are they? If they're smaller than 24 gauge (number greater than 24) somebody should get a firm talking-to. If they really are longer than 18" (it seems like you said they were 36"), then the ribbon should be 22 gauge or better. Are any of the conductors broken on the cable? I usually see them broken at one of the connectors on the drive end. This has been guilty of killing two of my Maxtor drives. > Frank -Brian To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 18: 4:52 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id BAEE537B40B for ; Tue, 21 Aug 2001 18:04:34 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 5EF8C20F1B; Tue, 21 Aug 2001 18:04:34 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <5.1.0.14.0.20010821205247.049785f0@192.168.0.12> Date: Tue, 21 Aug 2001 18:04:34 -0700 (PDT) From: Hodge Podge To: Mike Tancsa Subject: Re: 3ware stuff not ready for heavy duty useage-followup Cc: freebsd-hardware@freebsd.org Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 22-Aug-01 Mike Tancsa wrote: > > You didnt by chance change the Stripe size from the default of 64 did you? > I remember doing this _once_ and it caused me no end of grief. > Just looking at one of the production RAID10 boxes I have. Its a win2k > server running MS-SQL... Pretty busy and very busy in bursts when billing > for 10,000 users gets run twice a month. Its a 6400 card, Firmware > 1.0043.003. BIOS is BEXX 1.04.00.009 > > It has been in service for some time now without any problems. I have a > couple of RAID 10 devices on FreeBSD, but I dont have access to them right > now to see which firmware they are running. > > ---Mike > > Nope.. All standard. You will have to admit however that FreeBSD can beat on periferals much more so than Win2000 :) Nicole > > > >>---------------------------------------------------------------- > > -------------------------------------------------------------------- > Mike Tancsa, tel +1 519 651 3400 > Network Administration, mike@sentex.net > Sentex Communications www.sentex.net > Cambridge, Ontario Canada www.sentex.net/mike ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 18:10:11 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from cage.simianscience.com (cage.simianscience.com [64.7.134.1]) by hub.freebsd.org (Postfix) with ESMTP id 7FCB537B417 for ; Tue, 21 Aug 2001 18:09:47 -0700 (PDT) (envelope-from mike@sentex.net) Received: (from root@localhost) by cage.simianscience.com (8.11.5/8.11.5) id f7M19lf73626; Tue, 21 Aug 2001 21:09:47 -0400 (EDT) (envelope-from mike@sentex.net) Received: from chimp.sentex.net (fcage [192.168.0.2]) by cage.simianscience.com (8.11.5/8.11.5av) with ESMTP id f7M19gM73618; Tue, 21 Aug 2001 21:09:42 -0400 (EDT) (envelope-from mike@sentex.net) Message-Id: <5.1.0.14.0.20010821210719.0498ed90@192.168.0.12> X-Sender: mdtancsa@192.168.0.12 X-Mailer: QUALCOMM Windows Eudora Version 5.1 Date: Tue, 21 Aug 2001 21:09:41 -0400 To: Hodge Podge From: Mike Tancsa Subject: Re: 3ware stuff not ready for heavy duty useage-followup Cc: freebsd-hardware@freebsd.org In-Reply-To: References: <5.1.0.14.0.20010821205247.049785f0@192.168.0.12> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Virus-Scanned: by AMaViS perl-10 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org At 06:04 PM 8/21/2001 -0700, Hodge Podge wrote: > Nope.. All standard. > You will have to admit however that FreeBSD can beat on periferals much more >so than Win2000 :) Drag. it would have been nice if that were the case because it really did hose my 4 port unit when I tried a 128K stripe. Win2k... I wont go there ;-) ---Mike To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 18:14:18 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id D0FEA37B40E for ; Tue, 21 Aug 2001 18:13:55 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 954AC20F1A; Tue, 21 Aug 2001 18:13:55 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <005101c12aa5$7dd36160$0201a8c0@fear.wrath.net> Date: Tue, 21 Aug 2001 18:13:55 -0700 (PDT) From: Hodge Podge To: Brian Subject: Re: 3ware stuff not ready for heavy duty useage-followup Cc: freebsd-hardware@freebsd.org Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 22-Aug-01 Brian wrote: > > ----- Original Message ----- > From: "F. Even" > To: "Hodge Podge" ; "Michael VanLoon" > > Cc: ; > Sent: Tuesday, August 21, 2001 8:09 PM > Subject: Re: 3ware stuff not ready for heavy duty useage-followup > > >> Who sells systems w/ that many disks that is anemically underpowered? I >> have not seen them a'plenty. At least not without dual/redundant PS's. I >> can't fathom running that many devs. on a 300W PS, but it is probably a >> stretch even on a lone 400W, esp. if it has a lot of other devices, or a >> higher clocked chip w/ mounds of memory, those are all pieces that need >> power too. You are now talking about 400W, but you had mentioned trying >> this on a 300W before also...which is a ridiculous notion. >> >> I have a hard time believing that you have tossed SCSI systems together w/ > 8 >> drives on them and functioning peripherals, on a 300W PS. If it worked >> great for you, well, great. Lucky. Don't count on that as being a good >> practice though. Fire up an old AT PS to just handle a few of the drives, >> and see if that doesn't help out. > > I admit to being a dumb college kid. > > OK, the most energy I've ever seen a drive take is when it's powering up > (common sense). I can't remember seeing a drive that required more than 3 > amps to power up. 12v x 3a = 36 watts. A general rule of thumb is that the > read/write power is half of that that takes to spin the disk up. So let's > see, that would be 18 watts. > > 8 disks x 36 watts/disk ~ = 290 watts. So, she should be definitely safe > with a 400 watt power supply. It should very much definitely handle it when > running. > > Now, I've got a crappy 235watt power supply. It handles my six drives, my > dual katmai p3-550's, a pair of dual fan cpu fans, and three fans. Sure, > you can attempt to ridicule me for doing such things, but I shall ridicule > you for being impractical. > > > So I've got a question for Nicole since I haven't been watching the thread > as closely as I should. Are the drives completely and utterly dead? Do > they work as standalones in another machine? Do they stay spinning or do > they just repeatedly spin up and down? I imagine you'd know that if they > don't spin chances are the feet welded to the disk and heat got them and I > remember that you were quite sure heat was not a factor. If you can't get > them to work with a BSD machine and they do stay spun up, try sticking them > in a 32bit windows machine and format them with NTFS4 or NTFS5 (it works > sometimes, I haven't got the foggiest idea why). Can you run diagnostics on > the disk with the software that the manufacturer of the disk supplies? Nope.. Take them out of the RAID array, use them in JBOD and they seem to be running pretty well. They certainly format well. I am doing my massive gigabit linked rdist again.. so we shall see if anything happens. (this is with 61Gb 7200 RPM Maxtor drives at the moment) > Is there a cabling problem? I assume that all the cables are 80 conductor. > What gauge wire are they? Standard cables that come with the card. > If they're smaller than 24 gauge (number greater > than 24) somebody should get a firm talking-to. If they really are longer > than 18" (it seems like you said they were 36"), then the ribbon should be > 22 gauge or better. Are any of the conductors broken on the cable? I > usually see them broken at one of the connectors on the drive end. This has > been guilty of killing two of my Maxtor drives. No, I even made sure that their were no kinks in the cables, but its a good thought. Nicole >> Frank > > -Brian ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 20:16: 5 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from msgbas1.cos.agilent.com (msgbas1x.cos.agilent.com [192.6.9.33]) by hub.freebsd.org (Postfix) with ESMTP id AC63B37B401 for ; Tue, 21 Aug 2001 20:15:27 -0700 (PDT) (envelope-from darrylo@soco.agilent.com) Received: from msgrel1.cos.agilent.com (msgrel1.cos.agilent.com [130.29.152.77]) by msgbas1.cos.agilent.com (Postfix) with ESMTP id 11A5A15C3; Tue, 21 Aug 2001 21:15:27 -0600 (MDT) Received: from mina.soco.agilent.com (mina.soco.agilent.com [141.121.54.157]) by msgrel1.cos.agilent.com (Postfix) with ESMTP id C16D0CF; Tue, 21 Aug 2001 21:15:14 -0600 (MDT) Received: from mina.soco.agilent.com (darrylo@localhost [127.0.0.1]) by mina.soco.agilent.com (8.9.3 (PHNE_22672)/8.9.3 SMKit7.1.1_Agilent) with ESMTP id UAA06753; Tue, 21 Aug 2001 20:15:13 -0700 (PDT) Message-Id: <200108220315.UAA06753@mina.soco.agilent.com> To: Hodge Podge Cc: Michael VanLoon , freebsd-hardware@FreeBSD.ORG Subject: Re: 3ware stuff not ready for heavy duty useage-followup Reply-To: Darryl Okahata In-Reply-To: Your message of "Tue, 21 Aug 2001 16:48:25 PDT." Mime-Version: 1.0 (generated by tm-edit 1.6) Content-Type: text/plain; charset=US-ASCII Date: Tue, 21 Aug 2001 20:15:12 -0700 From: Darryl Okahata Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org [ Sorry about the long quoting, but the quoted parts really do need to be emphasized. ] Hodge Podge wrote: > On 21-Aug-01 Michael VanLoon wrote: > > > > The quality Enermax power supplies are a good place to look for some > > guidance on this. Remember that cheap no-name power supplies are typically > > going to handle this worse than well-made ones will. Their 300W model > > (EG301P) has a max output rating of 15A at 12V. This means that if all > > eight drives try to spin up at once, you are over-loading the power supply. > > This can result in startup errors. But even as indicated above, if all > > eight drives are doing full seek traffic all at once, even that might push > > you above the power supply ratings (16A on drives > 15A on power supply). > > > > And remember this is only the drives -- this doesn't count other stuff > > drawing 12V inside your case. Since the CPU and motherboard circuitry use > > the 3.3V and 5V taps, this likely will not crash your machine, but will > > cause hard drive errors. > > > > Even Enermax's biggest power supply, the 550W unit (EG651P) is just barely > > capable of providing enough power for simultaneous spin-up of all eight > > Maxtor drives (23.6A on drives just barely < 24A from PS). And that's > > assuming you don't have more than 0.4A draw on 12V from everything else in > > your system. > > I see.. So what you are saying is then that all those people who make and se > ll > systems with that many HD's more or less are all asking for trouble? > That all the scsi systems I have built or seen running similiarly and withou > t > errors anywere near this are just lucky? Maybe. The issue here is that you have not shown that there's an high enough probability that the power supply is NOT the culprit. Now, the problem could lie elsewhere, but you have *NOT* eliminated the power supply. Michael's made a lot of good points in the above, and you have not given enough evidence to "disprove" his points (or, at least, to show that it's not likely). Your points seem to be: "Vendors sell it this way. It must be good." Well, "previously-owned cars" are also sold. It doesn't mean that they're any good. M$ Windows is also sold. That doesn't mean that it's good for you, either. In another post, you wrote: > I would like to point to 1 example server that has 13 Drives in > it, and only 1 300 Watt power supply. > http://www.rackable.com/index-productsST.php3?checkit=noflash Personally, I wouldn't touch this, if it has 13 high-performance drives in it. As Michael's shown: 8 drives (without motherboard!) can be marginal with a 300W power supply. I'd hate to think what would happen with 13. "It works for others." Does it work with the exact same hardware configuration as yours (without the 3ware card)? The issue is that the "others" may be using SCSI drives (see the next point), they may be using lower-power (and slower) drives, or they may not be banging on all drives simultaneously. "SCSI works." Well, you really have not given any details. In the absence of such, I'd have to say that: 1. SCSI systems with lots of drives are often in external, stand-alone boxes without a motherboard. This means that there is no power-hungry motherboard competing for power. A "300W" power supply in a stand-alone external case will go farther (but still may or may not be enough) than a "300W" power supply in a PC. 2. IDE systems are often in large cases with a power-sucking motherboard (because IDE cables are not meant to be strung externally). Michael's calculations show that, EVEN WITHOUT A MOTHERBOARD, a 300W power supply can be marginal if eight drives are banged upon hard. You have not shown why this cannot be a problem for you. Now, the power supply may not be your problem, but you have not given any concrete (and technical!) reasons why. Just "touchy-feely" ones. ;-) You need to refute Michael's technical arguments. [ Going off on a slight tangent, it might be interesting to probe the voltages with an oscilloscope, preferably a sampling one if available (you've got to be careful about the usual electrocution, fire, and component damage hazards, though ;-). You probably won't be able to tell anything conclusive, however, unless the power's really dirty (which would be a good indication that the power supply is the culprit). Of course, you'd naturally have to do it under high-load conditions. ] [ Heh. I should talk. I've been meaning to put together a 3W-6800-based 8-drive box (I've had the parts for weeks, but haven't had the time to put it together). I've got an Enermax 451 power supply, and I've been *really* hoping that it'll work. We'll see how it goes (probably in a few weeks, though). ;-( ] -- Darryl Okahata darrylo@soco.agilent.com DISCLAIMER: this message is the author's personal opinion and does not constitute the support, opinion, or policy of Agilent Technologies, or of the little green men that have been following him all day. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 20:43:44 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from tandem.milestonerdl.com (tandem.milestonerdl.com [204.107.138.1]) by hub.freebsd.org (Postfix) with ESMTP id 4746C37B411 for ; Tue, 21 Aug 2001 20:43:29 -0700 (PDT) (envelope-from marc@milestonerdl.com) Received: from tandem (tandem [204.107.138.1]) by tandem.milestonerdl.com (8.11.2/8.10.0) with ESMTP id f7M4RJZ36730; Tue, 21 Aug 2001 23:27:19 -0500 (CDT) Date: Tue, 21 Aug 2001 23:27:19 -0500 (CDT) From: Marc Rassbach To: Darryl Okahata Cc: Hodge Podge , Michael VanLoon , freebsd-hardware@FreeBSD.ORG Subject: Re: 3ware stuff not ready for heavy duty useage-followup In-Reply-To: <200108220315.UAA06753@mina.soco.agilent.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Tue, 21 Aug 2001, Darryl Okahata wrote: Let me tell you all a story about a SCSI III RAID array..... > Your points seem to be: And this is why I decided to submit my 2 coppers. > It was a kingston 9 bay tower (black). Mylex card. Quantum Drives. Called Tech Data (supplier) Mylex and Quantum. All agreed the $30K of parts would work together. > "Vendors sell it this way. It must be good." Yes... YET Kingston sold a SCSI III box with ONE SCSI cable 2.5 meters long. (Hint: 6 per 1.5 meter chain is pushing a non LVD SCSI III. Got to learn that the hard way) No way in hell what I was sold was going to work. Reminder 1#: Unless you know actual non-sales people who have a version of what you are thinking of running, or you have run it in the past, best to go with the idea NONE of it will work. That way, you don't wear egg on your face, AND you look good when it does work. Hard to quote jobs with that attitude, but under promise and over-deliver is always a good MO. > "It works for others." Yes...same argument used for the Kingston tower AND the Quantum drives. Turns out the Quantums were vers 4 of the EEPROM and its broke. To REALLY figure out what is going on, you need REAL data. Your employer won't pay for you to play Qualtiy Control Engineer. That brings me to reminder #2: Always quote the 'known working solution' IE the high end solution where it is someone elses problem. That way, if they opt to choose the lower end solution, you have the out of 'You should have picked the higher end version if you wanted this to work'. Life is full of compermises. At this point, without good technical data of what/how the harddrives were handled, the power supply, the quality of the AC line, etc la, this thread is generating heat to keep one warm, but not alot of information. For all any of us know *ONE* gate deep in the 3ware is dead, causing the problem. (Had a SCO PC involved with a building lighting hit. Any mulitport serial card at 330 would fail. Move the cards to antoher machine at 330, it would work. Move the card to 360, and it would start working. Somewhere, a gate was dead on that machine.....) OR, the hard drive was abuse by a shipper. OR...... To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 21:58:44 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from elitists.org (www.elitists.org [64.40.73.38]) by hub.freebsd.org (Postfix) with ESMTP id 79F1F37B40E for ; Tue, 21 Aug 2001 21:58:37 -0700 (PDT) (envelope-from freebsdlists@elitists.org) Received: from blah (64-40-88-202.pk.dsl.grics.net [64.40.88.202]) by elitists.org (Postfix) with SMTP id C4C32213 for ; Wed, 22 Aug 2001 00:09:12 -0500 (CDT) Message-ID: <045e01c12ac7$7fc8a940$6601a8c0@elitists.org> From: "F. Even" To: References: Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Wed, 22 Aug 2001 00:01:26 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.00.2615.200 X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2615.200 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Real data would be helpful. Thus far, we know that there are 8 drives on a 3Ware card, maybe on a 300W, maybe 400W PS, also w/ 3 large fans plugged into it. What kind of motherboard/processors/video card/memory? Those all also matter in the power consumption discussion. ----- Original Message ----- From: Marc Rassbach To: Darryl Okahata Cc: Hodge Podge ; Michael VanLoon ; Sent: Tuesday, August 21, 2001 11:27 PM Subject: Re: 3ware stuff not ready for heavy duty useage-followup To REALLY figure out what is going on, you need REAL data. Your employer won't pay for you to play Qualtiy Control Engineer. That brings me to reminder #2: Always quote the 'known working solution' IE the high end solution where it is someone elses problem. That way, if they opt to choose the lower end solution, you have the out of 'You should have picked the higher end version if you wanted this to work'. Life is full of compermises. At this point, without good technical data of what/how the harddrives were handled, the power supply, the quality of the AC line, etc la, this thread is generating heat to keep one warm, but not alot of information. For all any of us know *ONE* gate deep in the 3ware is dead, causing the problem. (Had a SCO PC involved with a building lighting hit. Any mulitport serial card at 330 would fail. Move the cards to antoher machine at 330, it would work. Move the card to 360, and it would start working. Somewhere, a gate was dead on that machine.....) OR, the hard drive was abuse by a shipper. OR...... To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 22: 4:35 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from elitists.org (www.elitists.org [64.40.73.38]) by hub.freebsd.org (Postfix) with ESMTP id D968C37B411 for ; Tue, 21 Aug 2001 22:04:32 -0700 (PDT) (envelope-from freebsdlists@elitists.org) Received: from blah (64-40-88-202.pk.dsl.grics.net [64.40.88.202]) by elitists.org (Postfix) with SMTP id 19E03213; Wed, 22 Aug 2001 00:15:07 -0500 (CDT) Message-ID: <046901c12ac8$53bb63a0$6601a8c0@elitists.org> From: "F. Even" To: "Brian" , Cc: References: <03d801c12a9e$bab359c0$6601a8c0@elitists.org> <005101c12aa5$7dd36160$0201a8c0@fear.wrath.net> Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Wed, 22 Aug 2001 00:07:20 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.00.2615.200 X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2615.200 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org ----- Original Message ----- From: Brian To: Cc: Sent: Tuesday, August 21, 2001 7:58 PM Subject: Re: 3ware stuff not ready for heavy duty useage-followup Now, I've got a crappy 235watt power supply. It handles my six drives, my dual katmai p3-550's, a pair of dual fan cpu fans, and three fans. Sure, you can attempt to ridicule me for doing such things, but I shall ridicule you for being impractical. ------------------------------------ ...and you would be wrong, as your desktop a production server does not make. It might be fine for the light use of your desktop, but a server should be rock solid. I'd be willing to bet if those were P4's, you would see that take a dive. If you are running a server like that, I'm sorry...that is not being "practical," and that opens you up to ridicule for that...or at least no sympathy when it takes a dive. Frank To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 22:16:20 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from enterprise.spock.org (cm-24-29-85-81.nycap.rr.com [24.29.85.81]) by hub.freebsd.org (Postfix) with ESMTP id CBACF37B408 for ; Tue, 21 Aug 2001 22:16:14 -0700 (PDT) (envelope-from jon@enterprise.spock.org) Received: (from jon@localhost) by enterprise.spock.org serial EF600Q3T-B7F; Wed, 22 Aug 2001 01:16:06 -0400 (EDT) (envelope-from jon)$ Date: Wed, 22 Aug 2001 01:16:05 -0400 From: Jonathan Chen To: Matthew Jacob Cc: hardware@FreeBSD.ORG Subject: Re: looking for ia32 system that supports > 4GB memory and has 64 bit PCI Message-ID: <20010822011605.C78675@enterprise.spock.org> References: <20010821170539.Q23686-100000@wonky.feral.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: telnet/1.1x In-Reply-To: <20010821170539.Q23686-100000@wonky.feral.com>; from mjacob@feral.com on Tue, Aug 21, 2001 at 05:37:18PM -0700 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Tue, Aug 21, 2001 at 05:37:18PM -0700, Matthew Jacob wrote: > > I'm looking for in Intel IA32 system that has 64 bit PCI slots and can support > more than 4GB memory- it's time for me to start thinking about what 64 bit > DAC PCI really means. My STL2 board only supports up to 4GB. I've grovelled > around a bit on the Intel site, and don't see anything very helpful. > > I know that some of you are playing around with these systems now. What's > available and workable? SuperMicro (http://www.supermicro.om) sells boards with ServerWorks HE chipsets which meet your specification. I'm not aware of any other options though. -Jon To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Tue Aug 21 23:31:16 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id E744937B403 for ; Tue, 21 Aug 2001 23:31:11 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 717E320F22; Tue, 21 Aug 2001 23:31:11 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: Date: Tue, 21 Aug 2001 23:31:11 -0700 (PDT) From: Hodge Podge To: Marc Rassbach Subject: Re: 3ware stuff not ready for heavy duty useage-followup Cc: freebsd-hardware@FreeBSD.ORG, Michael VanLoon , Darryl Okahata Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 22-Aug-01 Marc Rassbach wrote: > > > On Tue, 21 Aug 2001, Darryl Okahata wrote: > Let me tell you all a story about a SCSI III RAID array..... > >> Your points seem to be: > > And this is why I decided to submit my 2 coppers. > It was a kingston 9 bay tower (black). Mylex card. Quantum Drives. > Called Tech Data (supplier) Mylex and Quantum. All agreed the $30K of > parts would work together. >> "Vendors sell it this way. It must be good." > Yes... YET Kingston sold a SCSI III box with ONE SCSI cable 2.5 meters > long. (Hint: 6 per 1.5 meter chain is pushing a non LVD SCSI III. Got > to learn that the hard way) No way in hell what I was sold was going to > work. > Reminder 1#: Unless you know actual non-sales people who have a version > of what you are thinking of running, or you have run it in the past, best > to go with the idea NONE of it will work. That way, you don't wear egg on > your face, AND you look good when it does work. Hard to quote jobs with > that attitude, but under promise and over-deliver is always a good MO. Which I do.. Several of.. 1 which I pointed out and people keep glazing over becouse it doesn't help them make their silly power supply point. >> "It works for others." > > Yes...same argument used for the Kingston tower AND the Quantum drives. > Turns out the Quantums were vers 4 of the EEPROM and its broke. I don't want to even touch how silly this is.. > > To REALLY figure out what is going on, you need REAL data. Your employer > won't pay for you to play Qualtiy Control Engineer. That brings me to > reminder #2: Always quote the 'known working solution' IE the high end > solution where it is someone elses problem. That way, if they opt to > choose the lower end solution, you have the out of 'You should have picked > the higher end version if you wanted this to work'. Life is full of > compermises. Welcome to how Sun and IBM walks its way in to most shops and why FreeBSD never gets a chance. I have heard it Sooo many times before. I want someone I can blame and point to. (are you a manager by chance?) If that is how you always operate do you only use FreeBSD when they won't go for your 'known working solution' you can point fingers with? > At this point, without good technical data of what/how the harddrives were > handled, the power supply, the quality of the AC line, etc la, this thread > is generating heat to keep one warm, but not alot of information. For all > any of us know *ONE* gate deep in the 3ware is dead, causing the > problem. (Had a SCO PC involved with a building lighting hit. Any > mulitport serial card at 330 would fail. Move the cards to antoher > machine at 330, it would work. Move the card to 360, and it would start > working. Somewhere, a gate was dead on that machine.....) OR, the hard > drive was abuse by a shipper. OR...... Yes however I will bet even money that if I put a seperate power supply on every friggen drive and still have the same problem someones gonna say.. I bet one of Those supplys was bad.. Can folks try, just try to imagine that they "could" be wrong and come up with some other reason? Do I honestly have to Prove it wrong in some scientific way before you are willing to imagine some other possibility? Jeeze. Some time I or someone else will have a chance to test the theory, but for now that is all it is. One thoery. Did you read, really read, my last two posts on this? Nicole Ok Now I am getting a little snide. It just feels like what galileo went through. He was almost killed for beliving that the earth revolved around the sun in contrary with current belifes. ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Wed Aug 22 0: 6:18 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from elitists.org (www.elitists.org [64.40.73.38]) by hub.freebsd.org (Postfix) with ESMTP id 7BE9837B406 for ; Wed, 22 Aug 2001 00:06:10 -0700 (PDT) (envelope-from freebsdlists@elitists.org) Received: from blah (64-40-88-202.pk.dsl.grics.net [64.40.88.202]) by elitists.org (Postfix) with SMTP id 313A7213; Wed, 22 Aug 2001 02:16:43 -0500 (CDT) Message-ID: <04d901c12ad9$48adbce0$6601a8c0@elitists.org> From: "F. Even" To: "Hodge Podge" , "Marc Rassbach" Cc: , "Michael VanLoon" References: Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Wed, 22 Aug 2001 02:08:28 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.00.2615.200 X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2615.200 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Until you have introduced one seperate/additional power supply into this mess though, you can't discount it!!! Jeez. There have been other theories tossed out, but damn, that is a LOT of devices in a tight power tolerance there. ALSO...what kind of system is this? P4? AMD? Those both need MORE POWER. It is not a "silly" suggestion. Can you imagine that YOU might be wrong in immediately discounting every suggestion put forth?! IF YOU know what it can and cannot be, then why did you bother to even post to this discussion list? There must be no problem then, and if there is, you must certainly know what it is then......and if that is the case, you should in fact be able to fix it, right? ...and that one manufacturer's link you posted earlier...note, it said "up to" 13 drives. Case probably comes with none, or they probably tell you that you need more power for that many. If you look at their other servers, none of them are that anemically powered. ...and your comparison to 1 and 2U servers is not relevant, as most of them won't have that many devices crammed into them, hence NOT needing that much power. Yeah...I have a couple 1U rack mountable VA boxes, and they only have I think 200W PS's....but, there is not that many devices being powered. Common sense here. No one is not necessarily discounting that there COULD BE other problems, but you seem to not want to investigate anything else except the card. If you can whip together one of those magical 300W/8+device SCSI machines to handle full-scale enterprise database access, then do that I guess. Have fun. ...oh please....the Galileo comparison is pathetic. ----- Original Message ----- From: Hodge Podge To: Marc Rassbach Cc: ; Michael VanLoon ; Darryl Okahata Sent: Wednesday, August 22, 2001 1:31 AM Subject: Re: 3ware stuff not ready for heavy duty useage-followup Yes however I will bet even money that if I put a seperate power supply on every friggen drive and still have the same problem someones gonna say.. I bet one of Those supplys was bad.. Can folks try, just try to imagine that they "could" be wrong and come up with some other reason? Do I honestly have to Prove it wrong in some scientific way before you are willing to imagine some other possibility? Jeeze. Some time I or someone else will have a chance to test the theory, but for now that is all it is. One thoery. Did you read, really read, my last two posts on this? Nicole Ok Now I am getting a little snide. It just feels like what galileo went through. He was almost killed for beliving that the earth revolved around the sun in contrary with current belifes. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Wed Aug 22 0:20:19 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id B78D037B407 for ; Wed, 22 Aug 2001 00:20:14 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 3583820F22; Wed, 22 Aug 2001 00:20:14 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <04d901c12ad9$48adbce0$6601a8c0@elitists.org> Date: Wed, 22 Aug 2001 00:20:14 -0700 (PDT) From: Hodge Podge To: "F. Even" Subject: Re: 3ware stuff not ready for heavy duty useage-followup Cc: Michael VanLoon , freebsd-hardware@FreeBSD.ORG, Marc Rassbach Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 22-Aug-01 F. Even wrote: > Until you have introduced one seperate/additional power supply into this > mess though, you can't discount it!!! Jeez. There have been other theories > tossed out, but damn, that is a LOT of devices in a tight power tolerance > there. ALSO...what kind of system is this? P4? AMD? Those both need MORE > POWER. It is not a "silly" suggestion. Can you imagine that YOU might be > wrong in immediately discounting every suggestion put forth?! IF YOU know > what it can and cannot be, then why did you bother to even post to this > discussion list? There must be no problem then, and if there is, you must > certainly know what it is then......and if that is the case, you should in > fact be able to fix it, right? Absolutly. However until I can test it.. Its just 1 Possibility. Also woudl you not agree that since it was stated that since one needs to have IDE's in teh same case as the MB that it woudl be a good idea for 3ware to do some tests with 8 drives to say.. Hey.. This is what you need if you are going to use our 8 port card? > > ...and that one manufacturer's link you posted earlier...note, it said "up > to" 13 drives. Case probably comes with none, or they probably tell you > that you need more power for that many. If you look at their other servers, > none of them are that anemically powered. I have seen the server. It is what is is it comes with all the drives. Yahoo and google use lots of them. May I also point to the 3ware Palisade device... A 1U box with 8 hard drives. READS "Has dual power supplies.. Only needs one.." Now I know that they are Not getting a 400watt super stable power supply into a 1U case... > ...and your comparison to 1 and 2U servers is not relevant, as most of them > won't have that many devices crammed into them, hence NOT needing that much > power. Yeah...I have a couple 1U rack mountable VA boxes, and they only > have I think 200W PS's....but, there is not that many devices being powered. > Common sense here. No one is not necessarily discounting that there COULD > BE other problems, but you seem to not want to investigate anything else > except the card. If you can whip together one of those magical > 300W/8+device SCSI machines to handle full-scale enterprise database access, > then do that I guess. Have fun. I made the comparison to point put that even 1U units with small power supplies often also have large CPU's and 2 -4 hard drives in them. Simple math. " but you seem to not want to investigate anything else" Hello? I seem to remember saying the exact opposite, but having more than 1 thing to test is wise won't you agree??? > ...oh please....the Galileo comparison is pathetic. Its late.. what do you expect War and Peace. Nicole > > ----- Original Message ----- > From: Hodge Podge > To: Marc Rassbach > Cc: ; Michael VanLoon ; > Darryl Okahata > Sent: Wednesday, August 22, 2001 1:31 AM > Subject: Re: 3ware stuff not ready for heavy duty useage-followup > > Yes however I will bet even money that if I put a seperate power supply on > every friggen drive and still have the same problem someones gonna say.. I > bet > one of Those supplys was bad.. Can folks try, just try to imagine that they > "could" be wrong and come up with some other reason? Do I honestly have to > Prove it wrong in some scientific way before you are willing to imagine some > other possibility? Jeeze. Some time I or someone else will have a chance to > test the theory, but for now that is all it is. One thoery. > > Did you read, really read, my last two posts on this? > > Nicole > Ok Now I am getting a little snide. It just feels like what galileo went > through. He was almost killed for beliving that the earth revolved around > the > sun in contrary with current belifes. ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Wed Aug 22 3:10:25 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from borja.sarenet.es (borja.sarenet.es [192.148.167.77]) by hub.freebsd.org (Postfix) with ESMTP id D243C37B40B for ; Wed, 22 Aug 2001 03:10:16 -0700 (PDT) (envelope-from borjam@sarenet.es) Received: from there (localhost [127.0.0.1]) by borja.sarenet.es (8.11.3/8.11.3) with SMTP id f7MA98V17043; Wed, 22 Aug 2001 12:09:09 +0200 (CEST) (envelope-from borjam@sarenet.es) Message-Id: <200108221009.f7MA98V17043@borja.sarenet.es> Content-Type: text/plain; charset="iso-8859-1" From: Borja Marcos Organization: Sarenet S.A. To: "Brian" Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Wed, 22 Aug 2001 12:09:08 +0200 X-Mailer: KMail [version 1.3] References: <03d801c12a9e$bab359c0$6601a8c0@elitists.org> <005101c12aa5$7dd36160$0201a8c0@fear.wrath.net> In-Reply-To: <005101c12aa5$7dd36160$0201a8c0@fear.wrath.net> Cc: freebsd-hardware@freebsd.org MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Wednesday 22 August 2001 02:58, you wrote: > I admit to being a dumb college kid. > > OK, the most energy I've ever seen a drive take is when it's powering u= p > (common sense). I can't remember seeing a drive that required more tha= n 3 > amps to power up. 12v x 3a =3D 36 watts. A general rule of thumb is t= hat > the read/write power is half of that that takes to spin the disk up. S= o > let's see, that would be 18 watts. > > 8 disks x 36 watts/disk ~ =3D 290 watts. So, she should be definitely = safe > with a 400 watt power supply. It should very much definitely handle it > when running. > > Now, I've got a crappy 235watt power supply. It handles my six drives,= my > dual katmai p3-550's, a pair of dual fan cpu fans, and three fans. Sur= e, > you can attempt to ridicule me for doing such things, but I shall ridic= ule > you for being impractical. =09It is not only a matter of watts. A 300 W PC power supply *cannot* giv= e 25 A=20 at 12 V. Such supplies use to have limitations. You can get 300 W adding = the=20 currents it can supply for +5 V, -5 V, +12 V and -12 V. =09Borja. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Wed Aug 22 3:18:42 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from borja.sarenet.es (borja.sarenet.es [192.148.167.77]) by hub.freebsd.org (Postfix) with ESMTP id 8D68037B406 for ; Wed, 22 Aug 2001 03:18:34 -0700 (PDT) (envelope-from borjamar@sarenet.es) Received: from there (localhost [127.0.0.1]) by borja.sarenet.es (8.11.3/8.11.3) with SMTP id f7MAHeV17056; Wed, 22 Aug 2001 12:17:45 +0200 (CEST) (envelope-from borjamar@sarenet.es) Message-Id: <200108221017.f7MAHeV17056@borja.sarenet.es> Content-Type: text/plain; charset="iso-8859-1" From: Borja Marcos To: Darryl Okahata Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Wed, 22 Aug 2001 12:17:40 +0200 X-Mailer: KMail [version 1.3] References: <200108220315.UAA06753@mina.soco.agilent.com> In-Reply-To: <200108220315.UAA06753@mina.soco.agilent.com> Cc: freebsd-hardware@freebsd.org MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Wednesday 22 August 2001 05:15, you wrote: > =09Well, "previously-owned cars" are also sold. It doesn't mean > =09that they're any good. M$ Windows is also sold. That doesn't > =09mean that it's good for you, either. =09I have seen really poor cases and power supplies around. Nowadays, wit= h many=20 people (I'm not saying that this is the case!) assuming that computers ar= e=20 unreliable and must be incredibly cheap, many manufacturers use poor qual= ity=20 components, even in "high-end" products. For example, I've got a "server"= box=20 (paid aboud $200 for it) approved by AMD for my Athlon system, and one of= the=20 fans has started to fail after two years. I'm tired of seeing Compaq or S= un=20 systems whose fans run for years. =09It is impossible to manufacture a good power supply and sell it for $2= 0. It=20 just wouldn't cover the prices of the components! > [ Going off on a slight tangent, it might be interesting to probe the > voltages with an oscilloscope, preferably a sampling one if available > (you've got to be careful about the usual electrocution, fire, and > component damage hazards, though ;-). You probably won't be able to > tell anything conclusive, however, unless the power's really dirty > (which would be a good indication that the power supply is the > culprit). Of course, you'd naturally have to do it under high-load > conditions. ] =09;-) The oscilloscope is a useful tool, indeed. I remember something I = saw=20 some years ago. We sent an industrial PC to a customer, and two days ago = the=20 disk was completely corrupted. We swapped it and the same happened. Someo= ne=20 checked the power line, and the UPS they were using was suplying a voltag= e=20 oscillating between 150 V and 240 V.=20 =09So, I don't think using an oscilloscope is "going on a tangent" ;-) =09Borja. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Wed Aug 22 3:20:22 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from borja.sarenet.es (borja.sarenet.es [192.148.167.77]) by hub.freebsd.org (Postfix) with ESMTP id 7732F37B406 for ; Wed, 22 Aug 2001 03:20:19 -0700 (PDT) (envelope-from borjamar@sarenet.es) Received: from there (localhost [127.0.0.1]) by borja.sarenet.es (8.11.3/8.11.3) with SMTP id f7MAJeV17060; Wed, 22 Aug 2001 12:19:41 +0200 (CEST) (envelope-from borjamar@sarenet.es) Message-Id: <200108221019.f7MAJeV17060@borja.sarenet.es> Content-Type: text/plain; charset="iso-8859-1" From: Borja Marcos To: Hodge Podge Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Wed, 22 Aug 2001 12:19:40 +0200 X-Mailer: KMail [version 1.3] References: In-Reply-To: Cc: freebsd-hardware@freebsd.org MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Wednesday 22 August 2001 08:31, you wrote: Welcome to how Sun and IBM walks its way in to most shops and why FreeB= SD > never gets a chance. I have heard it Sooo many times before. I want > someone I can blame and point to. (are you a manager by chance?) If th= at > is how you always operate do you only use FreeBSD when they won't go fo= r > your 'known working solution' you can point fingers with? =09This is not a FreeBSD issue, but a hardware issue... And I use FreeBSD= in=20 production or very critical tasks. I'm really happy with it. In fact I'm = in=20 love. =09Borja. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Wed Aug 22 5:33:53 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from home.smithconcepts.com (ubr-35.28.151.oviedo.cfl.rr.com [65.35.28.151]) by hub.freebsd.org (Postfix) with ESMTP id C76F437B410 for ; Wed, 22 Aug 2001 05:33:45 -0700 (PDT) (envelope-from b.j.smith@ieee.org) Received: from ieee.org (IDENT:bjsmith@bitman.oviedo.smithconcepts.com [172.24.24.192]) by home.smithconcepts.com (8.9.3/8.9.3) with ESMTP id IAA15786; Wed, 22 Aug 2001 08:23:38 -0400 Message-ID: <3B83A672.97EA7719@ieee.org> Date: Wed, 22 Aug 2001 08:32:50 -0400 From: Bryan-TheBS-Smith Organization: SmithConcepts, Inc. X-Mailer: Mozilla 4.77 [en] (X11; U; Linux 2.4.3-SGI_XFS_1.0.1 i686) X-Accept-Language: en MIME-Version: 1.0 To: Borja Marcos Cc: Hodge Podge , freebsd-hardware@FreeBSD.ORG Subject: Re: 3ware stuff not ready for heavy duty useage-followup References: <200108221019.f7MAJeV17060@borja.sarenet.es> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I have been following this hardware thread for awhile. Rule 1: Read the _actual_specs_ on your power supply! I've seen 250W PS that provided more current on the 3.3+5V lines than most 400W. If you have a newer CPU and a lot of add-in boards, you'll need it! Antec and Energmax (?) seem to have PowerPC&Cooling specs for 1/2-1/3rd the price. And I love Antec's case designs (especially the SX635 and SX1040), plus they just came out with a "cost effective" 350W PS ($50 versus $85 for their 400W). Rule 2: Add up the 12V current provided and match it against your drives. This one is simple enough. Although see #3 ... Rule 3: Add up the 12V current required for "start up" if you don't have SCSI Unlike SCSI, IDE doesn't provide a "delayed spindle" so you can offset the "startup current" so not all drives start at the same time. "Startup current" can really affect your PS, especially since it is usually 2X+ any other operation. Be wary with IDE and make sure you get at least a _good_ 400W PS if you've got 6+ drives total, possibly one of those Energmax 400/450peak and 550/650peak ones for 8-12. -- TheBS -- Bryan "TheBS" Smith mailto:b.j.smith@ieee.org chat:thebs413 Engineer AbsoluteValue Systems, Inc. http://www.linux-wlan.org President SmithConcepts, Inc. http://www.SmithConcepts.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Wed Aug 22 6:59:49 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from paperboy.sixforty.co.uk (paperboy.sixforty.co.uk [195.10.242.11]) by hub.freebsd.org (Postfix) with ESMTP id C222037B41C for ; Wed, 22 Aug 2001 06:59:29 -0700 (PDT) (envelope-from freebsd-hw@sixforty.co.uk) Received: (from root@localhost) by paperboy.sixforty.co.uk (8.11.1/8.11.1) id f7MDxCF18310; Wed, 22 Aug 2001 14:59:12 +0100 (BST) (envelope-from freebsd-hw@sixforty.co.uk) Delivered-To: val@picturetrail.com Received: from lfarr (daisy.int.epcdirect.co.uk [192.168.6.200]) by paperboy.sixforty.co.uk (8.11.1/8.11.1av) with ESMTP id f7MDx2618302; Wed, 22 Aug 2001 14:59:03 +0100 (BST) (envelope-from freebsd-hw@sixforty.co.uk) From: "Lawrence Farr" To: "'Hodge Podge'" Cc: , , "'Borja Marcos'" , "'Michael VanLoon'" , Subject: RE: 3ware stuff not ready for heavy duty useage- ATTN 3ware Date: Wed, 22 Aug 2001 14:59:10 +0100 Message-ID: <001001c12b12$a2162310$c806a8c0@lfarr> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook, Build 10.0.2627 Importance: Normal X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2462.0000 In-Reply-To: X-Virus-Scanned: by AMaViS perl-10 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Im just formatting an 8 drive (Maxtor 536DX 100Gb) 7000 series array, 400W supply. Pick a benchmark and I'll run it for a while. >-----Original Message----- >From: owner-freebsd-hardware@FreeBSD.ORG >[mailto:owner-freebsd-hardware@FreeBSD.ORG] On Behalf Of Hodge Podge >Sent: 22 August 2001 01:40 >To: Hodge Podge >Cc: mike.wentz@3ware.com; freebsd-hardware@FreeBSD.ORG; Borja >Marcos; Michael VanLoon; val@picturetrail.com >Subject: RE: 3ware stuff not ready for heavy duty useage- ATTN 3ware > > > > >OK.. I have an Idea. Since 3ware is selling an 8 port card.. >Ostensibly to be >used with 8 devices in the system, do they have any reccoemndations? > Have they done any empirical testing? > I mean it sounds like a good idea to say .. hey if you are >using our 8 port >card with 8 drives better make sure you have X power supply >rating etc in >their manual? > > Can someone at 3ware do some testing if this hasn't been done? > I will do what I can with what I have available, but obviosly their >testing would be more highly regarded. > > I am willing to go to 3ware and do the testing with them if >we can work >something out. I think it would be a good idea. > > Also is there anyone currently using 8 drives in a system >following this? What >are you using? > > > > Nicole > > > >******* |\ __ /| (`\ ******* > * * | o_o |__ ) ) * * > * * // \\ * * > * Nicole Harrington | AKA Hodge Podge * >----------------------(((---(((-------------------------------- > nicole@unixgirl.com http://www.unixgirl.com/ > webmistress@dangermouse.org http://www.dangermouse.org/ > nicole@deviantimages.com http://www.deviantimages.com/ > > -- Powered By Coca-Cola and FreeBSD -- > "The world is run by those who show up" > -- The Best Place for Your Web Site - www.WebWeaver.net -- > >---------------------------------------------------------------- > > > >To Unsubscribe: send mail to majordomo@FreeBSD.org >with "unsubscribe freebsd-hardware" in the body of the message > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Wed Aug 22 9:53: 3 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from msgbas2.cos.agilent.com (msgbas2x.cos.agilent.com [192.25.240.37]) by hub.freebsd.org (Postfix) with ESMTP id F2D1737B41B for ; Wed, 22 Aug 2001 09:52:33 -0700 (PDT) (envelope-from darrylo@soco.agilent.com) Received: from msgrel1.cos.agilent.com (msgrel1.cos.agilent.com [130.29.152.77]) by msgbas2.cos.agilent.com (Postfix) with ESMTP id 5D21E467; Wed, 22 Aug 2001 10:52:33 -0600 (MDT) Received: from mina.soco.agilent.com (mina.soco.agilent.com [141.121.54.157]) by msgrel1.cos.agilent.com (Postfix) with ESMTP id 8BF4EE8; Wed, 22 Aug 2001 10:52:32 -0600 (MDT) Received: from mina.soco.agilent.com (darrylo@localhost [127.0.0.1]) by mina.soco.agilent.com (8.9.3 (PHNE_22672)/8.9.3 SMKit7.1.1_Agilent) with ESMTP id JAA03752; Wed, 22 Aug 2001 09:52:31 -0700 (PDT) Message-Id: <200108221652.JAA03752@mina.soco.agilent.com> To: Hodge Podge Cc: Marc Rassbach , freebsd-hardware@FreeBSD.ORG, Michael VanLoon Subject: Re: 3ware stuff not ready for heavy duty useage-followup Reply-To: Darryl Okahata In-Reply-To: Your message of "Tue, 21 Aug 2001 23:31:11 PDT." Mime-Version: 1.0 (generated by tm-edit 1.6) Content-Type: text/plain; charset=US-ASCII Date: Wed, 22 Aug 2001 09:52:30 -0700 From: Darryl Okahata Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hodge Podge wrote: > Yes however I will bet even money that if I put a seperate power supply on > every friggen drive and still have the same problem someones gonna say.. I b > et > one of Those supplys was bad.. Can folks try, just try to imagine that they > "could" be wrong and come up with some other reason? Do I honestly have to > Prove it wrong in some scientific way before you are willing to imagine some > other possibility? Jeeze. Some time I or someone else will have a chance to > test the theory, but for now that is all it is. One thoery. OK, let's look at the other possibilities: 1. Non-3ware hardware problem (bad motherboard, RAM, etc.). Very unlikely, as this problem happens on "multiple systems". 2. Bad batch of 3ware boards. Unlikely, but a very small sliver of a possibility. 3. 3ware hardware bug. If so, you're screwed. There's probably nothing you can do about it. 4. 3ware firmware problem. If so, you're probably screwed. At the very least, you'll probably have to wait some unknown, probably long, period of time for a firmware update. 5. FreeBSD problem. Not very likely, but a possibility. Other people seem to be having success with 3ware and high loads. I have not seen anyone mention using an 8-drive setup, though (I get to do this in a few weeks, although the system won't generally be under high load). Unless you're conversant with FreeBSD disk driver debugging, you're at the mercy of the FreeBSD driver developer (yes, I know who it is), whom you may have unintentionally pissed off beyond redemption. At the very least, in order to fix any problems, he'd have to reproduce your problems. [ Note: as another person has mentioned, you're coming across as a real hard case (even before your recent messages). I'm sure it's unintentional, but you've got to be aware of this. If you want help, you don't want to (unintentionally) piss off the people who might be able to help you. Please note that many of the people here are anal-retentive analytics who need data, data, and more DATA (yes, I'll raise my hand ;-). You haven't given much details, and, for much of the details which you have given, you've given as part of "snippy"/"unintentionally insulting" responses or maddeningly dribbled them out across many postings. ] 6. Large noise sources near your systems. Unlikely, as you haven't mentioned any special situations (like having an arc welder, large motor, or transmitter near your systems). 7. Bad line power. Unlikely (well, unknown, as you haven't given any details), but, as Borja mentioned, a bad UPS can really screw you over. 8. Power supply problem. Unknown. Seems pretty likely, but you're also seeing this problem across multiple systems, which can imply that it's not a power supply problem -- however, you haven't said that any of the other systems have large, beefy power supplies. This is one of the few things that you can test and control. Well, the above are the possibilities as I see them. It's your choice. What do you want to do? -- Darryl Okahata darrylo@soco.agilent.com DISCLAIMER: this message is the author's personal opinion and does not constitute the support, opinion, or policy of Agilent Technologies, or of the little green men that have been following him all day. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Wed Aug 22 11: 0:59 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id ECD4337B40F for ; Wed, 22 Aug 2001 11:00:01 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 19B6D20F2E; Wed, 22 Aug 2001 11:00:00 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <200108221652.JAA03752@mina.soco.agilent.com> Date: Wed, 22 Aug 2001 11:00:00 -0700 (PDT) From: Hodge Podge To: Darryl Okahata Subject: Re: 3ware stuff not ready for heavy duty useage-followup Cc: Michael VanLoon , freebsd-hardware@FreeBSD.ORG, Marc Rassbach Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 22-Aug-01 Darryl Okahata wrote: > Hodge Podge wrote: > >> Yes however I will bet even money that if I put a seperate power supply on >> every friggen drive and still have the same problem someones gonna say.. I >> bet >> one of Those supplys was bad.. Can folks try, just try to imagine that they >> "could" be wrong and come up with some other reason? Do I honestly have to >> Prove it wrong in some scientific way before you are willing to imagine some >> other possibility? Jeeze. Some time I or someone else will have a chance to >> test the theory, but for now that is all it is. One thoery. > > OK, let's look at the other possibilities: > > 1. Non-3ware hardware problem (bad motherboard, RAM, etc.). > > Very unlikely, as this problem happens on "multiple systems". Ny belife as well. > 2. Bad batch of 3ware boards. > > Unlikely, but a very small sliver of a possibility. Also true. > 3. 3ware hardware bug. > > If so, you're screwed. There's probably nothing you can do about it. Very True > 4. 3ware firmware problem. > > If so, you're probably screwed. At the very least, you'll probably > have to wait some unknown, probably long, period of time for a > firmware update. My points. Everytime I loose a drive to the card, The drive tests fine elseware for other usage such as in JBOD. Also the continued failure of the system to be able to rebuild onto the hotspare is very bad. Also loosing 2 drives on the same plex (under RAID 10) preventing any hope of a rebuild points to the drives in many ways and how the card is interacting with them. > 5. FreeBSD problem. > > Not very likely, but a possibility. Other people seem to be having > success with 3ware and high loads. I have not seen anyone mention > using an 8-drive setup, though (I get to do this in a few weeks, > although the system won't generally be under high load). > > Unless you're conversant with FreeBSD disk driver debugging, you're > at the mercy of the FreeBSD driver developer (yes, I know who it is), > whom you may have unintentionally pissed off beyond redemption. At > the very least, in order to fix any problems, he'd have to reproduce > your problems. If I have somehow pissed off Mike I appologise. But that seems like pissing off the weatherman for complaining abt the rain. I can't see how this could have anything to do with the driver since the interaction causing the disks to dropout is between the card and the drive. Mike, if I have somehow managed to piss you off with this, please let me know how so I can correct that. The whole reason for my posting in the first place was.. Hey I have been having problems like mad, here is my reasoning why... be carefull and test a Lot before you rely on a similiar system. I don't think the Larger drives are ready for prime time under heavy loads. If it works for you.. great.. But be careful. > [ Note: as another person has mentioned, you're coming across as a > real hard case (even before your recent messages). I'm sure it's > unintentional, but you've got to be aware of this. If you want > help, you don't want to (unintentionally) piss off the people who > might be able to help you. Please note that many of the people > here are anal-retentive analytics who need data, data, and more > DATA (yes, I'll raise my hand ;-). You haven't given much details, > and, for much of the details which you have given, you've given as > part of "snippy"/"unintentionally insulting" responses or > maddeningly dribbled them out across many postings. ] Well, At first I was amazingly pissed off for loosing yet another weekend to having to rescue a system. Some of that may have come off incorrectly. I appologise if that has occured. I also do not have time to write a dissertation on the issue. Perhaps the details below will help. System1 - iteration 2 4U case with 300 Watt power supply AMD 900 Mhz proc on an ASUS MB (don't remember the model) 4 40 Gig Maxtor hard drives in RAID 10 3 40 Gig Maxtor hard drives as hot spares S3 video card - teac floppy - Intel dual port ether card 1 6800 series 8 port 3ware card with latest firmware IDE cables that came with the 3ware card. System 2 - iteration 2 4U case with 400 Watt power supply AMD 1.1 Ghz CPU Iwill 266 MB S3 video card - intel dual ethernet card - Netgear GB copper card 8 Maxtor 61 GB 7200 RPM hard drives - 7 in RAID 5 1 Hot spare 1 7800 8 port 3ware card with latest firmware IDE cables that came with the 3ware card. Iteration 2 means the 2nd attempt setup with the 3ware card. Prior itorations had the IBM IDE drives and slightly different configurations. > 6. Large noise sources near your systems. > > Unlikely, as you haven't mentioned any special situations (like > having an arc welder, large motor, or transmitter near your systems). Unlikly in the datacenter. > 7. Bad line power. > > Unlikely (well, unknown, as you haven't given any details), but, as > Borja mentioned, a bad UPS can really screw you over. Hmm Well Supposedly the power In AboveNet is pretty good. > 8. Power supply problem. > > Unknown. Seems pretty likely, but you're also seeing this problem > across multiple systems, which can imply that it's not a power supply > problem -- however, you haven't said that any of the other systems > have large, beefy power supplies. > > This is one of the few things that you can test and control. Somewhat yes. My time however is also being directed into building a SCSI system. The only problem we have ever had with any of the SCSI systems is when one of the brain dead zombies at abovenet hit reset on the wrong server for us. (I could tell you some horror stories from having to use ABN "remote hands" assistance) So far I would have had better luck with Mr Magoo. > Well, the above are the possibilities as I see them. It's your choice. > What do you want to do? Well since someone else has build a system that can be used for testing, I would be interested in what you and the others would like to do as a test. I do not belive he would have a sampling osciliscope of illrepute available to test for minute spikes so what would make people happy there? As far as what can be used to pound on the system that he has available I am uncertain. Certainly running the system as I had in RAID 5 with one hot spare would cause all the disks to work at once and figuring some way to feed it lots of data to write to the disks would be the best. Perhaps ideally, it would be nice if there would be a way to see what error messages are being sent to the 3ware card and how the card is dealing with them. What actions might create what errors and what occurs durring the rebuild process. Hope this is more of what you wanted. Nicole > -- > Darryl Okahata > darrylo@soco.agilent.com > > DISCLAIMER: this message is the author's personal opinion and does not > constitute the support, opinion, or policy of Agilent Technologies, or > of the little green men that have been following him all day. > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-hardware" in the body of the message ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Wed Aug 22 20:34: 3 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from mail2.siscom.net (mail2.siscom.net [209.251.2.52]) by hub.freebsd.org (Postfix) with SMTP id 4512237B405 for ; Wed, 22 Aug 2001 20:33:40 -0700 (PDT) (envelope-from radams@siscom.net) Received: (qmail 4725 invoked from network); 23 Aug 2001 03:33:33 -0000 Received: from unknown (HELO jason) (209.251.21.114) by mail2.siscom.net with SMTP; 23 Aug 2001 03:33:33 -0000 Message-ID: <00bd01c12b84$be0a2d60$7215fbd1@jason> From: "Robert J. Adams" To: References: <200108221652.JAA03752@mina.soco.agilent.com> Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Wed, 22 Aug 2001 23:28:27 -0400 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.50.4522.1200 X-MimeOLE: Produced By Microsoft MimeOLE V5.50.4522.1200 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hello, Just to add my two pennies here.. and to say "It has been done..." and works flawlessly. We currently have 3 servers running the following config: Tyan S2567U3AN mobo 2x Intel 1G Chip 2gig ram escalade 7800, 8 channel *16* WD 80gig drives and two servers running: Tyan S2567U3AN mobo 2x Intel 1G Chip 2gig ram escalade 6800, 8 channel *16* Maxtor 80gig drives All RAID5 All are in cases from rackmountpro.com that have a 450W mini redundant power supply. These servers are slammed pretty hard.. each taking in a full newsfeed etc. No problems at all.. We've lost 3 drives in 4 months, no problems w/ rebuilds. I couldn't be happier w/ the 3ware stuff.. Thanks, Jason ----- Original Message ----- From: "Darryl Okahata" To: "Hodge Podge" Cc: "Marc Rassbach" ; ; "Michael VanLoon" Sent: Wednesday, August 22, 2001 12:52 PM Subject: Re: 3ware stuff not ready for heavy duty useage-followup > Hodge Podge wrote: > > > Yes however I will bet even money that if I put a seperate power supply on > > every friggen drive and still have the same problem someones gonna say.. I b > > et > > one of Those supplys was bad.. Can folks try, just try to imagine that they > > "could" be wrong and come up with some other reason? Do I honestly have to > > Prove it wrong in some scientific way before you are willing to imagine some > > other possibility? Jeeze. Some time I or someone else will have a chance to > > test the theory, but for now that is all it is. One thoery. > > OK, let's look at the other possibilities: > > 1. Non-3ware hardware problem (bad motherboard, RAM, etc.). > > Very unlikely, as this problem happens on "multiple systems". > > 2. Bad batch of 3ware boards. > > Unlikely, but a very small sliver of a possibility. > > 3. 3ware hardware bug. > > If so, you're screwed. There's probably nothing you can do about it. > > 4. 3ware firmware problem. > > If so, you're probably screwed. At the very least, you'll probably > have to wait some unknown, probably long, period of time for a > firmware update. > > 5. FreeBSD problem. > > Not very likely, but a possibility. Other people seem to be having > success with 3ware and high loads. I have not seen anyone mention > using an 8-drive setup, though (I get to do this in a few weeks, > although the system won't generally be under high load). > > Unless you're conversant with FreeBSD disk driver debugging, you're > at the mercy of the FreeBSD driver developer (yes, I know who it is), > whom you may have unintentionally pissed off beyond redemption. At > the very least, in order to fix any problems, he'd have to reproduce > your problems. > > [ Note: as another person has mentioned, you're coming across as a > real hard case (even before your recent messages). I'm sure it's > unintentional, but you've got to be aware of this. If you want > help, you don't want to (unintentionally) piss off the people who > might be able to help you. Please note that many of the people > here are anal-retentive analytics who need data, data, and more > DATA (yes, I'll raise my hand ;-). You haven't given much details, > and, for much of the details which you have given, you've given as > part of "snippy"/"unintentionally insulting" responses or > maddeningly dribbled them out across many postings. ] > > 6. Large noise sources near your systems. > > Unlikely, as you haven't mentioned any special situations (like > having an arc welder, large motor, or transmitter near your systems). > > 7. Bad line power. > > Unlikely (well, unknown, as you haven't given any details), but, as > Borja mentioned, a bad UPS can really screw you over. > > 8. Power supply problem. > > Unknown. Seems pretty likely, but you're also seeing this problem > across multiple systems, which can imply that it's not a power supply > problem -- however, you haven't said that any of the other systems > have large, beefy power supplies. > > This is one of the few things that you can test and control. > > Well, the above are the possibilities as I see them. It's your choice. > What do you want to do? > > -- > Darryl Okahata > darrylo@soco.agilent.com > > DISCLAIMER: this message is the author's personal opinion and does not > constitute the support, opinion, or policy of Agilent Technologies, or > of the little green men that have been following him all day. > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-hardware" in the body of the message > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 4: 5:43 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from paperboy.sixforty.co.uk (paperboy.sixforty.co.uk [195.10.242.11]) by hub.freebsd.org (Postfix) with ESMTP id 2FB8437B407 for ; Thu, 23 Aug 2001 04:05:39 -0700 (PDT) (envelope-from freebsd-hw@sixforty.co.uk) Received: (from root@localhost) by paperboy.sixforty.co.uk (8.11.1/8.11.1) id f7NB5Ih42135; Thu, 23 Aug 2001 12:05:18 +0100 (BST) (envelope-from freebsd-hw@sixforty.co.uk) Delivered-To: nicole@unixgirl.com Received: from lfarr (daisy.int.epcdirect.co.uk [192.168.6.200]) by paperboy.sixforty.co.uk (8.11.1/8.11.1av) with ESMTP id f7NB59642126; Thu, 23 Aug 2001 12:05:09 +0100 (BST) (envelope-from freebsd-hw@sixforty.co.uk) From: "Lawrence Farr" To: "'Hodge Podge'" , "'Darryl Okahata'" Cc: "'Michael VanLoon'" , , "'Marc Rassbach'" Subject: RE: 3ware stuff not ready for heavy duty useage-followup Date: Thu, 23 Aug 2001 12:05:17 +0100 Message-ID: <004101c12bc3$81e74900$c80aa8c0@lfarr> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook, Build 10.0.2627 In-Reply-To: X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2462.0000 Importance: Normal X-Virus-Scanned: by AMaViS perl-10 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I left my server (previous email below) running a benchmark that I made up that took a 1mb file and cat'ed to another file until it got to 1Gb. I then read the file back by cat'ing to /dev/null, and repeated until I filled the partition (140Gb). It did this 3 times in total and got results like: Pass 23 - 1048576 kb written in 115 seconds, at 9118 kb/Sec Pass 23 - 1048576 kb read in 15 seconds, at 69905 kb/Sec Pass 24 - 1048576 kb written in 116 seconds, at 9039 kb/Sec Pass 24 - 1048576 kb read in 15 seconds, at 69905 kb/Sec It all works fine, but the writes are awful. Iozone seems to agree with me: File size set to 10240 KB Time Resolution = 0.000001 seconds. Processor cache size set to 1024 Kbytes. Processor cache line size set to 32 bytes. File stride size set to 17 * record size. random random KB reclen write rewrite read reread read write read 10240 4 9397 9461 266043 266458 236609 188083 253962 Anyone got any ideas for tuning this? Or is that it performance wise? How about splitting the drives to 4 stripe sets, and Raid 5 across them with vinum? Anyone else want to see any specific tests? >-----Original Message----- >From: Lawrence Farr [mailto:freebsd-hw@sixforty.co.uk] >Sent: 22 August 2001 14:59 >To: 'Hodge Podge' >Cc: 'mike.wentz@3ware.com'; 'freebsd-hardware@FreeBSD.ORG'; >'Borja Marcos'; 'Michael VanLoon'; 'val@picturetrail.com' >Subject: RE: 3ware stuff not ready for heavy duty useage- ATTN 3ware > > >Im just formatting an 8 drive (Maxtor 536DX 100Gb) 7000 series >array, 400W supply. > >Pick a benchmark and I'll run it for a while. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 4:11:13 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from borja.sarenet.es (borja.sarenet.es [192.148.167.77]) by hub.freebsd.org (Postfix) with ESMTP id E8E4437B409 for ; Thu, 23 Aug 2001 04:11:10 -0700 (PDT) (envelope-from borjamar@sarenet.es) Received: from there (localhost [127.0.0.1]) by borja.sarenet.es (8.11.3/8.11.3) with SMTP id f7NBANV22497; Thu, 23 Aug 2001 13:10:23 +0200 (CEST) (envelope-from borjamar@sarenet.es) Message-Id: <200108231110.f7NBANV22497@borja.sarenet.es> Content-Type: text/plain; charset="iso-8859-1" From: Borja Marcos To: "Lawrence Farr" Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Thu, 23 Aug 2001 13:10:22 +0200 X-Mailer: KMail [version 1.3] References: <004101c12bc3$81e74900$c80aa8c0@lfarr> In-Reply-To: <004101c12bc3$81e74900$c80aa8c0@lfarr> Cc: freebsd-hardware@freebsd.org MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Thursday 23 August 2001 13:05, you wrote: > Anyone got any ideas for tuning this? Or is that it performance wise? > How about splitting the drives to 4 stripe sets, and Raid 5 across them > with vinum? =09Raid5 is fast reading (same as a stripping) but writes are not so fast= , as=20 the system needs to calculate and write parity data. =09Borja. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 4:50:54 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from paperboy.sixforty.co.uk (paperboy.sixforty.co.uk [195.10.242.11]) by hub.freebsd.org (Postfix) with ESMTP id 6E94337B401 for ; Thu, 23 Aug 2001 04:50:49 -0700 (PDT) (envelope-from freebsd-hw@sixforty.co.uk) Received: (from root@localhost) by paperboy.sixforty.co.uk (8.11.1/8.11.1) id f7NBom943839 for freebsd-hardware@freebsd.org; Thu, 23 Aug 2001 12:50:48 +0100 (BST) (envelope-from freebsd-hw@sixforty.co.uk) Delivered-To: Received: from lfarr (daisy.int.epcdirect.co.uk [192.168.6.200]) by paperboy.sixforty.co.uk (8.11.1/8.11.1av) with ESMTP id f7NBoj643830 for ; Thu, 23 Aug 2001 12:50:46 +0100 (BST) (envelope-from freebsd-hw@sixforty.co.uk) From: "Lawrence Farr" To: Subject: RE: 3ware stuff not ready for heavy duty useage-followup Date: Thu, 23 Aug 2001 12:50:53 +0100 Message-ID: <004401c12bc9$dd262510$c80aa8c0@lfarr> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook, Build 10.0.2627 In-Reply-To: <200108231110.f7NBANV22497@borja.sarenet.es> X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2462.0000 Importance: Normal X-Virus-Scanned: by AMaViS perl-10 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Yep, Im aware of that. Just trying to squeeze the most out of it, And I am open to suggestions on tuning. It's still as fast as my external HW raid's..... >-----Original Message----- >From: Borja Marcos [mailto:borjamar@sarenet.es] >Sent: 23 August 2001 12:10 >To: Lawrence Farr >Cc: freebsd-hardware@freebsd.org >Subject: Re: 3ware stuff not ready for heavy duty useage-followup > > >On Thursday 23 August 2001 13:05, you wrote: > >> Anyone got any ideas for tuning this? Or is that it performance wise? >> How about splitting the drives to 4 stripe sets, and Raid 5 >across them >> with vinum? > > Raid5 is fast reading (same as a stripping) but writes >are not so fast, as >the system needs to calculate and write parity data. > > > > > Borja. > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 11:27:24 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from webpimps.net (lgb-DSL71-cust207.mpowercom.net [208.57.71.207]) by hub.freebsd.org (Postfix) with ESMTP id D67F837B401 for ; Thu, 23 Aug 2001 11:27:18 -0700 (PDT) (envelope-from click46@webpimps.net) Received: from WorldClient [127.0.0.1] by webpimps.net [127.0.0.1] with SMTP (MDaemon.v3.1.2.R) for ; Thu, 23 Aug 2001 11:25:22 -0700 Date: Thu, 23 Aug 2001 11:25:22 -0700 From: "Aaron" To: freebsd-hardware@freebsd.org Subject: Re: 3ware stuff not ready for heavy duty useage-followup X-Mailer: WorldClient Standard 3.1.2 X-MDRcpt-To: freebsd-hardware@freebsd.org X-MDRemoteIP: 127.0.0.1 X-Return-Path: click46@webpimps.net X-MDaemon-Deliver-To: freebsd-hardware@freebsd.org Message-Id: <20010823182718.D67F837B401@hub.freebsd.org> Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hello, After painstakingly reading the ENTIRE thread straight, I've got only one suggestion for you. I am by no means an expert on RAID, 3ware cards, harddrive, even FreeBSD. However, I have had experience with motherboards and can relay MANY experiences with VIA chipsets. While I have never seen a complaint like this before, VIA chipsets stick in my mind when it comes to anything RAID. If you have ANY complaint Intel chipset-based system on hand that can run that 3ware card, please try it. Being a moderator at the hardforum.com I've seen many people tear their hair out over the weirdest hardware issues and conflicts - especially with VIA hardware. It is my beleif that this is where you problem lies. Its slim, it sounds weird, but I'm sure you have an intel chipset-based box lying around you can at least test it on. Good Luck, - aaron --------------------------------------------- click46[wp] - AIM the click46 - ICQ 43450396 webpimps.net | bsdatwork.com | nerdserve.net moderator - o/c cooling forum @ hardforum.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 12:16:37 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from linux-wlan.com (cpe-66-1-218-98.fl.sprintbbd.net [66.1.218.98]) by hub.freebsd.org (Postfix) with ESMTP id 12C8337B403 for ; Thu, 23 Aug 2001 12:16:29 -0700 (PDT) (envelope-from b.j.smith@ieee.org) Received: from ieee.org (thebs.cc.absoval.com. [192.168.100.89]) by chef.cc.absoval.com (8.9.3/8.9.3) with ESMTP id VAA17183; Tue, 21 Aug 2001 21:13:19 -0400 Message-ID: <3B8306E5.9DBA13D3@ieee.org> Date: Tue, 21 Aug 2001 21:12:05 -0400 From: Bryan-TheBS-Smith Organization: SmithConcepts, Inc. X-Mailer: Mozilla 4.77 [en] (X11; U; Linux 2.4.3-SGI_XFS_1.0.1 i686) X-Accept-Language: en MIME-Version: 1.0 To: Brian Cc: freebsd-hardware@FreeBSD.ORG, nicole@unixgirl.com Subject: Re: 3ware stuff not ready for heavy duty useage-followup References: <03d801c12a9e$bab359c0$6601a8c0@elitists.org> <005101c12aa5$7dd36160$0201a8c0@fear.wrath.net> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I have been following this hardware thread for awhile. Rule 1: Read the _actual_specs_ on your power supply! I've seen 250W PS that provided more current on the 3.3+5V lines than most 400W. If you have a newer CPU and a lot of add-in boards, you'll need it! Antec and Energmax (?) seem to have PowerPC&Cooling specs for 1/2-1/3rd the price. And I love Antec's case designs (especially the SX635 and SX1040), plus they just came out with a "cost effective" 350W PS ($50 versus $85 for their 400W). Rule 2: Add up the 12V current provided and match it against your drives. This one is simple enough. Although see #3 ... Rule 3: Add up the 12V current required for "start up" if you don't have SCSI Unlike SCSI, IDE doesn't provide a "delayed spindle" so you can offset the "startup current" so not all drives start at the same time. "Startup current" can really affect your PS, especially since it is usually 2X+ any other operation. Be wary with IDE and make sure you get at least a _good_ 400W PS if you've got 6+ drives total, possibly one of those Energmax 400/450peak and 550/650peak ones for 8-12. -- TheBS -- Bryan "TheBS" Smith mailto:b.j.smith@ieee.org chat:thebs413 Engineer AbsoluteValue Systems, Inc. http://www.linux-wlan.org President SmithConcepts, Inc. http://www.SmithConcepts.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 12:38: 3 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from mail.skyrunner.net (mail.new-era.com [208.133.44.6]) by hub.freebsd.org (Postfix) with ESMTP id 3909A37B406 for ; Thu, 23 Aug 2001 12:37:54 -0700 (PDT) (envelope-from peter@skyrunner.net) Received: from skyrunne6e8soa (booray.new-era.com [208.150.25.130]) by mail.skyrunner.net (8.11.2/8.11.0/SuSE Linux 8.11.0-0.4) with SMTP id f7NJble12965 for ; Thu, 23 Aug 2001 15:37:47 -0400 From: "Peter Brezny" To: Subject: netgear nics Date: Thu, 23 Aug 2001 15:31:23 -0400 Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook IMO, Build 9.0.2416 (9.0.2911.0) Importance: Normal X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2919.6700 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Has anyone had particularly bad experiences with netgear nics under freebsd 4.2? Thanks Peter Brezny Skyrunner.net To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 12:54: 3 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from webpimps.net (lgb-DSL71-cust207.mpowercom.net [208.57.71.207]) by hub.freebsd.org (Postfix) with ESMTP id A3CD837B401 for ; Thu, 23 Aug 2001 12:54:00 -0700 (PDT) (envelope-from click46@webpimps.net) Received: from WorldClient [127.0.0.1] by webpimps.net [127.0.0.1] with SMTP (MDaemon.v3.1.2.R) for ; Thu, 23 Aug 2001 12:51:39 -0700 Date: Thu, 23 Aug 2001 12:51:39 -0700 From: "Aaron" To: mjacob@feral.com Cc: freebsd-hardware@freebsd.org Subject: RE: looking for ia32 system that supports > 4GB memory and has 64 bit PCI X-Mailer: WorldClient Standard 3.1.2 X-MDRcpt-To: freebsd-hardware@freebsd.org X-MDRemoteIP: 127.0.0.1 X-Return-Path: click46@webpimps.net X-MDaemon-Deliver-To: freebsd-hardware@freebsd.org Message-Id: <20010823195400.A3CD837B401@hub.freebsd.org> Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Tyan also has a motherboard with 8GB RAM capabilities - http://www.tyan.com/products/html/thunder2500_p.html The only downside is it is a Slot 1 Pentium III solution. - aaron --------------------------------------------- click46[wp] - AIM the click46 - ICQ 43450396 webpimps.net | bsdatwork.com | nerdserve.net moderator - o/c cooling forum @ hardforum.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 12:58:28 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from webpimps.net (lgb-DSL71-cust207.mpowercom.net [208.57.71.207]) by hub.freebsd.org (Postfix) with ESMTP id E43B637B40A for ; Thu, 23 Aug 2001 12:58:20 -0700 (PDT) (envelope-from click46@webpimps.net) Received: from WorldClient [127.0.0.1] by webpimps.net [127.0.0.1] with SMTP (MDaemon.v3.1.2.R) for ; Thu, 23 Aug 2001 12:55:44 -0700 Date: Thu, 23 Aug 2001 12:55:44 -0700 From: "Aaron" To: freebsd-hardware@freebsd.org Subject: RE: looking for ia32 system that supports > 4GB memory and has 64 bit PCI X-Mailer: WorldClient Standard 3.1.2 X-MDRcpt-To: freebsd-hardware@freebsd.org X-MDRemoteIP: 127.0.0.1 X-Return-Path: click46@webpimps.net X-MDaemon-Deliver-To: freebsd-hardware@freebsd.org Message-Id: <20010823195820.E43B637B40A@hub.freebsd.org> Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org My apologies. That Tyan motherboard is for OEM systems only. However it maybe something you would like to look into. - aaron --------------------------------------------- click46[wp] - AIM the click46 - ICQ 43450396 webpimps.net | bsdatwork.com | nerdserve.net moderator - o/c cooling forum @ hardforum.com -----Original Message----- From: "Aaron" To: mjacob@feral.com Date: Thu, 23 Aug 2001 12:51:39 -0700 Subject: RE: looking for ia32 system that supports > 4GB memory and has 64 bit PCI Tyan also has a motherboard with 8GB RAM capabilities - http://www.tyan.com/products/html/thunder2500_p.html The only downside is it is a Slot 1 Pentium III solution. - aaron --------------------------------------------- click46[wp] - AIM the click46 - ICQ 43450396 webpimps.net | bsdatwork.com | nerdserve.net moderator - o/c cooling forum @ hardforum.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 13: 4:42 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from beppo.feral.com (beppo.feral.com [192.67.166.79]) by hub.freebsd.org (Postfix) with ESMTP id DB4E637B408 for ; Thu, 23 Aug 2001 13:04:34 -0700 (PDT) (envelope-from mjacob@feral.com) Received: from mailhost.feral.com (mjacob@mailhost.feral.com [192.67.166.1]) by beppo.feral.com (8.11.3/8.11.3) with ESMTP id f7NK4WI98242; Thu, 23 Aug 2001 13:04:32 -0700 (PDT) (envelope-from mjacob@feral.com) Date: Thu, 23 Aug 2001 13:04:32 -0700 (PDT) From: Matthew Jacob X-Sender: mjacob@beppo Reply-To: mjacob@feral.com To: Aaron Cc: freebsd-hardware@FreeBSD.ORG Subject: RE: looking for ia32 system that supports > 4GB memory and has 64 bit PCI In-Reply-To: <20010823195400.A3CD837B401@hub.freebsd.org> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Thanks. I've had some really good suggestions. I now have a bid for a 7K$ 8GB single 900MHz PIII SuperMicro based system from colfax-intl.com where I usually have my one-offs built- this stills seems a tad pricey, but I'll probably actually buy it in the 4 procesor version. I noticed that they also offered some Tyan solutions as wlel. On Thu, 23 Aug 2001, Aaron wrote: > Tyan also has a motherboard with 8GB RAM capabilities - > http://www.tyan.com/products/html/thunder2500_p.html > The only downside is it is a Slot 1 Pentium III solution. > > - aaron > > --------------------------------------------- > click46[wp] - AIM the click46 - ICQ 43450396 > webpimps.net | bsdatwork.com | nerdserve.net > moderator - o/c cooling forum @ hardforum.com > > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-hardware" in the body of the message > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 13:12: 8 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from beppo.feral.com (beppo.feral.com [192.67.166.79]) by hub.freebsd.org (Postfix) with ESMTP id EA58337B405 for ; Thu, 23 Aug 2001 13:12:05 -0700 (PDT) (envelope-from mjacob@feral.com) Received: from mailhost.feral.com (mjacob@mailhost.feral.com [192.67.166.1]) by beppo.feral.com (8.11.3/8.11.3) with ESMTP id f7NKBuI98361; Thu, 23 Aug 2001 13:12:02 -0700 (PDT) (envelope-from mjacob@feral.com) Date: Thu, 23 Aug 2001 13:11:56 -0700 (PDT) From: Matthew Jacob X-Sender: mjacob@beppo Reply-To: mjacob@feral.com To: Bryan-TheBS-Smith Cc: hardware@FreeBSD.ORG Subject: Re: looking for ia32 system that supports > 4GB memory and has 64 bitPCI In-Reply-To: <3B856281.9A7059DA@ieee.org> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Thu, 23 Aug 2001, Bryan-TheBS-Smith wrote: > Matthew Jacob wrote: > > I'm looking for in Intel IA32 system that has 64 bit PCI slots > > and can suppor more than 4GB memory- it's time for me to start > > thinking about what 64 bit DAC PCI really means. My STL2 board > > only supports up to 4GB. I've grovelled around a bit on the Intel > > site, and don't see anything very helpful. > > The ServerWorks (fka RCC, Reliance Computer Corporation) ServerSet IIIHE > does upto (16) 1GB DIMMs (using ECC Registered PC100/133). Most > HE-based 2-processor (both P3/Xeon) mainboards come with 4-8 DIMMs, and > 4-processor (Xeon-only) mainboards xome with 8-16. It also have (3) PCI > channels -- (2) 64-bit, (1) 32-bit. > > Tyan has a 2-processor HE-based mainboard. SuperMicro has both 2 and > 4-processor HE-based mainboards. > > Supermicro also carries the cheaper ServerSet IIILE, but it only has 4 > DIMMs. But it does have (2) PCI channels -- (1) 64-bit, (1) 32-bit. The last is the gating item for me. The whole object is to start playing around with DAC stuff. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 13:35:50 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from panzer.kdm.org (panzer.kdm.org [216.160.178.169]) by hub.freebsd.org (Postfix) with ESMTP id 51CF337B626 for ; Thu, 23 Aug 2001 13:35:29 -0700 (PDT) (envelope-from ken@panzer.kdm.org) Received: (from ken@localhost) by panzer.kdm.org (8.9.3/8.9.1) id OAA99523; Thu, 23 Aug 2001 14:35:08 -0600 (MDT) (envelope-from ken) Date: Thu, 23 Aug 2001 14:35:08 -0600 From: "Kenneth D. Merry" To: Matthew Jacob Cc: Aaron , freebsd-hardware@FreeBSD.ORG Subject: Re: looking for ia32 system that supports > 4GB memory and has 64 bit PCI Message-ID: <20010823143508.A99255@panzer.kdm.org> References: <20010823195400.A3CD837B401@hub.freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2i In-Reply-To: ; from mjacob@feral.com on Thu, Aug 23, 2001 at 01:04:32PM -0700 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Thu, Aug 23, 2001 at 13:04:32 -0700, Matthew Jacob wrote: > > Thanks. I've had some really good suggestions. I now have a bid for a 7K$ 8GB > single 900MHz PIII SuperMicro based system from colfax-intl.com where I > usually have my one-offs built- this stills seems a tad pricey, but I'll > probably actually buy it in the 4 procesor version. I noticed that they also > offered some Tyan solutions as wlel. www.microx-press.com has the SuperMicro 8060 system (S2QE6 motherboard in a Supermicro SC860 (4U rack mount)) chassis for $2974.00. You can get 8GB of memory for it for $1670.24 (16 512MB DIMMs) from www.crucial.com (Micron memory, not cheap-o stuff). Even though that motherboard only needs PC100 memory, I would probably get PC133 memory instead since you'd be able to use it in more systems if you don't leave it all in there. The only other thing you'd need to do is figure out what sort of Xeons you want in the system. Getting four Xeons (at least the more-than-two-proc kind) will probably be the most expensive part of it. Micro X-press has 700MHz 1MB Xeons for $1299, so with four the total for all that would run about $9840. (Only $5943 with one Xeon.) The only thing is that those processors are out of stock there, but you could probably find them (or whatever sort of Xeon) somewhere else. Ken -- Kenneth Merry ken@kdm.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 13:37: 3 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from beppo.feral.com (beppo.feral.com [192.67.166.79]) by hub.freebsd.org (Postfix) with ESMTP id F3E9C37B409 for ; Thu, 23 Aug 2001 13:36:57 -0700 (PDT) (envelope-from mjacob@feral.com) Received: from mailhost.feral.com (mjacob@mailhost.feral.com [192.67.166.1]) by beppo.feral.com (8.11.3/8.11.3) with ESMTP id f7NKalI98693; Thu, 23 Aug 2001 13:36:47 -0700 (PDT) (envelope-from mjacob@feral.com) Date: Thu, 23 Aug 2001 13:36:47 -0700 (PDT) From: Matthew Jacob X-Sender: mjacob@beppo Reply-To: mjacob@feral.com To: "Kenneth D. Merry" Cc: Aaron , freebsd-hardware@FreeBSD.ORG Subject: Re: looking for ia32 system that supports > 4GB memory and has 64 bit PCI In-Reply-To: <20010823143508.A99255@panzer.kdm.org> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Excellent! One thing I get out of colfax doing this is that they do the burnin. But these are excellent leads! Thanks! On Thu, 23 Aug 2001, Kenneth D. Merry wrote: > On Thu, Aug 23, 2001 at 13:04:32 -0700, Matthew Jacob wrote: > > > > Thanks. I've had some really good suggestions. I now have a bid for a 7K$ 8GB > > single 900MHz PIII SuperMicro based system from colfax-intl.com where I > > usually have my one-offs built- this stills seems a tad pricey, but I'll > > probably actually buy it in the 4 procesor version. I noticed that they also > > offered some Tyan solutions as wlel. > > www.microx-press.com has the SuperMicro 8060 system (S2QE6 motherboard in a > Supermicro SC860 (4U rack mount)) chassis for $2974.00. > > You can get 8GB of memory for it for $1670.24 (16 512MB DIMMs) from > www.crucial.com (Micron memory, not cheap-o stuff). Even though that > motherboard only needs PC100 memory, I would probably get PC133 memory > instead since you'd be able to use it in more systems if you don't leave it > all in there. > > The only other thing you'd need to do is figure out what sort of Xeons you > want in the system. Getting four Xeons (at least the more-than-two-proc > kind) will probably be the most expensive part of it. > > Micro X-press has 700MHz 1MB Xeons for $1299, so with four the total for > all that would run about $9840. (Only $5943 with one Xeon.) The only > thing is that those processors are out of stock there, but you could > probably find them (or whatever sort of Xeon) somewhere else. > > Ken > -- > Kenneth Merry > ken@kdm.org > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 13:44:41 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id 6D06437B406 for ; Thu, 23 Aug 2001 13:44:37 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 11ED620F13; Thu, 23 Aug 2001 13:44:37 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <004101c12bc3$81e74900$c80aa8c0@lfarr> Date: Thu, 23 Aug 2001 13:44:37 -0700 (PDT) From: Hodge Podge To: Lawrence Farr Subject: RE: 3ware stuff not ready for heavy duty useage-followup Cc: Marc Rassbach , freebsd-hardware@freebsd.org, Michael VanLoon , Darryl Okahata Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Very Nice. Thanks! Well, I'm not sure what the power supply na-sayers might want as a test, but do you have a way to force data into the drives from an outside source? I was doing this for abt 6-8 Hrs when mine failed :( Lots of small files. Who knows.. maybe that was enough to woogle the power supply, maybe its a Via Chipset interaction problem... The bugger is what to do abt it? I talked it over with my Boss and I want to see if we can set something up with 3ware to do some testing. We house hundredes of thousands of small (~300k) files) and maybe that is the problem. Maybe its bad drives.. Altho we got them from different places. But damn, process of elimination for something like this is no small thing. Nicole On 23-Aug-01 Lawrence Farr wrote: > I left my server (previous email below) running a benchmark that I made > up that took > a 1mb file and cat'ed to another file until it got to 1Gb. > I then read the file back by cat'ing to /dev/null, and repeated until I > filled the > partition (140Gb). It did this 3 times in total and got results like: > > Pass 23 - 1048576 kb written in 115 seconds, at 9118 kb/Sec > Pass 23 - 1048576 kb read in 15 seconds, at 69905 kb/Sec > Pass 24 - 1048576 kb written in 116 seconds, at 9039 kb/Sec > Pass 24 - 1048576 kb read in 15 seconds, at 69905 kb/Sec > > It all works fine, but the writes are awful. Iozone seems to agree with > me: > > File size set to 10240 KB > Time Resolution = 0.000001 seconds. > Processor cache size set to 1024 Kbytes. > Processor cache line size set to 32 bytes. > File stride size set to 17 * record size. > random random > > KB reclen write rewrite read reread read write read > 10240 4 9397 9461 266043 266458 236609 188083 253962 > > Anyone got any ideas for tuning this? Or is that it performance wise? > How about splitting the drives to 4 stripe sets, and Raid 5 across them > with vinum? > > Anyone else want to see any specific tests? > >>-----Original Message----- >>From: Lawrence Farr [mailto:freebsd-hw@sixforty.co.uk] >>Sent: 22 August 2001 14:59 >>To: 'Hodge Podge' >>Cc: 'mike.wentz@3ware.com'; 'freebsd-hardware@FreeBSD.ORG'; >>'Borja Marcos'; 'Michael VanLoon'; 'val@picturetrail.com' >>Subject: RE: 3ware stuff not ready for heavy duty useage- ATTN 3ware >> >> >>Im just formatting an 8 drive (Maxtor 536DX 100Gb) 7000 series >>array, 400W supply. >> >>Pick a benchmark and I'll run it for a while. > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-hardware" in the body of the message ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 13:52:43 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from panzer.kdm.org (panzer.kdm.org [216.160.178.169]) by hub.freebsd.org (Postfix) with ESMTP id 2BDB737B40B for ; Thu, 23 Aug 2001 13:52:38 -0700 (PDT) (envelope-from ken@panzer.kdm.org) Received: (from ken@localhost) by panzer.kdm.org (8.9.3/8.9.1) id OAA99735; Thu, 23 Aug 2001 14:52:29 -0600 (MDT) (envelope-from ken) Date: Thu, 23 Aug 2001 14:52:29 -0600 From: "Kenneth D. Merry" To: Bryan-TheBS-Smith Cc: Matthew Jacob , Aaron , freebsd-hardware@FreeBSD.ORG Subject: Re: looking for ia32 system that supports > 4GB memory and has 64 bit PCI Message-ID: <20010823145229.A99674@panzer.kdm.org> References: <20010823195400.A3CD837B401@hub.freebsd.org> <20010823143508.A99255@panzer.kdm.org> <3B856B07.1FF654F@ieee.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2i In-Reply-To: <3B856B07.1FF654F@ieee.org>; from b.j.smith@ieee.org on Thu, Aug 23, 2001 at 04:43:51PM -0400 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Thu, Aug 23, 2001 at 16:43:51 -0400, Bryan-TheBS-Smith wrote: > "Kenneth D. Merry" wrote: > > You can get 8GB of memory for it for $1670.24 (16 512MB DIMMs) > > from www.crucial.com (Micron memory, not cheap-o stuff). > > Did you verify the mainboard against the memory at Crucial? > The ServerSet _requires_ registered ECC. Yes, I went through their little select-your-system interface. That's PC100, ECC, registered, CL2 memory, $104.39 per 512MB DIMM. PC133 (CL3, though) is the same price. > > Even though that motherboard only needs PC100 memory, I would > > probably get PC133 memory instead since you'd be able to use > > it in more systems if you don't leave it all in there. > > Not really. First off, the ServerWorks uses 100MHz for 100MHz FSB > CPUs, 133MHz for 133MHz FSB CPUs. No async option. Yes, but you can run PC133 memory just fine at 100MHz. The whole point is that he can use the memory in a system that requires registered PC100 or PC133 memory if he gets PC133 memory. You don't have that option if you only get PC100 memory. > Secondly, the i810/815s don't work with registered nor ECC SDRAM. > Some ViA chipsets might take issue with the registered as well. That's fine, there are plenty of other systems that can use registered ECC memory. What's your point here, anyway? Ken -- Kenneth Merry ken@kdm.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 14: 1:59 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from www1.asacomputers.com (gw1.asacomputers.com [209.10.224.7]) by hub.freebsd.org (Postfix) with ESMTP id EDBF337B412 for ; Thu, 23 Aug 2001 14:01:44 -0700 (PDT) (envelope-from kedar@asacomputers.com) Received: from kedar (empire.asacomputers.com [209.10.224.3]) by www1.asacomputers.com (8.10.1/8.10.1) with SMTP id f7NLaUw23380; Thu, 23 Aug 2001 14:36:30 -0700 (PDT) Message-Id: <4.1.20010823135604.038004f0@gw1.asacomputers.com> X-Sender: rajadnya@gw1.asacomputers.com X-Mailer: QUALCOMM Windows Eudora Pro Version 4.1 Date: Thu, 23 Aug 2001 13:59:27 -0700 To: "Aaron" , freebsd-hardware@FreeBSD.ORG From: Kedar Rajadnya Subject: RE: looking for ia32 system that supports > 4GB memory and has 64bit PCI In-Reply-To: <20010823195820.E43B637B40A@hub.freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hi, You would rather not, if possible. Tyan themselves have confessed to having some odd problems with the board. Some related to the USB, some with the memory sub-system, etc.... I would rather not be quoted, of course. :-) YMMV, Kedar. At 12:55 PM 8/23/01 -0700, Aaron wrote: >My apologies. That Tyan motherboard is for OEM systems only. However it >maybe something you would like to look into. > >- aaron > >--------------------------------------------- >click46[wp] - AIM the click46 - ICQ 43450396 >webpimps.net | bsdatwork.com | nerdserve.net >moderator - o/c cooling forum @ hardforum.com > > >-----Original Message----- >From: "Aaron" >To: mjacob@feral.com >Date: Thu, 23 Aug 2001 12:51:39 -0700 >Subject: RE: looking for ia32 system that supports > 4GB memory and has >64 bit PCI > >Tyan also has a motherboard with 8GB RAM capabilities - >http://www.tyan.com/products/html/thunder2500_p.html >The only downside is it is a Slot 1 Pentium III solution. > >- aaron > >--------------------------------------------- >click46[wp] - AIM the click46 - ICQ 43450396 >webpimps.net | bsdatwork.com | nerdserve.net >moderator - o/c cooling forum @ hardforum.com > > > >To Unsubscribe: send mail to majordomo@FreeBSD.org >with "unsubscribe freebsd-hardware" in the body of the message Regards, Kedar Rajadnya ASA Computers, Inc. 2354 Calle Del Mundo. Santa Clara, CA 95054. Tel: (408)654-2901 ext201 Cell: (408)799-7263 . Toll Free: (877)538-1272 Fax: (408)654-2910. ====================================== To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 14: 9: 1 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from msgbas2.cos.agilent.com (msgbas2x.cos.agilent.com [192.25.240.37]) by hub.freebsd.org (Postfix) with ESMTP id D725337B410 for ; Thu, 23 Aug 2001 14:08:56 -0700 (PDT) (envelope-from darrylo@soco.agilent.com) Received: from msgrel1.cos.agilent.com (msgrel1.cos.agilent.com [130.29.152.77]) by msgbas2.cos.agilent.com (Postfix) with ESMTP id 800F5A54; Thu, 23 Aug 2001 15:08:56 -0600 (MDT) Received: from mina.soco.agilent.com (mina.soco.agilent.com [141.121.54.157]) by msgrel1.cos.agilent.com (Postfix) with ESMTP id 709D84D4; Thu, 23 Aug 2001 15:08:55 -0600 (MDT) Received: from mina.soco.agilent.com (darrylo@localhost [127.0.0.1]) by mina.soco.agilent.com (8.9.3 (PHNE_22672)/8.9.3 SMKit7.1.1_Agilent) with ESMTP id OAA06408; Thu, 23 Aug 2001 14:08:54 -0700 (PDT) Message-Id: <200108232108.OAA06408@mina.soco.agilent.com> To: Hodge Podge Cc: Lawrence Farr , Marc Rassbach , freebsd-hardware@freebsd.org, Michael VanLoon Subject: Re: 3ware stuff not ready for heavy duty useage-followup Reply-To: Darryl Okahata In-Reply-To: Your message of "Thu, 23 Aug 2001 13:44:37 PDT." Mime-Version: 1.0 (generated by tm-edit 1.6) Content-Type: text/plain; charset=US-ASCII Date: Thu, 23 Aug 2001 14:08:54 -0700 From: Darryl Okahata Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hodge Podge > Who knows.. maybe that was enough to woogle the power supply, maybe its a Vi > a > Chipset interaction problem... The bugger is what to do abt it? Oh, jeez. Aaron's hit upon a definite possibility. Check out your motherboards ASAP: motherboards using the VIA KT133A/KT133 chipset with the VIA 686B Southbridge can get data corruption problems with high PCI traffic (I *think* this can affect 3ware cards, but I'm not 100% sure). For more info, see: http://www.au-ja.de/review-kt133a-1-en.html -- Darryl Okahata darrylo@soco.agilent.com DISCLAIMER: this message is the author's personal opinion and does not constitute the support, opinion, or policy of Agilent Technologies, or of the little green men that have been following him all day. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 14:27:53 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from panzer.kdm.org (panzer.kdm.org [216.160.178.169]) by hub.freebsd.org (Postfix) with ESMTP id 6257737B409 for ; Thu, 23 Aug 2001 14:27:50 -0700 (PDT) (envelope-from ken@panzer.kdm.org) Received: (from ken@localhost) by panzer.kdm.org (8.9.3/8.9.1) id PAA00357; Thu, 23 Aug 2001 15:27:37 -0600 (MDT) (envelope-from ken) Date: Thu, 23 Aug 2001 15:27:37 -0600 From: "Kenneth D. Merry" To: Bryan-TheBS-Smith Cc: Matthew Jacob , Aaron , freebsd-hardware@FreeBSD.ORG Subject: Re: looking for ia32 system that supports > 4GB memory and has 64 bit PCI Message-ID: <20010823152737.A255@panzer.kdm.org> References: <20010823195400.A3CD837B401@hub.freebsd.org> <20010823143508.A99255@panzer.kdm.org> <3B856B07.1FF654F@ieee.org> <20010823145229.A99674@panzer.kdm.org> <3B857172.77E73060@ieee.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2i In-Reply-To: <3B857172.77E73060@ieee.org>; from b.j.smith@ieee.org on Thu, Aug 23, 2001 at 05:11:14PM -0400 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Thu, Aug 23, 2001 at 17:11:14 -0400, Bryan-TheBS-Smith wrote: > "Kenneth D. Merry" wrote: > > That's fine, there are plenty of other systems that can use > > registered ECC memory. > > What systems? I don't know many that can use registered ECC memory, > other than the older i440BX/GX ones. And then the i440BX is limited > to 256MB/DIMM and i440GX is limited to 512MB/DIMM. Pretty much any Serverworks chipset board uses registered ECC memory. Tyan, ASUS, Supermicro, Dell, IBM and Intel all ship Serverworks chipset boards. It also works on the Alpha (XP1000) and Compaq Blazer (ia64) systems I've got. > > What's your point here, anyway? > > Just making sure you "did your homework." You did. I'm glad my "homework" meets with your approval. Ken -- Kenneth Merry ken@kdm.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 15:18:29 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from krell.webweaver.net (krell.webweaver.net [64.124.90.11]) by hub.freebsd.org (Postfix) with ESMTP id B9DFC37B407 for ; Thu, 23 Aug 2001 15:18:14 -0700 (PDT) (envelope-from nicole@unixgirl.com) Received: from xwin.nmhtech.com (xwin.daemontech.net [208.135.51.161]) by krell.webweaver.net (Postfix) with ESMTP id 6F17320F04; Thu, 23 Aug 2001 15:18:14 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <200108232108.OAA06408@mina.soco.agilent.com> Date: Thu, 23 Aug 2001 15:18:14 -0700 (PDT) From: Hodge Podge To: Darryl Okahata Subject: Re: 3ware stuff not ready for heavy duty useage-Ah ha Cc: Michael VanLoon , freebsd-hardware@freebsd.org, Marc Rassbach , Lawrence Farr Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 23-Aug-01 Darryl Okahata wrote: > Hodge Podge > >> Who knows.. maybe that was enough to woogle the power supply, maybe its a >> Vi >> a >> Chipset interaction problem... The bugger is what to do abt it? > > Oh, jeez. Aaron's hit upon a definite possibility. Check out your > motherboards ASAP: motherboards using the VIA KT133A/KT133 chipset with > the VIA 686B Southbridge can get data corruption problems with high PCI > traffic (I *think* this can affect 3ware cards, but I'm not 100% sure). > For more info, see: > Well Yea.. Thst fits us to a tee.. LOTS of data passing through the PCI buss. But I'm not sure how that would effect the rebuilding problems we had or why it would cause the card to think there is a drive problem. But its something to try. Several others privately have said that they have seen lots of failures in drives and or cards within abt 72 Hrs of testing or burn-in. After that however they seemed to work without much incident. So.. Thats fits us too. And now we want another shrubbery..... Nicole > http://www.au-ja.de/review-kt133a-1-en.html > > -- > Darryl Okahata > darrylo@soco.agilent.com > > DISCLAIMER: this message is the author's personal opinion and does not > constitute the support, opinion, or policy of Agilent Technologies, or > of the little green men that have been following him all day. > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-hardware" in the body of the message ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 16:16:55 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from webpimps.net (lgb-DSL71-cust207.mpowercom.net [208.57.71.207]) by hub.freebsd.org (Postfix) with ESMTP id B00C137B405 for ; Thu, 23 Aug 2001 16:16:51 -0700 (PDT) (envelope-from click46@webpimps.net) Received: from WorldClient [127.0.0.1] by webpimps.net [127.0.0.1] with SMTP (MDaemon.v3.1.2.R) for ; Thu, 23 Aug 2001 16:14:43 -0700 Date: Thu, 23 Aug 2001 16:14:42 -0700 From: "Aaron" To: "Tim" Cc: freebsd-hardware@freebsd.org Subject: Re: 3ware Escalade 6200 RAID Controller X-Mailer: WorldClient Standard 3.1.2 In-Reply-To: <20010823163832.A86219@futuresouth.com> X-MDRcpt-To: freebsd-hardware@freebsd.org X-MDRemoteIP: 127.0.0.1 X-Return-Path: click46@webpimps.net X-MDaemon-Deliver-To: freebsd-hardware@freebsd.org Message-Id: <20010823231651.B00C137B405@hub.freebsd.org> Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org -----Original Message----- From: Tim To: Kory Hamzeh Date: Thu, 23 Aug 2001 16:38:32 -0500 Subject: Re: 3ware Escalade 6200 RAID Controller > On Thu, Aug 23, 2001 at 02:24:27PM -0700, Kory Hamzeh wrote: > In our system, the drives actually show up as /dev/twed0s1. > I guess you could create the RAID volume on the existing system (and I > don't even know if you could do this without wiping out the old data), > boot from a FreeBSD floppy with a kernel that has 3ware driver on it, > then edit /etc/fstab. I am not sure that's much worse than the > alternative, if at all. > Using the two boot floppies from the /floppies directory, how do you edit /etc/fstab? I tried dearly to just find a friggin editor or SOMETHING. Hm, come to think of it I didnt try to mount it using the boot floppies. So could you do something like, boot with the boot floppies, mount your root partition - run vi from your hard drive and edit /etc/fstab and then reboot? I KNEW IT! I told myself - "The documentation says FreeBSD users hate having to reinstall..so there must be away around this without reinstalling". cool! - aaron --------------------------------------------- click46[wp] - AIM the click46 - ICQ 43450396 webpimps.net | bsdatwork.com | nerdserve.net moderator - o/c cooling forum @ hardforum.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 16:44:15 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from msgbas1.cos.agilent.com (msgbas1x.cos.agilent.com [192.25.240.36]) by hub.freebsd.org (Postfix) with ESMTP id A4A5C37B406 for ; Thu, 23 Aug 2001 16:44:08 -0700 (PDT) (envelope-from darrylo@soco.agilent.com) Received: from msgrel1.cos.agilent.com (msgrel1.cos.agilent.com [130.29.152.77]) by msgbas1.cos.agilent.com (Postfix) with ESMTP id 2D88D650; Thu, 23 Aug 2001 17:44:08 -0600 (MDT) Received: from mina.soco.agilent.com (mina.soco.agilent.com [141.121.54.157]) by msgrel1.cos.agilent.com (Postfix) with ESMTP id 7A487241; Thu, 23 Aug 2001 17:44:07 -0600 (MDT) Received: from mina.soco.agilent.com (darrylo@localhost [127.0.0.1]) by mina.soco.agilent.com (8.9.3 (PHNE_22672)/8.9.3 SMKit7.1.1_Agilent) with ESMTP id QAA08157; Thu, 23 Aug 2001 16:44:06 -0700 (PDT) Message-Id: <200108232344.QAA08157@mina.soco.agilent.com> To: "Aaron" Cc: freebsd-hardware@FreeBSD.ORG Subject: Re: 3ware Escalade 6200 RAID Controller Reply-To: Darryl Okahata In-Reply-To: Your message of "Thu, 23 Aug 2001 16:14:42 PDT." <20010823231651.B00C137B405@hub.freebsd.org> Mime-Version: 1.0 (generated by tm-edit 1.6) Content-Type: text/plain; charset=US-ASCII Date: Thu, 23 Aug 2001 16:44:06 -0700 From: Darryl Okahata Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org "Aaron" wrote: > Using the two boot floppies from the /floppies directory, how do you > edit /etc/fstab? I tried dearly to just find a friggin editor or Can't you use a bootable CDROM, or is your hardware too old? -- Darryl Okahata darrylo@soco.agilent.com DISCLAIMER: this message is the author's personal opinion and does not constitute the support, opinion, or policy of Agilent Technologies, or of the little green men that have been following him all day. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 19: 1:55 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from anaconda.acceleratedweb.net (anaconda.acceleratedweb.net [209.51.164.130]) by hub.freebsd.org (Postfix) with SMTP id 1A5BE37B401 for ; Thu, 23 Aug 2001 19:01:50 -0700 (PDT) (envelope-from simon@optinet.com) Received: (qmail 3787 invoked by uid 106); 24 Aug 2001 02:01:49 -0000 Received: from 66-65-36-21.nyc.rr.com (HELO sharky) (66.65.36.21) by anaconda.acceleratedweb.net with SMTP; 24 Aug 2001 02:01:49 -0000 From: "Simon" To: "Kenneth D. Merry" , "Matthew Jacob" Cc: "Aaron" , "freebsd-hardware@FreeBSD.ORG" Date: Thu, 23 Aug 2001 22:01:59 -0400 Reply-To: "Simon" X-Mailer: PMMail 2000 Professional (2.10.2010) For Windows 2000 (5.0.2195) In-Reply-To: <20010823143508.A99255@panzer.kdm.org> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Subject: Re: looking for ia32 system that supports > 4GB memory and has 64 bit PCI Message-Id: <20010824020150.1A5BE37B401@hub.freebsd.org> Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Quad CPU & 8GB of RAM, what OS? On Thu, 23 Aug 2001 14:35:08 -0600, Kenneth D. Merry wrote: >On Thu, Aug 23, 2001 at 13:04:32 -0700, Matthew Jacob wrote: >> >> Thanks. I've had some really good suggestions. I now have a bid for a 7K$ 8GB >> single 900MHz PIII SuperMicro based system from colfax-intl.com where I >> usually have my one-offs built- this stills seems a tad pricey, but I'll >> probably actually buy it in the 4 procesor version. I noticed that they also >> offered some Tyan solutions as wlel. > >www.microx-press.com has the SuperMicro 8060 system (S2QE6 motherboard in a >Supermicro SC860 (4U rack mount)) chassis for $2974.00. > >You can get 8GB of memory for it for $1670.24 (16 512MB DIMMs) from >www.crucial.com (Micron memory, not cheap-o stuff). Even though that >motherboard only needs PC100 memory, I would probably get PC133 memory >instead since you'd be able to use it in more systems if you don't leave it >all in there. > >The only other thing you'd need to do is figure out what sort of Xeons you >want in the system. Getting four Xeons (at least the more-than-two-proc >kind) will probably be the most expensive part of it. > >Micro X-press has 700MHz 1MB Xeons for $1299, so with four the total for >all that would run about $9840. (Only $5943 with one Xeon.) The only >thing is that those processors are out of stock there, but you could >probably find them (or whatever sort of Xeon) somewhere else. > >Ken >-- >Kenneth Merry >ken@kdm.org > >To Unsubscribe: send mail to majordomo@FreeBSD.org >with "unsubscribe freebsd-hardware" in the body of the message > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 19: 6:37 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from panzer.kdm.org (panzer.kdm.org [216.160.178.169]) by hub.freebsd.org (Postfix) with ESMTP id 36B5D37B40B for ; Thu, 23 Aug 2001 19:06:35 -0700 (PDT) (envelope-from ken@panzer.kdm.org) Received: (from ken@localhost) by panzer.kdm.org (8.9.3/8.9.1) id UAA02530; Thu, 23 Aug 2001 20:06:28 -0600 (MDT) (envelope-from ken) Date: Thu, 23 Aug 2001 20:06:28 -0600 From: "Kenneth D. Merry" To: Simon Cc: Matthew Jacob , Aaron , "freebsd-hardware@FreeBSD.ORG" Subject: Re: looking for ia32 system that supports > 4GB memory and has 64 bit PCI Message-ID: <20010823200628.A2518@panzer.kdm.org> References: <20010823143508.A99255@panzer.kdm.org> <200108240201.UAA02492@panzer.kdm.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2i In-Reply-To: <200108240201.UAA02492@panzer.kdm.org>; from simon@optinet.com on Thu, Aug 23, 2001 at 10:01:59PM -0400 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Thu, Aug 23, 2001 at 22:01:59 -0400, Simon wrote: > > Quad CPU & 8GB of RAM, what OS? FreeBSD with PAE support, Matt wants to play around with it. See the beginning of the thread. Ken -- Kenneth Merry ken@kdm.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 20:15:43 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from ns1.avatar.com (ns1.avatar.com [199.33.206.1]) by hub.freebsd.org (Postfix) with ESMTP id AE1AC37B409 for ; Thu, 23 Aug 2001 20:15:39 -0700 (PDT) (envelope-from kory@avatar.com) Received: from tomcat (tomcat.avatar.com [199.33.206.20]) by ns1.avatar.com (8.12.0.Beta8/8.12.0.Beta8) with SMTP id f7O3DaUM003344 for ; Thu, 23 Aug 2001 20:13:36 -0700 (PDT) From: "Kory Hamzeh" To: Subject: Errors using the OnStream DI30 ADR Drive Date: Thu, 23 Aug 2001 20:15:21 -0700 Message-ID: <007401c12c4b$028aba60$14ce21c7@avatar.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook 8.5, Build 4.71.2173.0 X-MimeOLE: Produced By Microsoft MimeOLE V5.50.4522.1200 In-Reply-To: <20010824082704.Q459@k7.mavetju.org> Importance: Normal Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I'm running 4.3-RELEASE GENERIC kernel with an OnStream DI-30 IDE tape drive. Things seem to work well as long as I use a 32K block size, however, the drive seems to get this error: ast0: WEOF - ILLEGAL REQUEST asc=24 ascq=00 error=04 whenever an end of file mark is written to it. Doing a "mt -f /dev/nrast0 fsf 1" cause I/O error, but that maybe because an EOF mark was never written because of the error listed above. Checking the mail archives, I noticed that someone else had the exact same problem, but no there was no follow up postings. Any help on how to fix this problem with be great. Any suggestion of an inexpensive way to backup a 30gig drive would be good too, that way I can throw out the onstream drive. Thanks, Kory To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Thu Aug 23 23: 1:37 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from beppo.feral.com (beppo.feral.com [192.67.166.79]) by hub.freebsd.org (Postfix) with ESMTP id BB71137B409 for ; Thu, 23 Aug 2001 23:01:34 -0700 (PDT) (envelope-from mjacob@feral.com) Received: from mailhost.feral.com (mjacob@mailhost.feral.com [192.67.166.1]) by beppo.feral.com (8.11.3/8.11.3) with ESMTP id f7O61QI02552; Thu, 23 Aug 2001 23:01:27 -0700 (PDT) (envelope-from mjacob@feral.com) Date: Thu, 23 Aug 2001 23:01:26 -0700 (PDT) From: Matthew Jacob X-Sender: mjacob@beppo Reply-To: mjacob@feral.com To: Simon Cc: "Kenneth D. Merry" , Aaron , "freebsd-hardware@FreeBSD.ORG" Subject: Re: looking for ia32 system that supports > 4GB memory and has 64 bit PCI In-Reply-To: <200108240202.f7O220I01366@beppo.feral.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Thu, 23 Aug 2001, Simon wrote: > > Quad CPU & 8GB of RAM, what OS? Multiple OS's - we'll see what sticks. We'll see if FreeBSD cuts it. I'll be trying some of the latest Linux patches. I'll check NetBSD. I'll try Solaris 2.8 Intel and what's up. Maybe OpenBSD. Probably Connexus (traakan.com's OS). The main interest for me is converting the QLogic driver (isp(4)) to be 64 bit DAC ready. It runs on multiple architectures and platforms. -matt To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Fri Aug 24 0:19:16 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from elitists.org (www.elitists.org [64.40.73.38]) by hub.freebsd.org (Postfix) with ESMTP id E0D0D37B409 for ; Fri, 24 Aug 2001 00:19:10 -0700 (PDT) (envelope-from freebsdlists@elitists.org) Received: from blah (64-40-88-202.pk.dsl.grics.net [64.40.88.202]) by elitists.org (Postfix) with SMTP id AAAF3213; Fri, 24 Aug 2001 02:29:40 -0500 (CDT) Message-ID: <021f01c12c6d$85f57d00$6501a8c0@elitists.org> From: "F. Even" To: "Hodge Podge" Cc: References: Subject: Re: 3ware stuff not ready for heavy duty useage-followup Date: Fri, 24 Aug 2001 02:22:24 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.00.2615.200 X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2615.200 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I think something as simple as laying another PS out, plugging half the drives into them, and starting them up off of that would suffice. Either wire up a hard switch for one, or use an AT PS. ----- Original Message ----- From: Hodge Podge To: Lawrence Farr Cc: Marc Rassbach ; ; Michael VanLoon ; Darryl Okahata Sent: Thursday, August 23, 2001 3:44 PM Subject: RE: 3ware stuff not ready for heavy duty useage-followup Very Nice. Thanks! Well, I'm not sure what the power supply na-sayers might want as a test, but do you have a way to force data into the drives from an outside source? I was doing this for abt 6-8 Hrs when mine failed :( Lots of small files. Who knows.. maybe that was enough to woogle the power supply, maybe its a Via Chipset interaction problem... The bugger is what to do abt it? I talked it over with my Boss and I want to see if we can set something up with 3ware to do some testing. We house hundredes of thousands of small (~300k) files) and maybe that is the problem. Maybe its bad drives.. Altho we got them from different places. But damn, process of elimination for something like this is no small thing. Nicole On 23-Aug-01 Lawrence Farr wrote: > I left my server (previous email below) running a benchmark that I made > up that took > a 1mb file and cat'ed to another file until it got to 1Gb. > I then read the file back by cat'ing to /dev/null, and repeated until I > filled the > partition (140Gb). It did this 3 times in total and got results like: > > Pass 23 - 1048576 kb written in 115 seconds, at 9118 kb/Sec > Pass 23 - 1048576 kb read in 15 seconds, at 69905 kb/Sec > Pass 24 - 1048576 kb written in 116 seconds, at 9039 kb/Sec > Pass 24 - 1048576 kb read in 15 seconds, at 69905 kb/Sec > > It all works fine, but the writes are awful. Iozone seems to agree with > me: > > File size set to 10240 KB > Time Resolution = 0.000001 seconds. > Processor cache size set to 1024 Kbytes. > Processor cache line size set to 32 bytes. > File stride size set to 17 * record size. > random random > > KB reclen write rewrite read reread read write read > 10240 4 9397 9461 266043 266458 236609 188083 253962 > > Anyone got any ideas for tuning this? Or is that it performance wise? > How about splitting the drives to 4 stripe sets, and Raid 5 across them > with vinum? > > Anyone else want to see any specific tests? > >>-----Original Message----- >>From: Lawrence Farr [mailto:freebsd-hw@sixforty.co.uk] >>Sent: 22 August 2001 14:59 >>To: 'Hodge Podge' >>Cc: 'mike.wentz@3ware.com'; 'freebsd-hardware@FreeBSD.ORG'; >>'Borja Marcos'; 'Michael VanLoon'; 'val@picturetrail.com' >>Subject: RE: 3ware stuff not ready for heavy duty useage- ATTN 3ware >> >> >>Im just formatting an 8 drive (Maxtor 536DX 100Gb) 7000 series >>array, 400W supply. >> >>Pick a benchmark and I'll run it for a while. > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-hardware" in the body of the message ******* |\ __ /| (`\ ******* * * | o_o |__ ) ) * * * * // \\ * * * Nicole Harrington | AKA Hodge Podge * ----------------------(((---(((-------------------------------- nicole@unixgirl.com http://www.unixgirl.com/ webmistress@dangermouse.org http://www.dangermouse.org/ nicole@deviantimages.com http://www.deviantimages.com/ -- Powered By Coca-Cola and FreeBSD -- "The world is run by those who show up" -- The Best Place for Your Web Site - www.WebWeaver.net -- ---------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Fri Aug 24 4:51:22 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from paperboy.sixforty.co.uk (paperboy.sixforty.co.uk [195.10.242.11]) by hub.freebsd.org (Postfix) with ESMTP id 52FB337B409 for ; Fri, 24 Aug 2001 04:51:14 -0700 (PDT) (envelope-from freebsd-hw@sixforty.co.uk) Received: (from root@localhost) by paperboy.sixforty.co.uk (8.11.1/8.11.1) id f7OBp5t74431; Fri, 24 Aug 2001 12:51:05 +0100 (BST) (envelope-from freebsd-hw@sixforty.co.uk) Delivered-To: nicole@unixgirl.com Received: from lfarr (daisy.int.epcdirect.co.uk [192.168.6.200]) by paperboy.sixforty.co.uk (8.11.1/8.11.1av) with ESMTP id f7OBoi674414; Fri, 24 Aug 2001 12:50:45 +0100 (BST) (envelope-from freebsd-hw@sixforty.co.uk) From: "Lawrence Farr" To: "'Hodge Podge'" , , "'Marc Rassbach'" , "'Michael VanLoon'" , "'Darryl Okahata'" Subject: RE: 3ware stuff not ready for heavy duty useage-followup Date: Fri, 24 Aug 2001 12:50:54 +0100 Message-ID: <004901c12c93$11ff6750$c80aa8c0@lfarr> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook, Build 10.0.2627 In-Reply-To: X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2462.0000 Importance: Normal X-Virus-Scanned: by AMaViS perl-10 Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Just to further cloud the issue, it's on an Asus A7Vc, and has now been filled Completely, and the contents read a few times just for good measure! Last night I plugged it into our gigabit switch, and pulled roughly 200Gb from 2 different Netatalk servers, which have 2 files for every file you store (One is a resource fork For the mac clients). Average file size is around 3mb, and the resource forks are a Couple of k. All went OK, so I read the lot out again to /dev/null, then deleted it. It's going to Do the whole test again tonight when some of my other servers are quiet. >-----Original Message----- >From: Hodge Podge [mailto:nicole@unixgirl.com] >Sent: 23 August 2001 21:45 >To: Lawrence Farr >Cc: Marc Rassbach; freebsd-hardware@freebsd.org; Michael >VanLoon; Darryl Okahata >Subject: RE: 3ware stuff not ready for heavy duty useage-followup > > > > Very Nice. Thanks! > Well, I'm not sure what the power supply na-sayers might want >as a test, but >do you have a way to force data into the drives from an outside source? > I was doing this for abt 6-8 Hrs when mine failed :( Lots of >small files. > > Who knows.. maybe that was enough to woogle the power supply, >maybe its a Via >Chipset interaction problem... The bugger is what to do abt it? > I talked it over with my Boss and I want to see if we can set >something up >with 3ware to do some testing. We house hundredes of thousands >of small (~300k) >files) and maybe that is the problem. Maybe its bad drives.. >Altho we got them >from different places. But damn, process of elimination for >something like >this is no small thing. > > > Nicole > > > >On 23-Aug-01 Lawrence Farr wrote: >> I left my server (previous email below) running a benchmark >that I made >> up that took >> a 1mb file and cat'ed to another file until it got to 1Gb. >> I then read the file back by cat'ing to /dev/null, and >repeated until I >> filled the >> partition (140Gb). It did this 3 times in total and got results like: >> >> Pass 23 - 1048576 kb written in 115 seconds, at 9118 kb/Sec >> Pass 23 - 1048576 kb read in 15 seconds, at 69905 kb/Sec >> Pass 24 - 1048576 kb written in 116 seconds, at 9039 kb/Sec >> Pass 24 - 1048576 kb read in 15 seconds, at 69905 kb/Sec >> >> It all works fine, but the writes are awful. Iozone seems to >agree with >> me: >> >> File size set to 10240 KB >> Time Resolution = 0.000001 seconds. >> Processor cache size set to 1024 Kbytes. >> Processor cache line size set to 32 bytes. >> File stride size set to 17 * record size. >> >random random >> >> KB reclen write rewrite read reread read >write read >> 10240 4 9397 9461 266043 266458 236609 >188083 253962 >> >> Anyone got any ideas for tuning this? Or is that it performance wise? >> How about splitting the drives to 4 stripe sets, and Raid 5 >across them >> with vinum? >> >> Anyone else want to see any specific tests? >> >>>-----Original Message----- >>>From: Lawrence Farr [mailto:freebsd-hw@sixforty.co.uk] >>>Sent: 22 August 2001 14:59 >>>To: 'Hodge Podge' >>>Cc: 'mike.wentz@3ware.com'; 'freebsd-hardware@FreeBSD.ORG'; >>>'Borja Marcos'; 'Michael VanLoon'; 'val@picturetrail.com' >>>Subject: RE: 3ware stuff not ready for heavy duty useage- ATTN 3ware >>> >>> >>>Im just formatting an 8 drive (Maxtor 536DX 100Gb) 7000 series >>>array, 400W supply. >>> >>>Pick a benchmark and I'll run it for a while. >> >> >> To Unsubscribe: send mail to majordomo@FreeBSD.org >> with "unsubscribe freebsd-hardware" in the body of the message > > > >******* |\ __ /| (`\ ******* > * * | o_o |__ ) ) * * > * * // \\ * * > * Nicole Harrington | AKA Hodge Podge * >----------------------(((---(((-------------------------------- > nicole@unixgirl.com http://www.unixgirl.com/ > webmistress@dangermouse.org http://www.dangermouse.org/ > nicole@deviantimages.com http://www.deviantimages.com/ > > -- Powered By Coca-Cola and FreeBSD -- > "The world is run by those who show up" > -- The Best Place for Your Web Site - www.WebWeaver.net -- > >---------------------------------------------------------------- > > > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Fri Aug 24 14:59: 1 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from ns1.avatar.com (ns1.avatar.com [199.33.206.1]) by hub.freebsd.org (Postfix) with ESMTP id 631DA37B40C for ; Fri, 24 Aug 2001 14:58:56 -0700 (PDT) (envelope-from kory@avatar.com) Received: from tomcat (tomcat.avatar.com [199.33.206.20]) by ns1.avatar.com (8.12.0.Beta8/8.12.0.Beta8) with SMTP id f7OLumUM007152 for ; Fri, 24 Aug 2001 14:56:49 -0700 (PDT) From: "Kory Hamzeh" To: Subject: Adding 3ware RAID AFTER FBSD has been installed Date: Fri, 24 Aug 2001 14:58:35 -0700 Message-ID: <004a01c12ce7$ec8214a0$14ce21c7@avatar.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook 8.5, Build 4.71.2173.0 X-MIMEOLE: Produced By Microsoft MimeOLE V5.50.4522.1200 Importance: Normal Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I need to add RAID 1 to one of our web servers. I went ahead and purchased the 3ware 6200 controller, and have run into these potential problems, even before I've installed the hardware: 1. Can a drive containing data be added to this controller and then have the drive mirror'ed on the second drive? I asked this question from 3ware and they said they will get back to me. 2. Assuming I solved problem # 1, here's another one: since the system is already configured and it is currently and IDE system and will become SCSI by using the 3ware controller, all of the disk device names will change. This means the system won't boot. I need to change the name of the root file system, mount the root filesystem, and then edit /etc/fstab to edit the name of the /var and /usr file systems. How do you change the name of the root filesystem? How does the kernel know with filesystem to mount as root? 3. Will the 3ware controller change the perceived drive geometry in anyway which might cause the system not to boot? I am also looking at the Fasttrack 100, but I read in the mail archives that the RAID functionality doesn't work under FBSD. The ARCO Raid controller is the only I know that work totally transparently because it sits in between the controller and the drive. It even comes with a floppy you can boot with to mirror one drive from another. It is the slowest of all of these controllers, so it is my last resort. I'm begging for help here, guys! Thanks, Kory To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Fri Aug 24 15:11:17 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from webpimps.net (lgb-DSL71-cust207.mpowercom.net [208.57.71.207]) by hub.freebsd.org (Postfix) with ESMTP id E511337B407 for ; Fri, 24 Aug 2001 15:11:15 -0700 (PDT) (envelope-from click46@webpimps.net) Received: from WorldClient [127.0.0.1] by webpimps.net [127.0.0.1] with SMTP (MDaemon.v3.1.2.R) for ; Fri, 24 Aug 2001 15:08:48 -0700 Date: Fri, 24 Aug 2001 15:08:48 -0700 From: "Aaron" To: freebsd-hardware@freebsd.org Cc: kory@avatar.com Subject: RE: Adding 3ware RAID AFTER FBSD has been installed X-Mailer: WorldClient Standard 3.1.2 X-MDRcpt-To: kory@avatar.com X-MDRemoteIP: 127.0.0.1 X-Return-Path: click46@webpimps.net X-MDaemon-Deliver-To: freebsd-hardware@freebsd.org Message-Id: <20010824221115.E511337B407@hub.freebsd.org> Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org As for #1, I would sure hope so - it only makes sense right? You might want to check the man page for the 3ware driver. I've been told you *should* be able edit your /etc/fstab with the boot floppies. I'm doing some testing myself currently. Check BSDatwork.com in the next week for a write up. - aaron --------------------------------------------- click46[wp] - AIM the click46 - ICQ 43450396 webpimps.net | bsdatwork.com | nerdserve.net moderator - o/c cooling forum @ hardforum.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Fri Aug 24 15:19: 2 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from ns1.avatar.com (ns1.avatar.com [199.33.206.1]) by hub.freebsd.org (Postfix) with ESMTP id 2BEC937B407 for ; Fri, 24 Aug 2001 15:18:59 -0700 (PDT) (envelope-from kory@avatar.com) Received: from tomcat (tomcat.avatar.com [199.33.206.20]) by ns1.avatar.com (8.12.0.Beta8/8.12.0.Beta8) with SMTP id f7OMGpUM007238; Fri, 24 Aug 2001 15:16:51 -0700 (PDT) From: "Kory Hamzeh" To: "Bryan-TheBS-Smith" Cc: Subject: RE: Adding 3ware RAID AFTER FBSD has been installed Date: Fri, 24 Aug 2001 15:18:38 -0700 Message-ID: <004b01c12cea$b968b120$14ce21c7@avatar.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook 8.5, Build 4.71.2173.0 In-Reply-To: <3B86CFDB.25361848@ieee.org> X-MIMEOLE: Produced By Microsoft MimeOLE V5.50.4522.1200 Importance: Normal Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hi Bryan, > -----Original Message----- > From: me@linux-wlan.com [mailto:me@linux-wlan.com]On Behalf Of > Bryan-TheBS-Smith > Kory Hamzeh wrote: > > 1. Can a drive containing data be added to this controller > > and then have the drive mirror'ed on the second drive? > > I'm assuming not since there is blocking going on and sector > reservation. This is the "price you pay" when you go with a true > hardware ATA solution. You _could_ probably mirror your existing > drive if you went with one of those "trick BIOS" ATA-RAID > controllers (like HPT370, Promise or other card). > > > I asked this question from 3ware and they said they will > > get back to me. > > That's funny! I guess there _might_ be a way to "convert" it > on-the-fly, since you can boot the disk as "dumb" on the 3Ware card. They have a "drive repair" function in their bios & 3dm task. I *think* that is how you would do it. > > > The ARCO Raid controller is the only I know that work > > totally transparently because it sits in between the > > controller and the drive. It even comes with a floppy > > you can boot with to mirror one drive from another. It > > is the slowest of all of these controllers, so it is my > > last resort. > > The 3Ware is another hardware solution. They seem to have perfected > the RAID-0, 1, 0+1 (aka 10) performance, although RAID-5 write > performance is horrendous without a good amount of on-board cache > memory (plus they don't seem to have their RAID-5 firmware perfected > yet either). > Did you mean to say "3ware" is another solution or where you thinking about another controller? It seems that I can NOT add 3ware to an existing system. I don't think I can even run vinum at this point. Kory To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Fri Aug 24 15:34: 8 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from ns1.avatar.com (ns1.avatar.com [199.33.206.1]) by hub.freebsd.org (Postfix) with ESMTP id 7F42D37B407 for ; Fri, 24 Aug 2001 15:34:06 -0700 (PDT) (envelope-from kory@avatar.com) Received: from tomcat (tomcat.avatar.com [199.33.206.20]) by ns1.avatar.com (8.12.0.Beta8/8.12.0.Beta8) with SMTP id f7OMVwUM007311; Fri, 24 Aug 2001 15:31:58 -0700 (PDT) From: "Kory Hamzeh" To: "Bryan-TheBS-Smith" Cc: Subject: RE: Adding 3ware RAID AFTER FBSD has been installed Date: Fri, 24 Aug 2001 15:33:45 -0700 Message-ID: <004c01c12cec$d6152ae0$14ce21c7@avatar.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook 8.5, Build 4.71.2173.0 In-Reply-To: <3B86D49A.A59E8341@ieee.org> X-MIMEOLE: Produced By Microsoft MimeOLE V5.50.4522.1200 Importance: Normal Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org > > Did you mean to say "3ware" is another solution or where > > you thinking about another controller? > > I meant that like the ARCO (which I have never used, so I can only > assume), the 3Ware card is a true hardware RAID solution. It > completely separates the rest of the system from the ATA drives -- > the microcontroller handles all conversations between them. > > > It seems that I can NOT add 3ware to an existing system. > > I don't think I can even run vinum at this point. > > Then your OS isn't loading the 3Ware driver I assume? What I'm trying to say is that the ARCO can be installed in a system that is already configured with an operating system since it is transparent and does not change the drive geometry (it only supports RAID 1). The 3ware, on the other hand, must be installed before you install the OS. If the ARCO had 3ware's TwinStore technology (splitting a read request into two parallel reads on different drives), I'd be using it right now. Thanks, Kory To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Fri Aug 24 16: 1:23 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from ns1.avatar.com (ns1.avatar.com [199.33.206.1]) by hub.freebsd.org (Postfix) with ESMTP id 8954837B409 for ; Fri, 24 Aug 2001 16:01:19 -0700 (PDT) (envelope-from kory@avatar.com) Received: from tomcat (tomcat.avatar.com [199.33.206.20]) by ns1.avatar.com (8.12.0.Beta8/8.12.0.Beta8) with SMTP id f7OMxBUM007434; Fri, 24 Aug 2001 15:59:11 -0700 (PDT) From: "Kory Hamzeh" To: "Bryan-TheBS-Smith" Cc: Subject: RE: Adding 3ware RAID AFTER FBSD has been installed Date: Fri, 24 Aug 2001 16:00:59 -0700 Message-ID: <004d01c12cf0$a3ced960$14ce21c7@avatar.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook 8.5, Build 4.71.2173.0 In-Reply-To: <3B86D918.230F3D84@ieee.org> X-MIMEOLE: Produced By Microsoft MimeOLE V5.50.4522.1200 Importance: Normal Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org > > Kory Hamzeh wrote: > > What I'm trying to say is that the ARCO can be installed > > in a system that is already configured with an operating > > system since it is transparent and does not change the > > drive geometry (it only supports RAID 1). > > Oh, so what it is is a mirroring "bridge" because you are still > using the on-board/system IDE controllers? Very cool. In fact, I > wondered if anyone was going to do something like that. I also > assume that you have to use two of the exact same drives? It is a kind of a bridge. You connect the ARCO RAID controller to you IDE controller, and then you connect the two (or four) drives to the ARCO controller. The system IDE controller will only see one drive. If you hook up four drive to the ARCO, the first two drives will be the Master Primary and Mirror, and the second two drives will be the Slave primary and master. In such a case, the system will see two IDE drive, one master and one slave. Its very nifty. No they don't have to be the exact same drive. The drive the system will see will be the size of the smaller of the primary/mirror pair. > > BTW, how much do they cost? > They are very reasonable priced: http://www.arcoide.com/inddupl2.htm. There is about 6 different physical configurations of the controller. I know a person that run this controller with Open/BSD without any problems. They could add the parallel reads fairly easily (of course, I don't know the hardware internals, I'm only guessing here). Kory To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Fri Aug 24 16: 3:46 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from great4.greatschools.net (great4.greatschools.net [199.4.104.154]) by hub.freebsd.org (Postfix) with ESMTP id 0DC0337B403 for ; Fri, 24 Aug 2001 16:03:44 -0700 (PDT) (envelope-from jdd@greatschools.net) Received: from localhost (jdd@localhost) by great4.greatschools.net (8.11.1/8.11.1) with ESMTP id f7ON3N625127 for ; Fri, 24 Aug 2001 16:03:23 -0700 (PDT) (envelope-from jdd@greatschools.net) Date: Fri, 24 Aug 2001 16:03:23 -0700 (PDT) From: John David Duncan To: freebsd-hardware@freebsd.org Subject: Mylex RAID question Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org The mly(4) manual page states: Logical devices (array drives) attached to the controller are presented to the SCSI subsystem as though they were direct-access devices on a virtual SCSI bus. Physical devices which are not claimed by a logical device are presented on SCSI channels which match the physical channels on the controller. Does this mean that I can attach a SCSI drive to the RAID controller, but not configure it as part of an array, and then access it as a normal drive? If so, can I also boot from it? - JD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Fri Aug 24 16:55:32 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from ns1.avatar.com (ns1.avatar.com [199.33.206.1]) by hub.freebsd.org (Postfix) with ESMTP id 5AE1137B405 for ; Fri, 24 Aug 2001 16:55:30 -0700 (PDT) (envelope-from kory@avatar.com) Received: from tomcat (tomcat.avatar.com [199.33.206.20]) by ns1.avatar.com (8.12.0.Beta8/8.12.0.Beta8) with SMTP id f7ONrMUM007647; Fri, 24 Aug 2001 16:53:22 -0700 (PDT) From: "Kory Hamzeh" To: "Aaron" , Subject: RE: Adding 3ware RAID AFTER FBSD has been installed Date: Fri, 24 Aug 2001 16:55:10 -0700 Message-ID: <005001c12cf8$35b5c120$14ce21c7@avatar.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook 8.5, Build 4.71.2173.0 In-Reply-To: <20010824221115.E511337B407@hub.freebsd.org> X-MIMEOLE: Produced By Microsoft MimeOLE V5.50.4522.1200 Importance: Normal Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org > I've been told you *should* be able edit your /etc/fstab with the boot > floppies. I'm doing some testing myself currently. Check BSDatwork.com in > the next week for a write up. > Oh, you definitely can edit /etc/fstab from floppies. Boot off of the floppies, and manually mount the root file system, then edit /etc/fstab. What I can't figure out (and I'm sure the answer is very very simple), is how the kernel determines what device to mount as root. Remember, it can't read /etc/fstab until is has mounted root. It's making me crazy! :-) I'm sure its buried in some man page that I keep overlooking. Kory To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Fri Aug 24 17:36:23 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from mail.wrs.com (unknown-1-11.windriver.com [147.11.1.11]) by hub.freebsd.org (Postfix) with ESMTP id 779F137B409 for ; Fri, 24 Aug 2001 17:36:20 -0700 (PDT) (envelope-from jhb@FreeBSD.org) Received: from laptop.baldwin.cx (john@[147.11.46.201]) by mail.wrs.com (8.9.3/8.9.1) with ESMTP id RAA18644; Fri, 24 Aug 2001 17:36:08 -0700 (PDT) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <005001c12cf8$35b5c120$14ce21c7@avatar.com> Date: Fri, 24 Aug 2001 17:36:14 -0700 (PDT) From: John Baldwin To: Kory Hamzeh Subject: RE: Adding 3ware RAID AFTER FBSD has been installed Cc: freebsd-hardware@FreeBSD.org, Aaron Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 24-Aug-01 Kory Hamzeh wrote: >> I've been told you *should* be able edit your /etc/fstab with the boot >> floppies. I'm doing some testing myself currently. Check BSDatwork.com in >> the next week for a write up. >> > > Oh, you definitely can edit /etc/fstab from floppies. Boot off of the > floppies, and manually mount the root file system, then edit /etc/fstab. > > What I can't figure out (and I'm sure the answer is very very simple), is > how the kernel determines what device to mount as root. Remember, it can't > read /etc/fstab until is has mounted root. It's making me crazy! :-) I'm > sure its buried in some man page that I keep overlooking. The loader reads /etc/fstab and passes in the rootdev via an environment variable. The older boot blocks (boot2) pass in a major and minor device number of the root device (IIRC). > Kory -- John Baldwin -- http://www.FreeBSD.org/~jhb/ PGP Key: http://www.baldwin.cx/~john/pgpkey.asc "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Sat Aug 25 6:49:15 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from smtp.noos.fr (lafontaine.noos.net [212.198.2.72]) by hub.freebsd.org (Postfix) with ESMTP id 5F4F937B40A for ; Sat, 25 Aug 2001 06:49:12 -0700 (PDT) (envelope-from root@gits.dyndns.org) Received: (qmail 51177580 invoked by uid 0); 25 Aug 2001 13:49:10 -0000 Received: from unknown (HELO gits.dyndns.org) ([212.198.231.187]) (envelope-sender ) by 212.198.2.72 (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP for ; 25 Aug 2001 13:49:10 -0000 Received: (from root@localhost) by gits.dyndns.org (8.11.6/8.11.6) id f7PDn8X07309; Sat, 25 Aug 2001 15:49:08 +0200 (CEST) (envelope-from root) Message-Id: <200108251349.f7PDn8X07309@gits.dyndns.org> Subject: Re: Sound Blaster Live! support? In-Reply-To: <004901c1220b$951d6200$0e00000a@tomcat> To: "Andrew C. Hornback" Date: Sat, 25 Aug 2001 15:49:07 +0200 (CEST) Cc: FreeBSD-Hardware Reply-To: clefevre@citeweb.net From: Cyrille Lefevre Organization: ACME X-Face: V|+c;4!|B?E%BE^{E6);aI.[<97Zd*>^#%Y5Cxv;%Y[PT-LW3;A:fRrJ8+^k"e7@+30g0YD0*^^3jgyShN7o?a]C la*Zv'5NA,=963bM%J^o]C X-Mailer: ELM [version 2.4ME+ PL94b (25)] MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=US-ASCII Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Andrew C. Hornback wrote: > I'm in the process of spec-ing out machine destined to run FreeBSD, and I > was wondering about the SB Live! support. My client is wanting to put a SB > Live! Platnium 5.1 in this machine. > > I'd like to know if this board is supported (which I believe it is), and > which of the features of it are supported. Namely, is the Live! Drive setup > supported? This box is going to be used as a workstation for digital > content creation (Dual PIII, 4 Gigs of memory, all SCSI internals), I just > want to go with the best sound card on the market with it. don't know the real status, but try : http://www.posi.net/freebsd/drivers/driver-info.phtml?ID=37 Cyrille. -- home: mailto:clefevre@redirect.to UNIX is user-friendly; it's just particular about who it chooses to be friends with. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Sat Aug 25 18: 0: 2 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from mass.dis.org (mass.dis.org [216.240.45.41]) by hub.freebsd.org (Postfix) with ESMTP id CAF9E37B401 for ; Sat, 25 Aug 2001 17:59:58 -0700 (PDT) (envelope-from msmith@mass.dis.org) Received: from mass.dis.org (localhost [127.0.0.1]) by mass.dis.org (8.11.4/8.11.3) with ESMTP id f7Q14vn22027; Sat, 25 Aug 2001 18:05:00 -0700 (PDT) (envelope-from msmith@mass.dis.org) Message-Id: <200108260105.f7Q14vn22027@mass.dis.org> X-Mailer: exmh version 2.1.1 10/15/1999 To: John David Duncan Cc: freebsd-hardware@freebsd.org Subject: Re: Mylex RAID question In-reply-to: Your message of "Fri, 24 Aug 2001 16:03:23 PDT." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 25 Aug 2001 18:04:57 -0700 From: Mike Smith Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org > > The mly(4) manual page states: > > Logical devices (array drives) attached to the controller are presented > to the SCSI subsystem as though they were direct-access devices on a > virtual SCSI bus. Physical devices which are not claimed by a logical > device are presented on SCSI channels which match the physical channels > on the controller. > > > Does this mean that I can attach a SCSI drive to the RAID controller, > but not configure it as part of an array, and then access it as a normal > drive? If so, can I also boot from it? The manpage is slightly out of sync with the way the driver works these days; the passthrough approach is disabled by default. You would not be able to boot from such a drive, no. You could configure it as a JBOD with the array config utility, though. -- ... every activity meets with opposition, everyone who acts has his rivals and unfortunately opponents also. But not because people want to be opponents, rather because the tasks and relationships force people to take different points of view. [Dr. Fritz Todt] V I C T O R Y N O T V E N G E A N C E To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Sat Aug 25 18: 1:21 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from mass.dis.org (mass.dis.org [216.240.45.41]) by hub.freebsd.org (Postfix) with ESMTP id 5F88837B40D for ; Sat, 25 Aug 2001 18:01:19 -0700 (PDT) (envelope-from msmith@mass.dis.org) Received: from mass.dis.org (localhost [127.0.0.1]) by mass.dis.org (8.11.4/8.11.3) with ESMTP id f7Q16Kn22054; Sat, 25 Aug 2001 18:06:20 -0700 (PDT) (envelope-from msmith@mass.dis.org) Message-Id: <200108260106.f7Q16Kn22054@mass.dis.org> X-Mailer: exmh version 2.1.1 10/15/1999 To: "Kory Hamzeh" Cc: freebsd-hardware@freebsd.org Subject: Re: Adding 3ware RAID AFTER FBSD has been installed In-reply-to: Your message of "Fri, 24 Aug 2001 14:58:35 PDT." <004a01c12ce7$ec8214a0$14ce21c7@avatar.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 25 Aug 2001 18:06:20 -0700 From: Mike Smith Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org > > I need to add RAID 1 to one of our web servers. I went ahead and purchased > the 3ware 6200 controller, and have run into these potential problems, even > before I've installed the hardware: > > 1. Can a drive containing data be added to this controller and then have the > drive mirror'ed on the second drive? I asked this question from 3ware and > they said they will get back to me. No, it cannot. This basically kills the rest of your questions. -- ... every activity meets with opposition, everyone who acts has his rivals and unfortunately opponents also. But not because people want to be opponents, rather because the tasks and relationships force people to take different points of view. [Dr. Fritz Todt] V I C T O R Y N O T V E N G E A N C E To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Sat Aug 25 18:23: 4 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from mass.dis.org (mass.dis.org [216.240.45.41]) by hub.freebsd.org (Postfix) with ESMTP id 5B6F637B411 for ; Sat, 25 Aug 2001 18:22:58 -0700 (PDT) (envelope-from msmith@mass.dis.org) Received: from mass.dis.org (localhost [127.0.0.1]) by mass.dis.org (8.11.4/8.11.3) with ESMTP id f7Q1Rsn22431; Sat, 25 Aug 2001 18:27:54 -0700 (PDT) (envelope-from msmith@mass.dis.org) Message-Id: <200108260127.f7Q1Rsn22431@mass.dis.org> X-Mailer: exmh version 2.1.1 10/15/1999 To: "Aaron" Cc: "Tim" , freebsd-hardware@freebsd.org Subject: Re: 3ware Escalade 6200 RAID Controller In-reply-to: Your message of "Thu, 23 Aug 2001 16:14:42 PDT." <20010823231651.B00C137B405@hub.freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 25 Aug 2001 18:27:54 -0700 From: Mike Smith Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org > Using the two boot floppies from the /floppies directory, how do you > edit /etc/fstab? I tried dearly to just find a friggin editor or > SOMETHING. Hm, come to think of it I didnt try to mount it using the boot > floppies. So could you do something like, boot with the boot floppies, > mount your root partition - run vi from your hard drive and > edit /etc/fstab and then reboot? I KNEW IT! I told myself - "The > documentation says FreeBSD users hate having to reinstall..so there must > be away around this without reinstalling". Set vfs.root.mountfrom in the loader to the device you want to be root, eg. ok set vfs.root.mountfrom="ufs:/dev/ad0s2a" -- ... every activity meets with opposition, everyone who acts has his rivals and unfortunately opponents also. But not because people want to be opponents, rather because the tasks and relationships force people to take different points of view. [Dr. Fritz Todt] V I C T O R Y N O T V E N G E A N C E To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message From owner-freebsd-hardware Sat Aug 25 22:33:39 2001 Delivered-To: freebsd-hardware@freebsd.org Received: from light-house.net (mars.light-house.net [206.152.252.7]) by hub.freebsd.org (Postfix) with SMTP id DEA3737B406 for ; Sat, 25 Aug 2001 22:33:35 -0700 (PDT) (envelope-from petkus@sault.com) Received: (qmail 83322 invoked from network); 26 Aug 2001 05:33:34 -0000 Received: from rud1-00.light-house.net (HELO localhost.localdomain) (206.152.224.2) by mars.light-house.net with SMTP; 26 Aug 2001 05:33:34 -0000 From: K To: freebsd-hardware@freebsd.org Subject: SoundFusion audio help Date: Sat, 25 Aug 2001 11:29:37 -0400 X-Mailer: KMail [version 1.0.28] Content-Type: text/plain MIME-Version: 1.0 Message-Id: <01082511304200.31258@localhost.localdomain> Content-Transfer-Encoding: 8bit Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hello there I got a ThinkPad A21m, it has a Crystal SoundFusion card, do this cards are still experimental or are they supposed to work fine now? FreeBSD 4.3 here. Errr, well, just in case the answer is yes, i compiled kernel with pcm and csa, i rebooted, i cat /dev/sndstat'd and reported me what its suppose to report (can't paste right now), i cd /dev'd and sh MAKEDEV snd0 and agan reported no errors but well... it just doesn't sound heh, im using KDE, i think i read on IRC that it might cause problem, dunno. Thanks in Advance Alcachofo Demv P.S. (please CC: me a responce) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message