From owner-freebsd-fs Sun Nov 8 03:38:47 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id DAA00287 for freebsd-fs-outgoing; Sun, 8 Nov 1998 03:38:47 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from magicnet.magicnet.net (magicnet.magicnet.net [204.96.116.9]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id DAA00261 for ; Sun, 8 Nov 1998 03:38:10 -0800 (PST) (envelope-from bill@bilver.magicnet.net) Received: (from uucp@localhost) by magicnet.magicnet.net (8.8.6/8.8.8) with UUCP id GAA08054; Sun, 8 Nov 1998 06:35:29 -0500 (EST) Received: (from bill@localhost) by bilver.magicnet.net (8.9.1/8.9.1) id GAA21734; Sun, 8 Nov 1998 06:30:17 -0500 (EST) From: Bill Vermillion Message-Id: <199811081130.GAA21734@bilver.magicnet.net> Subject: Re: RAID1 Software vs Hardware In-Reply-To: <19981108094916.T499@freebie.lemis.com> from Greg Lehey at "Nov 8, 98 09:49:16 am" To: grog@lemis.com (Greg Lehey) Date: Sun, 8 Nov 1998 06:30:17 -0500 (EST) Cc: freebsd-fs@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL38 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Greg Lehey recently said: > On Saturday, 7 November 1998 at 8:31:26 -0500, Bill Vermillion > wrote: > > > Greg Lehey recently said: > > > >> On Friday, 6 November 1998 at 19:42:15 -0500, Bill Vermillion > >> wrote: > >> > >>> Christopher Nielsen recently said: > >>>> Your really not going to see very good performance with RAID > >>>> if you're using only two spindles (i.e., discs). ... > >>> I've found that I get a 50% throughput increase (typical)when > >>> running RAID 0 with 2 drives. > >> That's what theory would tell you. > > No - not theory. Measured in real-life - running HW raid 0 - on > > a clients SCO system. We needed more speed. It may be slightly > > under 50% - but it's darn close. > Theory would tell you 50%. Practice shows it's darn close. If I > had said "yes, that's what happens", somebody would have looked > from the other perspective and said "not quite". > > I have timed the same drive on SCO and FreeBSD - a 9GB 'cudda, > > and the raw SCO performance through the file-system is in the > > 3MB/min range, while using the FreeBSD file-system - as shipped > > - no mods, etc,. it is between 2 and 3 times faster than SCO's. > Which operating system? FreeBSD 2.5 versus SCO Opensever 5.0.4. I don't know whether it part of this can be contritubted to FreeBSD's synchronous writes, or whether it is all file system implementation dependant. The drive was on loan to a customer. They had a pair of old 4GB 'cuddas (slower than current drives), and lost a drive. I borrowed a 9GB 'cudda about 1230 AM and had them running. I used iozone the next week when the new 4GB returned. What surpsied me was that the older pair of 4GB in a RAID 0 were slower than the single 9GB - but only by about 200K/sec. The specs on the different models accounted for that. Individually the 2 older 4GBs were about 1/3 slower but were about the same in RAID 0. > > They current have 6 classes - 0 thru 5 - and there is a chart > > in Adaptec's book on I/O subsytems listing the pro's'/con's of > > each. RAID2/3/4 aren't used, and from what I've seen drives that > > use to have spindle sync for byte/sector striping aren't being > > made anymore. But with drives now at 20MB/sec+ speeds, the old > > needs are gone. > Correct. You'd be surprised how many products offer RAID-2/3/4, > though. I think the product manager got a checklist to tick off. I > have deliberately left these three out of Vinum. A more correct choice of words should have been "raid-2/3/4" are commonly used. I seem to recall the spindle sync is not in the neweset 'cuddas and Cheetahs, while it was in the earilier 'cuddas. > >>> but it will boost the read throughput if different files are > >>> being accessed, just as if you load balanced multiple single > >>> disks.. > >> BTW, ccd always reads from the same copy of the data, so this > >> doesn't work. But in principle you're right. > > > > Reading from two disks for different files is one of the touted > > features of most HW implementations. > Put it this way, I don't know of any other implementation, SW or > HW, which is this primitive. ... You are speaking of 'ccd' when you make this statement? I trimmed previous posters quotes - and I believe the ccd comment came from you. I also think that is primitive. Doing that make the drive act like only a backup device. > Vinum has a choice of round robin (default) or always reading from > a specific drive (which can be an advantage if you have a ramdisk, > for example). Yup. I can't see much use for a RAID in RAM. :-) Bill To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sun Nov 8 04:18:01 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id EAA05923 for freebsd-fs-outgoing; Sun, 8 Nov 1998 04:18:01 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from magicnet.magicnet.net (magicnet.magicnet.net [204.96.116.9]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id EAA05905 for ; Sun, 8 Nov 1998 04:17:57 -0800 (PST) (envelope-from bill@bilver.magicnet.net) Received: (from uucp@localhost) by magicnet.magicnet.net (8.8.6/8.8.8) with UUCP id HAA11729 for freebsd-fs@freebsd.org; Sun, 8 Nov 1998 07:15:39 -0500 (EST) Received: (from bill@localhost) by bilver.magicnet.net (8.9.1/8.9.1) id HAA22232 for freebsd-fs@freebsd.org; Sun, 8 Nov 1998 07:19:04 -0500 (EST) From: Bill Vermillion Message-Id: <199811081219.HAA22232@bilver.magicnet.net> Subject: Correction: Re: RAID1 Software vs Hardware To: freebsd-fs@FreeBSD.ORG Date: Sun, 8 Nov 1998 07:19:04 -0500 (EST) X-Mailer: ELM [version 2.4ME+ PL38 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org ARGH. What am I doing up this early on Sunday! Bill Vermillion recently said: > A more correct choice of words should have been "raid-2/3/4" are > commonly used. I seem to recall the spindle sync is not in the ^--- insert NOT as in "not commonly used". Spell checkers don't make up for stupidty Bill -- bill@bilver.magicnet.net | bv@wjv.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sun Nov 8 05:00:22 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id FAA09739 for freebsd-fs-outgoing; Sun, 8 Nov 1998 05:00:22 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from ns1.yes.no (ns1.yes.no [195.204.136.10]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id FAA09734 for ; Sun, 8 Nov 1998 05:00:20 -0800 (PST) (envelope-from eivind@bitbox.follo.net) Received: from bitbox.follo.net (bitbox.follo.net [195.204.143.218]) by ns1.yes.no (8.9.1a/8.9.1) with ESMTP id OAA09110; Sun, 8 Nov 1998 14:00:05 +0100 (CET) Received: (from eivind@localhost) by bitbox.follo.net (8.8.8/8.8.6) id OAA17113; Sun, 8 Nov 1998 14:00:05 +0100 (MET) Message-ID: <19981108140005.03003@follo.net> Date: Sun, 8 Nov 1998 14:00:05 +0100 From: Eivind Eklund To: Bill Vermillion , Greg Lehey Cc: freebsd-fs@FreeBSD.ORG Subject: Re: RAID1 Software vs Hardware References: <19981108094916.T499@freebie.lemis.com> <199811081130.GAA21734@bilver.magicnet.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.89.1i In-Reply-To: <199811081130.GAA21734@bilver.magicnet.net>; from Bill Vermillion on Sun, Nov 08, 1998 at 06:30:17AM -0500 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sun, Nov 08, 1998 at 06:30:17AM -0500, Bill Vermillion wrote: > > Vinum has a choice of round robin (default) or always reading from > > a specific drive (which can be an advantage if you have a ramdisk, > > for example). > > Yup. I can't see much use for a RAID in RAM. :-) Make one of the disks work as an extremely fast cache. Or it may be NVRAM - you still want it backed up somewhere. Eivind. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sun Nov 8 07:28:55 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id HAA20470 for freebsd-fs-outgoing; Sun, 8 Nov 1998 07:28:55 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.15.68.22]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id HAA20461 for ; Sun, 8 Nov 1998 07:28:50 -0800 (PST) (envelope-from bde@godzilla.zeta.org.au) Received: (from bde@localhost) by godzilla.zeta.org.au (8.8.7/8.8.7) id CAA07261; Mon, 9 Nov 1998 02:28:35 +1100 Date: Mon, 9 Nov 1998 02:28:35 +1100 From: Bruce Evans Message-Id: <199811081528.CAA07261@godzilla.zeta.org.au> To: freebsd-fs@FreeBSD.ORG, richard@jezebel.demon.co.uk Subject: Re: Should a corrupt floppy disk cause a panic? Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >Subject: Should a corrupt floppy disk cause a panic? Yes. >This is question on policy. > >The msdosfs will panic and the system will die if you mount a >floppy with a corrupt format. I have an image of such a floppy >and I can crash my system every time. Suitably damaged ffs file systems should also cause panics (as soon as possible so that the damage doesn't grow). fsck_foofs must be run before mounting [possibly-]damaged foofs file systems. This is not so easy for msdosfs file systems since there is no fsck_msdosfs. Bruce To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sun Nov 8 08:42:05 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id IAA26188 for freebsd-fs-outgoing; Sun, 8 Nov 1998 08:42:05 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from ns1.yes.no (ns1.yes.no [195.204.136.10]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id IAA26183 for ; Sun, 8 Nov 1998 08:42:01 -0800 (PST) (envelope-from eivind@bitbox.follo.net) Received: from bitbox.follo.net (bitbox.follo.net [195.204.143.218]) by ns1.yes.no (8.9.1a/8.9.1) with ESMTP id RAA10841; Sun, 8 Nov 1998 17:34:21 +0100 (CET) Received: (from eivind@localhost) by bitbox.follo.net (8.8.8/8.8.6) id RAA06154; Sun, 8 Nov 1998 17:32:55 +0100 (MET) Message-ID: <19981108173255.57550@follo.net> Date: Sun, 8 Nov 1998 17:32:55 +0100 From: Eivind Eklund To: Bruce Evans , freebsd-fs@FreeBSD.ORG, richard@jezebel.demon.co.uk Subject: Re: Should a corrupt floppy disk cause a panic? References: <199811081528.CAA07261@godzilla.zeta.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.89.1i In-Reply-To: <199811081528.CAA07261@godzilla.zeta.org.au>; from Bruce Evans on Mon, Nov 09, 1998 at 02:28:35AM +1100 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Mon, Nov 09, 1998 at 02:28:35AM +1100, Bruce Evans wrote: > >Subject: Should a corrupt floppy disk cause a panic? > > Yes. NO. Not unconditonally. > >This is question on policy. > > > >The msdosfs will panic and the system will die if you mount a > >floppy with a corrupt format. I have an image of such a floppy > >and I can crash my system every time. > > Suitably damaged ffs file systems should also cause panics (as soon as > possible so that the damage doesn't grow). fsck_foofs must be run > before mounting [possibly-]damaged foofs file systems. This is not so > easy for msdosfs file systems since there is no fsck_msdosfs. Suitably damaged ffs file systems should block for further writes. A panic() is not the only way of blocking for further writes, and for high-availability systems it is a bad way. This should be tunable, of course, as an unattended system would probably be better off panic'ing and rebooting, to get the system to automatically come up again with the filesystem available. However, for systems with many filesystems active, it might be much better to loose access to that single filesystem than to take down the entire machine for a reboot. Eivind. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sun Nov 8 19:56:43 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id TAA03238 for freebsd-fs-outgoing; Sun, 8 Nov 1998 19:56:43 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from allegro.lemis.com (allegro.lemis.com [192.109.197.134]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id TAA03230 for ; Sun, 8 Nov 1998 19:56:40 -0800 (PST) (envelope-from grog@freebie.lemis.com) Received: from freebie.lemis.com (freebie.lemis.com [192.109.197.137]) by allegro.lemis.com (8.9.1/8.9.0) with ESMTP id OAA11005; Mon, 9 Nov 1998 14:26:01 +1030 (CST) Received: (from grog@localhost) by freebie.lemis.com (8.9.1/8.9.0) id OAA11200; Mon, 9 Nov 1998 14:26:01 +1030 (CST) Message-ID: <19981109142601.F499@freebie.lemis.com> Date: Mon, 9 Nov 1998 14:26:01 +1030 From: Greg Lehey To: "Justin T. Gibbs" Cc: "Kenneth D. Merry" , bill@bilver.magicnet.net, freebsd-fs@FreeBSD.ORG Subject: Re: RAID1 Software vs Hardware References: <19981108173920.N499@freebie.lemis.com> <199811080724.AAA03989@pluto.plutotech.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i In-Reply-To: <199811080724.AAA03989@pluto.plutotech.com>; from Justin T. Gibbs on Sun, Nov 08, 1998 at 12:17:36AM -0700 WWW-Home-Page: http://www.lemis.com/~grog Organization: LEMIS, PO Box 460, Echunga SA 5153, Australia Phone: +61-8-8388-8286 Fax: +61-8-8388-8725 Mobile: +61-41-739-7062 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sunday, 8 November 1998 at 0:17:36 -0700, Justin T. Gibbs wrote: >>> RAID 3 is still used, and is still useful. All of Pluto's products (see >>> http://www.plutotech.com) use RAID 3. It works quite well for video data. >> >> I suppose it gives you good throughput. But how do you handle the I/O >> load? Are you effectively delivering a single video stream? > > RAID 3 is ideal when your data requests are always a multiple of the strip > size. I'm not sure we're talking about the same thing. In my book, RAID-3 is a RAID-4 with a stripe size of 1 byte. How do you define it? Greg -- See complete headers for address, home page and phone numbers finger grog@lemis.com for PGP public key To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sun Nov 8 19:59:37 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id TAA03692 for freebsd-fs-outgoing; Sun, 8 Nov 1998 19:59:37 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from allegro.lemis.com (allegro.lemis.com [192.109.197.134]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id TAA03683 for ; Sun, 8 Nov 1998 19:59:33 -0800 (PST) (envelope-from grog@freebie.lemis.com) Received: from freebie.lemis.com (freebie.lemis.com [192.109.197.137]) by allegro.lemis.com (8.9.1/8.9.0) with ESMTP id OAA11312; Mon, 9 Nov 1998 14:29:17 +1030 (CST) Received: (from grog@localhost) by freebie.lemis.com (8.9.1/8.9.0) id OAA11209; Mon, 9 Nov 1998 14:29:15 +1030 (CST) Message-ID: <19981109142915.G499@freebie.lemis.com> Date: Mon, 9 Nov 1998 14:29:15 +1030 From: Greg Lehey To: Bill Vermillion Cc: freebsd-fs@FreeBSD.ORG Subject: Re: RAID1 Software vs Hardware References: <19981108094916.T499@freebie.lemis.com> <199811081130.GAA21734@bilver.magicnet.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i In-Reply-To: <199811081130.GAA21734@bilver.magicnet.net>; from Bill Vermillion on Sun, Nov 08, 1998 at 06:30:17AM -0500 WWW-Home-Page: http://www.lemis.com/~grog Organization: LEMIS, PO Box 460, Echunga SA 5153, Australia Phone: +61-8-8388-8286 Fax: +61-8-8388-8725 Mobile: +61-41-739-7062 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sunday, 8 November 1998 at 6:30:17 -0500, Bill Vermillion wrote: > Greg Lehey recently said: >> On Saturday, 7 November 1998 at 8:31:26 -0500, Bill Vermillion wrote: >>> Greg Lehey recently said: >>>> BTW, ccd always reads from the same copy of the data, so this >>>> doesn't work. But in principle you're right. >>> Reading from two disks for different files is one of the touted >>> features of most HW implementations. >> >> Put it this way, I don't know of any other implementation, SW or >> HW, which is this primitive. ... > > You are speaking of 'ccd' when you make this statement? I trimmed > previous posters quotes - and I believe the ccd comment came from > you. Correct in both cases. Trim more and you get what I have above. > I also think that is primitive. Doing that make the drive act like > only a backup device. Right. >> Vinum has a choice of round robin (default) or always reading from >> a specific drive (which can be an advantage if you have a ramdisk, >> for example). > > Yup. I can't see much use for a RAID in RAM. :-) I don't know. RAM disks don't seem as popular as they used to be, but it's still possible. The same situation would occur if one of the plexes was remote (a thing I have on the wish list for Vinum). Greg -- See complete headers for address, home page and phone numbers finger grog@lemis.com for PGP public key To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sun Nov 8 22:25:34 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id WAA16491 for freebsd-fs-outgoing; Sun, 8 Nov 1998 22:25:34 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from pluto.plutotech.com (mail.plutotech.com [206.168.67.137]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id WAA16486 for ; Sun, 8 Nov 1998 22:25:33 -0800 (PST) (envelope-from gibbs@plutotech.com) Received: from narnia.plutotech.com (narnia.plutotech.com [206.168.67.130]) by pluto.plutotech.com (8.8.7/8.8.5) with ESMTP id XAA25317; Sun, 8 Nov 1998 23:24:22 -0700 (MST) Message-Id: <199811090624.XAA25317@pluto.plutotech.com> X-Mailer: exmh version 2.0.2 2/24/98 To: Greg Lehey cc: "Justin T. Gibbs" , "Kenneth D. Merry" , bill@bilver.magicnet.net, freebsd-fs@FreeBSD.ORG Subject: Re: RAID1 Software vs Hardware In-reply-to: Your message of "Mon, 09 Nov 1998 14:26:01 +1030." <19981109142601.F499@freebie.lemis.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 08 Nov 1998 23:17:36 -0700 From: "Justin T. Gibbs" Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >On Sunday, 8 November 1998 at 0:17:36 -0700, Justin T. Gibbs wrote: >>>> RAID 3 is still used, and is still useful. All of Pluto's products (see >>>> http://www.plutotech.com) use RAID 3. It works quite well for video data. >>> >>> I suppose it gives you good throughput. But how do you handle the I/O >>> load? Are you effectively delivering a single video stream? >> >> RAID 3 is ideal when your data requests are always a multiple of the strip >> size. > >I'm not sure we're talking about the same thing. In my book, RAID-3 >is a RAID-4 with a stripe size of 1 byte. How do you define it? RAID-3 confines parity to 1 member of the array. The size of the stripe is not a part of the specification. In the case of Pluto products, we usually use a stripe size of 1MB which implies a per-unit access of 1MB/N-1 (N being number of members in the RAID group). >Greg -- Justin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sun Nov 8 22:27:03 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id WAA16642 for freebsd-fs-outgoing; Sun, 8 Nov 1998 22:27:03 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from allegro.lemis.com (allegro.lemis.com [192.109.197.134]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id WAA16637 for ; Sun, 8 Nov 1998 22:26:59 -0800 (PST) (envelope-from grog@freebie.lemis.com) Received: from freebie.lemis.com (freebie.lemis.com [192.109.197.137]) by allegro.lemis.com (8.9.1/8.9.0) with ESMTP id QAA11904; Mon, 9 Nov 1998 16:56:19 +1030 (CST) Received: (from grog@localhost) by freebie.lemis.com (8.9.1/8.9.0) id QAA15369; Mon, 9 Nov 1998 16:56:13 +1030 (CST) Message-ID: <19981109165612.K499@freebie.lemis.com> Date: Mon, 9 Nov 1998 16:56:12 +1030 From: Greg Lehey To: "Justin T. Gibbs" Cc: "Kenneth D. Merry" , bill@bilver.magicnet.net, freebsd-fs@FreeBSD.ORG Subject: RAID-3 and RAID-4 (was: RAID1 Software vs Hardware) References: <19981109142601.F499@freebie.lemis.com> <199811090624.XAA25317@pluto.plutotech.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i In-Reply-To: <199811090624.XAA25317@pluto.plutotech.com>; from Justin T. Gibbs on Sun, Nov 08, 1998 at 11:17:36PM -0700 WWW-Home-Page: http://www.lemis.com/~grog Organization: LEMIS, PO Box 460, Echunga SA 5153, Australia Phone: +61-8-8388-8286 Fax: +61-8-8388-8725 Mobile: +61-41-739-7062 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sunday, 8 November 1998 at 23:17:36 -0700, Justin T. Gibbs wrote: >> On Sunday, 8 November 1998 at 0:17:36 -0700, Justin T. Gibbs wrote: >>>>> RAID 3 is still used, and is still useful. All of Pluto's products (see >>>>> http://www.plutotech.com) use RAID 3. It works quite well for video data. >>>> >>>> I suppose it gives you good throughput. But how do you handle the I/O >>>> load? Are you effectively delivering a single video stream? >>> >>> RAID 3 is ideal when your data requests are always a multiple of the strip >>> size. >> >> I'm not sure we're talking about the same thing. In my book, RAID-3 >> is a RAID-4 with a stripe size of 1 byte. How do you define it? > > RAID-3 confines parity to 1 member of the array. The size of the stripe > is not a part of the specification. In the case of Pluto products, we > usually use a stripe size of 1MB which implies a per-unit access of > 1MB/N-1 (N being number of members in the RAID group). This looks like RAID-4 to me. Where do you see the difference? Greg -- See complete headers for address, home page and phone numbers finger grog@lemis.com for PGP public key To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sun Nov 8 22:31:32 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id WAA16901 for freebsd-fs-outgoing; Sun, 8 Nov 1998 22:31:32 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from pluto.plutotech.com (mail.plutotech.com [206.168.67.137]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id WAA16896 for ; Sun, 8 Nov 1998 22:31:31 -0800 (PST) (envelope-from gibbs@plutotech.com) Received: from narnia.plutotech.com (narnia.plutotech.com [206.168.67.130]) by pluto.plutotech.com (8.8.7/8.8.5) with ESMTP id XAA25531; Sun, 8 Nov 1998 23:29:51 -0700 (MST) Message-Id: <199811090629.XAA25531@pluto.plutotech.com> X-Mailer: exmh version 2.0.2 2/24/98 To: Greg Lehey cc: "Justin T. Gibbs" , "Kenneth D. Merry" , bill@bilver.magicnet.net, freebsd-fs@FreeBSD.ORG Subject: Re: RAID-3 and RAID-4 (was: RAID1 Software vs Hardware) In-reply-to: Your message of "Mon, 09 Nov 1998 16:56:12 +1030." <19981109165612.K499@freebie.lemis.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 08 Nov 1998 23:23:04 -0700 From: "Justin T. Gibbs" Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >> RAID-3 confines parity to 1 member of the array. The size of the stripe >> is not a part of the specification. In the case of Pluto products, we >> usually use a stripe size of 1MB which implies a per-unit access of >> 1MB/N-1 (N being number of members in the RAID group). > >This looks like RAID-4 to me. Where do you see the difference? RAID-4 adds the ability to do smaller than whole stripe updates with only touching the affected members of the stripe and the parity. RAID-3 concerns itself only with whole strip accesses. Since we have full control over the stripe size and know in advance the type of data we will store and the way it is accessed, RAID-3 is sufficient for Pluto's application. -- Justin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sun Nov 8 22:45:42 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id WAA18081 for freebsd-fs-outgoing; Sun, 8 Nov 1998 22:45:42 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from allegro.lemis.com (allegro.lemis.com [192.109.197.134]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id WAA18072 for ; Sun, 8 Nov 1998 22:45:39 -0800 (PST) (envelope-from grog@freebie.lemis.com) Received: from freebie.lemis.com (freebie.lemis.com [192.109.197.137]) by allegro.lemis.com (8.9.1/8.9.0) with ESMTP id RAA11963; Mon, 9 Nov 1998 17:15:00 +1030 (CST) Received: (from grog@localhost) by freebie.lemis.com (8.9.1/8.9.0) id RAA15545; Mon, 9 Nov 1998 17:14:59 +1030 (CST) Message-ID: <19981109171458.A15539@freebie.lemis.com> Date: Mon, 9 Nov 1998 17:14:58 +1030 From: Greg Lehey To: "Justin T. Gibbs" Cc: "Kenneth D. Merry" , bill@bilver.magicnet.net, freebsd-fs@FreeBSD.ORG Subject: Re: RAID-3 and RAID-4 (was: RAID1 Software vs Hardware) References: <19981109165612.K499@freebie.lemis.com> <199811090629.XAA25531@pluto.plutotech.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i In-Reply-To: <199811090629.XAA25531@pluto.plutotech.com>; from Justin T. Gibbs on Sun, Nov 08, 1998 at 11:23:04PM -0700 WWW-Home-Page: http://www.lemis.com/~grog Organization: LEMIS, PO Box 460, Echunga SA 5153, Australia Phone: +61-8-8388-8286 Fax: +61-8-8388-8725 Mobile: +61-41-739-7062 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sunday, 8 November 1998 at 23:23:04 -0700, Justin T. Gibbs wrote: >>> RAID-3 confines parity to 1 member of the array. The size of the stripe >>> is not a part of the specification. In the case of Pluto products, we >>> usually use a stripe size of 1MB which implies a per-unit access of >>> 1MB/N-1 (N being number of members in the RAID group). >> >> This looks like RAID-4 to me. Where do you see the difference? > > RAID-4 adds the ability to do smaller than whole stripe updates with only > touching the affected members of the stripe and the parity. RAID-3 > concerns itself only with whole strip accesses. Since we have full control > over the stripe size and know in advance the type of data we will store > and the way it is accessed, RAID-3 is sufficient for Pluto's application. Hmmm. I looked up my references and found that they are obviously incorrect, though I hadn't noticed that before. Where (on the web) can I find a reliable definition? If I see this correctly, then, are you saying the big difference between RAID-3 and RAID-4 is in the software, not in the storage layout? Greg -- See complete headers for address, home page and phone numbers finger grog@lemis.com for PGP public key To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Nov 9 00:22:27 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id AAA27359 for freebsd-fs-outgoing; Mon, 9 Nov 1998 00:22:27 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.15.68.22]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id AAA27354 for ; Mon, 9 Nov 1998 00:22:21 -0800 (PST) (envelope-from bde@godzilla.zeta.org.au) Received: (from bde@localhost) by godzilla.zeta.org.au (8.8.7/8.8.7) id TAA12725; Mon, 9 Nov 1998 19:21:51 +1100 Date: Mon, 9 Nov 1998 19:21:51 +1100 From: Bruce Evans Message-Id: <199811090821.TAA12725@godzilla.zeta.org.au> To: bde@zeta.org.au, eivind@yes.no, freebsd-fs@FreeBSD.ORG, richard@jezebel.demon.co.uk Subject: Re: Should a corrupt floppy disk cause a panic? Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >> Suitably damaged ffs file systems should also cause panics (as soon as >> possible so that the damage doesn't grow). fsck_foofs must be run >> before mounting [possibly-]damaged foofs file systems. This is not so >> easy for msdosfs file systems since there is no fsck_msdosfs. > >Suitably damaged ffs file systems should block for further writes. A >panic() is not the only way of blocking for further writes, and for >high-availability systems it is a bad way. This should be tunable, of >course, as an unattended system would probably be better off panic'ing >and rebooting, to get the system to automatically come up again with >the filesystem available. However, for systems with many filesystems >active, it might be much better to loose access to that single >filesystem than to take down the entire machine for a reboot. Yes, when a panic occurs (deep in a non-ffs routine, due to memory corruption caused by using invalid data from the disk), it is easy for the system to unwind the state to when the error occurred and make ffs wait there ;-). Bruce To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Nov 9 00:57:26 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id AAA00903 for freebsd-fs-outgoing; Mon, 9 Nov 1998 00:57:26 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from datasail.it ([194.177.99.2]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id AAA00895 for ; Mon, 9 Nov 1998 00:57:22 -0800 (PST) (envelope-from bago@datasail.it) Received: from lust (194.177.99.15) by datasail.it with SMTP (Eudora Internet Mail Server 1.1.2); Mon, 9 Nov 1998 10:59:04 +0000 Message-ID: <006c01be0bbf$76a42300$0f63b1c2@lust.datasail.it> From: "Bagnara Stefano" To: "FreeBSD filesystems" Subject: RAIDing freebsd.... Date: Mon, 9 Nov 1998 10:00:56 +0100 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 4.72.2106.4 X-MimeOLE: Produced By Microsoft MimeOLE V4.72.2106.4 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org This is the first time i get so many answer to a question in a mailing list.... many thanx to all... So let's sort the problems: 1. I need 8/10 gigs of useable space on the system and i'll try to get it with software RAID: should be better to use 3 x 4gigs than 2 x 9 gigs (as my original idea). After all your posts i concluded (sorry for my english) that 3 x 4 gigs is less expensive and faster, but... is the software RAID configuration the same? or with RAID3 it is more difficult than RAID1? 2. This is the first time i install FreeBSD. I used a lot linux before. Can i set up the whole system with software RAID and get it to work anyway if one disk fail? (as in HW RAID). 3. Where can i find an hardware compatibility lists for RAID controllers? i've read the Handbook but i only found classic SCSI cards. Any suggestion about a specific controller? To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Nov 9 02:05:23 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id CAA08771 for freebsd-fs-outgoing; Mon, 9 Nov 1998 02:05:23 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from datasail.it ([194.177.99.2]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id CAA08766 for ; Mon, 9 Nov 1998 02:05:15 -0800 (PST) (envelope-from bago@datasail.it) Received: from lust (194.177.99.15) by datasail.it with SMTP (Eudora Internet Mail Server 1.1.2); Mon, 9 Nov 1998 12:06:40 +0000 Message-ID: <007f01be0bc8$e81f9060$0f63b1c2@lust.datasail.it> From: "Bagnara Stefano" To: "FreeBSD filesystems" Subject: Allways RAIDing... Date: Mon, 9 Nov 1998 11:08:29 +0100 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 4.72.2106.4 X-MimeOLE: Produced By Microsoft MimeOLE V4.72.2106.4 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I cannot find a SCSI card for RAID3. AAA-131-SA from Adaptec does RAID0/1/5 ... in RAID5 needs a minimum of 3 disks... but... with 3 disks and RAID5 if a disk fail the whole system die? or RAID5 can handle redundancy with only 3 disks? Any idea if FreeBSD support AAA-131-SA? it's not on the HW compatibility list... but no RAID controllers are on it.... Many thanks again. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Nov 9 02:21:33 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id CAA10060 for freebsd-fs-outgoing; Mon, 9 Nov 1998 02:21:33 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from ns1.yes.no (ns1.yes.no [195.204.136.10]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id CAA10054 for ; Mon, 9 Nov 1998 02:21:27 -0800 (PST) (envelope-from eivind@bitbox.follo.net) Received: from bitbox.follo.net (bitbox.follo.net [195.204.143.218]) by ns1.yes.no (8.9.1a/8.9.1) with ESMTP id LAA20582; Mon, 9 Nov 1998 11:21:01 +0100 (CET) Received: (from eivind@localhost) by bitbox.follo.net (8.8.8/8.8.6) id LAA10047; Mon, 9 Nov 1998 11:21:01 +0100 (MET) Message-ID: <19981109112101.13646@follo.net> Date: Mon, 9 Nov 1998 11:21:01 +0100 From: Eivind Eklund To: Bruce Evans , freebsd-fs@FreeBSD.ORG, richard@jezebel.demon.co.uk Subject: Re: Should a corrupt floppy disk cause a panic? References: <199811090821.TAA12725@godzilla.zeta.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.89.1i In-Reply-To: <199811090821.TAA12725@godzilla.zeta.org.au>; from Bruce Evans on Mon, Nov 09, 1998 at 07:21:51PM +1100 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Mon, Nov 09, 1998 at 07:21:51PM +1100, Bruce Evans wrote: > Yes, when a panic occurs (deep in a non-ffs routine, due to memory > corruption caused by using invalid data from the disk), it is easy > for the system to unwind the state to when the error occurred and > make ffs wait there ;-). That doesn't really matter for the 'should' side of this - ideally, it should not always panic() for those corrupted filesystems. This should not be too hard to fix, either - install invariant checks before exiting the FFS routines. Unfortunately, I've not yet found anything that document those invariants, or the on-disk format of FFS. I've seen papers that hint at these, but no actual exact documentation (without reading the code to see what it does, which hardly is documentation, and has to be repeated each time you have to know). Eivind. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Nov 9 02:38:16 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id CAA12018 for freebsd-fs-outgoing; Mon, 9 Nov 1998 02:38:16 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from ns1.yes.no (ns1.yes.no [195.204.136.10]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id CAA12000; Mon, 9 Nov 1998 02:38:12 -0800 (PST) (envelope-from eivind@bitbox.follo.net) Received: from bitbox.follo.net (bitbox.follo.net [195.204.143.218]) by ns1.yes.no (8.9.1a/8.9.1) with ESMTP id LAA20918; Mon, 9 Nov 1998 11:37:54 +0100 (CET) Received: (from eivind@localhost) by bitbox.follo.net (8.8.8/8.8.6) id LAA10161; Mon, 9 Nov 1998 11:37:54 +0100 (MET) Message-ID: <19981109113753.00487@follo.net> Date: Mon, 9 Nov 1998 11:37:53 +0100 From: Eivind Eklund To: Bagnara Stefano , freebsd-scsi@FreeBSD.ORG Subject: Re: Allways RAIDing... References: <007f01be0bc8$e81f9060$0f63b1c2@lust.datasail.it> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.89.1i In-Reply-To: <007f01be0bc8$e81f9060$0f63b1c2@lust.datasail.it>; from Bagnara Stefano on Mon, Nov 09, 1998 at 11:08:29AM +0100 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Please post any followups to FreeBSD-scsi only (ie, do not re-introduce FreeBSD-fs). Thanks! On Mon, Nov 09, 1998 at 11:08:29AM +0100, Bagnara Stefano wrote: > I cannot find a SCSI card for RAID3. AAA-131-SA from Adaptec does RAID0/1/5 > ... in RAID5 needs a minimum of 3 disks... but... with 3 disks and RAID5 if > a disk fail the whole system die? or RAID5 can handle redundancy with only 3 > disks? RAID5 can handle redundancy with only three disks. > Any idea if FreeBSD support AAA-131-SA? it's not on the HW compatibility > list... but no RAID controllers are on it.... I have no idea what the AAA-131-SA even is, from a programmers standpoint. I don't think we support it. I'm running with a DPT controller, and am fairly happy with it (due to this being a really old board, they don't have and won't produce a workaround for a bug in my BIOS, but apart from that I've had absolutely no problems). I also believe these are faster than the Adaptecs. The FreeBSD driver is stable and actively maintained (to the degree it need maintenance - this hasn't really been that much). Eivind. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Nov 9 15:02:34 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id PAA03800 for freebsd-fs-outgoing; Mon, 9 Nov 1998 15:02:34 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from allegro.lemis.com (allegro.lemis.com [192.109.197.134]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id PAA03794 for ; Mon, 9 Nov 1998 15:02:31 -0800 (PST) (envelope-from grog@freebie.lemis.com) Received: from freebie.lemis.com (freebie.lemis.com [192.109.197.137]) by allegro.lemis.com (8.9.1/8.9.0) with ESMTP id JAA15186; Tue, 10 Nov 1998 09:32:08 +1030 (CST) Received: (from grog@localhost) by freebie.lemis.com (8.9.1/8.9.0) id JAA17544; Tue, 10 Nov 1998 09:32:06 +1030 (CST) Message-ID: <19981110093206.Y499@freebie.lemis.com> Date: Tue, 10 Nov 1998 09:32:06 +1030 From: Greg Lehey To: Bagnara Stefano , FreeBSD filesystems Subject: Re: RAIDing freebsd.... References: <006c01be0bbf$76a42300$0f63b1c2@lust.datasail.it> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i In-Reply-To: <006c01be0bbf$76a42300$0f63b1c2@lust.datasail.it>; from Bagnara Stefano on Mon, Nov 09, 1998 at 10:00:56AM +0100 WWW-Home-Page: http://www.lemis.com/~grog Organization: LEMIS, PO Box 460, Echunga SA 5153, Australia Phone: +61-8-8388-8286 Fax: +61-8-8388-8725 Mobile: +61-41-739-7062 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Monday, 9 November 1998 at 10:00:56 +0100, Bagnara Stefano wrote: > This is the first time i get so many answer to a question in a mailing > list.... > many thanx to all... > > So let's sort the problems: > > 1. I need 8/10 gigs of useable space on the system and i'll try to get it > with software RAID: should be better to use 3 x 4gigs than 2 x 9 gigs (as my > original idea). After all your posts i concluded (sorry for my english) that > 3 x 4 gigs is less expensive and faster, but... is the software RAID > configuration the same? or with RAID3 it is more difficult than > RAID1? No software RAID-3 is available. Do you mean RAID-5? With RAID-5, even 3 disks is rather on the low side. 2 disks is too few: in this case, RAID-1 is a better option, but you lose 50% of the storage space. RAID-5 will lose one disk, so it's better to have a lot of disks. > 2. This is the first time i install FreeBSD. I used a lot linux before. Can > i set up the whole system with software RAID and get it to work anyway if > one disk fail? (as in HW RAID). Yes, with Vinum, but not with ccd. You need to reconfigure and reboot to recover from a ccd disk failure. > 3. Where can i find an hardware compatibility lists for RAID controllers? > i've read the Handbook but i only found classic SCSI cards. Any suggestion > about a specific controller? Currently DPT's the only game in town. Greg -- See complete headers for address, home page and phone numbers finger grog@lemis.com for PGP public key To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Nov 9 15:09:29 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id PAA04430 for freebsd-fs-outgoing; Mon, 9 Nov 1998 15:09:29 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from allegro.lemis.com (allegro.lemis.com [192.109.197.134]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id PAA04416 for ; Mon, 9 Nov 1998 15:09:24 -0800 (PST) (envelope-from grog@freebie.lemis.com) Received: from freebie.lemis.com (freebie.lemis.com [192.109.197.137]) by allegro.lemis.com (8.9.1/8.9.0) with ESMTP id JAA15217; Tue, 10 Nov 1998 09:39:01 +1030 (CST) Received: (from grog@localhost) by freebie.lemis.com (8.9.1/8.9.0) id JAA17563; Tue, 10 Nov 1998 09:39:00 +1030 (CST) Message-ID: <19981110093900.A499@freebie.lemis.com> Date: Tue, 10 Nov 1998 09:39:00 +1030 From: Greg Lehey To: Bagnara Stefano , FreeBSD filesystems Subject: Re: Allways RAIDing... References: <007f01be0bc8$e81f9060$0f63b1c2@lust.datasail.it> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i In-Reply-To: <007f01be0bc8$e81f9060$0f63b1c2@lust.datasail.it>; from Bagnara Stefano on Mon, Nov 09, 1998 at 11:08:29AM +0100 WWW-Home-Page: http://www.lemis.com/~grog Organization: LEMIS, PO Box 460, Echunga SA 5153, Australia Phone: +61-8-8388-8286 Fax: +61-8-8388-8725 Mobile: +61-41-739-7062 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Monday, 9 November 1998 at 11:08:29 +0100, Bagnara Stefano wrote: > I cannot find a SCSI card for RAID3. For a very good reason. Why do you want one? > AAA-131-SA from Adaptec does RAID0/1/5 ... in RAID5 needs a minimum > of 3 disks... Well, so would RAID-3 if there were any implementations. > but... with 3 disks and RAID5 if a disk fail the whole system die? No. > or RAID5 can handle redundancy with only 3 disks? That's the intention. > Any idea if FreeBSD support AAA-131-SA? it's not on the HW compatibility > list... but no RAID controllers are on it.... No. Only DPT is supported. Greg -- See complete headers for address, home page and phone numbers finger grog@lemis.com for PGP public key To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Tue Nov 10 11:33:32 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id LAA04212 for freebsd-fs-outgoing; Tue, 10 Nov 1998 11:33:32 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from silver.gn.iaf.nl (silver.gn.iaf.nl [193.67.144.11]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id LAA04206 for ; Tue, 10 Nov 1998 11:33:28 -0800 (PST) (envelope-from wilko@yedi.iaf.nl) Received: from uni4nn.gn.iaf.nl (osmium.gn.iaf.nl [193.67.144.12]) by silver.gn.iaf.nl (8.8.8/8.8.8) with SMTP id UAA27627; Tue, 10 Nov 1998 20:33:07 +0100 Received: by uni4nn.gn.iaf.nl with UUCP id AA16446 (5.67b/IDA-1.5); Tue, 10 Nov 1998 20:18:42 +0100 Received: (from wilko@localhost) by yedi.iaf.nl (8.8.8/8.6.12) id SAA00652; Tue, 10 Nov 1998 18:58:04 +0100 (CET) From: Wilko Bulte Message-Id: <199811101758.SAA00652@yedi.iaf.nl> Subject: Re: RAIDing freebsd.... In-Reply-To: <19981110093206.Y499@freebie.lemis.com> from Greg Lehey at "Nov 10, 98 09:32:06 am" To: grog@lemis.com (Greg Lehey) Date: Tue, 10 Nov 1998 18:58:04 +0100 (CET) Cc: bago@datasail.it, freebsd-fs@FreeBSD.ORG X-Organisation: Private FreeBSD site - Arnhem, The Netherlands X-Pgp-Info: PGP public key at 'finger wilko@freefall.freebsd.org' X-Mailer: ELM [version 2.4ME+ PL38 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org As Greg Lehey wrote... > On Monday, 9 November 1998 at 10:00:56 +0100, Bagnara Stefano wrote: [snip] > > 3. Where can i find an hardware compatibility lists for RAID controllers? > > i've read the Handbook but i only found classic SCSI cards. Any suggestion > > about a specific controller? > > Currently DPT's the only game in town. I'd say you could also go for a SCSI-SCSI RAID box. So, not a backplane raid controller (which obviously needs a driver to work) but a standalone raid box hooked to (e.g.) an Adaptec. Problem is that it will be more expensive in most cases.. Wilko _ ______________________________________________________________________ | / o / / _ Bulte email: wilko@yedi.iaf.nl |/|/ / / /( (_) Arnhem, The Netherlands WWW : http://www.tcja.nl ______________________________________________ Powered by FreeBSD __________ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Nov 13 20:43:36 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id UAA13424 for freebsd-fs-outgoing; Fri, 13 Nov 1998 20:43:36 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from acrserv-1.acrny.com (internet.acrny.com [207.252.53.2]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id UAA13410; Fri, 13 Nov 1998 20:43:34 -0800 (PST) (envelope-from adam.furman@usi.net) Received: by ACRSERV-1 with Internet Mail Service (5.5.2232.9) id ; Fri, 13 Nov 1998 23:42:44 -0500 Message-ID: <41156768DA32D211A97600C0F0313F01393E@ACRSERV-1> From: Adam Furman To: "'freebsd-hackers@freebsd.org'" , "'freebsd-fs@freebsd.org'" Cc: Adam Furman Subject: Server going into Kernel Debug mode Date: Fri, 13 Nov 1998 23:42:35 -0500 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2232.9) Content-Type: text/plain Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I'm running FreeBSD 2.2.5 on an Pentium 133 with 128megs of Memory. My server seems to be crashing now every couple of hours and goes into Kernel Debug mode. The server was running for 184 days before it started to encore any problems. It gave me trouble for about 3 days and it all of sudden stop giving me trouble and ran for another month. The server again is giving me problems. The error message that is comming up on the console is as follows. Any help in this problem would be great. I need to know what could be wrong so I can fix that problem so this doesn't keep happening. Thanks Adam Furman (error message) calcrv: negative time: -6131984 vsec fatal trap 12: page fault while in kernel mode fault virtual address = 0x4 fault code = supervisor read, page not present instruction pointer = 0x8:0xf0153ed9 stack pointer = 0x10:0xefbfff74 frame pointer = 0x10:0xefbfff84 code segment = base 0x0, limit 0xfffff, type 0x1b = DPL 0, Pres 1, det32 1, gran 1 processor eflags = interrupt enabled, resume, IUPL=0 current process = 177(SSHD1) interrupt mask = kernel: type 12 trap, code =0 stoped at _ip_slowtimot0x49: mov1 0x4(%ebx),%eax db> To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Nov 13 20:46:53 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id UAA13802 for freebsd-fs-outgoing; Fri, 13 Nov 1998 20:46:53 -0800 (PST) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from Loki.orland.u91.k12.me.us (Loki.orland.u91.k12.me.us [169.244.111.67]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id UAA13797; Fri, 13 Nov 1998 20:46:50 -0800 (PST) (envelope-from netmonger@genesis.ispace.com) Received: from celeris (56k-port4020.ime.net [209.90.195.30]) by Loki.orland.u91.k12.me.us (8.9.1/8.8.8-Loki) with SMTP id XAA00527; Fri, 13 Nov 1998 23:46:10 -0500 (EST) (envelope-from netmonger@genesis.ispace.com) X-Server-ID: Loki.orland.u91.k12.me.us, OCSNet - Orland Maine USA X-Coord-Name: Drew "Droobie" Baxter, OneNetwork Exchange X-Coord-Addr: Droobie@Openlink.orland.me.us X-Coord-Pager: USA: 207-471-2719, http://pagedroo.orland.me.us Message-Id: <4.1.19981113234248.00ae9ca0@genesis.ispace.com> X-Sender: netmonger@genesis.ispace.com X-Mailer: QUALCOMM Windows Eudora Pro Version 4.1 Date: Fri, 13 Nov 1998 23:43:58 -0500 To: Adam Furman , "'freebsd-hackers@freebsd.org'" , "'freebsd-fs@freebsd.org'" From: Drew Baxter Subject: Re: Server going into Kernel Debug mode Cc: Adam Furman In-Reply-To: <41156768DA32D211A97600C0F0313F01393E@ACRSERV-1> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org At 11:42 PM 11/13/98 -0500, Adam Furman wrote: >I'm running FreeBSD 2.2.5 on an Pentium 133 with 128megs of Memory. My >server seems to be crashing now every couple of hours and goes into Kernel >Debug mode. The server was running for 184 days before it started to encore >any problems. It gave me trouble for about 3 days and it all of sudden stop >giving me trouble and ran for another month. The server again is giving me >problems. The error message that is comming up on the console is as >follows. Any help in this problem would be great. I need to know what >could be wrong so I can fix that problem so this doesn't keep happening. >Thanks >Adam Furman > >(error message) >calcrv: negative time: -6131984 vsec >fatal trap 12: page fault while in kernel mode >fault virtual address = 0x4 >fault code = supervisor read, page not present >instruction pointer = 0x8:0xf0153ed9 >stack pointer = 0x10:0xefbfff74 >frame pointer = 0x10:0xefbfff84 > >code segment = base 0x0, limit 0xfffff, type 0x1b > = DPL 0, Pres 1, det32 1, gran 1 >processor eflags = interrupt enabled, resume, IUPL=0 >current process = 177(SSHD1) >interrupt mask = >kernel: type 12 trap, code =0 >stoped at _ip_slowtimot0x49: mov1 0x4(%ebx),%eax >db> You wouldn't by any chance have kernel-level debugging on do you? (option DDB?). I had it in my kernel for a while, but the thing would do exactly that, and then it would go and beep eradically.. That doesn't work very well when the machine is over 30 miles away. --- Drew "Droobie" Baxter Network Admin/Professional Computer Nerd(TM) OneEX: The OneNetwork Exchange 207-942-0275 http://www.droo.orland.me.us My Latest Kernel: FreeBSD 3.0-CURRENT (ONEEX) #14: Mon Oct 19 22:36:58 EDT 1998 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message