From owner-freebsd-fs Sun Mar 26 0:48:14 2000 Delivered-To: freebsd-fs@freebsd.org Received: from mail.cs.tu-berlin.de (mail.cs.tu-berlin.de [130.149.17.13]) by hub.freebsd.org (Postfix) with ESMTP id 1E3F337B82C for ; Sun, 26 Mar 2000 00:48:11 -0800 (PST) (envelope-from loewis@cs.tu-berlin.de) Received: from rubel.cs.tu-berlin.de (loewis@rubel.cs.tu-berlin.de [130.149.20.46]) by mail.cs.tu-berlin.de (8.9.3/8.9.3) with ESMTP id KAA21188; Sun, 26 Mar 2000 10:46:28 +0200 (MET DST) Received: (from loewis@localhost) by rubel.cs.tu-berlin.de (8.9.3/8.9.3) id KAA07470; Sun, 26 Mar 2000 10:46:22 +0200 (MET DST) Date: Sun, 26 Mar 2000 10:46:22 +0200 (MET DST) Message-Id: <200003260846.KAA07470@rubel.cs.tu-berlin.de> X-Authentication-Warning: rubel.cs.tu-berlin.de: loewis set sender to loewis@cs.tu-berlin.de using -f From: "Martin v.Loewis" To: krentel@dreamscape.com Cc: freebsd-fs@FreeBSD.ORG, bde@zeta.org.au, kwc@world.std.com In-reply-to: <200003252337.SAA05240@dreamscape.com> (krentel@dreamscape.com) Subject: Re: ext2fs optional features References: <200003252337.SAA05240@dreamscape.com> Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org What is e2fstools? Is this a Linux package? It's the package that provides mke2fs, e2fsck, and the e2fs library; thus it is not really a "Linux" package - for example, it is used on the Hurd, as well. It is available from http://sourceforge.net/project/?group_id=2406 Regards, Martin P.S. I misreported the name of the package; it is actually e2fsprogs... To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sun Mar 26 15:16: 9 2000 Delivered-To: freebsd-fs@freebsd.org Received: from starburst.demon.co.uk (starburst.demon.co.uk [194.222.114.233]) by hub.freebsd.org (Postfix) with ESMTP id 1B33537BAA4; Sun, 26 Mar 2000 15:16:02 -0800 (PST) (envelope-from richard@starburst.demon.co.uk) Received: (from richard@localhost) by starburst.demon.co.uk (8.8.7/8.8.7) id WAA01211; Sun, 26 Mar 2000 22:25:22 +0100 From: Richard Wendland Message-Id: <200003262125.WAA01211@starburst.demon.co.uk> Subject: Re: FreeBSD random I/O performance issues To: julian@elischer.org (Julian Elischer) Date: Sun, 26 Mar 2000 22:25:21 +0100 (BST) Cc: dillon@apollo.backplane.com (Matthew Dillon), current@freebsd.org, fs@freebsd.org Reply-To: richard@netcraft.com In-Reply-To: <38D9B306.2781E494@elischer.org> from "Julian Elischer" at Mar 22, 2000 11:34:11 PM Reply-To: richard@wendland.org.uk X-Mailer: ELM [version 2.5 PL2] 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 > This is one of the things that made us do so badly > in the benchmarks against NT/Linux last year. If the benchmarks included random I/O I would think so. By creating a small synthetic program exhibiting the problem, I may have obscured the scale of the real-world consequences of this problem. Here are some test results from a slightly simplified program and data that Netcraft regularly runs. This is a simple perl DB_File program that reads 10 million input records, creating and updating a Berkeley DB file from that input. At finish the DBM is 78MB logical size, 67MB physical size (it's sparse), with 2176918 keys. These benchmark results aren't perfect, since some of the machines weren't completely idle, but they aren't far off. Elapse time OS Disc 4 hrs, 2 mins 2.2.8-STABLE Atlas II, 7200RPM, 512KB buff 3 hr, 17 mins 3.3-RELEASE ATA IBM Deskstar 34GXP, 7200RPM, 2MB 3 hr, 2 mins 3.3-STABLE IBM Ultrastar 18ES, 7200RPM, 2MB buff 1 hr, 43 mins 2.2.7-RELEASE Cheetah 9, 10000RPM, 1MB buff 51 mins 2.2.7-RELEASE Cheetah 9, 10000RPM, 1MB buff, 5 way ccd striped, interleave=64 31 mins Linux 2.2.13 IBM Ultrastar 18ES, 7200RPM, 2MB buff The run on Linux seemed CPU bound at times, with 87% CPU utilisation overall. The Linux system and the 3.3-STABLE/Ultrastar 18ES machine are both similar Dell 1300s. Netcraft runs quite a few DBM programs. You can probably see why I've gone to a fair amount of effort benchmarking to pin this performance problem down, and hopefully encourage the development of a fix. Netcraft uses heavily striped fast discs, in part to make these DBM programs run at a reasonable speed, as it turns out to overcome a software deficiency. Actually DBM performance on FreeBSD can be significantly improved by: $DB_HASH->{cachesize} = 64 * 1024 * 1024; which I commented out for this test; I doubt most DBM users set this. So our programs don't now run quite as slow as the results above suggest, by in effect creating a very large in-process write buffer. On FreeBSD this test program does about 28+2191019io according to csh 'time', I assume that's in 8KB blocks, in which case it's 16.7GB of I/O. In 51 mins that's 5.6MB/sec, on top of the seeks. Richard -- Richard Wendland richard@netcraft.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Mar 27 4:39:50 2000 Delivered-To: freebsd-fs@freebsd.org Received: from europe.std.com (europe.std.com [199.172.62.20]) by hub.freebsd.org (Postfix) with ESMTP id 842EC37BB20 for ; Mon, 27 Mar 2000 04:39:42 -0800 (PST) (envelope-from kwc@world.std.com) Received: from world.std.com (root@world-f.std.com [199.172.62.5]) by europe.std.com (8.9.3/8.9.3) with ESMTP id HAA18024 for ; Mon, 27 Mar 2000 07:39:38 -0500 (EST) Received: (from kwc@localhost) by world.std.com (8.9.3/8.9.3) id HAA09498; Mon, 27 Mar 2000 07:35:36 -0500 (EST) Date: Mon, 27 Mar 2000 07:35:36 -0500 (EST) From: Kenneth W Cochran Message-Id: <200003271235.HAA09498@world.std.com> To: freebsd-fs@freebsd.org Subject: Re: ext2fs optional features Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >From krentel@dreamscape.com Fri Mar 24 22:14:21 2000 >Date: Fri, 24 Mar 2000 22:10:50 -0500 (EST) >To: freebsd-fs@FreeBSD.ORG >Subject: ext2fs optional features >Cc: kwc@world.std.com > >This question was asked in -stable a couple days ago, but it >really belongs in -fs. Ok... >Recently, some changes were made to the ext2fs support that >prohibit R/W mounts for some newer ext2fs partitions with >optional features. I've seen this with Red Hat 6.1 and >Slackware 7. Red Hat 6.0 seems to use an older format. Check. Slackware 7 in my case. Ext2 filesystems made with Slackware 4 appear to do ok with FreeBSD's ext2 support. >This is what Linux's tune2fs reports: Hmmm, which distribution/kernel version? > # tune2fs -l /dev/sdb2 > tune2fs 1.15, 18-Jul-1999 for EXT2 FS 0.5b, 95/08/09 > Filesystem volume name: > Last mounted on: > Filesystem UUID: 38a27662-0012-11d4-8f7a-ead76bc87798 > Filesystem magic number: 0xEF53 > Filesystem revision #: 1 (dynamic) > Filesystem features: sparse_super > Filesystem state: not clean > Errors behavior: Continue > Filesystem OS type: Linux > ... > >And this is what appears in the logs: > > Mar 24 21:36:47 blue /kernel: WARNING: R/W mount of dev 0x3040a > denied due to unsupported optional features Yep. That's what I get too. FreeBSD 3.4-stable (about a week "old" now) trying to access Linux (Slackware 7.0) ext2 filesystems. >What are the optional features? What does "sparse_super" do? >Does Linux actually use these features, or are they for future use? > >Is it possible to support R/W mounts with these features? > >I remember 3.4-release let me mount the same filesystem R/W. >Was I unknowingly corrupting the filesystem, or running some >risk of a panic? > >I noticed that tune2fs also reported: > > Block size: 4096 > Fragment size: 4096 > >Does Linux really not support fragments?? I was stunned. > >Much thanks for any answers. > >--Mark Krentel To Mark's questions I might add: (Most likely a Linux question...) Is there a way, perhaps in Linux with its tunefs, to adjust or "turn off" those "optional features" (other things too?) in such a way that FreeBSD's ext2 support will work? In other words, what would be an "optimal filesystem config" in Linux for FreeBSD's use? -kc To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Mar 27 12:10:24 2000 Delivered-To: freebsd-fs@freebsd.org Received: from io.dreamscape.com (io.dreamscape.com [206.64.128.6]) by hub.freebsd.org (Postfix) with ESMTP id 6022C37C144 for ; Mon, 27 Mar 2000 12:10:15 -0800 (PST) (envelope-from krentel@dreamscape.com) Received: from dreamscape.com (sA22-p14.dreamscape.com [209.217.202.78]) by io.dreamscape.com (8.9.3/8.8.4) with ESMTP id PAA10873; Mon, 27 Mar 2000 15:09:22 -0500 (EST) X-Dreamscape-Track-A: sA22-p14.dreamscape.com [209.217.202.78] X-Dreamscape-Track-B: Mon, 27 Mar 2000 15:09:22 -0500 (EST) Received: (from krentel@localhost) by dreamscape.com (8.9.3/8.9.3) id PAA02812; Mon, 27 Mar 2000 15:09:27 -0500 (EST) (envelope-from krentel) Date: Mon, 27 Mar 2000 15:09:27 -0500 (EST) From: "Mark W. Krentel" Message-Id: <200003272009.PAA02812@dreamscape.com> To: freebsd-fs@freebsd.org Subject: Re: ext2fs optional features Cc: kwc@world.std.com Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > Hmmm, which distribution/kernel version? For me, Red Hat 6.1 and kernel 2.2.12, but you'll get the same answer with Slackware 7. The key attributes are: Filesystem revision #: 1 (dynamic) Filesystem features: sparse_super You'll need a filesystem without sparse_super and probably revision 0. > Is there a way, perhaps in Linux with its tunefs, to adjust or > "turn off" those "optional features" (other things too?) in such > a way that FreeBSD's ext2 support will work? As a workaround, you can boot a Linux live filesystem or rescue disk and manually run mke2fs as: # mke2fs -r0 -s0 /dev/whatever Then reinstall Linux, telling it to NOT reformat the partitions. Of course, this will erase any data on the partition, so you'll have to either dump or tar the filesystem or else reinstall from scratch. I don't think you can turn off these features without remaking the partition. But I think the real answer to Kenneth's and my question is that Freebsd doesn't support these optional features and isn't likely to in the near future. Can anyone offer a more optimistic outlook? --Mark Krentel To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Tue Mar 28 6:24:28 2000 Delivered-To: freebsd-fs@freebsd.org Received: from europe.std.com (europe.std.com [199.172.62.20]) by hub.freebsd.org (Postfix) with ESMTP id 9E31637BEB8 for ; Tue, 28 Mar 2000 06:24:21 -0800 (PST) (envelope-from kwc@world.std.com) Received: from world.std.com (root@world-f.std.com [199.172.62.5]) by europe.std.com (8.9.3/8.9.3) with ESMTP id JAA00317; Tue, 28 Mar 2000 09:24:14 -0500 (EST) Received: (from kwc@localhost) by world.std.com (8.9.3/8.9.3) id JAA18752; Tue, 28 Mar 2000 09:20:55 -0500 (EST) Date: Tue, 28 Mar 2000 09:20:55 -0500 (EST) From: Kenneth W Cochran Message-Id: <200003281420.JAA18752@world.std.com> To: "Mark W. Krentel" Subject: Re: ext2fs optional features Cc: freebsd-fs@freebsd.org Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >From krentel@dreamscape.com Mon Mar 27 15:13:54 2000 >Date: Mon, 27 Mar 2000 15:09:27 -0500 (EST) >Subject: Re: ext2fs optional features > >> Hmmm, which distribution/kernel version? > >For me, Red Hat 6.1 and kernel 2.2.12, but you'll get the same >answer with Slackware 7. The key attributes are: > > Filesystem revision #: 1 (dynamic) > Filesystem features: sparse_super > >You'll need a filesystem without sparse_super and probably >revision 0. > >> Is there a way, perhaps in Linux with its tunefs, to adjust or >> "turn off" those "optional features" (other things too?) in such >> a way that FreeBSD's ext2 support will work? > >As a workaround, you can boot a Linux live filesystem or rescue >disk and manually run mke2fs as: > > # mke2fs -r0 -s0 /dev/whatever > >Then reinstall Linux, telling it to NOT reformat the partitions. >Of course, this will erase any data on the partition, so you'll >have to either dump or tar the filesystem or else reinstall from >scratch. I don't think you can turn off these features without >remaking the partition. > >But I think the real answer to Kenneth's and my question is that >Freebsd doesn't support these optional features and isn't likely to >in the near future. Can anyone offer a more optimistic outlook? > >--Mark Krentel This is an edited diff-list from "tune2fs -l" on 2 Linux ext2 filesystems I have; the "old" one works r/w with FreeBSD's ext2 support (I believe it was made with Slackware 4.0), the "new" one (made with Slackware 7.0) only works readonly. OSes are FreeBSD 3.4-stable, as of 2000/03/28 & Slackware Linux 7.0 with kernel 2.2.14. I deleted what appeared to be non-relevant things (inode counts, etc...) tune2fs 1.15, 18-Jul-1999 for EXT2 FS 0.5b, 95/08/09 4c4 < Filesystem UUID: --- > Filesystem UUID: 256642ba-cff5-11d3-949e-8f1d32744825 6,8c6,8 < Filesystem revision #: 0 (original) < Filesystem features: (none) < Filesystem state: clean --- > Filesystem revision #: 1 (dynamic) > Filesystem features: sparse_super > Filesystem state: not clean As Mark has mentioned, I'm guessing that the critical pieces are the Filesystem revision # & the Filesystem features. According to the Linux tune2fs manpage, the "features" (ie. sparse_super) can be toggled with tune2fs. (No, I have *not* tried it... Too afraid... :) No mention is made, though, of the revision #, so I'd bet that must be & is set at filesystem creation. :/ What I'm Looking For... A way to share data between dual-booting FreeBSD & Linux. So far, the best way I've found (YMMV :) is via FreeBSD's ext2 support. My experience with Linux's ufs support has been Very Very Bad. With Linux "migrating" toware its new "ext3" filesystem, it would seem to me that the most appropriate way for this kind of "sharing" would be to create a "buffer filesystem" as ext2 version 0 with no special features... And, of course, I would think this to make a good addition to FreeBSD FAQs & docs. :) -kc To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Wed Mar 29 14:50: 6 2000 Delivered-To: freebsd-fs@freebsd.org Received: from mail.webmonster.de (datasink.webmonster.de [194.162.162.209]) by hub.freebsd.org (Postfix) with SMTP id B596737B64C for ; Wed, 29 Mar 2000 14:49:57 -0800 (PST) (envelope-from karsten@rohrbach.de) Received: (qmail 25971 invoked by uid 1000); 29 Mar 2000 22:49:55 -0000 Date: Thu, 30 Mar 2000 00:49:55 +0200 From: "Karsten W. Rohrbach" To: Bruce Evans Cc: "Mark W. Krentel" , freebsd-fs@FreeBSD.ORG, kwc@world.std.com Subject: Re: ext2fs optional features Message-ID: <20000330004955.B24631@rohrbach.de> Reply-To: karsten@rohrbach.de References: <200003250310.WAA00537@dreamscape.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 1.0i In-Reply-To: ; from bde@zeta.org.au on Sat, Mar 25, 2000 at 09:27:28PM +1100 X-Arbitrary-Number-Of-The-Day: 42 X-Sender: karsten@rohrbach.de Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Bruce Evans(bde@zeta.org.au)@Sat, Mar 25, 2000 at 09:27:28PM +1100: > On Fri, 24 Mar 2000, Mark W. Krentel wrote: [...] > > > > What are the optional features? What does "sparse_super" do? > > They are extensions that modify the filesystem format. I don't know > exactly what "sparse_super" does. FreeBSD's ext2fs knows even less. > AFAIK sparse_super is just a different density of super block backups on your block device. in the old ext2fs version you had plenty of SB backup copies on your fs which leads to slow mounting, etc., if your run for example on a RAID which has a large fs on it so you got thousands of SB copies to check (and of course update if you modify the SB). i guess tytso revamped these structures a little bit to optimize the fs to news servers since you got large spool areas on them... support was added in the 2.1.x kernels and is told to be stable in 2.2.x. more information could be in the e2fsutils package -- there are some other optimizations as well, for example storing a mime-type with the file metadata (this was not used yet i think, but since there is webfs -- a http server in a nfs export vfs manner -- this option will become more important. > > Does Linux actually use these features, or are they for future use? > > Linux has supported the ext2fs "filetype" and "sparse_super" features > for several years. Otherwise, they wouldn't be the default for the > current version of mkfs.ext2fs. > > > Is it possible to support R/W mounts with these features? > > Everything is possible in software :-). > ...if there actually _are_ changelogs in place ;-) source code management is not one of linux's strong points... /k -- > knowledge is power. power corrupts. study hard, be evil http://www.webmonster.de http://www.apache.de http://www.splatterworld.de (NIC-HDL KR433/KR11-RIPE) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Wed Mar 29 14:52:44 2000 Delivered-To: freebsd-fs@freebsd.org Received: from mail.webmonster.de (datasink.webmonster.de [194.162.162.209]) by hub.freebsd.org (Postfix) with SMTP id E9F3337B68E for ; Wed, 29 Mar 2000 14:52:36 -0800 (PST) (envelope-from karsten@rohrbach.de) Received: (qmail 26072 invoked by uid 1000); 29 Mar 2000 22:52:32 -0000 Date: Thu, 30 Mar 2000 00:52:32 +0200 From: "Karsten W. Rohrbach" To: Kenneth W Cochran Cc: freebsd-fs@FreeBSD.ORG Subject: Re: ext2fs optional features Message-ID: <20000330005232.C24631@rohrbach.de> Reply-To: karsten@rohrbach.de References: <200003271235.HAA09498@world.std.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 1.0i In-Reply-To: <200003271235.HAA09498@world.std.com>; from kwc@world.std.com on Mon, Mar 27, 2000 at 07:35:36AM -0500 X-Arbitrary-Number-Of-The-Day: 42 X-Sender: karsten@rohrbach.de Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Kenneth W Cochran(kwc@world.std.com)@Mon, Mar 27, 2000 at 07:35:36AM -0500: [...] > > To Mark's questions I might add: > > (Most likely a Linux question...) > Is there a way, perhaps in Linux with its tunefs, to adjust or > "turn off" those "optional features" (other things too?) in such > a way that FreeBSD's ext2 support will work? at least if you mke2fs a filesystem by hand you can turn those options off, yes. > > In other words, what would be an "optimal filesystem config" in > Linux for FreeBSD's use? none, with freebsd's current ext2 implementation i would say here /k -- > If you don't understand or are scared by any of the above > ask your parents or an adult to help you. http://www.webmonster.de http://www.apache.de http://www.splatterworld.de (NIC-HDL KR433/KR11-RIPE) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Mar 31 2:58:10 2000 Delivered-To: freebsd-fs@freebsd.org Received: from lanturn.express.ru (lanturn.kmost.express.ru [212.24.37.109]) by hub.freebsd.org (Postfix) with ESMTP id 8123437B919 for ; Fri, 31 Mar 2000 02:58:00 -0800 (PST) (envelope-from vova@express.ru) Received: from vova (helo=localhost) by lanturn.express.ru with local-esmtp (Exim 3.11 #1) id 12az83-0003dU-00 for freebsd-fs@FreeBSD.ORG; Fri, 31 Mar 2000 14:58:15 +0400 Date: Fri, 31 Mar 2000 14:58:15 +0400 (MSD) From: vova@express.ru X-Sender: vova@lanturn.kmost.express.ru To: freebsd-fs@FreeBSD.ORG Subject: SCSI bus Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hi I have question about two SCSI controllers on one SCSI bus, I want to run following configuration: one FreeBSD with SCSI controler, with mounted disks in read/write mode, and another FreeBSD with SCSI controller on the same bus with mounted disks in read-only mode. So can two controllers correctly handle SCSI bus with FreeBSD drivers ? (I mean aic78* controllers) -- TSB Russian Express, Moscow Vladimir B. Grebenschikov, vova@express.ru To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Mar 31 11:57:47 2000 Delivered-To: freebsd-fs@freebsd.org Received: from mail.du.gtn.com (mail.du.gtn.com [194.77.9.57]) by hub.freebsd.org (Postfix) with ESMTP id 532C737BCFC for ; Fri, 31 Mar 2000 11:57:30 -0800 (PST) (envelope-from ticso@cicely8.cicely.de) Received: from mail.cicely.de (cicely.de [194.231.9.142]) by mail.du.gtn.com (8.9.3/8.9.3) with ESMTP id VAA14798; Fri, 31 Mar 2000 21:55:55 +0200 (MET DST) Received: from cicely8.cicely.de (cicely8.cicely.de [10.1.2.10]) by mail.cicely.de (8.9.3/8.9.0) with ESMTP id VAA19820; Fri, 31 Mar 2000 21:56:53 +0200 (CEST) Received: (from ticso@localhost) by cicely8.cicely.de (8.9.3/8.9.2) id VAA19976; Fri, 31 Mar 2000 21:57:57 +0200 (CEST) (envelope-from ticso) Date: Fri, 31 Mar 2000 21:57:56 +0200 From: Bernd Walter To: vova@express.ru Cc: freebsd-fs@FreeBSD.ORG Subject: Re: SCSI bus Message-ID: <20000331215756.A19890@cicely8.cicely.de> References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 1.0pre3i In-Reply-To: Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Fri, Mar 31, 2000 at 02:58:15PM +0400, vova@express.ru wrote: > > Hi > > I have question about two SCSI controllers on one SCSI bus, > > I want to run following configuration: one FreeBSD with SCSI controler, > with mounted disks in read/write mode, and another FreeBSD with SCSI > controller on the same bus with mounted disks in read-only mode. > > So can two controllers correctly handle SCSI bus with FreeBSD drivers ? > (I mean aic78* controllers) I don't expect this to work because the readonly side can't know when the incore informations outdates. The two controller side shouldn't be the problem - but I can't say for shure as I don't know the CAM system much and havn't tried. -- B.Walter COSMO-Project http://www.cosmo-project.de ticso@cicely.de Usergroup info@cosmo-project.de To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Mar 31 12: 2: 2 2000 Delivered-To: freebsd-fs@freebsd.org Received: from lanturn.express.ru (lanturn.kmost.express.ru [212.24.37.109]) by hub.freebsd.org (Postfix) with ESMTP id 2801437BAB4 for ; Fri, 31 Mar 2000 12:01:57 -0800 (PST) (envelope-from vova@express.ru) Received: from vova (helo=localhost) by lanturn.express.ru with local-esmtp (Exim 3.11 #1) id 12b7bs-0003sw-00; Sat, 01 Apr 2000 00:01:36 +0400 Date: Sat, 1 Apr 2000 00:01:36 +0400 (MSD) From: vova@express.ru X-Sender: vova@lanturn.kmost.express.ru To: Bernd Walter Cc: freebsd-fs@FreeBSD.ORG Subject: Re: SCSI bus In-Reply-To: <20000331215756.A19890@cicely8.cicely.de> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Fri, 31 Mar 2000, Bernd Walter wrote: > > I have question about two SCSI controllers on one SCSI bus, > > > > I want to run following configuration: one FreeBSD with SCSI controler, > > with mounted disks in read/write mode, and another FreeBSD with SCSI > > controller on the same bus with mounted disks in read-only mode. > > > > So can two controllers correctly handle SCSI bus with FreeBSD drivers ? > > (I mean aic78* controllers) > > I don't expect this to work because the readonly side can't know when the > incore informations outdates. Yes, it can be a problem, but may be this may be solved by disabling any cache on read-only side (or setting expire time in one sec) ? > The two controller side shouldn't be the problem - but I can't say for shure > as I don't know the CAM system much and havn't tried. > -- > B.Walter COSMO-Project http://www.cosmo-project.de > ticso@cicely.de Usergroup info@cosmo-project.de -- TSB Russian Express, Moscow Vladimir B. Grebenschikov, vova@express.ru To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sat Apr 1 17: 3:39 2000 Delivered-To: freebsd-fs@freebsd.org Received: from apollo.backplane.com (apollo.backplane.com [216.240.41.2]) by hub.freebsd.org (Postfix) with ESMTP id EFED437B5ED; Sat, 1 Apr 2000 17:03:34 -0800 (PST) (envelope-from dillon@apollo.backplane.com) Received: (from dillon@localhost) by apollo.backplane.com (8.9.3/8.9.1) id RAA43602; Sat, 1 Apr 2000 17:03:24 -0800 (PST) (envelope-from dillon) Date: Sat, 1 Apr 2000 17:03:24 -0800 (PST) From: Matthew Dillon Message-Id: <200004020103.RAA43602@apollo.backplane.com> To: Richard Wendland Cc: Paul Richards , Alfred Perlstein , Poul-Henning Kamp , current@FreeBSD.ORG, fs@FreeBSD.ORG Subject: Re: FreeBSD random I/O performance issues References: <200003221544.PAA08760@ns0.netcraft.com> Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I've committed an 80% fix for the random seek / write performance issue. The rest of the fix will come later when Kirk commits his shared-lock-buffer-cache idea. I've committed it into -current and will MFC it into -stable in a week if there aren't any problems. I do not intend to MFC it into 3.x. This should solve most of the random-I/O latency issues with read-after-write on buffers. Basically what had to be done was to continue to call the clustering code as before (so reallocblks still gets called), but only issue write_behind I/O if the writes are generally sequential. If the writes are random, even big writes, we do not issue write-behind I/O. -Matt To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message