From owner-freebsd-fs@FreeBSD.ORG Sun Jun 4 21:36:45 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id BEC5A16B2A6 for ; Sun, 4 Jun 2006 21:36:45 +0000 (UTC) (envelope-from hsoftdev17@gmail.com) Received: from wr-out-0506.google.com (wr-out-0506.google.com [64.233.184.237]) by mx1.FreeBSD.org (Postfix) with ESMTP id CE2C643D7C for ; Sun, 4 Jun 2006 21:36:43 +0000 (GMT) (envelope-from hsoftdev17@gmail.com) Received: by wr-out-0506.google.com with SMTP id i20so875198wra for ; Sun, 04 Jun 2006 14:36:41 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=IU1RQbCsYHoxejppaHgH1819EkO6NXqtFI99ek5ySFafB/31TWCFOZtGqE5uO3gPzL6kog0YE8abde1d4OYDYrHFOiykq6SSeAoYEnlIEeyXNdjQiOyU1InDzL80FJKVOSOvEWBabZfuKQsHnW1IAZJQD/TyqLD2zqfLs56x6oY= Received: by 10.54.79.7 with SMTP id c7mr4280244wrb; Sun, 04 Jun 2006 14:36:41 -0700 (PDT) Received: by 10.54.89.10 with HTTP; Sun, 4 Jun 2006 14:36:41 -0700 (PDT) Message-ID: <6845d25a0606041436j5f964aeeo7bc02b61b98b790a@mail.gmail.com> Date: Sun, 4 Jun 2006 17:36:41 -0400 From: "Dave Stephens" To: "freebsd-fs@freebsd.org" MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline Subject: capacity issue? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Jun 2006 21:36:48 -0000 OS Version: FreeBSD 6.1 It seems like the capacity of my drive is being reported incorrectly by df. I'm not sure if this is a specific issue with the SATA drive or controller in the server, but I figured I would ask around. There is only 1 physical drive in this server. SATA Drive -------------------------------------------------------------------------------- ad8: 286168MB at ata4-master SATA150 SATA Controllers -------------------------------------------------------------------------------- atapci1: port 0xeff0-0xeff7,0xefe4-0xefe7,0xefa8-0xefaf,0xefe0-0xefe3,0xef 90-0xef9f irq 17 at device 5.0 on pci0 ata2: on atapci1 ata3: on atapci1 atapci2: port 0xefa0-0xefa7,0xef8c-0xef8f,0xef80-0xef87,0xef88-0xef8b,0xe f60-0xef6f mem 0xfebfac00-0xfebfadff irq 17 at device 9.0 on pci0 ata4: on atapci2 ata5: on atapci2 Note that atapci1 is built onto the motherboard and doesn't seem to be supported by FreeBSD at this time (no HDDs can be found during install when they are attached to it.) Mounting (dmesg) -------------------------------------------------------------------------------------------- swapon: adding /dev/ad8s2b as swap device Starting file system checks: /dev/ad8s1a: FILE SYSTEM CLEAN; SKIPPING CHECKS /dev/ad8s1a: clean, 221765 free (2981 frags, 27348 blocks, 1.2% fragmentation) /dev/ad8s4d: FILE SYSTEM CLEAN; SKIPPING CHECKS /dev/ad8s4d: clean, 9668716 free (980 frags, 1208467 blocks, 0.0% fragmentation) /dev/ad8s4f: FILE SYSTEM CLEAN; SKIPPING CHECKS /dev/ad8s4f: clean, 51380314 free (18 frags, 6422537 blocks, 0.0% fragmentation) /dev/ad8s3d: FILE SYSTEM CLEAN; SKIPPING CHECKS /dev/ad8s3d: clean, 28290946 free (32938 frags, 3532251 blocks, 0.1% fragmentation) /dev/ad8s3e: FILE SYSTEM CLEAN; SKIPPING CHECKS /dev/ad8s3e: clean, 9904253 free (1589 frags, 1237833 blocks, 0.0% fragmentation) /dev/ad8s4e: FILE SYSTEM CLEAN; SKIPPING CHECKS /dev/ad8s4e: clean, 37032718 free (998 frags, 4628965 blocks, 0.0% fragmentation) output from df --------------------------------------------------------------------------------- Filesystem Size Used Avail Capacity Mounted on /dev/ad8s1a 494M 61M 394M 13% / devfs 1.0K 1.0K 0B 100% /dev /dev/ad8s4d 19G 497M 17G 3% /home /dev/ad8s4f 98G 1.4G 89G 2% /photo /dev/ad8s3d 57G 2.8G 49G 5% /usr /dev/ad8s3e 19G 46M 17G 0% /var /dev/ad8s4e 76G 5.0G 65G 7% /www last time i checked (just as examples) 98G - 1.4G is not 89G (/photo) 57G - 2.8G is not 49G (/usr) 76G - 5.0G is not 65G (/www) Can anyone tell me what's going on here? Dave From owner-freebsd-fs@FreeBSD.ORG Sun Jun 4 21:46:29 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 62BC016A97B for ; Sun, 4 Jun 2006 21:46:29 +0000 (UTC) (envelope-from maxim@macomnet.ru) Received: from mp2.macomnet.net (mp2.macomnet.net [195.128.64.6]) by mx1.FreeBSD.org (Postfix) with ESMTP id CCD1C43D45 for ; Sun, 4 Jun 2006 21:46:28 +0000 (GMT) (envelope-from maxim@macomnet.ru) Received: from localhost (localhost [127.0.0.1]) by mp2.macomnet.net (8.13.4/8.13.3) with ESMTP id k54LkQHl081687; Mon, 5 Jun 2006 01:46:26 +0400 (MSD) (envelope-from maxim@macomnet.ru) Date: Mon, 5 Jun 2006 01:46:26 +0400 (MSD) From: Maxim Konovalov To: Dave Stephens In-Reply-To: <6845d25a0606041436j5f964aeeo7bc02b61b98b790a@mail.gmail.com> Message-ID: <20060605014455.K81640@mp2.macomnet.net> References: <6845d25a0606041436j5f964aeeo7bc02b61b98b790a@mail.gmail.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: "freebsd-fs@freebsd.org" Subject: Re: capacity issue? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Jun 2006 21:46:29 -0000 [...] > output from df > --------------------------------------------------------------------------------- > Filesystem Size Used Avail Capacity Mounted on > /dev/ad8s1a 494M 61M 394M 13% / > devfs 1.0K 1.0K 0B 100% /dev > /dev/ad8s4d 19G 497M 17G 3% /home > /dev/ad8s4f 98G 1.4G 89G 2% /photo > /dev/ad8s3d 57G 2.8G 49G 5% /usr > /dev/ad8s3e 19G 46M 17G 0% /var > /dev/ad8s4e 76G 5.0G 65G 7% /www > > last time i checked (just as examples) > 98G - 1.4G is not 89G (/photo) > 57G - 2.8G is not 49G (/usr) > 76G - 5.0G is not 65G (/www) > > Can anyone tell me what's going on here? VeryFAQ. man tunefs, /-m -- Maxim Konovalov From owner-freebsd-fs@FreeBSD.ORG Sun Jun 4 21:49:35 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 18B3816A706 for ; Sun, 4 Jun 2006 21:49:34 +0000 (UTC) (envelope-from duane@dwpc.dwlabs.ca) Received: from smtpout.eastlink.ca (smtpout.eastlink.ca [24.222.0.30]) by mx1.FreeBSD.org (Postfix) with ESMTP id 449BD43D67 for ; Sun, 4 Jun 2006 21:49:30 +0000 (GMT) (envelope-from duane@dwpc.dwlabs.ca) Received: from ip03.eastlink.ca ([24.222.10.15]) by mta01.eastlink.ca (Sun Java System Messaging Server 6.2-4.03 (built Sep 22 2005)) with ESMTP id <0J0C00EF9V8Q0ZK0@mta01.eastlink.ca> for freebsd-fs@freebsd.org; Sun, 04 Jun 2006 18:48:26 -0300 (ADT) Received: from blk-224-199-230.eastlink.ca (HELO dwpc.dwlabs.ca) ([24.224.199.230]) by ip03.eastlink.ca with ESMTP; Sun, 04 Jun 2006 18:49:29 -0300 Received: from dwpc.dwlabs.ca (localhost [127.0.0.1]) by dwpc.dwlabs.ca (8.13.6/8.13.6) with ESMTP id k54LmgPK005020; Sun, 04 Jun 2006 18:48:42 -0300 (ADT envelope-from duane@dwpc.dwlabs.ca) Received: (from duane@localhost) by dwpc.dwlabs.ca (8.13.6/8.13.6/Submit) id k54Lmfpb005019; Sun, 04 Jun 2006 18:48:41 -0300 (ADT envelope-from duane) Date: Sun, 04 Jun 2006 18:48:41 -0300 From: Duane Whitty In-reply-to: <6845d25a0606041436j5f964aeeo7bc02b61b98b790a@mail.gmail.com> To: Dave Stephens Message-id: <20060604214841.GC960@dwpc.dwlabs.ca> MIME-version: 1.0 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT Content-disposition: inline X-BrightmailFiltered: true X-Brightmail-Tracker: AAAAAQAAA+k= References: <6845d25a0606041436j5f964aeeo7bc02b61b98b790a@mail.gmail.com> User-Agent: Mutt/1.4.2.1i Cc: freebsd-fs@freebsd.org Subject: Re: capacity issue? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Jun 2006 21:49:36 -0000 On Sun, Jun 04, 2006 at 05:36:41PM -0400, Dave Stephens wrote: > OS Version: FreeBSD 6.1 > > It seems like the capacity of my drive is being reported incorrectly > by df. I'm not sure if this is a specific issue with the SATA drive > or controller in the server, but I figured I would ask around. There > is only 1 physical drive in this server. > > SATA Drive > -------------------------------------------------------------------------------- > ad8: 286168MB at ata4-master SATA150 > > SATA Controllers > -------------------------------------------------------------------------------- > atapci1: port > 0xeff0-0xeff7,0xefe4-0xefe7,0xefa8-0xefaf,0xefe0-0xefe3,0xef > 90-0xef9f irq 17 at device 5.0 on pci0 > ata2: on atapci1 > ata3: on atapci1 > atapci2: port > 0xefa0-0xefa7,0xef8c-0xef8f,0xef80-0xef87,0xef88-0xef8b,0xe > f60-0xef6f mem 0xfebfac00-0xfebfadff irq 17 at device 9.0 on pci0 > ata4: on atapci2 > ata5: on atapci2 > > Note that atapci1 is built onto the motherboard and doesn't seem to be > supported by FreeBSD at this time (no HDDs can be found during install > when they are attached to it.) > > Mounting (dmesg) > -------------------------------------------------------------------------------------------- > swapon: adding /dev/ad8s2b as swap device > Starting file system checks: > /dev/ad8s1a: FILE SYSTEM CLEAN; SKIPPING CHECKS > /dev/ad8s1a: clean, 221765 free (2981 frags, 27348 blocks, 1.2% > fragmentation) > /dev/ad8s4d: FILE SYSTEM CLEAN; SKIPPING CHECKS > /dev/ad8s4d: clean, 9668716 free (980 frags, 1208467 blocks, 0.0% > fragmentation) > /dev/ad8s4f: FILE SYSTEM CLEAN; SKIPPING CHECKS > /dev/ad8s4f: clean, 51380314 free (18 frags, 6422537 blocks, 0.0% > fragmentation) > /dev/ad8s3d: FILE SYSTEM CLEAN; SKIPPING CHECKS > /dev/ad8s3d: clean, 28290946 free (32938 frags, 3532251 blocks, 0.1% > fragmentation) > /dev/ad8s3e: FILE SYSTEM CLEAN; SKIPPING CHECKS > /dev/ad8s3e: clean, 9904253 free (1589 frags, 1237833 blocks, 0.0% > fragmentation) > /dev/ad8s4e: FILE SYSTEM CLEAN; SKIPPING CHECKS > /dev/ad8s4e: clean, 37032718 free (998 frags, 4628965 blocks, 0.0% > fragmentation) > > output from df > --------------------------------------------------------------------------------- > Filesystem Size Used Avail Capacity Mounted on > /dev/ad8s1a 494M 61M 394M 13% / > devfs 1.0K 1.0K 0B 100% /dev > /dev/ad8s4d 19G 497M 17G 3% /home > /dev/ad8s4f 98G 1.4G 89G 2% /photo > /dev/ad8s3d 57G 2.8G 49G 5% /usr > /dev/ad8s3e 19G 46M 17G 0% /var > /dev/ad8s4e 76G 5.0G 65G 7% /www > > last time i checked (just as examples) > 98G - 1.4G is not 89G (/photo) > 57G - 2.8G is not 49G (/usr) > 76G - 5.0G is not 65G (/www) > > Can anyone tell me what's going on here? > > Dave > _______________________________________________ Hi, Avail = (Size - "elbow room") - Used The FFS algorithms need a little free space, about 5% I think, in order to function efficiently. This is also why you can df report a disk more than 100% used. Hth, Duane Whitty -- duane@dwlabs.ca From owner-freebsd-fs@FreeBSD.ORG Mon Jun 5 02:25:21 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id AAAEC16A512 for ; Mon, 5 Jun 2006 02:25:21 +0000 (UTC) (envelope-from anderson@centtech.com) Received: from mh2.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 54B7D43D46 for ; Mon, 5 Jun 2006 02:25:21 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [192.168.42.22] (andersonbox2.centtech.com [192.168.42.22]) by mh2.centtech.com (8.13.1/8.13.1) with ESMTP id k552PE9a069517; Sun, 4 Jun 2006 21:25:17 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <4483960F.5000102@centtech.com> Date: Sun, 04 Jun 2006 21:25:19 -0500 From: Eric Anderson User-Agent: Thunderbird 1.5.0.2 (X11/20060506) MIME-Version: 1.0 To: Duane Whitty References: <6845d25a0606041436j5f964aeeo7bc02b61b98b790a@mail.gmail.com> <20060604214841.GC960@dwpc.dwlabs.ca> In-Reply-To: <20060604214841.GC960@dwpc.dwlabs.ca> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.87.1/1512/Sun Jun 4 04:58:49 2006 on mh2.centtech.com X-Virus-Status: Clean Cc: freebsd-fs@freebsd.org, Dave Stephens Subject: Re: capacity issue? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Jun 2006 02:25:23 -0000 Duane Whitty wrote: > On Sun, Jun 04, 2006 at 05:36:41PM -0400, Dave Stephens wrote: >> OS Version: FreeBSD 6.1 >> >> It seems like the capacity of my drive is being reported incorrectly >> by df. I'm not sure if this is a specific issue with the SATA drive >> or controller in the server, but I figured I would ask around. There >> is only 1 physical drive in this server. >> >> SATA Drive >> -------------------------------------------------------------------------------- >> ad8: 286168MB at ata4-master SATA150 >> >> SATA Controllers >> -------------------------------------------------------------------------------- >> atapci1: port >> 0xeff0-0xeff7,0xefe4-0xefe7,0xefa8-0xefaf,0xefe0-0xefe3,0xef >> 90-0xef9f irq 17 at device 5.0 on pci0 >> ata2: on atapci1 >> ata3: on atapci1 >> atapci2: port >> 0xefa0-0xefa7,0xef8c-0xef8f,0xef80-0xef87,0xef88-0xef8b,0xe >> f60-0xef6f mem 0xfebfac00-0xfebfadff irq 17 at device 9.0 on pci0 >> ata4: on atapci2 >> ata5: on atapci2 >> >> Note that atapci1 is built onto the motherboard and doesn't seem to be >> supported by FreeBSD at this time (no HDDs can be found during install >> when they are attached to it.) >> >> Mounting (dmesg) >> -------------------------------------------------------------------------------------------- >> swapon: adding /dev/ad8s2b as swap device >> Starting file system checks: >> /dev/ad8s1a: FILE SYSTEM CLEAN; SKIPPING CHECKS >> /dev/ad8s1a: clean, 221765 free (2981 frags, 27348 blocks, 1.2% >> fragmentation) >> /dev/ad8s4d: FILE SYSTEM CLEAN; SKIPPING CHECKS >> /dev/ad8s4d: clean, 9668716 free (980 frags, 1208467 blocks, 0.0% >> fragmentation) >> /dev/ad8s4f: FILE SYSTEM CLEAN; SKIPPING CHECKS >> /dev/ad8s4f: clean, 51380314 free (18 frags, 6422537 blocks, 0.0% >> fragmentation) >> /dev/ad8s3d: FILE SYSTEM CLEAN; SKIPPING CHECKS >> /dev/ad8s3d: clean, 28290946 free (32938 frags, 3532251 blocks, 0.1% >> fragmentation) >> /dev/ad8s3e: FILE SYSTEM CLEAN; SKIPPING CHECKS >> /dev/ad8s3e: clean, 9904253 free (1589 frags, 1237833 blocks, 0.0% >> fragmentation) >> /dev/ad8s4e: FILE SYSTEM CLEAN; SKIPPING CHECKS >> /dev/ad8s4e: clean, 37032718 free (998 frags, 4628965 blocks, 0.0% >> fragmentation) >> >> output from df >> --------------------------------------------------------------------------------- >> Filesystem Size Used Avail Capacity Mounted on >> /dev/ad8s1a 494M 61M 394M 13% / >> devfs 1.0K 1.0K 0B 100% /dev >> /dev/ad8s4d 19G 497M 17G 3% /home >> /dev/ad8s4f 98G 1.4G 89G 2% /photo >> /dev/ad8s3d 57G 2.8G 49G 5% /usr >> /dev/ad8s3e 19G 46M 17G 0% /var >> /dev/ad8s4e 76G 5.0G 65G 7% /www >> >> last time i checked (just as examples) >> 98G - 1.4G is not 89G (/photo) >> 57G - 2.8G is not 49G (/usr) >> 76G - 5.0G is not 65G (/www) >> >> Can anyone tell me what's going on here? >> >> Dave >> _______________________________________________ > > Hi, > > Avail = (Size - "elbow room") - Used > > The FFS algorithms need a little free space, about 5% I think, > in order to function efficiently. This is also why you can > df report a disk more than 100% used. > > Hth, > > Duane Whitty Right, it's 8% unless specified otherwise. Root is the only user that can use the reserved 8%, but usage of that space causes fragmentation and a performance penalty. Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology Anything that works is better than anything that doesn't. ------------------------------------------------------------------------ From owner-freebsd-fs@FreeBSD.ORG Mon Jun 5 20:34:29 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 474AC16C676 for ; Mon, 5 Jun 2006 20:34:29 +0000 (UTC) (envelope-from bastiaanpu@welmers.net) Received: from smtp-vbr13.xs4all.nl (smtp-vbr13.xs4all.nl [194.109.24.33]) by mx1.FreeBSD.org (Postfix) with ESMTP id AA5C543D58 for ; Mon, 5 Jun 2006 20:34:27 +0000 (GMT) (envelope-from bastiaanpu@welmers.net) Received: from routeduvel.rembrandtkd.welmers.net (welmers.xs4all.nl [80.126.238.7]) by smtp-vbr13.xs4all.nl (8.13.6/8.13.6) with ESMTP id k55KYP7l008683 for ; Mon, 5 Jun 2006 22:34:26 +0200 (CEST) (envelope-from bastiaanpu@welmers.net) Received: by routeduvel.rembrandtkd.welmers.net (Postfix, from userid 1023) id C1C1814422; Mon, 5 Jun 2006 22:34:32 +0200 (CEST) Date: Mon, 5 Jun 2006 22:34:32 +0200 From: Bastiaan Welmers To: freebsd-fs@freebsd.org Message-ID: <20060605203432.GA21420@routeduvel.rembrandtkd.welmers.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.4.2.1i X-Disclaimer: running NetBSD X-Virus-Scanned: by XS4ALL Virus Scanner Subject: execution from unionfs issue X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Jun 2006 20:34:41 -0000 Hi, I was wondering the following behavior from a unionfs mounted tree was normal or a bug: When mounting a tree on a directory as lower layer and I execute a binary from the lower layer, it will create a non-executable copy of the binary file on the upper layer: # mkdir /tmp/bin # mount -t unionfs -o -b /bin /tmp/bin # cd /tmp/bin # ./ls -l .... -r-xr-xr-x 1 root wheel 24232 30 mei 04:06 ls # ./ls -l ./ls: Permission denied # /bin/ls -l .... -rw-r--r-- 1 root wheel 24232 5 jun 22:23 ls # cd / # umount /tmp/bin # ls -l /tmp/bin -rw-r--r-- 1 root wheel 24232 5 jun 22:23 ls using -b or not (inversing upper/lower layer or not) does not matter, without -b same problem (when mounting /tmp/bin on /bin this time). It look likes when executing files it will try to open it read-write or something (for updating access time?) and unionfs creates a new (non-executable) copy on the upper layer. I don't know this is desirable behavior or not in general, to me it isn't at least. (I use it to provide basic userland for jails) I found the "noatime" mount option helps to resolve the problem, but I can't find this in any documentation. I'm using FreeBSD 6.1-RELEASE i386 GENERIC. /Bastiaan From owner-freebsd-fs@FreeBSD.ORG Mon Jun 5 21:25:29 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 66D2516B116 for ; Mon, 5 Jun 2006 21:17:37 +0000 (UTC) (envelope-from saturnero@freesbie.org) Received: from out.alice.it (smtp-out01.alice.it [85.33.2.12]) by mx1.FreeBSD.org (Postfix) with ESMTP id AE19243D45 for ; Mon, 5 Jun 2006 21:17:33 +0000 (GMT) (envelope-from saturnero@freesbie.org) Received: from FBCMMO01.fbc.local ([192.168.68.195]) by out.alice.it with Microsoft SMTPSVC(6.0.3790.1830); Mon, 5 Jun 2006 23:17:33 +0200 Received: from client.alice.it ([192.168.68.142]) by FBCMMO01.fbc.local with Microsoft SMTPSVC(6.0.3790.1830); Mon, 5 Jun 2006 23:17:33 +0200 Received: from [192.168.99.16] ([87.5.150.129]) by client.alice.it with Microsoft SMTPSVC(6.0.3790.1830); Mon, 5 Jun 2006 23:17:33 +0200 Message-ID: <44849F67.8050509@freesbie.org> Date: Mon, 05 Jun 2006 23:17:27 +0200 From: Dario Freni User-Agent: Mozilla Thunderbird 1.5.0.4 (Macintosh/20060530) MIME-Version: 1.0 To: Bastiaan Welmers References: <20060605203432.GA21420@routeduvel.rembrandtkd.welmers.net> In-Reply-To: <20060605203432.GA21420@routeduvel.rembrandtkd.welmers.net> X-Enigmail-Version: 0.94.0.0 OpenPGP: url=http://www.saturnero.net/saturnero.asc Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enigAE4A4C46A876A718904D1433" X-OriginalArrivalTime: 05 Jun 2006 21:17:33.0795 (UTC) FILETIME=[76296330:01C688E5] Cc: freebsd-fs@freebsd.org Subject: Re: execution from unionfs issue X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Jun 2006 21:25:36 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enigAE4A4C46A876A718904D1433 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Bastiaan Welmers wrote: > I was wondering the following behavior from a unionfs mounted tree was > normal or a bug: > [...] > I'm using FreeBSD 6.1-RELEASE i386 GENERIC. >=20 Unionfs implementation on 6.x is actually really buggy. Try with daichi's patch: http://people.freebsd.org/~daichi/unionfs/ Latest patch for the 6.x is: http://people.freebsd.org/~daichi/unionfs/unionfs6-p13.diff Bye, --=20 Dario Freni (saturnero@freesbie.org) FreeSBIE project is looking for a new builder machine! Check http://www.freesbie.org/donations.html --------------enigAE4A4C46A876A718904D1433 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (Darwin) iD8DBQFEhJ9symi72IiShysRAm9YAKD1gi6egCVo8o3Sh0KD+N5CSSUwawCdEAwH CpEghrpGwqnqTD1eAUPIVXU= =tSVV -----END PGP SIGNATURE----- --------------enigAE4A4C46A876A718904D1433-- From owner-freebsd-fs@FreeBSD.ORG Tue Jun 6 01:14:01 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C8E2116ACC3 for ; Tue, 6 Jun 2006 00:32:39 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4197143D45 for ; Tue, 6 Jun 2006 00:32:36 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [192.168.254.14] (imini.samsco.home [192.168.254.14]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k560WUKn012263; Mon, 5 Jun 2006 18:32:35 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4484CE37.3060001@samsco.org> Date: Mon, 05 Jun 2006 18:37:11 -0600 From: Scott Long User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.7.7) Gecko/20050416 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Bastiaan Welmers References: <20060605203432.GA21420@routeduvel.rembrandtkd.welmers.net> In-Reply-To: <20060605203432.GA21420@routeduvel.rembrandtkd.welmers.net> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Status: No, score=-1.4 required=3.8 tests=ALL_TRUSTED autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: freebsd-fs@freebsd.org Subject: Re: execution from unionfs issue X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 06 Jun 2006 01:14:09 -0000 Bastiaan Welmers wrote: > Hi, > > I was wondering the following behavior from a unionfs mounted tree was > normal or a bug: > > When mounting a tree on a directory as lower layer and I execute a > binary from the lower layer, it will create a non-executable copy of the > binary file on the upper layer: > > # mkdir /tmp/bin > > # mount -t unionfs -o -b /bin /tmp/bin > > # cd /tmp/bin > > # ./ls -l > .... > -r-xr-xr-x 1 root wheel 24232 30 mei 04:06 ls > > # ./ls -l > ./ls: Permission denied > > # /bin/ls -l > .... > -rw-r--r-- 1 root wheel 24232 5 jun 22:23 ls > > # cd / > > # umount /tmp/bin > > # ls -l /tmp/bin > -rw-r--r-- 1 root wheel 24232 5 jun 22:23 ls > > using -b or not (inversing upper/lower layer or not) does not matter, > without -b same problem (when mounting /tmp/bin on /bin this time). > > It look likes when executing files it will try to open it read-write or > something (for updating access time?) and unionfs creates a new > (non-executable) copy on the upper layer. > I don't know this is desirable behavior or not in general, to me it > isn't at least. (I use it to provide basic userland for jails) I found > the "noatime" mount option helps to resolve the problem, but I can't find > this in any documentation. > > I'm using FreeBSD 6.1-RELEASE i386 GENERIC. > The copy is created in the upper so that the access time can be updated. This is intentional. The permission that the upper copy is created with is obviously wrong though. I would have thought that the copy node would have the same attributes and access properties of original node. Do try the new-and-improved unionfs patches that the sibling post refered to. If it still doesn't work, then I imagine that GOTO-san would be happy to help fix it. Scott From owner-freebsd-fs@FreeBSD.ORG Wed Jun 7 02:49:47 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E80C716B590 for ; Wed, 7 Jun 2006 02:40:35 +0000 (UTC) (envelope-from bde@zeta.org.au) Received: from mailout1.pacific.net.au (mailout1.pacific.net.au [61.8.0.84]) by mx1.FreeBSD.org (Postfix) with ESMTP id 55A3643D49 for ; Wed, 7 Jun 2006 02:40:35 +0000 (GMT) (envelope-from bde@zeta.org.au) Received: from mailproxy1.pacific.net.au (mailproxy1.pacific.net.au [61.8.0.86]) by mailout1.pacific.net.au (Postfix) with ESMTP id E955532913E; Wed, 7 Jun 2006 12:40:33 +1000 (EST) Received: from katana.zip.com.au (katana.zip.com.au [61.8.7.246]) by mailproxy1.pacific.net.au (8.13.4/8.13.4/Debian-3sarge1) with ESMTP id k572eORX022789; Wed, 7 Jun 2006 12:40:32 +1000 Date: Wed, 7 Jun 2006 12:40:24 +1000 (EST) From: Bruce Evans X-X-Sender: bde@delplex.bde.org To: Scott Long In-Reply-To: <4484CE37.3060001@samsco.org> Message-ID: <20060607122438.G4780@delplex.bde.org> References: <20060605203432.GA21420@routeduvel.rembrandtkd.welmers.net> <4484CE37.3060001@samsco.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-fs@freebsd.org Subject: Re: execution from unionfs issue X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 07 Jun 2006 02:49:52 -0000 On Mon, 5 Jun 2006, Scott Long wrote: > Bastiaan Welmers wrote: >> When mounting a tree on a directory as lower layer and I execute a >> binary from the lower layer, it will create a non-executable copy of the >> binary file on the upper layer: >> >> It look likes when executing files it will try to open it read-write or >> something (for updating access time?) and unionfs creates a new >> (non-executable) copy on the upper layer. I don't know this is desirable >> behavior or not in general, to me it >> isn't at least. (I use it to provide basic userland for jails) I found >> the "noatime" mount option helps to resolve the problem, but I can't find >> this in any documentation. > The copy is created in the upper so that the access time can be updated. > This is intentional. The permission that the upper copy is created with > is obviously wrong though. I would have thought that the copy node > would have the same attributes and access properties of original node. > Do try the new-and-improved unionfs patches that the sibling post > refered to. If it still doesn't work, then I imagine that GOTO-san > would be happy to help fix it. It's a bug for updating an access time on exec or read to create a copy of the file. Probably the file is read-only and, due to a bug, unionfs thinks that it needs a update to update the access time on exec. It would be obviously wrong to make a copy on read, but equally obviously wrong to not update the access time on read iff lower layers would do that. Exec doesn't require write access for updating the access time any more than read does (it just requires exec access corresponding to read requiring read access). Unionfs should pass all requests to update access to lower layers. Setting of access times on exec is supposed not to happen unless all levels of the file system support it (since for some file systems it would be a large pessimization, and some levels might just not support it). Bruce From owner-freebsd-fs@FreeBSD.ORG Thu Jun 8 18:17:09 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D5FE316EEDE for ; Thu, 8 Jun 2006 16:19:28 +0000 (UTC) (envelope-from gorgonite@freesurf.fr) Received: from smtp-out.freesurf.fr (messidor.freesurf.fr [212.43.206.29]) by mx1.FreeBSD.org (Postfix) with ESMTP id 771CE43D48 for ; Thu, 8 Jun 2006 16:19:26 +0000 (GMT) (envelope-from gorgonite@freesurf.fr) Received: from freesurf.fr (jose.freesurf.fr [212.43.206.13]) by smtp-out.freesurf.fr (Postfix) with SMTP id 13AD34C2CC for ; Thu, 8 Jun 2006 18:18:05 +0200 (CEST) Received: from 147.250.1.2 (proxying for unknown) (SquirrelMail authenticated user gorgonite) by jose.freesurf.fr with HTTP; Thu, 8 Jun 2006 18:18:02 +0200 (CEST) Message-ID: <33162.147.250.1.2.1149783482.squirrel@jose.freesurf.fr> Date: Thu, 8 Jun 2006 18:18:02 +0200 (CEST) From: "Gorgonite" To: X-Priority: 3 Importance: Normal X-MSMail-Priority: Normal X-Mailer: SquirrelMail (version 1.2.5) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Subject: [gvinum] add a disk in concat mode X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: gorgonite@freesurf.fr List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 08 Jun 2006 18:17:10 -0000 Hello, I run on FreeBSD v6.1 I have a disk with 300Go (/dev/ad0) in concat mode with gvinum (myvol.p0) I would like to add a disk of 200Go (/dev/ad2) on this volume, but without erasing my previous data (ad0) I executed this script Code: #! /bin/sh dd if=/dev/zero of=/dev/ad2 count=2 disklabel /dev/ad2 | disklabel -B -R -r ad2 /dev/stdin newsfs /dev/ad2c gvinum create gvinum.conf with this gvinum.conf Code: drive b device /dev/ad2c plex name myvol.p1 org concat vol myvol sd length 188358m drive b it seems to be okay for gvinum... and I wanted to update my "partition" Code: growfs -S "483g" /dev/gvinum/myvol but it failed with "grow is not growing..." Can anyone help me, please ? Thanks. ps: sorry for my bad english :'( From owner-freebsd-fs@FreeBSD.ORG Thu Jun 8 21:29:55 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 819B916A613; Thu, 8 Jun 2006 17:46:18 +0000 (UTC) (envelope-from mi+mx@aldan.algebra.com) Received: from aldan.algebra.com (aldan.algebra.com [216.254.65.224]) by mx1.FreeBSD.org (Postfix) with ESMTP id A849943D49; Thu, 8 Jun 2006 17:46:17 +0000 (GMT) (envelope-from mi+mx@aldan.algebra.com) Received: from corbulon.video-collage.com (static-151-204-231-237.bos.east.verizon.net [151.204.231.237]) by aldan.algebra.com (8.13.6/8.13.6) with ESMTP id k58HkGQo032468 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Thu, 8 Jun 2006 13:46:16 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) Received: from [172.21.130.86] (mx-broadway [38.98.68.18]) by corbulon.video-collage.com (8.13.6/8.13.6) with ESMTP id k58HkAG2033423 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Thu, 8 Jun 2006 13:46:10 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) From: Mikhail Teterin Organization: Virtual Estates, Inc. To: fs@freebsd.org, mckusick@freebsd.org Date: Thu, 8 Jun 2006 13:46:04 -0400 User-Agent: KMail/1.9.1 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200606081346.04908.mi+mx@aldan.algebra.com> X-Virus-Scanned: ClamAV 0.88/1520/Wed Jun 7 17:47:18 2006 on corbulon.video-collage.com X-Virus-Status: Clean X-Scanned-By: MIMEDefang 2.43 Cc: Subject: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 08 Jun 2006 21:29:55 -0000 Our amd64 6.1-STABLE system is used to collect backup dumps from production systems (mostly -- Solaris) via NFS. When in progrss, the dumps arrive at an average rate of 20Mb/s. Every once in a while I notice a discrepancy in the amount of used space on the backup FS as reported by df vs. that reported by the total du. Unmounting the FS and fsck-ing it fixes the problem with fsck reporting (despite the clean unmount): SUMMARY BLK COUNT(S) WRONG IN SUPERBLK SALVAGE? yes The FS is intended for very few very large files and was created with "newfs -b 65536 -O1" (no softupdates). This workaround (explicit fsck) is acceptable for us, but it is a sign of some kind of rot, and I thought, you'd like to know... Yours, -mi From owner-freebsd-fs@FreeBSD.ORG Thu Jun 8 21:54:09 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8FF9B16AB32 for ; Thu, 8 Jun 2006 21:54:09 +0000 (UTC) (envelope-from anderson@centtech.com) Received: from mh1.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id A230044A6F for ; Thu, 8 Jun 2006 19:34:42 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [10.177.171.220] (neutrino.centtech.com [10.177.171.220]) by mh1.centtech.com (8.13.1/8.13.1) with ESMTP id k58JYUrT031539; Thu, 8 Jun 2006 14:34:31 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <44887BCF.7020409@centtech.com> Date: Thu, 08 Jun 2006 14:34:39 -0500 From: Eric Anderson User-Agent: Thunderbird 1.5.0.2 (X11/20060506) MIME-Version: 1.0 To: gorgonite@freesurf.fr References: <33162.147.250.1.2.1149783482.squirrel@jose.freesurf.fr> In-Reply-To: <33162.147.250.1.2.1149783482.squirrel@jose.freesurf.fr> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.87.1/1522/Thu Jun 8 10:54:38 2006 on mh1.centtech.com X-Virus-Status: Clean Cc: freebsd-fs@freebsd.org Subject: Re: [gvinum] add a disk in concat mode X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 08 Jun 2006 21:54:09 -0000 Gorgonite wrote: > Hello, > > > I run on FreeBSD v6.1 > I have a disk with 300Go (/dev/ad0) in concat mode with gvinum (myvol.p0) > I would like to add a disk of 200Go (/dev/ad2) on this volume, but without > erasing my previous data (ad0) > > I executed this script > > Code: > #! /bin/sh dd if=/dev/zero of=/dev/ad2 count=2 disklabel /dev/ad2 | > disklabel -B -R -r ad2 /dev/stdin newsfs /dev/ad2c gvinum create gvinum.conf > > > with this gvinum.conf > > Code: > drive b device /dev/ad2c plex name myvol.p1 org concat vol myvol sd length > 188358m drive b > > > > it seems to be okay for gvinum... and I wanted to update my "partition" > > Code: > growfs -S "483g" /dev/gvinum/myvol > > > > but it failed with "grow is not growing..." > > > Can anyone help me, please ? > Thanks. > > > ps: sorry for my bad english :'( Did you unmount the filesystem? Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology Anything that works is better than anything that doesn't. ------------------------------------------------------------------------ From owner-freebsd-fs@FreeBSD.ORG Thu Jun 8 21:54:27 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 10E5516AB5E for ; Thu, 8 Jun 2006 21:54:27 +0000 (UTC) (envelope-from gorgonite@freesurf.fr) Received: from smtp-out.freesurf.fr (messidor.freesurf.fr [212.43.206.29]) by mx1.FreeBSD.org (Postfix) with ESMTP id 74E1443DD0 for ; Thu, 8 Jun 2006 21:53:19 +0000 (GMT) (envelope-from gorgonite@freesurf.fr) Received: from freesurf.fr (jose.freesurf.fr [212.43.206.13]) by smtp-out.freesurf.fr (Postfix) with SMTP id D89724CF16; Thu, 8 Jun 2006 22:51:45 +0200 (CEST) Received: from 82.67.244.132 (SquirrelMail authenticated user gorgonite) by jose.freesurf.fr with HTTP; Thu, 8 Jun 2006 22:51:42 +0200 (CEST) Message-ID: <2170.82.67.244.132.1149799902.squirrel@jose.freesurf.fr> Date: Thu, 8 Jun 2006 22:51:42 +0200 (CEST) From: "Gorgonite" To: X-Priority: 3 In-Reply-To: <44887BCF.7020409@centtech.com> References: <44887BCF.7020409@centtech.com> Importance: Normal X-MSMail-Priority: Normal X-Mailer: SquirrelMail (version 1.2.5) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Cc: freebsd-fs@freebsd.org Subject: Re: [gvinum] add a disk in concat mode X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: gorgonite@freesurf.fr List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 08 Jun 2006 21:54:27 -0000 > Gorgonite wrote: >> Hello, >> >> >> I run on FreeBSD v6.1 >> I have a disk with 300Go (/dev/ad0) in concat mode with gvinum >> (myvol.p0) I would like to add a disk of 200Go (/dev/ad2) on this >> volume, but without erasing my previous data (ad0) >> >> I executed this script >> >> Code: >> #! /bin/sh dd if=/dev/zero of=/dev/ad2 count=2 disklabel /dev/ad2 | >> disklabel -B -R -r ad2 /dev/stdin newsfs /dev/ad2c gvinum create >> gvinum.conf >> >> >> with this gvinum.conf >> >> Code: >> drive b device /dev/ad2c plex name myvol.p1 org concat vol myvol sd >> length 188358m drive b >> >> >> >> it seems to be okay for gvinum... and I wanted to update my >> "partition" >> >> Code: >> growfs -S "483g" /dev/gvinum/myvol >> >> >> >> but it failed with "grow is not growing..." >> >> >> Can anyone help me, please ? >> Thanks. >> >> >> ps: sorry for my bad english :'( > > > Did you unmount the filesystem? Yes, of course... Thanks for your fast answer ;) From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 01:04:07 2006 Return-Path: X-Original-To: FreeBSD-fs@FreeBSD.org Delivered-To: FreeBSD-fs@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 643DE16A474 for ; Fri, 9 Jun 2006 01:04:07 +0000 (UTC) (envelope-from trhodes@FreeBSD.org) Received: from pittgoth.com (ns1.pittgoth.com [216.38.206.188]) by mx1.FreeBSD.org (Postfix) with ESMTP id A351D43D7D for ; Fri, 9 Jun 2006 01:04:00 +0000 (GMT) (envelope-from trhodes@FreeBSD.org) Received: from localhost (net-ix.gw.ai.net [205.134.160.6] (may be forged)) (authenticated bits=0) by pittgoth.com (8.13.4/8.13.4) with ESMTP id k5915Epa037244 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NOT) for ; Thu, 8 Jun 2006 21:05:15 -0400 (EDT) (envelope-from trhodes@FreeBSD.org) Date: Thu, 8 Jun 2006 21:03:50 -0400 From: Tom Rhodes To: FreeBSD-fs@FreeBSD.org Message-Id: <20060608210350.47706f4e.trhodes@FreeBSD.org> X-Mailer: Sylpheed version 1.0.6 (GTK+ 1.2.10; i386-portbld-freebsd7.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Subject: Block based distributed file system X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 01:04:07 -0000 Hey, Just got hit with questions about "block based distributed file system solutions on BSD." Similar to NetBSD iSCSI or Redhat's GFS. Any ideas on how to do this on FreeBSD? Perhaps docs somewhere I can read? Thanks, -- Tom Rhodes From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 03:36:03 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5257116A473 for ; Fri, 9 Jun 2006 03:36:03 +0000 (UTC) (envelope-from hsoftdev17@gmail.com) Received: from nf-out-0910.google.com (nf-out-0910.google.com [64.233.182.189]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8D59243D8B for ; Fri, 9 Jun 2006 03:36:01 +0000 (GMT) (envelope-from hsoftdev17@gmail.com) Received: by nf-out-0910.google.com with SMTP id b2so502746nfe for ; Thu, 08 Jun 2006 20:35:58 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=rvB3VDfsm5ygmDaXf7ujJy98htylh5E1wN5+jhLQguWhIG7siIgxoWgUXJWK+FZmr83k32qtVSjg/DdZg6P4TtsHyM6tU5caiod58oDbx3dwgpu58oXaLwiDTb5BRiawPtCVSPwkc2O9xqZ9Pnp7Id9LXpz+n7MvXtnv1HqMuRE= Received: by 10.49.78.6 with SMTP id f6mr1994932nfl; Thu, 08 Jun 2006 20:35:58 -0700 (PDT) Received: by 10.49.58.18 with HTTP; Thu, 8 Jun 2006 20:35:58 -0700 (PDT) Message-ID: <6845d25a0606082035q527a8f6bx97a82fe0698fbf43@mail.gmail.com> Date: Thu, 8 Jun 2006 23:35:58 -0400 From: "Dave Stephens" To: freebsd-fs@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline Subject: SATA Error X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 03:36:03 -0000 OS Version: FreeBSD 6.1 What appears to be repeated failures keep occurring with the SATA drive or controller in my server. The error is a series of 3 repeated messages where the only difference appears to be the offset and the LBA. All of the hardware in this server is brand new and is not believed to be in faulty. If anyone could tell me what is going on with this, or if it is a known issue point me at how I might patch something or otherwise fix it. The server does not go down after the error, but the error is disconcerting none the less and leaves me worrying about hard drive data integrity. Sample Error Message...... -------------------------------------------------- g_vfs_done() : ad8s4e[WRITE(offset=59959787520, length=131072)]error=5 ad8: TIMEOUT - WRITE_DMA48 retrying (1 retry left) LBA=xxxxxxxxxxx ad8: FAILURE - WRITE_DMA48 status=51 error=10 LBA=xxxxxxxxxxx Here is some related info cut out of dmesg..... SATA Drive -------------------------------------------------------------------------------- ad8: 286168MB at ata4-master SATA150 SATA Controllers -------------------------------------------------------------------------------- atapci1: port 0xeff0-0xeff7,0xefe4-0xefe7,0xefa8-0xefaf,0xefe0-0xefe3,0xef 90-0xef9f irq 17 at device 5.0 on pci0 ata2: on atapci1 ata3: on atapci1 atapci2: port 0xefa0-0xefa7,0xef8c-0xef8f,0xef80-0xef87,0xef88-0xef8b,0xe f60-0xef6f mem 0xfebfac00-0xfebfadff irq 17 at device 9.0 on pci0 ata4: on atapci2 ata5: on atapci2 Note that atapci1 is built onto the motherboard and doesn't seem to be supported by FreeBSD at this time (no HDDs can be found during install when they are attached to it.) From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 06:56:57 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D831116A492 for ; Fri, 9 Jun 2006 06:56:57 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30313.mail.mud.yahoo.com (web30313.mail.mud.yahoo.com [68.142.201.231]) by mx1.FreeBSD.org (Postfix) with SMTP id 5ED7E43D70 for ; Fri, 9 Jun 2006 06:56:57 +0000 (GMT) (envelope-from arne_woerner@yahoo.com) Received: (qmail 31227 invoked by uid 60001); 9 Jun 2006 06:56:56 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:Received:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=2iFpv2Y0r8vLWxPp6Ak9B0obMIme2DTXOUaJh+GKis4IqiZRjL3SW/85Iz6U+W1+b+3TuqHBSEIi+aUlswdj0iIAs/mIikSBPZLhybFIiQ9aC/KIFdXtknRkHvxDXmywtjevOmyjaXzssVB5H1xwfmuKtE6EGorWXurlDAxwNQM= ; Message-ID: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> Received: from [213.54.74.233] by web30313.mail.mud.yahoo.com via HTTP; Thu, 08 Jun 2006 23:56:56 PDT Date: Thu, 8 Jun 2006 23:56:56 -0700 (PDT) From: "R. B. Riddick" To: Mikhail Teterin , fs@freebsd.org In-Reply-To: <200606081346.04908.mi+mx@aldan.algebra.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Cc: Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 06:56:57 -0000 --- Mikhail Teterin wrote: > Every once in a while I notice a discrepancy in the amount of used space on > the backup FS as reported by df vs. that reported by the total du. > I say, does that discrepancy persist, when you just wait some time? I would guess, that something has an open file descriptor on a deleted file, so that this file cannot be really deleted (it just disappears from the directory tree)... -Arne __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 07:18:51 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E9BF916A41B; Fri, 9 Jun 2006 07:18:51 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 541EA43D73; Fri, 9 Jun 2006 07:18:48 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [192.168.254.14] (imini.samsco.home [192.168.254.14]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k597IVpn036045; Fri, 9 Jun 2006 01:18:36 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4489226F.8070704@samsco.org> Date: Fri, 09 Jun 2006 01:25:35 -0600 From: Scott Long User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.7.7) Gecko/20050416 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Mikhail Teterin References: <200606081346.04908.mi+mx@aldan.algebra.com> In-Reply-To: <200606081346.04908.mi+mx@aldan.algebra.com> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Status: No, score=-1.4 required=3.8 tests=ALL_TRUSTED autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: fs@freebsd.org, mckusick@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 07:18:52 -0000 Mikhail Teterin wrote: > Our amd64 6.1-STABLE system is used to collect backup dumps from production > systems (mostly -- Solaris) via NFS. When in progrss, the dumps arrive at an > average rate of 20Mb/s. > > Every once in a while I notice a discrepancy in the amount of used space on > the backup FS as reported by df vs. that reported by the total du. > > Unmounting the FS and fsck-ing it fixes the problem with fsck reporting > (despite the clean unmount): > > SUMMARY BLK COUNT(S) WRONG IN SUPERBLK > SALVAGE? yes > > The FS is intended for very few very large files and was created > with "newfs -b 65536 -O1" (no softupdates). > > This workaround (explicit fsck) is acceptable for us, but it is a sign of some > kind of rot, and I thought, you'd like to know... > > Yours, > > -mi Due to delayed writes in NFS, I guess that it would be very possible for df and du to disagree at times; a file might get grown due to a setattr call over the wire (which would be reflected in du), but not actually grow to consume more disk blocks until the delayed writes get committed. In any case, it's very worrying that an unmount would not flush all of this and return the filesystem to consistency. Scott From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 08:14:14 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 08FD116A419 for ; Fri, 9 Jun 2006 08:14:14 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from fw.zoral.com.ua (ll-227.216.82.212.sovam.net.ua [212.82.216.227]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0553D43D79 for ; Fri, 9 Jun 2006 08:14:12 +0000 (GMT) (envelope-from kostikbel@gmail.com) Received: from deviant.kiev.zoral.com.ua (root@deviant.kiev.zoral.com.ua [10.1.1.148]) by fw.zoral.com.ua (8.13.4/8.13.4) with ESMTP id k598CfIL043645 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 9 Jun 2006 11:12:41 +0300 (EEST) (envelope-from kostikbel@gmail.com) Received: from deviant.kiev.zoral.com.ua (kostik@localhost [127.0.0.1]) by deviant.kiev.zoral.com.ua (8.13.6/8.13.6) with ESMTP id k598E0gj021927; Fri, 9 Jun 2006 11:14:00 +0300 (EEST) (envelope-from kostikbel@gmail.com) Received: (from kostik@localhost) by deviant.kiev.zoral.com.ua (8.13.6/8.13.6/Submit) id k598DxZ8021926; Fri, 9 Jun 2006 11:13:59 +0300 (EEST) (envelope-from kostikbel@gmail.com) X-Authentication-Warning: deviant.kiev.zoral.com.ua: kostik set sender to kostikbel@gmail.com using -f Date: Fri, 9 Jun 2006 11:13:59 +0300 From: Konstantin Belousov To: Mikhail Teterin Message-ID: <20060609081359.GH54415@deviant.kiev.zoral.com.ua> References: <200606081346.04908.mi+mx@aldan.algebra.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="WIIRZ1HQ6FgrlPgb" Content-Disposition: inline In-Reply-To: <200606081346.04908.mi+mx@aldan.algebra.com> User-Agent: Mutt/1.4.2.1i X-Virus-Scanned: ClamAV version 0.88.2, clamav-milter version 0.88.2 on fw.zoral.com.ua X-Virus-Status: Clean Cc: fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 08:14:14 -0000 --WIIRZ1HQ6FgrlPgb Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Thu, Jun 08, 2006 at 01:46:04PM -0400, Mikhail Teterin wrote: > Our amd64 6.1-STABLE system is used to collect backup dumps from producti= on=20 > systems (mostly -- Solaris) via NFS. When in progrss, the dumps arrive at= an=20 > average rate of 20Mb/s. >=20 > Every once in a while I notice a discrepancy in the amount of used space = on=20 > the backup FS as reported by df vs. that reported by the total du. >=20 > Unmounting the FS and fsck-ing it fixes the problem with fsck reporting= =20 > (despite the clean unmount): >=20 > SUMMARY BLK COUNT(S) WRONG IN SUPERBLK > SALVAGE? yes >=20 > The FS is intended for very few very large files and was created=20 > with "newfs -b 65536 -O1" (no softupdates). >=20 > This workaround (explicit fsck) is acceptable for us, but it is a sign of= some=20 > kind of rot, and I thought, you'd like to know... >=20 > Yours, >=20 > -mi Wild guess: try rev. 1.673 of the sys/kern/vfs_subr.c. --WIIRZ1HQ6FgrlPgb Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.3 (FreeBSD) iD8DBQFEiS3GC3+MBN1Mb4gRAn4NAKDOUaK171CGo8W458X0GrUgqzO1qgCfdJLC c5R3cNnLyJRu4jFqWOnxDkk= =Xq7v -----END PGP SIGNATURE----- --WIIRZ1HQ6FgrlPgb-- From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 10:22:01 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E688516A41F for ; Fri, 9 Jun 2006 10:22:01 +0000 (UTC) (envelope-from db@nipsi.de) Received: from mx.meta-spinner.de (mx.meta-spinner.de [213.39.242.178]) by mx1.FreeBSD.org (Postfix) with ESMTP id 72DFB43D79 for ; Fri, 9 Jun 2006 10:22:00 +0000 (GMT) (envelope-from db@nipsi.de) Received: from mx.meta-spinner.de (localhost [127.0.0.1]) by mx.meta-spinner.de (Postfix) with ESMTP id 638437E21A for ; Fri, 9 Jun 2006 12:21:59 +0200 (CEST) Received: from [192.168.1.101] (unknown [192.168.1.101]) by mx.meta-spinner.de (Postfix) with ESMTP id 0E2CD7E0F7 for ; Fri, 9 Jun 2006 12:21:58 +0200 (CEST) Message-ID: <44894C24.9040603@nipsi.de> Date: Fri, 09 Jun 2006 12:23:32 +0200 From: Dennis Berger User-Agent: Thunderbird 1.5.0.2 (X11/20060522) MIME-Version: 1.0 To: freebsd-fs@freebsd.org Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV using ClamSMTP Subject: xfs write support? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 10:22:02 -0000 from commitmessage today Log: Sync XFS for FreeBSD tree with newer changes from SGI XFS for Linux tree. Improve support for writing to XFS partitions. So improve support for writing means what? That there is actually support for it? I'm wondering maybe i missed something. Can I write to xfs partitions now? Nice to see some ongoing work ;-) regards, Dennis From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 10:53:42 2006 Return-Path: X-Original-To: freebsd-fs@FreeBSD.ORG Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9015616A418 for ; Fri, 9 Jun 2006 10:53:42 +0000 (UTC) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (lurza.secnetix.de [83.120.8.8]) by mx1.FreeBSD.org (Postfix) with ESMTP id DD2AF43D70 for ; Fri, 9 Jun 2006 10:53:41 +0000 (GMT) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (pahevu@localhost [127.0.0.1]) by lurza.secnetix.de (8.13.4/8.13.4) with ESMTP id k59ArZhb029627 for ; Fri, 9 Jun 2006 12:53:40 +0200 (CEST) (envelope-from oliver.fromme@secnetix.de) Received: (from olli@localhost) by lurza.secnetix.de (8.13.4/8.13.1/Submit) id k59ArYQs029626; Fri, 9 Jun 2006 12:53:34 +0200 (CEST) (envelope-from olli) Date: Fri, 9 Jun 2006 12:53:34 +0200 (CEST) Message-Id: <200606091053.k59ArYQs029626@lurza.secnetix.de> From: Oliver Fromme To: freebsd-fs@FreeBSD.ORG In-Reply-To: <200606081346.04908.mi+mx@aldan.algebra.com> X-Newsgroups: list.freebsd-fs User-Agent: tin/1.8.0-20051224 ("Ronay") (UNIX) (FreeBSD/4.11-STABLE (i386)) X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-2.1.2 (lurza.secnetix.de [127.0.0.1]); Fri, 09 Jun 2006 12:53:40 +0200 (CEST) Cc: Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: freebsd-fs@FreeBSD.ORG List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 10:53:42 -0000 Mikhail Teterin wrote: > The FS is intended for very few very large files and was created > with "newfs -b 65536 -O1" (no softupdates). Did you also increase the fragment size (-f option)? The default is 2048 bytes, and I wouldn't expect a b/f ratio of 32:1 to work very well. In fact I'm surprised that you have so little problems. :-) If you intend to have very few very large files that are accessed sequentially most of the time, it is probably better to set both block and fragment size to the same value (e.g. 16k), essentially disabling fragmentation. You should also reduce the inode density by specifying a larger bytes-per-inode value (-i option), a typical value would be 262144 (2^18). Carefully fiddling with the -g and -h options might also improve performance a bit, see newfs(8). Best regards Oliver -- Oliver Fromme, secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing Dienstleistungen mit Schwerpunkt FreeBSD: http://www.secnetix.de/bsd Any opinions expressed in this message may be personal to the author and may not necessarily reflect the opinions of secnetix in any way. PI: int f[9814],b,c=9814,g,i;long a=1e4,d,e,h; main(){for(;b=c,c-=14;i=printf("%04d",e+d/a),e=d%a) while(g=--b*2)d=h*b+a*(i?f[b]:a/5),h=d/--g,f[b]=d%g;} From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 12:10:10 2006 Return-Path: X-Original-To: FreeBSD-fs@freebsd.org Delivered-To: FreeBSD-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id F1E9416A418; Fri, 9 Jun 2006 12:10:09 +0000 (UTC) (envelope-from anderson@centtech.com) Received: from mh2.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7E4FD43D73; Fri, 9 Jun 2006 12:10:09 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [10.177.171.220] (neutrino.centtech.com [10.177.171.220]) by mh2.centtech.com (8.13.1/8.13.1) with ESMTP id k59CA8qK070572; Fri, 9 Jun 2006 07:10:08 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <44896526.7030303@centtech.com> Date: Fri, 09 Jun 2006 07:10:14 -0500 From: Eric Anderson User-Agent: Thunderbird 1.5.0.2 (X11/20060506) MIME-Version: 1.0 To: Tom Rhodes References: <20060608210350.47706f4e.trhodes@FreeBSD.org> In-Reply-To: <20060608210350.47706f4e.trhodes@FreeBSD.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.87.1/1523/Fri Jun 9 02:10:10 2006 on mh2.centtech.com X-Virus-Status: Clean Cc: FreeBSD-fs@freebsd.org Subject: Re: Block based distributed file system X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 12:10:10 -0000 Tom Rhodes wrote: > Hey, > > Just got hit with questions about "block based distributed file > system solutions on BSD." Similar to NetBSD iSCSI or Redhat's > GFS. Any ideas on how to do this on FreeBSD? Perhaps docs > somewhere I can read? Thanks, > I'm not sure whether you're looking for a network block device, or a distributed file system, but there are a few options: iscsi for freebsd (very new, patches floating), ggate (geom gate - share a geom device over the net), and nbd serving from FreeBSD. As far as a distributed file system for FreeBSD, the only real options are NFS, coda, afs, and Ivan Voras' tdfs (runs under Fuse, probably lightly tested). There is no cluster file system for FreeBSD (this makes me very sad), and I've tried at length to gather people to build or port one. What are your needs? Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology Anything that works is better than anything that doesn't. ------------------------------------------------------------------------ From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 12:11:56 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1F8C516A474 for ; Fri, 9 Jun 2006 12:11:56 +0000 (UTC) (envelope-from anderson@centtech.com) Received: from mh2.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0363F43D90 for ; Fri, 9 Jun 2006 12:11:47 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [10.177.171.220] (neutrino.centtech.com [10.177.171.220]) by mh2.centtech.com (8.13.1/8.13.1) with ESMTP id k59CBlAK070841; Fri, 9 Jun 2006 07:11:47 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <4489658C.9090609@centtech.com> Date: Fri, 09 Jun 2006 07:11:56 -0500 From: Eric Anderson User-Agent: Thunderbird 1.5.0.2 (X11/20060506) MIME-Version: 1.0 To: Dave Stephens References: <6845d25a0606082035q527a8f6bx97a82fe0698fbf43@mail.gmail.com> In-Reply-To: <6845d25a0606082035q527a8f6bx97a82fe0698fbf43@mail.gmail.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.87.1/1523/Fri Jun 9 02:10:10 2006 on mh2.centtech.com X-Virus-Status: Clean Cc: freebsd-fs@freebsd.org Subject: Re: SATA Error X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 12:11:56 -0000 Dave Stephens wrote: > OS Version: FreeBSD 6.1 > > What appears to be repeated failures keep occurring with the SATA > drive or controller in my server. The error is a series of 3 > repeated messages where the only difference appears to be the offset > and the LBA. All of the hardware in this server is brand new and is > not believed to be in faulty. If anyone could tell me what is going > on with this, or if it is a known issue point me at how I might patch > something or otherwise fix it. The server does not go down after the > error, but the error is disconcerting none the less and leaves me > worrying about hard drive data integrity. > > Sample Error Message...... > -------------------------------------------------- > > g_vfs_done() : ad8s4e[WRITE(offset=59959787520, length=131072)]error=5 > ad8: TIMEOUT - WRITE_DMA48 retrying (1 retry left) LBA=xxxxxxxxxxx > ad8: FAILURE - WRITE_DMA48 status=51 error=10 > LBA=xxxxxxxxxxx > > > Here is some related info cut out of dmesg..... > > SATA Drive > -------------------------------------------------------------------------------- > > ad8: 286168MB at ata4-master SATA150 > > SATA Controllers > -------------------------------------------------------------------------------- > > atapci1: port > 0xeff0-0xeff7,0xefe4-0xefe7,0xefa8-0xefaf,0xefe0-0xefe3,0xef > 90-0xef9f irq 17 at device 5.0 on pci0 > ata2: on atapci1 > ata3: on atapci1 > atapci2: port > 0xefa0-0xefa7,0xef8c-0xef8f,0xef80-0xef87,0xef88-0xef8b,0xe > f60-0xef6f mem 0xfebfac00-0xfebfadff irq 17 at device 9.0 on pci0 > ata4: on atapci2 > ata5: on atapci2 > > Note that atapci1 is built onto the motherboard and doesn't seem to be > supported by FreeBSD at this time (no HDDs can be found during install > when they are attached to it.) This doesn't look like a filesystem problem at all - it looks more like either a disk problem, or an ATA issue. My money goes to a drive issue (after all, it *is* ATA :)). Can you try a different drive? Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology Anything that works is better than anything that doesn't. ------------------------------------------------------------------------ From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 12:27:55 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D96D716A41A for ; Fri, 9 Jun 2006 12:27:55 +0000 (UTC) (envelope-from anderson@centtech.com) Received: from mh1.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5CA5643D93 for ; Fri, 9 Jun 2006 12:27:51 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [10.177.171.220] (neutrino.centtech.com [10.177.171.220]) by mh1.centtech.com (8.13.1/8.13.1) with ESMTP id k59CRog6091369 for ; Fri, 9 Jun 2006 07:27:51 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <4489694F.1050503@centtech.com> Date: Fri, 09 Jun 2006 07:27:59 -0500 From: Eric Anderson User-Agent: Thunderbird 1.5.0.2 (X11/20060506) MIME-Version: 1.0 To: freebsd-fs@freebsd.org References: <200606091053.k59ArYQs029626@lurza.secnetix.de> In-Reply-To: <200606091053.k59ArYQs029626@lurza.secnetix.de> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.87.1/1523/Fri Jun 9 02:10:10 2006 on mh1.centtech.com X-Virus-Status: Clean Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 12:27:55 -0000 Oliver Fromme wrote: > Mikhail Teterin wrote: > > The FS is intended for very few very large files and was created > > with "newfs -b 65536 -O1" (no softupdates). > > Did you also increase the fragment size (-f option)? > The default is 2048 bytes, and I wouldn't expect a b/f > ratio of 32:1 to work very well. In fact I'm surprised > that you have so little problems. :-) > > If you intend to have very few very large files that are > accessed sequentially most of the time, it is probably > better to set both block and fragment size to the same > value (e.g. 16k), essentially disabling fragmentation. > You should also reduce the inode density by specifying > a larger bytes-per-inode value (-i option), a typical > value would be 262144 (2^18). > > Carefully fiddling with the -g and -h options might also > improve performance a bit, see newfs(8). He should also use UFS2, and disable softupdates (if he really doesn't want them). No reason I can think of to use UFS1, but that doesn't mean there isn't a bug lurking in UFS1. Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology Anything that works is better than anything that doesn't. ------------------------------------------------------------------------ From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 13:04:22 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 019AA16A418 for ; Fri, 9 Jun 2006 13:04:22 +0000 (UTC) (envelope-from hsoftdev17@gmail.com) Received: from nf-out-0910.google.com (nf-out-0910.google.com [64.233.182.186]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2C5BD43D73 for ; Fri, 9 Jun 2006 13:04:20 +0000 (GMT) (envelope-from hsoftdev17@gmail.com) Received: by nf-out-0910.google.com with SMTP id l23so565940nfc for ; Fri, 09 Jun 2006 06:04:20 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=oLdEArCZnfJjYoPSlExhYn13uNvqTEnpbIjlHpxKwzhCV1gX+2VQFu63S1aonyrSIM3ycmO5tj4DrMaw9xSqmeF0O32guPrZ38uw/BYdPwaJVxJVwauf1pMvAA+wFG/KCKLW98fFjTjwOuCaEscUL/0IBNdqAzxlR3l/CPxgzbU= Received: by 10.48.255.20 with SMTP id c20mr1893468nfi; Fri, 09 Jun 2006 06:04:18 -0700 (PDT) Received: by 10.49.58.18 with HTTP; Fri, 9 Jun 2006 06:04:18 -0700 (PDT) Message-ID: <6845d25a0606090604g546a47f9h361085e6077c2bca@mail.gmail.com> Date: Fri, 9 Jun 2006 09:04:18 -0400 From: "Dave Stephens" To: freebsd-fs@freebsd.org In-Reply-To: <4489658C.9090609@centtech.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <6845d25a0606082035q527a8f6bx97a82fe0698fbf43@mail.gmail.com> <4489658C.9090609@centtech.com> Subject: Re: SATA Error X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 13:04:22 -0000 The drive is literally brand new, and unfortunatately it's the only SATA drive in my collection. I'm not ruling out DOA on the drive, but everything involving formatting it, installing onto it, etc., seemed to work with no issues at all. I bring this up mostly because I realize that the SATA driver is reasonably new and may still have bugs. Someone far more advanced than me would have to verify whether or not it is a bug at all and/or fix any bugs in that driver. The best I can do to help is offer any requested info and mention the problem I'm having. :) Dave On 6/9/06, Eric Anderson wrote: > Dave Stephens wrote: > > OS Version: FreeBSD 6.1 > > > > What appears to be repeated failures keep occurring with the SATA > > drive or controller in my server. The error is a series of 3 > > repeated messages where the only difference appears to be the offset > > and the LBA. All of the hardware in this server is brand new and is > > not believed to be in faulty. If anyone could tell me what is going > > on with this, or if it is a known issue point me at how I might patch > > something or otherwise fix it. The server does not go down after the > > error, but the error is disconcerting none the less and leaves me > > worrying about hard drive data integrity. > > > > Sample Error Message...... > > -------------------------------------------------- > > > > g_vfs_done() : ad8s4e[WRITE(offset=59959787520, length=131072)]error=5 > > ad8: TIMEOUT - WRITE_DMA48 retrying (1 retry left) LBA=xxxxxxxxxxx > > ad8: FAILURE - WRITE_DMA48 status=51 error=10 > > LBA=xxxxxxxxxxx > > > > > > Here is some related info cut out of dmesg..... > > > > SATA Drive > > -------------------------------------------------------------------------------- > > > > ad8: 286168MB at ata4-master SATA150 > > > > SATA Controllers > > -------------------------------------------------------------------------------- > > > > atapci1: port > > 0xeff0-0xeff7,0xefe4-0xefe7,0xefa8-0xefaf,0xefe0-0xefe3,0xef > > 90-0xef9f irq 17 at device 5.0 on pci0 > > ata2: on atapci1 > > ata3: on atapci1 > > atapci2: port > > 0xefa0-0xefa7,0xef8c-0xef8f,0xef80-0xef87,0xef88-0xef8b,0xe > > f60-0xef6f mem 0xfebfac00-0xfebfadff irq 17 at device 9.0 on pci0 > > ata4: on atapci2 > > ata5: on atapci2 > > > > Note that atapci1 is built onto the motherboard and doesn't seem to be > > supported by FreeBSD at this time (no HDDs can be found during install > > when they are attached to it.) > > This doesn't look like a filesystem problem at all - it looks more like > either a disk problem, or an ATA issue. My money goes to a drive issue > (after all, it *is* ATA :)). > > > Can you try a different drive? > > Eric > > > > > -- > ------------------------------------------------------------------------ > Eric Anderson Sr. Systems Administrator Centaur Technology > Anything that works is better than anything that doesn't. > ------------------------------------------------------------------------ > From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 13:18:55 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4619816A41A for ; Fri, 9 Jun 2006 13:18:55 +0000 (UTC) (envelope-from kabaev@gmail.com) Received: from nz-out-0102.google.com (nz-out-0102.google.com [64.233.162.205]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8046943D77 for ; Fri, 9 Jun 2006 13:18:54 +0000 (GMT) (envelope-from kabaev@gmail.com) Received: by nz-out-0102.google.com with SMTP id 9so791424nzo for ; Fri, 09 Jun 2006 06:18:54 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:date:from:to:cc:subject:message-id:in-reply-to:references:x-mailer:mime-version:content-type; b=SBSFp/nPOUFAFjZQfg7EGr5mJtAQ8GY/DX7FiwIobDeCMRV1SzhX+LldFU7VEJcFZZP/9YIzvEYf2wpML2IhBerSIi57UAQnz94CR8FPgfhSwgKuZQR61U+++mQzygHpx9KMucfVOey4TeR5xEcBQ6ikJ4kXZu5p6mqhj/umNNw= Received: by 10.65.51.13 with SMTP id d13mr2960633qbk; Fri, 09 Jun 2006 06:18:54 -0700 (PDT) Received: from kan.dnsalias.net ( [24.63.93.195]) by mx.gmail.com with ESMTP id 1sm1322980qbh.2006.06.09.06.18.53; Fri, 09 Jun 2006 06:18:53 -0700 (PDT) Date: Fri, 9 Jun 2006 09:18:52 -0400 From: Alexander Kabaev To: Dennis Berger Message-ID: <20060609091852.01816294@kan.dnsalias.net> In-Reply-To: <44894C24.9040603@nipsi.de> References: <44894C24.9040603@nipsi.de> X-Mailer: Sylpheed-Claws 2.2.0 (GTK+ 2.8.17; i386-portbld-freebsd7.0) Mime-Version: 1.0 Content-Type: multipart/signed; boundary=Sig_YgXMmGeXVFKEWfssK.1wy1Y; protocol="application/pgp-signature"; micalg=PGP-SHA1 Cc: freebsd-fs@freebsd.org Subject: Re: xfs write support? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 13:18:55 -0000 --Sig_YgXMmGeXVFKEWfssK.1wy1Y Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable On Fri, 09 Jun 2006 12:23:32 +0200 Dennis Berger wrote: > from commitmessage today >=20 > Log: > Sync XFS for FreeBSD tree with newer changes from SGI XFS for Linux > tree. Improve support for writing to XFS partitions. > =20 >=20 >=20 > So improve support for writing means what? That there is actually=20 > support for it? > I'm wondering maybe i missed something. Can I write to xfs partitions > now? >=20 > Nice to see some ongoing work ;-) >=20 > regards, > Dennis > _______________________________________________ > freebsd-fs@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-fs > To unsubscribe, send any mail to "freebsd-fs-unsubscribe@freebsd.org" It is a work in progress. --=20 Alexander Kabaev --Sig_YgXMmGeXVFKEWfssK.1wy1Y Content-Type: application/pgp-signature; name=signature.asc Content-Disposition: attachment; filename=signature.asc -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.3 (FreeBSD) iD8DBQFEiXU8Q6z1jMm+XZYRAtw4AKDVYqu7thC7/NEqNn4V4XvA/ayLtgCfbcoC BeQ/4wglbS6Isja965LhE3c= =POZJ -----END PGP SIGNATURE----- --Sig_YgXMmGeXVFKEWfssK.1wy1Y-- From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 13:24:08 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 0C09D16A419 for ; Fri, 9 Jun 2006 13:24:08 +0000 (UTC) (envelope-from zanecb@midwest-connections.com) Received: from mail.midwest-connections.com (mail.midwest-connections.com [69.148.152.10]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1F07443D8B for ; Fri, 9 Jun 2006 13:24:04 +0000 (GMT) (envelope-from zanecb@midwest-connections.com) Received: (qmail 23704 invoked by uid 503); 9 Jun 2006 13:26:34 -0000 Received: from unknown (HELO zerda) (zanecb@69.155.32.130) by 0 with ESMTPA; 9 Jun 2006 13:26:34 -0000 Date: Fri, 9 Jun 2006 08:29:08 -0500 From: "Zane C.B." To: "Dave Stephens" Message-ID: <20060609082908.3f61a0c1@zerda> In-Reply-To: <6845d25a0606082035q527a8f6bx97a82fe0698fbf43@mail.gmail.com> References: <6845d25a0606082035q527a8f6bx97a82fe0698fbf43@mail.gmail.com> Organization: Midwest Connections Inc. X-Mailer: Sylpheed-Claws 2.2.0 (GTK+ 2.8.18; i386-portbld-freebsd6.1) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org Subject: Re: SATA Error X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 13:24:08 -0000 On Thu, 8 Jun 2006 23:35:58 -0400 "Dave Stephens" wrote: > OS Version: FreeBSD 6.1 > > What appears to be repeated failures keep occurring with the SATA > drive or controller in my server. The error is a series of 3 > repeated messages where the only difference appears to be the offset > and the LBA. All of the hardware in this server is brand new and is > not believed to be in faulty. If anyone could tell me what is going > on with this, or if it is a known issue point me at how I might patch > something or otherwise fix it. The server does not go down after the > error, but the error is disconcerting none the less and leaves me > worrying about hard drive data integrity. > > Sample Error Message...... > -------------------------------------------------- > > g_vfs_done() : ad8s4e[WRITE(offset=59959787520, length=131072)]error=5 > ad8: TIMEOUT - WRITE_DMA48 retrying (1 retry left) LBA=xxxxxxxxxxx > ad8: FAILURE - WRITE_DMA48 status=51 error=10 > LBA=xxxxxxxxxxx > > > Here is some related info cut out of dmesg..... > > SATA Drive > -------------------------------------------------------------------------------- > ad8: 286168MB at ata4-master SATA150 > > SATA Controllers > -------------------------------------------------------------------------------- > atapci1: port > 0xeff0-0xeff7,0xefe4-0xefe7,0xefa8-0xefaf,0xefe0-0xefe3,0xef > 90-0xef9f irq 17 at device 5.0 on pci0 > ata2: on atapci1 > ata3: on atapci1 > atapci2: port > 0xefa0-0xefa7,0xef8c-0xef8f,0xef80-0xef87,0xef88-0xef8b,0xe > f60-0xef6f mem 0xfebfac00-0xfebfadff irq 17 at device 9.0 on pci0 > ata4: on atapci2 > ata5: on atapci2 > > Note that atapci1 is built onto the motherboard and doesn't seem to be > supported by FreeBSD at this time (no HDDs can be found during install > when they are attached to it.) The SiI 3112 is very flaky. I suggest going with a highpoint. I do not know about the SiS chip there. From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 14:51:38 2006 Return-Path: X-Original-To: freebsd-fs@FreeBSD.ORG Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4D7EF16A418 for ; Fri, 9 Jun 2006 14:51:38 +0000 (UTC) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (lurza.secnetix.de [83.120.8.8]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3CE7D43D95 for ; Fri, 9 Jun 2006 14:51:37 +0000 (GMT) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (yjsbap@localhost [127.0.0.1]) by lurza.secnetix.de (8.13.4/8.13.4) with ESMTP id k59EpQE0039644 for ; Fri, 9 Jun 2006 16:51:32 +0200 (CEST) (envelope-from oliver.fromme@secnetix.de) Received: (from olli@localhost) by lurza.secnetix.de (8.13.4/8.13.1/Submit) id k59EpQnt039643; Fri, 9 Jun 2006 16:51:26 +0200 (CEST) (envelope-from olli) Date: Fri, 9 Jun 2006 16:51:26 +0200 (CEST) Message-Id: <200606091451.k59EpQnt039643@lurza.secnetix.de> From: Oliver Fromme To: freebsd-fs@FreeBSD.ORG In-Reply-To: <4489694F.1050503@centtech.com> X-Newsgroups: list.freebsd-fs User-Agent: tin/1.8.0-20051224 ("Ronay") (UNIX) (FreeBSD/4.11-STABLE (i386)) X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-2.1.2 (lurza.secnetix.de [127.0.0.1]); Fri, 09 Jun 2006 16:51:32 +0200 (CEST) Cc: Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: freebsd-fs@FreeBSD.ORG List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 14:51:38 -0000 Eric Anderson wrote: > He should also use UFS2, and disable softupdates (if he really doesn't > want them). He already mentioned that he didn't enable soft-updates. > No reason I can think of to use UFS1, but that doesn't mean > there isn't a bug lurking in UFS1. If he doesn't need UFS2 features, using UFS1 will save some space, because inode data is smaller in UFS1 (128 vs. 256 bytes per inode). However, that really doesn't matter much if he reduces the inode density as I recommended. On a 300 GB file system using the default newfs parameters, you have about 36 million inodes. So using UFS1 will save about 4500 MB of space (vs. UFS2). However, with an inode density of 2^18 there are only 1 million inodes, so UFS1 makes only a difference of 136 MB. Best regards Oliver -- Oliver Fromme, secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing Dienstleistungen mit Schwerpunkt FreeBSD: http://www.secnetix.de/bsd Any opinions expressed in this message may be personal to the author and may not necessarily reflect the opinions of secnetix in any way. "To this day, many C programmers believe that 'strong typing' just means pounding extra hard on the keyboard." -- Peter van der Linden From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 15:02:31 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 34BDF16A419 for ; Fri, 9 Jun 2006 15:02:31 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9EA8C43D73 for ; Fri, 9 Jun 2006 15:02:28 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [192.168.254.14] (imini.samsco.home [192.168.254.14]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k59F2LGV038571 for ; Fri, 9 Jun 2006 09:02:26 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <44898F33.3000304@samsco.org> Date: Fri, 09 Jun 2006 09:09:39 -0600 From: Scott Long User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.7.7) Gecko/20050416 X-Accept-Language: en-us, en MIME-Version: 1.0 To: freebsd-fs@freebsd.org References: <200606091053.k59ArYQs029626@lurza.secnetix.de> In-Reply-To: <200606091053.k59ArYQs029626@lurza.secnetix.de> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Status: No, score=-1.4 required=3.8 tests=ALL_TRUSTED autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 15:02:31 -0000 Oliver Fromme wrote: > Mikhail Teterin wrote: > > The FS is intended for very few very large files and was created > > with "newfs -b 65536 -O1" (no softupdates). > > Did you also increase the fragment size (-f option)? > The default is 2048 bytes, and I wouldn't expect a b/f > ratio of 32:1 to work very well. In fact I'm surprised > that you have so little problems. :-) > Oh shoot, I didn't even notice this part of his posting. Yes, anything more than an 8:1 ratio simply will not work. I don't recall if newfs is smart enough to automatically scale the frag size when only the block size is set, but if it's not then this is definitely a problem. Scott From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 16:28:08 2006 Return-Path: X-Original-To: freebsd-fs@FreeBSD.ORG Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7370716A419 for ; Fri, 9 Jun 2006 16:28:08 +0000 (UTC) (envelope-from rwatson@FreeBSD.org) Received: from cyrus.watson.org (cyrus.watson.org [209.31.154.42]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2BC1E43D77 for ; Fri, 9 Jun 2006 16:28:08 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from fledge.watson.org (fledge.watson.org [209.31.154.41]) by cyrus.watson.org (Postfix) with ESMTP id 5F01E46C2E for ; Fri, 9 Jun 2006 12:28:06 -0400 (EDT) Date: Fri, 9 Jun 2006 17:28:06 +0100 (BST) From: Robert Watson X-X-Sender: robert@fledge.watson.org To: freebsd-fs@FreeBSD.ORG In-Reply-To: <200606091451.k59EpQnt039643@lurza.secnetix.de> Message-ID: <20060609172713.A31718@fledge.watson.org> References: <200606091451.k59EpQnt039643@lurza.secnetix.de> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 16:28:08 -0000 On Fri, 9 Jun 2006, Oliver Fromme wrote: > > No reason I can think of to use UFS1, but that doesn't mean there isn't a > > bug lurking in UFS1. > > If he doesn't need UFS2 features, using UFS1 will save some space, because > inode data is smaller in UFS1 (128 vs. 256 bytes per inode). However, that > really doesn't matter much if he reduces the inode density as I recommended. > > On a 300 GB file system using the default newfs parameters, you have about > 36 million inodes. So using UFS1 will save about 4500 MB of space (vs. > UFS2). However, with an inode density of 2^18 there are only 1 million > inodes, so UFS1 makes only a difference of 136 MB. Ah, I took "A few very large files" to mean "A few very large files that are probably too large for UFS1 to represent, as very large is getting very large lately" :-). Switching to UFS1 under those circumstances would be problematic. Robert N M Watson From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 16:53:51 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8454D16A418 for ; Fri, 9 Jun 2006 16:53:51 +0000 (UTC) (envelope-from mi+mx@aldan.algebra.com) Received: from aldan.algebra.com (aldan.algebra.com [216.254.65.224]) by mx1.FreeBSD.org (Postfix) with ESMTP id EF3D843D70 for ; Fri, 9 Jun 2006 16:53:50 +0000 (GMT) (envelope-from mi+mx@aldan.algebra.com) Received: from corbulon.video-collage.com (static-151-204-231-237.bos.east.verizon.net [151.204.231.237]) by aldan.algebra.com (8.13.6/8.13.6) with ESMTP id k59GrnHh036203 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Fri, 9 Jun 2006 12:53:49 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) Received: from [172.21.130.86] (mx-broadway [38.98.68.18]) by corbulon.video-collage.com (8.13.6/8.13.6) with ESMTP id k59GrgaY006563 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 9 Jun 2006 12:53:43 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) From: Mikhail Teterin Organization: Virtual Estates, Inc. To: "R. B. Riddick" Date: Fri, 9 Jun 2006 12:53:37 -0400 User-Agent: KMail/1.9.1 References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> In-Reply-To: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> MIME-Version: 1.0 Content-Type: text/plain; charset="koi8-u" Content-Transfer-Encoding: 8bit Content-Disposition: inline Message-Id: <200606091253.37446.mi+mx@aldan.algebra.com> X-Virus-Scanned: ClamAV 0.88/1523/Fri Jun 9 03:10:10 2006 on corbulon.video-collage.com X-Virus-Status: Clean X-Scanned-By: MIMEDefang 2.43 Cc: fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 16:53:51 -0000 п'ятниця 09 червень 2006 02:56, R. B. Riddick написав: > I say, does that discrepancy persist, when you just wait some time? Yes... I'm noticing this hours after the dumps ended... > I would guess, that something has an open file descriptor on a deleted > file, so that this file cannot be really deleted (it just disappears from > the directory tree)... If anything did, I wouldn't be able to umount the filesystem cleanly, would I? Yet, it unmounts peacefully, even though the subsequent fsck finds the superblock summary to be incorrect. When I tried to use the FS as a scratch for an unrelated thing, though, I noticed some processes hanging in nbufkv state. Google-ing led me to the: http://lists.freebsd.org/pipermail/freebsd-current/2003-June/004702.html Is this 3 year old advise *still* true? I rebuilt the kernel with BKVASIZE bumped to 64K (the block size on the FS in question) and am running another batch of dumps right now. When it is over, I'll check the df/du... Yours, -mi From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 16:59:26 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B85FE16A419 for ; Fri, 9 Jun 2006 16:59:26 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 341C743D73 for ; Fri, 9 Jun 2006 16:59:23 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [10.10.3.185] ([69.15.205.254]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k59Gwxsk039364; Fri, 9 Jun 2006 10:59:04 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4489A8CC.8030307@samsco.org> Date: Fri, 09 Jun 2006 10:58:52 -0600 From: Scott Long User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.12) Gecko/20060206 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Mikhail Teterin References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091253.37446.mi+mx@aldan.algebra.com> In-Reply-To: <200606091253.37446.mi+mx@aldan.algebra.com> Content-Type: text/plain; charset=KOI8-U; format=flowed Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=0.0 required=3.8 tests=none autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 16:59:26 -0000 Mikhail Teterin wrote: > п'ятниця 09 червень 2006 02:56, R. B. Riddick написав: > >>I say, does that discrepancy persist, when you just wait some time? > > > Yes... I'm noticing this hours after the dumps ended... > > >>I would guess, that something has an open file descriptor on a deleted >>file, so that this file cannot be really deleted (it just disappears from >>the directory tree)... > > > If anything did, I wouldn't be able to umount the filesystem cleanly, would I? > Yet, it unmounts peacefully, even though the subsequent fsck finds the > superblock summary to be incorrect. > > When I tried to use the FS as a scratch for an unrelated thing, though, I > noticed some processes hanging in nbufkv state. Google-ing led me to the: > > http://lists.freebsd.org/pipermail/freebsd-current/2003-June/004702.html > > Is this 3 year old advise *still* true? I rebuilt the kernel with BKVASIZE > bumped to 64K (the block size on the FS in question) and am running another > batch of dumps right now. When it is over, I'll check the df/du... > > Yours, > > -mi Can you actually measure a performance difference with using the -b 65535 option on newfs? All of the I/O is buffered anyways and contiguous data is already going to be written in 64k blocks. Scott From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 17:13:20 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8CD7F16A418 for ; Fri, 9 Jun 2006 17:13:20 +0000 (UTC) (envelope-from mi+mx@aldan.algebra.com) Received: from aldan.algebra.com (aldan.algebra.com [216.254.65.224]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0112643D73 for ; Fri, 9 Jun 2006 17:13:17 +0000 (GMT) (envelope-from mi+mx@aldan.algebra.com) Received: from corbulon.video-collage.com (static-151-204-231-237.bos.east.verizon.net [151.204.231.237]) by aldan.algebra.com (8.13.6/8.13.6) with ESMTP id k59HDG2k036305 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Fri, 9 Jun 2006 13:13:17 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) Received: from [172.21.130.86] (mx-broadway [38.98.68.18]) by corbulon.video-collage.com (8.13.6/8.13.6) with ESMTP id k59HDAXc006896 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 9 Jun 2006 13:13:11 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) From: Mikhail Teterin Organization: Virtual Estates, Inc. To: Scott Long Date: Fri, 9 Jun 2006 13:13:04 -0400 User-Agent: KMail/1.9.1 References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091253.37446.mi+mx@aldan.algebra.com> <4489A8CC.8030307@samsco.org> In-Reply-To: <4489A8CC.8030307@samsco.org> MIME-Version: 1.0 Content-Type: text/plain; charset="koi8-u" Content-Transfer-Encoding: 8bit Content-Disposition: inline Message-Id: <200606091313.04913.mi+mx@aldan.algebra.com> X-Virus-Scanned: ClamAV 0.88/1523/Fri Jun 9 03:10:10 2006 on corbulon.video-collage.com X-Virus-Status: Clean X-Scanned-By: MIMEDefang 2.43 Cc: fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 17:13:20 -0000 п'ятниця 09 червень 2006 12:58, Scott Long написав: > Can you actually measure a performance difference with using the -b > 65535 option on newfs?  All of the I/O is buffered anyways and > contiguous data is already going to be written in 64k blocks. My reasons for using the largest block size was more of the space efficiency -- the fs typically holds no more than 20 files in 10 directories, but the smallest file is 1Gb in length. This is also why I chose ufs1 (-O1) over ufs2 -- we don't need ACLs on this filesystem. I never benchmarked the speed on the single drives, other than to compare with my RAID5 array (which puzzlingly always loses to a single drive, but that's a different story). Thanks, -mi From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 17:20:30 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id CCE2516A418 for ; Fri, 9 Jun 2006 17:20:30 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 48A2743D78 for ; Fri, 9 Jun 2006 17:20:30 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [10.10.3.185] ([69.15.205.254]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k59HKF2w039463; Fri, 9 Jun 2006 11:20:21 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4489ADC9.3090809@samsco.org> Date: Fri, 09 Jun 2006 11:20:09 -0600 From: Scott Long User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.12) Gecko/20060206 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Mikhail Teterin References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091253.37446.mi+mx@aldan.algebra.com> <4489A8CC.8030307@samsco.org> <200606091313.04913.mi+mx@aldan.algebra.com> In-Reply-To: <200606091313.04913.mi+mx@aldan.algebra.com> Content-Type: text/plain; charset=KOI8-U; format=flowed Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=0.0 required=3.8 tests=none autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 17:20:30 -0000 Mikhail Teterin wrote: > п'ятниця 09 червень 2006 12:58, Scott Long написав: > >>Can you actually measure a performance difference with using the -b >>65535 option on newfs? All of the I/O is buffered anyways and >>contiguous data is already going to be written in 64k blocks. > > > My reasons for using the largest block size was more of the space > efficiency -- the fs typically holds no more than 20 files in 10 directories, > but the smallest file is 1Gb in length. This is also why I chose ufs1 (-O1) > over ufs2 -- we don't need ACLs on this filesystem. > The space savings you get from UFS1 is that the inodes are half the size and the indorect blocks can hold more block pointers. I don't believe that ACLs play a difference here. > I never benchmarked the speed on the single drives, other than to compare with > my RAID5 array (which puzzlingly always loses to a single drive, but that's a > different story). All depends on access alignment and cache behaviour. Scott From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 17:27:51 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id ED43016A418 for ; Fri, 9 Jun 2006 17:27:51 +0000 (UTC) (envelope-from anderson@centtech.com) Received: from mh1.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7357743D78 for ; Fri, 9 Jun 2006 17:27:51 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [10.177.171.220] (neutrino.centtech.com [10.177.171.220]) by mh1.centtech.com (8.13.1/8.13.1) with ESMTP id k59HRPVV039426; Fri, 9 Jun 2006 12:27:25 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <4489AF86.2080901@centtech.com> Date: Fri, 09 Jun 2006 12:27:34 -0500 From: Eric Anderson User-Agent: Thunderbird 1.5.0.2 (X11/20060506) MIME-Version: 1.0 To: Mikhail Teterin References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091253.37446.mi+mx@aldan.algebra.com> <4489A8CC.8030307@samsco.org> <200606091313.04913.mi+mx@aldan.algebra.com> In-Reply-To: <200606091313.04913.mi+mx@aldan.algebra.com> Content-Type: text/plain; charset=KOI8-U; format=flowed Content-Transfer-Encoding: 8bit X-Virus-Scanned: ClamAV 0.87.1/1523/Fri Jun 9 02:10:10 2006 on mh1.centtech.com X-Virus-Status: Clean Cc: fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 17:27:52 -0000 Mikhail Teterin wrote: > п'ятниця 09 червень 2006 12:58, Scott Long написав: >> Can you actually measure a performance difference with using the -b >> 65535 option on newfs? All of the I/O is buffered anyways and >> contiguous data is already going to be written in 64k blocks. > > My reasons for using the largest block size was more of the space > efficiency -- the fs typically holds no more than 20 files in 10 directories, > but the smallest file is 1Gb in length. This is also why I chose ufs1 (-O1) > over ufs2 -- we don't need ACLs on this filesystem. > > I never benchmarked the speed on the single drives, other than to compare with > my RAID5 array (which puzzlingly always loses to a single drive, but that's a > different story). Just curious - what NFS mount options are being used, and are you changing any sysctl's (vfs/nfs related)? Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology Anything that works is better than anything that doesn't. ------------------------------------------------------------------------ From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 17:29:10 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 6F25D16A46F for ; Fri, 9 Jun 2006 17:29:10 +0000 (UTC) (envelope-from mi+mx@aldan.algebra.com) Received: from aldan.algebra.com (aldan.algebra.com [216.254.65.224]) by mx1.FreeBSD.org (Postfix) with ESMTP id 72A1743D79 for ; Fri, 9 Jun 2006 17:29:09 +0000 (GMT) (envelope-from mi+mx@aldan.algebra.com) Received: from corbulon.video-collage.com (static-151-204-231-237.bos.east.verizon.net [151.204.231.237]) by aldan.algebra.com (8.13.6/8.13.6) with ESMTP id k59HT3DD036364 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Fri, 9 Jun 2006 13:29:04 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) Received: from [172.21.130.86] (mx-broadway [38.98.68.18]) by corbulon.video-collage.com (8.13.6/8.13.6) with ESMTP id k59HSvZu007144 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 9 Jun 2006 13:28:58 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) From: Mikhail Teterin Organization: Virtual Estates, Inc. To: Scott Long Date: Fri, 9 Jun 2006 13:28:51 -0400 User-Agent: KMail/1.9.1 References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091313.04913.mi+mx@aldan.algebra.com> <4489ADC9.3090809@samsco.org> In-Reply-To: <4489ADC9.3090809@samsco.org> MIME-Version: 1.0 Content-Type: text/plain; charset="koi8-u" Content-Transfer-Encoding: 8bit Content-Disposition: inline Message-Id: <200606091328.52183.mi+mx@aldan.algebra.com> X-Virus-Scanned: ClamAV 0.88/1523/Fri Jun 9 03:10:10 2006 on corbulon.video-collage.com X-Virus-Status: Clean X-Scanned-By: MIMEDefang 2.43 Cc: fs@freebsd.org Subject: single disk vs. RAID5 (amr) X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 17:29:10 -0000 [Subject changed] п'ятниця 09 червень 2006 13:20, Scott Long написав: > > I never benchmarked the speed on the single drives, other than to compare > > with my RAID5 array (which puzzlingly always loses to a single drive, but > > that's a different story). > > All depends on access alignment and cache behaviour. Well, this does not tell me much :-( I compare a single disk vs. a RAID5 array of 6 such disks joined using amr(4). I tried to figure out the best FS-parameters for the RAID, but whatever I tried, it was always quite inferior to the the single drive -- on both reading and writing. Perhaps, adding the battery-backup option to the RAID card would improve things, but I expected it to be faster even without it. -mi From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 17:30:22 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A80DE16A418 for ; Fri, 9 Jun 2006 17:30:22 +0000 (UTC) (envelope-from mi+mx@aldan.algebra.com) Received: from aldan.algebra.com (aldan.algebra.com [216.254.65.224]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0EEBF43D73 for ; Fri, 9 Jun 2006 17:30:21 +0000 (GMT) (envelope-from mi+mx@aldan.algebra.com) Received: from corbulon.video-collage.com (static-151-204-231-237.bos.east.verizon.net [151.204.231.237]) by aldan.algebra.com (8.13.6/8.13.6) with ESMTP id k59HUKsh036371 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Fri, 9 Jun 2006 13:30:21 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) Received: from [172.21.130.86] (mx-broadway [38.98.68.18]) by corbulon.video-collage.com (8.13.6/8.13.6) with ESMTP id k59HUF25007908 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 9 Jun 2006 13:30:15 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) From: Mikhail Teterin Organization: Virtual Estates, Inc. To: Scott Long Date: Fri, 9 Jun 2006 13:30:09 -0400 User-Agent: KMail/1.9.1 References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091313.04913.mi+mx@aldan.algebra.com> <4489ADC9.3090809@samsco.org> In-Reply-To: <4489ADC9.3090809@samsco.org> MIME-Version: 1.0 Content-Type: text/plain; charset="koi8-u" Content-Transfer-Encoding: 8bit Content-Disposition: inline Message-Id: <200606091330.10007.mi+mx@aldan.algebra.com> X-Virus-Scanned: ClamAV 0.88/1523/Fri Jun 9 03:10:10 2006 on corbulon.video-collage.com X-Virus-Status: Clean X-Scanned-By: MIMEDefang 2.43 Cc: fs@freebsd.org Subject: Space-saving of UFS1 X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 17:30:22 -0000 п'ятниця 09 червень 2006 13:20, Scott Long написав: > The space savings you get from UFS1 is that the inodes are half the size > and the indorect blocks can hold more block pointers.  I don't believe > that ACLs play a difference here. Aren't the ACLs recorded in the inodes -- which would explain, why those are twice larger in UFS2? Thanks! -mi From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 17:33:56 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 668D616A46F for ; Fri, 9 Jun 2006 17:33:56 +0000 (UTC) (envelope-from mi+mx@aldan.algebra.com) Received: from aldan.algebra.com (aldan.algebra.com [216.254.65.224]) by mx1.FreeBSD.org (Postfix) with ESMTP id D757543D72 for ; Fri, 9 Jun 2006 17:33:55 +0000 (GMT) (envelope-from mi+mx@aldan.algebra.com) Received: from corbulon.video-collage.com (static-151-204-231-237.bos.east.verizon.net [151.204.231.237]) by aldan.algebra.com (8.13.6/8.13.6) with ESMTP id k59HXrPo036387 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Fri, 9 Jun 2006 13:33:54 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) Received: from [172.21.130.86] (mx-broadway [38.98.68.18]) by corbulon.video-collage.com (8.13.6/8.13.6) with ESMTP id k59HXlob007943 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 9 Jun 2006 13:33:48 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) From: Mikhail Teterin Organization: Virtual Estates, Inc. To: Eric Anderson Date: Fri, 9 Jun 2006 13:33:42 -0400 User-Agent: KMail/1.9.1 References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091313.04913.mi+mx@aldan.algebra.com> <4489AF86.2080901@centtech.com> In-Reply-To: <4489AF86.2080901@centtech.com> MIME-Version: 1.0 Content-Type: text/plain; charset="koi8-u" Content-Transfer-Encoding: 8bit Content-Disposition: inline Message-Id: <200606091333.42619.mi+mx@aldan.algebra.com> X-Virus-Scanned: ClamAV 0.88/1523/Fri Jun 9 03:10:10 2006 on corbulon.video-collage.com X-Virus-Status: Clean X-Scanned-By: MIMEDefang 2.43 Cc: fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 17:33:56 -0000 п'ятниця 09 червень 2006 13:27, Eric Anderson написав: > Just curious - what NFS mount options are being used, The fs is accessed by the remote client machines (mostly -- Solaris) via automounters -- with the default parameters. > and are you changing any sysctl's (vfs/nfs related)? No, should I? -mi From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 17:41:39 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 10E7616A41B for ; Fri, 9 Jun 2006 17:41:39 +0000 (UTC) (envelope-from rick@kiwi-computer.com) Received: from kiwi-computer.com (megan.kiwi-computer.com [63.224.10.3]) by mx1.FreeBSD.org (Postfix) with SMTP id 5E81D43D78 for ; Fri, 9 Jun 2006 17:41:38 +0000 (GMT) (envelope-from rick@kiwi-computer.com) Received: (qmail 42622 invoked by uid 2001); 9 Jun 2006 17:41:36 -0000 Date: Fri, 9 Jun 2006 12:41:36 -0500 From: "Rick C. Petty" To: Mikhail Teterin Message-ID: <20060609174136.GA42457@megan.kiwi-computer.com> References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091313.04913.mi+mx@aldan.algebra.com> <4489ADC9.3090809@samsco.org> <200606091330.10007.mi+mx@aldan.algebra.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200606091330.10007.mi+mx@aldan.algebra.com> User-Agent: Mutt/1.4.2.1i Cc: fs@freebsd.org Subject: Re: Space-saving of UFS1 X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: rick-freebsd@kiwi-computer.com List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 17:41:39 -0000 On Fri, Jun 09, 2006 at 01:30:09PM -0400, Mikhail Teterin wrote: > > Aren't the ACLs recorded in the inodes -- which would explain, why those are > twice larger in UFS2? Thanks! No, the disk inode (/usr/include/ufs/ufs/dinode.h) contains only pointers to the external attributes block(s). The primary reason UFS2 dinodes are larger than UFS1 are the conversion from 32 to 64 bit pointers and a few extra time structures (e.g. the inode creation time). If your files are minimally 1GB in size, I would think you would need UFS2 for the larger pointers. -- Rick C. Petty From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 17:43:46 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C69FF16A41A for ; Fri, 9 Jun 2006 17:43:46 +0000 (UTC) (envelope-from anderson@centtech.com) Received: from mh2.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 70E4143D72 for ; Fri, 9 Jun 2006 17:43:46 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [10.177.171.220] (neutrino.centtech.com [10.177.171.220]) by mh2.centtech.com (8.13.1/8.13.1) with ESMTP id k59HhdBN023332; Fri, 9 Jun 2006 12:43:39 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <4489B353.9050808@centtech.com> Date: Fri, 09 Jun 2006 12:43:47 -0500 From: Eric Anderson User-Agent: Thunderbird 1.5.0.2 (X11/20060506) MIME-Version: 1.0 To: Mikhail Teterin References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091313.04913.mi+mx@aldan.algebra.com> <4489AF86.2080901@centtech.com> <200606091333.42619.mi+mx@aldan.algebra.com> In-Reply-To: <200606091333.42619.mi+mx@aldan.algebra.com> Content-Type: text/plain; charset=KOI8-U; format=flowed Content-Transfer-Encoding: 8bit X-Virus-Scanned: ClamAV 0.87.1/1523/Fri Jun 9 02:10:10 2006 on mh2.centtech.com X-Virus-Status: Clean Cc: fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 17:43:46 -0000 Mikhail Teterin wrote: > п'ятниця 09 червень 2006 13:27, Eric Anderson написав: >> Just curious - what NFS mount options are being used, > > The fs is accessed by the remote client machines (mostly -- Solaris) via > automounters -- with the default parameters. > >> and are you changing any sysctl's (vfs/nfs related)? > > No, should I? > > -mi Shouldn't need to - I just recalled having seen some strange problems long ago when 'tweaking' some vfs sysctls, and wondering if you had possibly done the same. I'm curious to know if just local heavy writes would cause the problem, or if it has to be through NFS. Also, possibly adding the 'sync' option to the fs mount point could change things.. I'm not sure what those things would tell us for sure, but they would be interesting none-the-less. Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology Anything that works is better than anything that doesn't. ------------------------------------------------------------------------ From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 18:28:03 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5699A16A47E for ; Fri, 9 Jun 2006 18:28:03 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4C95443D90 for ; Fri, 9 Jun 2006 18:27:07 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [10.10.3.185] ([69.15.205.254]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k59IQopm039763; Fri, 9 Jun 2006 12:26:56 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4489BD63.7060309@samsco.org> Date: Fri, 09 Jun 2006 12:26:43 -0600 From: Scott Long User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.12) Gecko/20060206 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Mikhail Teterin References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091313.04913.mi+mx@aldan.algebra.com> <4489ADC9.3090809@samsco.org> <200606091330.10007.mi+mx@aldan.algebra.com> In-Reply-To: <200606091330.10007.mi+mx@aldan.algebra.com> Content-Type: text/plain; charset=KOI8-U; format=flowed Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=0.0 required=3.8 tests=none autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: fs@freebsd.org Subject: Re: Space-saving of UFS1 X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 18:28:03 -0000 Mikhail Teterin wrote: > п'ятниця 09 червень 2006 13:20, Scott Long написав: > >>The space savings you get from UFS1 is that the inodes are half the size >>and the indorect blocks can hold more block pointers. I don't believe >>that ACLs play a difference here. > > > Aren't the ACLs recorded in the inodes -- which would explain, why those are > twice larger in UFS2? Thanks! > > -mi The inode size was extended from 128 bytes to 256 bytes to allow for 64-bit block pointers. This includes 12 direct block pointers and one pointer for each of the single, double, and triple indirect blocks. That didn't fill left some extra space in the 256 bytes, so ACL size info and block pointers were put in there. However, ACLs are just a side effect of the larger size, not the sole reason. And, ACLs are not actually stored in the inode, only block pointers to them are. Scott From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 18:41:15 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id BF12416A41F for ; Fri, 9 Jun 2006 18:41:15 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3FB9543D70 for ; Fri, 9 Jun 2006 18:41:14 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [10.10.3.185] ([69.15.205.254]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k59IexLE039811; Fri, 9 Jun 2006 12:41:04 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4489C0B5.3010902@samsco.org> Date: Fri, 09 Jun 2006 12:40:53 -0600 From: Scott Long User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.12) Gecko/20060206 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Mikhail Teterin References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091313.04913.mi+mx@aldan.algebra.com> <4489AF86.2080901@centtech.com> <200606091333.42619.mi+mx@aldan.algebra.com> In-Reply-To: <200606091333.42619.mi+mx@aldan.algebra.com> Content-Type: text/plain; charset=KOI8-U; format=flowed Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=0.0 required=3.8 tests=none autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 18:41:15 -0000 Mikhail Teterin wrote: > п'ятниця 09 червень 2006 13:27, Eric Anderson написав: > >>Just curious - what NFS mount options are being used, > > > The fs is accessed by the remote client machines (mostly -- Solaris) via > automounters -- with the default parameters. > > >>and are you changing any sysctl's (vfs/nfs related)? > > > No, should I? > > -mi Well, before we get too far off on tangents, would you mind running dumpfs on the filesystem and posting the first block of information? Scott From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 18:45:14 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id DCC1316A41A for ; Fri, 9 Jun 2006 18:45:14 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5929843D72 for ; Fri, 9 Jun 2006 18:45:14 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [10.10.3.185] ([69.15.205.254]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k59Ij0MM039832; Fri, 9 Jun 2006 12:45:05 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4489C1A6.40605@samsco.org> Date: Fri, 09 Jun 2006 12:44:54 -0600 From: Scott Long User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.12) Gecko/20060206 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Mikhail Teterin References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091313.04913.mi+mx@aldan.algebra.com> <4489ADC9.3090809@samsco.org> <200606091328.52183.mi+mx@aldan.algebra.com> In-Reply-To: <200606091328.52183.mi+mx@aldan.algebra.com> Content-Type: text/plain; charset=KOI8-U; format=flowed Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=0.0 required=3.8 tests=none autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: fs@freebsd.org Subject: Re: single disk vs. RAID5 (amr) X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 18:45:14 -0000 Mikhail Teterin wrote: > [Subject changed] > > п'ятниця 09 червень 2006 13:20, Scott Long написав: > >>>I never benchmarked the speed on the single drives, other than to compare >>>with my RAID5 array (which puzzlingly always loses to a single drive, but >>>that's a different story). >> >>All depends on access alignment and cache behaviour. > > > Well, this does not tell me much :-( I compare a single disk vs. a RAID5 array > of 6 such disks joined using amr(4). I tried to figure out the best > FS-parameters for the RAID, but whatever I tried, it was always quite > inferior to the the single drive -- on both reading and writing. > > Perhaps, adding the battery-backup option to the RAID card would improve > things, but I expected it to be faster even without it. > > -mi THere are two things to consider. First is that FreeBSD mis-aligns the filesysytem blocks if you are using an fdisk/MBR header on the disk. This misalignment doesn't affect single disks, but it greatly affects RAID, and especially RAID-5. An easy way to check this is to compare the performance on an array that has just the filesystem on it and no MBR or disklabel information. The second is that the LSI controllers will turn the cache off if a battery is not present. This won't affect read speed much, but it will greatly affect write speed. Scott From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 18:46:51 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 90ACD16A41A for ; Fri, 9 Jun 2006 18:46:51 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0D09443D77 for ; Fri, 9 Jun 2006 18:46:50 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [10.10.3.185] ([69.15.205.254]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k59IkakU039840; Fri, 9 Jun 2006 12:46:41 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4489C206.8020507@samsco.org> Date: Fri, 09 Jun 2006 12:46:30 -0600 From: Scott Long User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.12) Gecko/20060206 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Eric Anderson References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091253.37446.mi+mx@aldan.algebra.com> <4489A8CC.8030307@samsco.org> <200606091313.04913.mi+mx@aldan.algebra.com> <4489AF86.2080901@centtech.com> In-Reply-To: <4489AF86.2080901@centtech.com> Content-Type: text/plain; charset=KOI8-U; format=flowed Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=0.0 required=3.8 tests=none autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: Mikhail Teterin , fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 18:46:51 -0000 Eric Anderson wrote: > Mikhail Teterin wrote: > >> п'ятниця 09 червень 2006 12:58, Scott Long написав: >> >>> Can you actually measure a performance difference with using the -b >>> 65535 option on newfs? All of the I/O is buffered anyways and >>> contiguous data is already going to be written in 64k blocks. >> >> >> My reasons for using the largest block size was more of the space >> efficiency -- the fs typically holds no more than 20 files in 10 >> directories, but the smallest file is 1Gb in length. This is also why >> I chose ufs1 (-O1) over ufs2 -- we don't need ACLs on this filesystem. >> >> I never benchmarked the speed on the single drives, other than to >> compare with my RAID5 array (which puzzlingly always loses to a single >> drive, but that's a different story). > > > Just curious - what NFS mount options are being used, and are you > changing any sysctl's (vfs/nfs related)? > It's hard to beleive that NFS would be responsible for corrupting the filesystem. You should be able to have a consistent and correct unmount regardless of whether NFS is in use or what options it is using. Scott From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 18:59:03 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7045616A418 for ; Fri, 9 Jun 2006 18:59:03 +0000 (UTC) (envelope-from mi+mx@aldan.algebra.com) Received: from aldan.algebra.com (aldan.algebra.com [216.254.65.224]) by mx1.FreeBSD.org (Postfix) with ESMTP id A804C43D70 for ; Fri, 9 Jun 2006 18:59:02 +0000 (GMT) (envelope-from mi+mx@aldan.algebra.com) Received: from corbulon.video-collage.com (static-151-204-231-237.bos.east.verizon.net [151.204.231.237]) by aldan.algebra.com (8.13.6/8.13.6) with ESMTP id k59Iwvgo036637 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Fri, 9 Jun 2006 14:58:58 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) Received: from [172.21.130.86] (mx-broadway [38.98.68.18]) by corbulon.video-collage.com (8.13.6/8.13.6) with ESMTP id k59IwpC6010641 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 9 Jun 2006 14:58:52 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) From: Mikhail Teterin Organization: Virtual Estates, Inc. To: Scott Long Date: Fri, 9 Jun 2006 14:58:46 -0400 User-Agent: KMail/1.9.1 References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091333.42619.mi+mx@aldan.algebra.com> <4489C0B5.3010902@samsco.org> In-Reply-To: <4489C0B5.3010902@samsco.org> MIME-Version: 1.0 Content-Type: text/plain; charset="koi8-u" Content-Transfer-Encoding: 8bit Content-Disposition: inline Message-Id: <200606091458.46504.mi+mx@aldan.algebra.com> X-Virus-Scanned: ClamAV 0.88/1523/Fri Jun 9 03:10:10 2006 on corbulon.video-collage.com X-Virus-Status: Clean X-Scanned-By: MIMEDefang 2.43 Cc: fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 18:59:03 -0000 п'ятниця 09 червень 2006 14:40, Scott Long написав: > Well, before we get too far off on tangents, would you mind running > dumpfs on the filesystem and posting the first block of information? Do you want this now, or when/if I see the corruption again? > It's hard to beleive that NFS would be responsible for corrupting the > filesystem. You should be able to have a consistent and correct unmount > regardless of whether NFS is in use or what options it is using. The other potential "oddity" is that the files are eagerly awaited (via kevent()) by a process running on my NFS server, which mmaps the freshly written chunks (as soon as kevent() returns) and compresses them onto another filesystem. It looks like this: 20060609:14:53:03: mzip: the input size grew from 201031680 to 201064448. Ok... 20060609:14:53:03: mzip: mmap-ing 32768 bytes of /staging/gonzo:4100/TD_THEIR_211-060609-145243.dmp (201064448) starting at 201031680 20060609:14:53:03: mzip: eaten: 32768 of 32768, produced 0 20060609:14:53:03: mzip: Unmapping 32768 bytes starting at 0x80052c000 As soon as the dump is over, and the last portion of it is compressed, the dump is deleted. None of this should be causing the corruption I observed a few times, but any of it could, for it is all mildly unusual :-/ Yours, -mi From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 19:44:54 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7978116A41B for ; Fri, 9 Jun 2006 19:44:54 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2488343D8D for ; Fri, 9 Jun 2006 19:44:47 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [10.10.3.185] ([69.15.205.254]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k59JiPXm040160; Fri, 9 Jun 2006 13:44:31 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4489CF93.3030906@samsco.org> Date: Fri, 09 Jun 2006 13:44:19 -0600 From: Scott Long User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.12) Gecko/20060206 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Mikhail Teterin References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091333.42619.mi+mx@aldan.algebra.com> <4489C0B5.3010902@samsco.org> <200606091458.46504.mi+mx@aldan.algebra.com> In-Reply-To: <200606091458.46504.mi+mx@aldan.algebra.com> Content-Type: text/plain; charset=KOI8-U; format=flowed Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=0.0 required=3.8 tests=none autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 19:44:54 -0000 Mikhail Teterin wrote: > п'ятниця 09 червень 2006 14:40, Scott Long написав: > >>Well, before we get too far off on tangents, would you mind running >>dumpfs on the filesystem and posting the first block of information? > > > Do you want this now, or when/if I see the corruption again? > Do it now, no need to wait for more corruption. I just want to see what the block+frag properties are. > >>It's hard to beleive that NFS would be responsible for corrupting the >>filesystem. You should be able to have a consistent and correct unmount >>regardless of whether NFS is in use or what options it is using. > > > The other potential "oddity" is that the files are eagerly awaited (via > kevent()) by a process running on my NFS server, which mmaps the freshly > written chunks (as soon as kevent() returns) and compresses them onto > another filesystem. It looks like this: > > 20060609:14:53:03: mzip: the input size grew from 201031680 to 201064448. Ok... > 20060609:14:53:03: mzip: mmap-ing 32768 bytes of /staging/gonzo:4100/TD_THEIR_211-060609-145243.dmp (201064448) starting at 201031680 > 20060609:14:53:03: mzip: eaten: 32768 of 32768, produced 0 > 20060609:14:53:03: mzip: Unmapping 32768 bytes starting at 0x80052c000 > > As soon as the dump is over, and the last portion of it is compressed, > the dump is deleted. None of this should be causing the corruption I > observed a few times, but any of it could, for it is all mildly unusual :-/ > Still, an unmount should flush everything and not leave you with any incorrect information on the filesystem. I have an app that mounts and unmounts NFS filesystems on a frequent basis and does operations on them that factor down into mmap calls, and I've never seen any problems like this. So, I'm very curious and concerned about what you're seeing. Scott From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 21:17:59 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2645F16A41B for ; Fri, 9 Jun 2006 21:17:59 +0000 (UTC) (envelope-from user@dhp.com) Received: from shell.dhp.com (shell.dhp.com [199.245.105.1]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5DFCB43D70 for ; Fri, 9 Jun 2006 21:17:58 +0000 (GMT) (envelope-from user@dhp.com) Received: by shell.dhp.com (Postfix, from userid 896) id F37AA31316; Fri, 9 Jun 2006 17:17:51 -0400 (EDT) Date: Fri, 9 Jun 2006 17:17:51 -0400 (EDT) From: Ensel Sharon To: freebsd-fs@freebsd.org Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Subject: quick check - adaptec 2820sa on FreeBSD 6.1 ? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 21:17:59 -0000 I see that adaptec publishes drivers for FreeBSD 5.3 and 5.4 for the pciX card 2820SA. I find very little archived mailing list discussion concerning this card. Bottom line: if I boot up a 6.1-RELEASE iso in a machine with this card in it, should I expect to install onto it and boot onto it, and all to be well ? Thanks a lot. From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 21:21:36 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 53AFD16A418 for ; Fri, 9 Jun 2006 21:21:36 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id C9E6543D70 for ; Fri, 9 Jun 2006 21:21:35 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [10.10.3.185] ([69.15.205.254]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k59LLPCm040642; Fri, 9 Jun 2006 15:21:30 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4489E64F.402@samsco.org> Date: Fri, 09 Jun 2006 15:21:19 -0600 From: Scott Long User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.12) Gecko/20060206 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Ensel Sharon References: In-Reply-To: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Status: No, score=0.0 required=3.8 tests=none autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: freebsd-fs@freebsd.org Subject: Re: quick check - adaptec 2820sa on FreeBSD 6.1 ? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 21:21:36 -0000 Ensel Sharon wrote: > I see that adaptec publishes drivers for FreeBSD 5.3 and 5.4 for the pciX > card 2820SA. I find very little archived mailing list discussion > concerning this card. > > Bottom line: if I boot up a 6.1-RELEASE iso in a machine with this card in > it, should I expect to install onto it and boot onto it, and all to be > well ? > > Thanks a lot. > Are you asking because you need advice on whether or not to purchase it? Yes, it will work, but if you already have the card then you should test it out for yourself and make sure that it meets your needs. Scott From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 21:28:11 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3471E16A41B for ; Fri, 9 Jun 2006 21:28:11 +0000 (UTC) (envelope-from user@dhp.com) Received: from shell.dhp.com (shell.dhp.com [199.245.105.1]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8EFE943D7B for ; Fri, 9 Jun 2006 21:28:10 +0000 (GMT) (envelope-from user@dhp.com) Received: by shell.dhp.com (Postfix, from userid 896) id 2C9AD3130D; Fri, 9 Jun 2006 17:28:05 -0400 (EDT) Date: Fri, 9 Jun 2006 17:28:05 -0400 (EDT) From: Ensel Sharon To: freebsd-fs@freebsd.org Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Subject: Re: quick check - adaptec 2820sa on FreeBSD 6.1 ? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 21:28:11 -0000 > Are you asking because you need advice on whether or not to purchase it? Yes. I do not own it and am trying to decide whether to buy the 2810SA, which is explicitly mentioned in the 6.1-RELEASE hardware notes, OR the 2820sa which has raid-6, which I want very much. So it sounds like it works just as well as any other aac, like my trusty old PERCs ? In the product description, they list the supported raid levels (0,1,5,10,50) and then list other raid levels (1E,5EE,6,60) under "advanced data protection suite". That's just market copy, right ? Those other raid levels are selectable and controlled trough the raid bios like everyone is always used to ? Or is there some wacky software or plug-in or daughterboard or something ? I want to use raid-6 with FreeBSD, is what I am trying to say. Thanks for your help. From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 21:37:46 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 86FE016A418 for ; Fri, 9 Jun 2006 21:37:46 +0000 (UTC) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (core6.multiplay.co.uk [85.236.96.23]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5E04A43D8B for ; Fri, 9 Jun 2006 21:37:42 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([212.135.219.179]) by multiplay.co.uk (multiplay.co.uk [85.236.96.23]) (MDaemon PRO v9.0.1) with ESMTP id md50002642513.msg for ; Fri, 09 Jun 2006 22:37:33 +0100 Message-ID: <005c01c68c0c$e1d9c780$b3db87d4@multiplay.co.uk> From: "Steven Hartland" To: "Ensel Sharon" , References: Date: Fri, 9 Jun 2006 22:37:10 +0100 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=original Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.2869 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 X-Spam-Processed: multiplay.co.uk, Fri, 09 Jun 2006 22:37:33 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 212.135.219.179 X-Return-Path: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-fs@freebsd.org X-MDAV-Processed: multiplay.co.uk, Fri, 09 Jun 2006 22:37:34 +0100 Cc: Subject: Re: quick check - adaptec 2820sa on FreeBSD 6.1 ? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 21:37:46 -0000 Ensel Sharon wrote: > I want to use raid-6 with FreeBSD, is what I am trying to say. The Areca controller is definitely supported and provides hardware RAID 6 support. Steve ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 21:42:30 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 76DCD16A473 for ; Fri, 9 Jun 2006 21:42:30 +0000 (UTC) (envelope-from user@dhp.com) Received: from shell.dhp.com (shell.dhp.com [199.245.105.1]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9E28A43D73 for ; Fri, 9 Jun 2006 21:42:29 +0000 (GMT) (envelope-from user@dhp.com) Received: by shell.dhp.com (Postfix, from userid 896) id 4C99F3130D; Fri, 9 Jun 2006 17:42:26 -0400 (EDT) Date: Fri, 9 Jun 2006 17:42:26 -0400 (EDT) From: Ensel Sharon To: Steven Hartland In-Reply-To: <005c01c68c0c$e1d9c780$b3db87d4@multiplay.co.uk> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: freebsd-fs@freebsd.org Subject: Re: quick check - adaptec 2820sa on FreeBSD 6.1 ? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 21:42:30 -0000 On Fri, 9 Jun 2006, Steven Hartland wrote: > Ensel Sharon wrote: > > I want to use raid-6 with FreeBSD, is what I am trying to say. > > The Areca controller is definitely supported and provides > hardware RAID 6 support. Thanks. I already have an infrastructure built around aaccli, automated alerts, and training, etc. I am sort of wedded to PERC/aac/adaptec/etc. I just want to make sure that the 2820sa is just as nicely working and supported as any other PERC/aac, and that raid-6 support is accessed and used through the BIOS just like any other raid configuration on any other aac card... Can someone confirm that ? From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 22:06:41 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id EF85016A418 for ; Fri, 9 Jun 2006 22:06:41 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6DF8543D72 for ; Fri, 9 Jun 2006 22:06:41 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [10.10.3.185] ([69.15.205.254]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k59M6WdT040923; Fri, 9 Jun 2006 16:06:38 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4489F0E1.5020109@samsco.org> Date: Fri, 09 Jun 2006 16:06:25 -0600 From: Scott Long User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.12) Gecko/20060206 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Ensel Sharon References: In-Reply-To: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Status: No, score=0.0 required=3.8 tests=none autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: freebsd-fs@freebsd.org Subject: Re: quick check - adaptec 2820sa on FreeBSD 6.1 ? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 22:06:42 -0000 Ensel Sharon wrote: > > On Fri, 9 Jun 2006, Steven Hartland wrote: > > >>Ensel Sharon wrote: >> >>>I want to use raid-6 with FreeBSD, is what I am trying to say. >> >>The Areca controller is definitely supported and provides >>hardware RAID 6 support. > > > > Thanks. I already have an infrastructure built around aaccli, automated > alerts, and training, etc. I am sort of wedded to PERC/aac/adaptec/etc. > > I just want to make sure that the 2820sa is just as nicely working and > supported as any other PERC/aac, and that raid-6 support is accessed and > used through the BIOS just like any other raid configuration on any other > aac card... > > Can someone confirm that ? > Yes, it works. Again, if it's critical to your business or operations, then you'll want to validate it first. From your posting, I imagine that you understand and appreciate this already. Scott From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 23:11:05 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9CCD716A474; Fri, 9 Jun 2006 23:11:05 +0000 (UTC) (envelope-from bde@zeta.org.au) Received: from mailout2.pacific.net.au (mailout2.pacific.net.au [61.8.0.115]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8CC7643D82; Fri, 9 Jun 2006 23:11:03 +0000 (GMT) (envelope-from bde@zeta.org.au) Received: from mailproxy1.pacific.net.au (mailproxy1.pacific.net.au [61.8.2.162]) by mailout2.pacific.net.au (Postfix) with ESMTP id 226C58512F; Sat, 10 Jun 2006 09:11:02 +1000 (EST) Received: from katana.zip.com.au (katana.zip.com.au [61.8.7.246]) by mailproxy1.pacific.net.au (8.13.4/8.13.4/Debian-3sarge1) with ESMTP id k59NAxg1017493; Sat, 10 Jun 2006 09:11:00 +1000 Date: Sat, 10 Jun 2006 09:10:59 +1000 (EST) From: Bruce Evans X-X-Sender: bde@delplex.bde.org To: Robert Watson In-Reply-To: <20060609172713.A31718@fledge.watson.org> Message-ID: <20060610075606.B14403@delplex.bde.org> References: <200606091451.k59EpQnt039643@lurza.secnetix.de> <20060609172713.A31718@fledge.watson.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 23:11:05 -0000 On Fri, 9 Jun 2006, Robert Watson wrote: > On Fri, 9 Jun 2006, Oliver Fromme wrote: >> ... >> On a 300 GB file system using the default newfs parameters, you have about >> 36 million inodes. So using UFS1 will save about 4500 MB of space (vs. >> UFS2). However, with an inode density of 2^18 there are only 1 million >> inodes, so UFS1 makes only a difference of 136 MB. > > Ah, I took "A few very large files" to mean "A few very large files that are > probably too large for UFS1 to represent, as very large is getting very large > lately" :-). Switching to UFS1 under those circumstances would be > problematic. I don't know about UFS1 and UFS2 ;), but with the same block size ffs1 can represent much larger files than ffs2. This is because the data type for block numbers in ffs2 is twice as large as in ffs1, so indirect blocks can store twice as many block numbers in ffs1 and in ffs2. There are 3 levels of indirect blocks, so this factor of 2 applies 3 times, giving ratio of about 8 for the maximum file size in ffs1 vs ffs2. More precisely: nindir = blocksize / sizeof(blocknumber) maxfilesize = (nindir^3 + O(nindir^2)) * blocksize (I'm now confused about block vs fragment addressing. I think block numbers are actually frag numbers, so I had fragsize in the rightmost term in the above, but newfs uses blocksize. The following numbers may be off by a factor of blocksize/fragsize from this.) The default block/frag size of 16KB/2KB thus gives a maxfilesize of about 4K^3 * 16KB = 1024TB in ffs1 but only 2K^3 * 16KB = 128TB in ffs2. A block/frag size of 64KB/8KB this gives a maxfilesize of about 16K^3 * 64KB = 262144TB in ffs1 but only 32768TB in ffs2. The file size limit that ffs2 increases is the maximum size of a non-sparse file. This is quite different. Now the limit is physical addressibility of blocks. I think the block numbers really are fragment numbers in this context (but beware of errors by a factor of blocksize/fragsize in the fiollowing) , so the limit is: maxphysfilesize = (maxblocknumber + 1) * fragsize - 1 The default block/frag size of 16KB/2KB thus gives a maxphysfilesize of about 4G*4G * 2KB = 32G TB in ffs2 but only 4G * 2KB = 8TB in ffs1. The default block/frag size of 64KB/8KB thus gives a maxphysfilesize of about 4G*4G * 8KB = 128G TB in ffs2 but only 4G * 8KB = 32TB in ffs1. You can also use easily larger fragments if you want a larger maxphysfilesize in ffs1. The limit with 64KB-frags is 128TB. Larger sizes require increasing limits in vfs_bio starting with MAXBSIZE. The latter and even the former would give ffs file systems that wouldn't work in most implementations of ffs. Maximum file sizes (both physical and virtual) are also limited by other implementation details: (1) in FreeBSD before FreeBSD-5, vfs_bio and disk drivers can only access 1TB, so physical file sizes larger than 1TB cannot work since physical _filesystem_ sizes larger than 1TB cannot work. (2) in some versions of FreeBSD-5 (maybe only in pre-release versions), a bug in ffs1 causes truncation of disk addresses befor they reach vfs_bio, so physical _filesystem_ sizes larger than 1TB cannot work in ffs1. (3) ffs1 has a bogus internal limit of maxfilesize = (maxblocknumber + 1) / 2 * blocksize - 1 This confuses maxfilesize with maxphysfilesize and is obviously off by a factor of 2 and is probably off by a factor of blocksize/fragsize too. For most choices of block/frag sizes (all except 4K/512 IIRC), at limits maxfilesize unnecessarily, but the error factors in it result in it only limiting maxphysfilesize for non-default choices. Bruce From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 23:27:47 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3342E16A46F for ; Fri, 9 Jun 2006 23:27:47 +0000 (UTC) (envelope-from user@dhp.com) Received: from shell.dhp.com (shell.dhp.com [199.245.105.1]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3FDEA43D72 for ; Fri, 9 Jun 2006 23:27:46 +0000 (GMT) (envelope-from user@dhp.com) Received: by shell.dhp.com (Postfix, from userid 896) id 168A8312F5; Fri, 9 Jun 2006 19:27:40 -0400 (EDT) Date: Fri, 9 Jun 2006 19:27:40 -0400 (EDT) From: Ensel Sharon To: Scott Long In-Reply-To: <4489F0E1.5020109@samsco.org> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: freebsd-fs@freebsd.org Subject: Re: quick check - adaptec 2820sa on FreeBSD 6.1 ? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 23:27:47 -0000 Scott, On Fri, 9 Jun 2006, Scott Long wrote: > > I just want to make sure that the 2820sa is just as nicely working and > > supported as any other PERC/aac, and that raid-6 support is accessed and > > used through the BIOS just like any other raid configuration on any other > > aac card... > > > > Can someone confirm that ? > > > > Yes, it works. Again, if it's critical to your business or operations, > then you'll want to validate it first. From your posting, I imagine > that you understand and appreciate this already. I'm sorry to beat this dead horse. THis is the last question, promise: I already trust critical business operations to PERC/aac on FreeBSD 6.1. Do you have any knowledge, or any reason to believe, that a 2820sa is any less reliable or trustworthy ? Thanks. From owner-freebsd-fs@FreeBSD.ORG Fri Jun 9 23:45:44 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1F44C16A46F for ; Fri, 9 Jun 2006 23:45:44 +0000 (UTC) (envelope-from rwatson@FreeBSD.org) Received: from cyrus.watson.org (cyrus.watson.org [209.31.154.42]) by mx1.FreeBSD.org (Postfix) with ESMTP id 609E443D73 for ; Fri, 9 Jun 2006 23:45:42 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from fledge.watson.org (fledge.watson.org [209.31.154.41]) by cyrus.watson.org (Postfix) with ESMTP id D499B46CCD; Fri, 9 Jun 2006 19:45:41 -0400 (EDT) Date: Sat, 10 Jun 2006 00:45:41 +0100 (BST) From: Robert Watson X-X-Sender: robert@fledge.watson.org To: Scott Long In-Reply-To: <4489BD63.7060309@samsco.org> Message-ID: <20060610004447.A26068@fledge.watson.org> References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091313.04913.mi+mx@aldan.algebra.com> <4489ADC9.3090809@samsco.org> <200606091330.10007.mi+mx@aldan.algebra.com> <4489BD63.7060309@samsco.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: Mikhail Teterin , fs@freebsd.org Subject: Re: Space-saving of UFS1 X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Jun 2006 23:45:44 -0000 On Fri, 9 Jun 2006, Scott Long wrote: > The inode size was extended from 128 bytes to 256 bytes to allow for 64-bit > block pointers. This includes 12 direct block pointers and one pointer for > each of the single, double, and triple indirect blocks. That didn't fill > left some extra space in the 256 bytes, so ACL size info and block pointers > were put in there. However, ACLs are just a side effect of the larger size, > not the sole reason. And, ACLs are not actually stored in the inode, only > block pointers to them are. While the technical statements above are correct, actually, the extended attribute storage was the primary motivation for getting UFS2 development kicked off. Since it required rolling the file system layout, we did 64-bit support at the same time, dropped back in the birth time, etc. Robert N M Watson From owner-freebsd-fs@FreeBSD.ORG Sat Jun 10 00:07:08 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id AA34916A41B for ; Sat, 10 Jun 2006 00:07:08 +0000 (UTC) (envelope-from bde@zeta.org.au) Received: from mailout1.pacific.net.au (mailout1.pacific.net.au [61.8.0.84]) by mx1.FreeBSD.org (Postfix) with ESMTP id 44D0143D83 for ; Sat, 10 Jun 2006 00:06:58 +0000 (GMT) (envelope-from bde@zeta.org.au) Received: from mailproxy1.pacific.net.au (mailproxy1.pacific.net.au [61.8.2.162]) by mailout1.pacific.net.au (Postfix) with ESMTP id 2D62B329F9A; Sat, 10 Jun 2006 10:06:57 +1000 (EST) Received: from katana.zip.com.au (katana.zip.com.au [61.8.7.246]) by mailproxy1.pacific.net.au (8.13.4/8.13.4/Debian-3sarge1) with ESMTP id k5A06qiI021008; Sat, 10 Jun 2006 10:06:55 +1000 Date: Sat, 10 Jun 2006 10:06:51 +1000 (EST) From: Bruce Evans X-X-Sender: bde@delplex.bde.org To: Scott Long In-Reply-To: <4489A8CC.8030307@samsco.org> Message-ID: <20060610091109.R14403@delplex.bde.org> References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091253.37446.mi+mx@aldan.algebra.com> <4489A8CC.8030307@samsco.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: Mikhail Teterin , fs@freebsd.org Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 10 Jun 2006 00:07:08 -0000 On Fri, 9 Jun 2006, Scott Long wrote: > Mikhail Teterin wrote: >> When I tried to use the FS as a scratch for an unrelated thing, though, I >> noticed some processes hanging in nbufkv state. Google-ing led me to the: >> >> http://lists.freebsd.org/pipermail/freebsd-current/2003-June/004702.html >> >> Is this 3 year old advise *still* true? I rebuilt the kernel with BKVASIZE Probably. >> bumped to 64K (the block size on the FS in question) and am running another >> batch of dumps right now. When it is over, I'll check the df/du... > > Can you actually measure a performance difference with using the -b 65535 > option on newfs? All of the I/O is buffered anyways and contiguous data is > already going to be written in 64k blocks. I can measure a performance loss with larger block sizes, but mainly with small files, the default BKVASIZE, and larger fragment sizes too. On a WDC ATA drive which is quite slow for small block sizes (4K, 8K and 16K tansfer at 26MB/S and 32K+ at 49MB/S), a block/frag sizes of 32K/4K gives much the same throughput for copying /usr/src as does 16K/2K, but about half as much throughput for 32K/32K. I stopped benchmarking block sizes of 64K because old benchmarks showed that they only gave performance losses for /usr/src. With only large files, the fragment size shouldn't matter, but the block size shouldn't matter either once it is not too small, since files should be laid out contiguously and small blocks should be clustered into large ones efficiently. However, contiguous layout and clustering don't work perfectly and/or very efficiently, and using large block sizes like the default of 16K is an easy way to increase contiguity and reduce overheads for clustering. Fragmentation (discontiguity, not the fragmentation reported by fsck), tends to be very large for old, active file systems and typically reduces efficiency of trees like /home/ncvs by a factor of 5-10. Bruce From owner-freebsd-fs@FreeBSD.ORG Sat Jun 10 00:57:41 2006 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B32B516A482 for ; Sat, 10 Jun 2006 00:57:41 +0000 (UTC) (envelope-from mi+mx@aldan.algebra.com) Received: from aldan.algebra.com (aldan.algebra.com [216.254.65.224]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6999043D83 for ; Sat, 10 Jun 2006 00:57:34 +0000 (GMT) (envelope-from mi+mx@aldan.algebra.com) Received: from corbulon.video-collage.com (static-151-204-231-237.bos.east.verizon.net [151.204.231.237]) by aldan.algebra.com (8.13.6/8.13.6) with ESMTP id k5A0vO7u037588 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Fri, 9 Jun 2006 20:57:25 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) Received: from [172.21.130.86] (mx-broadway [38.98.68.18]) by corbulon.video-collage.com (8.13.6/8.13.6) with ESMTP id k5A0vIEw017057 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 9 Jun 2006 20:57:19 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) From: Mikhail Teterin Organization: Virtual Estates, Inc. To: Bruce Evans Date: Fri, 9 Jun 2006 20:57:13 -0400 User-Agent: KMail/1.9.1 References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <4489A8CC.8030307@samsco.org> <20060610091109.R14403@delplex.bde.org> In-Reply-To: <20060610091109.R14403@delplex.bde.org> MIME-Version: 1.0 Content-Type: text/plain; charset="koi8-u" Content-Transfer-Encoding: 8bit Content-Disposition: inline Message-Id: <200606092057.13416.mi+mx@aldan.algebra.com> X-Virus-Scanned: ClamAV 0.88/1523/Fri Jun 9 03:10:10 2006 on corbulon.video-collage.com X-Virus-Status: Clean X-Scanned-By: MIMEDefang 2.43 Cc: fs@freebsd.org Subject: Severe impact of fragmentation (was: heavy NFS writes lead ...) X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 10 Jun 2006 00:57:41 -0000 п'ятниця 09 червень 2006 20:06, Bruce Evans написав: > Fragmentation (discontiguity, not the fragmentation reported by fsck), tends > to be very large for old, active file systems and typically reduces > efficiency of trees like /home/ncvs by a factor of 5-10. Ouch... "In-place" defragemntation program, anyone? -mi From owner-freebsd-fs@FreeBSD.ORG Sat Jun 10 01:24:48 2006 Return-Path: X-Original-To: fs@FreeBSD.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D728316A41B; Sat, 10 Jun 2006 01:24:48 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4F02943D72; Sat, 10 Jun 2006 01:24:45 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [192.168.254.14] (imini.samsco.home [192.168.254.14]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id k5A1OThg041829; Fri, 9 Jun 2006 19:24:34 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <448A2116.3020504@samsco.org> Date: Fri, 09 Jun 2006 19:32:06 -0600 From: Scott Long User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.7.7) Gecko/20050416 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Robert Watson References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091313.04913.mi+mx@aldan.algebra.com> <4489ADC9.3090809@samsco.org> <200606091330.10007.mi+mx@aldan.algebra.com> <4489BD63.7060309@samsco.org> <20060610004447.A26068@fledge.watson.org> In-Reply-To: <20060610004447.A26068@fledge.watson.org> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Status: No, score=-1.4 required=3.8 tests=ALL_TRUSTED autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: Mikhail Teterin , fs@FreeBSD.org Subject: Re: Space-saving of UFS1 X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 10 Jun 2006 01:24:48 -0000 Robert Watson wrote: > > On Fri, 9 Jun 2006, Scott Long wrote: > >> The inode size was extended from 128 bytes to 256 bytes to allow for >> 64-bit block pointers. This includes 12 direct block pointers and one >> pointer for each of the single, double, and triple indirect blocks. >> That didn't fill left some extra space in the 256 bytes, so ACL size >> info and block pointers were put in there. However, ACLs are just a >> side effect of the larger size, not the sole reason. And, ACLs are >> not actually stored in the inode, only block pointers to them are. > > > While the technical statements above are correct, actually, the extended > attribute storage was the primary motivation for getting UFS2 > development kicked off. Since it required rolling the file system > layout, we did 64-bit support at the same time, dropped back in the > birth time, etc. > > Robert N M Watson Ah, sorry, I had it backwards. Scott From owner-freebsd-fs@FreeBSD.ORG Sat Jun 10 16:34:03 2006 Return-Path: X-Original-To: freebsd-fs@FreeBSD.ORG Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 85DE416A41A for ; Sat, 10 Jun 2006 16:34:03 +0000 (UTC) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (lurza.secnetix.de [83.120.8.8]) by mx1.FreeBSD.org (Postfix) with ESMTP id B72AE454CF for ; Sat, 10 Jun 2006 09:46:51 +0000 (GMT) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (mdazwt@localhost [127.0.0.1]) by lurza.secnetix.de (8.13.4/8.13.4) with ESMTP id k5A9keXJ073655 for ; Sat, 10 Jun 2006 11:46:45 +0200 (CEST) (envelope-from oliver.fromme@secnetix.de) Received: (from olli@localhost) by lurza.secnetix.de (8.13.4/8.13.1/Submit) id k5A9kdtS073613; Sat, 10 Jun 2006 11:46:39 +0200 (CEST) (envelope-from olli) Date: Sat, 10 Jun 2006 11:46:39 +0200 (CEST) Message-Id: <200606100946.k5A9kdtS073613@lurza.secnetix.de> From: Oliver Fromme To: freebsd-fs@FreeBSD.ORG In-Reply-To: <20060609172713.A31718@fledge.watson.org> X-Newsgroups: list.freebsd-fs User-Agent: tin/1.8.0-20051224 ("Ronay") (UNIX) (FreeBSD/4.11-STABLE (i386)) X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-2.1.2 (lurza.secnetix.de [127.0.0.1]); Sat, 10 Jun 2006 11:46:45 +0200 (CEST) Cc: Subject: Re: heavy NFS writes lead to corrup summary in superblock X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: freebsd-fs@FreeBSD.ORG List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 10 Jun 2006 16:34:03 -0000 Robert Watson wrote: > Oliver Fromme wrote: > > If he doesn't need UFS2 features, using UFS1 will save some space, > > because inode data is smaller in UFS1 (128 vs. 256 bytes per > > inode). However, that really doesn't matter much if he reduces the > > inode density as I recommended. > > > > On a 300 GB file system using the default newfs parameters, you > > have about 36 million inodes. So using UFS1 will save about 4500 > > MB of space (vs. UFS2). However, with an inode density of 2^18 > > there are only 1 million inodes, so UFS1 makes only a difference of > > 136 MB. > > Ah, I took "A few very large files" to mean "A few very large files > that are probably too large for UFS1 to represent, as very large > is getting very large lately" :-). Switching to UFS1 under those > circumstances would be problematic. Last time I checked, the maximum file size limit (for non- sparse files) on UFS1 is larger than the maximum file system size limit (1 TB, IIRC), and therefore a non-issue in this case. (The limit for sparse files is 8 TB, but dump files aren't sparse anyway.) Best regards Oliver -- Oliver Fromme, secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing Dienstleistungen mit Schwerpunkt FreeBSD: http://www.secnetix.de/bsd Any opinions expressed in this message may be personal to the author and may not necessarily reflect the opinions of secnetix in any way. "Python is an experiment in how much freedom programmers need. Too much freedom and nobody can read another's code; too little and expressiveness is endangered." -- Guido van Rossum From owner-freebsd-fs@FreeBSD.ORG Sat Jun 10 19:58:48 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id CF57216A41A; Sat, 10 Jun 2006 19:58:48 +0000 (UTC) (envelope-from mark@islandnet.com) Received: from cluster.islandnet.com (cluster.islandnet.com [199.175.106.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8456A43E01; Sat, 10 Jun 2006 19:58:37 +0000 (GMT) (envelope-from mark@islandnet.com) Received: from [199.175.106.221] (port=13202 helo=helpdesk.islandnet.com) by cluster01.islandnet.com with SMTP id 1Fp9bR-0006Rg-4m ; Sat, 10 Jun 2006 12:58:37 -0700 Date: Sat, 10 Jun 2006 12:58:37 -0700 Message-ID: <448b246d-9da2@helpdesk.islandnet.com> References: <447fa140-96fe@helpdesk.islandnet.com> From: Mark Morley To: freebsd-fs@freebsd.org, freebsd-stable@freebsd.org Content-type: text/plain MIME-Version: 1.0 X-Priority: 3 X-Mailer: Helpdesk Webmail (http://helpdesk.islandnet.com) X-Originating-IP: [24.108.70.188] X-GeoIP: CA Canada Cc: Subject: Re: NFS processes locking up!! X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Mark Morley List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 10 Jun 2006 19:58:48 -0000 > > > makeoptions COPTFLAGS="-O2 -pipe -funroll-loops -ffast-math" > > > > Don't use leet meaningless compiler flags, and try again :) > > > > Kris > > D'oh! I don't normally have that in my kernel configs. > That carried forward from the old server. I'll remove those and > see how it goes. Well, that made no difference I'm afraid. I removed all make options, cleaned the source tree, deleted /usr/obj/* and completely rebuilt world as well as the kernel. A few days later it did the exact same thing. The change in compiler options did seem to lower the load averages a bit though. Possibly related: I am seeing "ufs_rename: fvp == tvp (can't happen)" messages periodically. Maybe one or two every 2-3 hours. Any chance that's a symptom of something related? Mark -- Mark Morley Owner / Administrator Islandnet.com From owner-freebsd-fs@FreeBSD.ORG Sat Jun 10 20:08:18 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1CF4F16A47C for ; Sat, 10 Jun 2006 20:08:18 +0000 (UTC) (envelope-from gorgonite@freesurf.fr) Received: from smtp-out.freesurf.fr (messidor.freesurf.fr [212.43.206.29]) by mx1.FreeBSD.org (Postfix) with ESMTP id C2B3C4406D for ; Sat, 10 Jun 2006 20:05:13 +0000 (GMT) (envelope-from gorgonite@freesurf.fr) Received: from freesurf.fr (jose.freesurf.fr [212.43.206.13]) by smtp-out.freesurf.fr (Postfix) with SMTP id C264F4D2C3 for ; Sat, 10 Jun 2006 22:05:14 +0200 (CEST) Received: from 82.67.244.132 (SquirrelMail authenticated user gorgonite) by jose.freesurf.fr with HTTP; Sat, 10 Jun 2006 22:05:12 +0200 (CEST) Message-ID: <51067.82.67.244.132.1149969912.squirrel@jose.freesurf.fr> Date: Sat, 10 Jun 2006 22:05:12 +0200 (CEST) From: "Gorgonite" To: X-Priority: 3 In-Reply-To: <33162.147.250.1.2.1149783482.squirrel@jose.freesurf.fr> References: <33162.147.250.1.2.1149783482.squirrel@jose.freesurf.fr> Importance: Normal X-MSMail-Priority: Normal X-Mailer: SquirrelMail (version 1.2.5) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Subject: Re: [gvinum] add a disk in concat mode X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: gorgonite@freesurf.fr List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 10 Jun 2006 20:08:18 -0000 Hello, I hope the gvinum list will give you enough pieces of information to be able to help me. ------------------------------------- data# gvinum gvinum -> start gvinum -> list 2 drives: D a State: up /dev/ad0 A: 9007/286188 MB (3%)D b State: up /dev/ad2 A: 6122/194480 MB (3%) 1 volume: V myvol State: up Plexes: 2 Size: 183 GB 2 plexes: P myvol.p0 C State: up Subdisks: 1 Size: 270 GB P myvol.p1 C State: down Subdisks: 1 Size: 183 GB 2 subdisks: S myvol.p0.s0 State: up D: a Size: 270 GB S myvol.p1.s0 State: stale D: b Size: 183 GB ------------------------------------- Thanks. > Hello, > > > I run on FreeBSD v6.1 > I have a disk with 300Go (/dev/ad0) in concat mode with gvinum > (myvol.p0) I would like to add a disk of 200Go (/dev/ad2) on this > volume, but without erasing my previous data (ad0) > > I executed this script > > Code: > #! /bin/sh dd if=/dev/zero of=/dev/ad2 count=2 disklabel /dev/ad2 | > disklabel -B -R -r ad2 /dev/stdin newsfs /dev/ad2c gvinum create > gvinum.conf > > > with this gvinum.conf > > Code: > drive b device /dev/ad2c plex name myvol.p1 org concat vol myvol sd > length 188358m drive b > > > > it seems to be okay for gvinum... and I wanted to update my "partition" > > Code: > growfs -S "483g" /dev/gvinum/myvol > > > > but it failed with "grow is not growing..." > > > Can anyone help me, please ? > Thanks. > > > ps: sorry for my bad english :'( > > > _______________________________________________ > freebsd-fs@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-fs > To unsubscribe, send any mail to "freebsd-fs-unsubscribe@freebsd.org" From owner-freebsd-fs@FreeBSD.ORG Sat Jun 10 21:06:20 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A45DE16A4A5 for ; Sat, 10 Jun 2006 21:06:20 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30305.mail.mud.yahoo.com (web30305.mail.mud.yahoo.com [68.142.200.98]) by mx1.FreeBSD.org (Postfix) with SMTP id A18034429F for ; Sat, 10 Jun 2006 20:46:22 +0000 (GMT) (envelope-from arne_woerner@yahoo.com) Received: (qmail 78899 invoked by uid 60001); 10 Jun 2006 20:46:21 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:Received:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=JKhVp5KytW3iHC+3zWWPmdL3vFv2lxtF2+FC/TIqyVgL7b0a4zW286LfQWgtNnPFHA8EO7XvFKT4ijKejoYmFsKwsTJQfrpyX9qf4aUuk4wtbEkqz6Tue9SEC3OGxCuVQPqeBUVkJo8ostUmbQDnRe9zaySI+fXCpGZroOvJhQE= ; Message-ID: <20060610204621.78897.qmail@web30305.mail.mud.yahoo.com> Received: from [213.54.74.233] by web30305.mail.mud.yahoo.com via HTTP; Sat, 10 Jun 2006 13:46:21 PDT Date: Sat, 10 Jun 2006 13:46:21 -0700 (PDT) From: "R. B. Riddick" To: gorgonite@freesurf.fr, freebsd-fs@freebsd.org In-Reply-To: <51067.82.67.244.132.1149969912.squirrel@jose.freesurf.fr> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Cc: Subject: Re: [gvinum] add a disk in concat mode X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 10 Jun 2006 21:06:21 -0000 Hi! I just crashed my box with the kernel module "geom_vinum". Now I remember better again, why I do not use geom_vinum but geom_mirror and geom_stripe... :-)) Did you try to use geom_concat instead of geom_vinum? Maybe it even works with some luck, when u do it like this: 0. Back up your file system on /dev/ad0... ;-)) 1. Back up the last sector of your /dev/ad0 (because: it could contain important file system data) to /dev/ad2 (first sector *nudge* *nudge*). :-) When we concat later, everything would be as before... 2. Do it like the man page (gconcat(8)) explains it (but without the newfs command): gconcat label data /dev/da0 /dev/da2 growfs /dev/concat/data 3. tahdah...! ;-)) Maybe you should try to get rid of geom_vinum before you do it, so that geom_vinum cannot interfere with geom_concat... I wish u good luck! ;-) Bye Arne --- Gorgonite wrote: > Hello, > > > > I hope the gvinum list will give you enough pieces of information to be able > to help me. > > ------------------------------------- > > data# gvinum > gvinum -> start > gvinum -> list > 2 drives: > D a State: up /dev/ad0 A: 9007/286188 MB > (3%)D b State: up /dev/ad2 A: 6122/194480 MB > (3%) > 1 volume: > V myvol State: up Plexes: 2 Size: 183 GB > > 2 plexes: > P myvol.p0 C State: up Subdisks: 1 Size: 270 GB > P myvol.p1 C State: down Subdisks: 1 Size: 183 GB > > 2 subdisks: > S myvol.p0.s0 State: up D: a Size: 270 GB > S myvol.p1.s0 State: stale D: b Size: 183 GB > > ------------------------------------- > > Thanks. > > > > Hello, > > > > > > I run on FreeBSD v6.1 > > I have a disk with 300Go (/dev/ad0) in concat mode with gvinum > > (myvol.p0) I would like to add a disk of 200Go (/dev/ad2) on this > > volume, but without erasing my previous data (ad0) > > > > I executed this script > > > > Code: > > #! /bin/sh dd if=/dev/zero of=/dev/ad2 count=2 disklabel /dev/ad2 | > > disklabel -B -R -r ad2 /dev/stdin newsfs /dev/ad2c gvinum create > > gvinum.conf > > > > > > with this gvinum.conf > > > > Code: > > drive b device /dev/ad2c plex name myvol.p1 org concat vol myvol sd > > length 188358m drive b > > > > > > > > it seems to be okay for gvinum... and I wanted to update my "partition" > > > > Code: > > growfs -S "483g" /dev/gvinum/myvol > > > > > > > > but it failed with "grow is not growing..." > > > > > > Can anyone help me, please ? > > Thanks. > > > > > > ps: sorry for my bad english :'( > > > > > > _______________________________________________ > > freebsd-fs@freebsd.org mailing list > > http://lists.freebsd.org/mailman/listinfo/freebsd-fs > > To unsubscribe, send any mail to "freebsd-fs-unsubscribe@freebsd.org" > > > > _______________________________________________ > freebsd-fs@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-fs > To unsubscribe, send any mail to "freebsd-fs-unsubscribe@freebsd.org" > __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com From owner-freebsd-fs@FreeBSD.ORG Sat Jun 10 23:19:03 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3195716A418 for ; Sat, 10 Jun 2006 23:19:03 +0000 (UTC) (envelope-from zbeeble@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.168]) by mx1.FreeBSD.org (Postfix) with ESMTP id C73DC43D5A for ; Sat, 10 Jun 2006 23:18:55 +0000 (GMT) (envelope-from zbeeble@gmail.com) Received: by ug-out-1314.google.com with SMTP id m2so1775282ugc for ; Sat, 10 Jun 2006 16:18:54 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:references; b=W3g5ZfMWR+NyPtlnMsuPU4Qru9uEEmKs65D4scbBAuVnZW43uzzc++2qy/opKzl9tSHBOGAS94DKTdrt46L39CbrH+Tt3Wxc6IKZ1DrUVzozKg22FToOemvnnedb7p/NTO2Y0yCNwowVvR6+0fhonELdWF4H4A1yNQ0PqZH1ZQo= Received: by 10.67.100.12 with SMTP id c12mr3750780ugm; Sat, 10 Jun 2006 15:23:46 -0700 (PDT) Received: by 10.67.96.5 with HTTP; Sat, 10 Jun 2006 15:23:46 -0700 (PDT) Message-ID: <5f67a8c40606101523q42311e46y51d23786ef3a15c0@mail.gmail.com> Date: Sat, 10 Jun 2006 18:23:46 -0400 From: "Zaphod Beeblebrox" To: "Mark Morley" In-Reply-To: <448b246d-9da2@helpdesk.islandnet.com> MIME-Version: 1.0 References: <447fa140-96fe@helpdesk.islandnet.com> <448b246d-9da2@helpdesk.islandnet.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: freebsd-fs@freebsd.org, freebsd-stable@freebsd.org Subject: Re: NFS processes locking up!! X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 10 Jun 2006 23:19:03 -0000 [nfsd's and other processes locking in 'D' state] One thing I've seen cause this kind of thing is a disk that needs to be manually fsck'd. Try bringing up the system in single user and manually fsck'ing the volume. I have no idea what causes this kind of state --- where the disk is bad, but not calling for an fsck. It could just be random bad bits, but I've seen this behaviour more than once.