From owner-freebsd-fs@FreeBSD.ORG Mon Jun 18 15:06:07 2007 Return-Path: X-Original-To: freebsd-fs@FreeBSD.org Delivered-To: freebsd-fs@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id E5B6A16A468; Mon, 18 Jun 2007 15:06:07 +0000 (UTC) (envelope-from delphij@delphij.net) Received: from tarsier.geekcn.org (tarsier.geekcn.org [210.51.165.229]) by mx1.freebsd.org (Postfix) with ESMTP id BE9D613C469; Mon, 18 Jun 2007 15:06:06 +0000 (UTC) (envelope-from delphij@delphij.net) Received: from localhost (tarsier.geekcn.org [210.51.165.229]) by tarsier.geekcn.org (Postfix) with ESMTP id 791EAEB16D1; Mon, 18 Jun 2007 22:49:30 +0800 (CST) X-Virus-Scanned: amavisd-new at geekcn.org Received: from tarsier.geekcn.org ([210.51.165.229]) by localhost (mail.geekcn.org [210.51.165.229]) (amavisd-new, port 10024) with ESMTP id WnKo4ZKz1dbD; Mon, 18 Jun 2007 22:49:27 +0800 (CST) Received: from charlie.delphij.net (unknown [221.221.171.60]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by tarsier.geekcn.org (Postfix) with ESMTP id AF5A6EB15B4; Mon, 18 Jun 2007 22:49:26 +0800 (CST) DomainKey-Signature: a=rsa-sha1; s=default; d=delphij.net; c=nofws; q=dns; h=message-id:date:from:user-agent:mime-version:to:subject: x-enigmail-version:openpgp:content-type:content-transfer-encoding; b=p9JV+E7KtGL4ZHhbm70vXkQ5FC3x0Owk5XGw7jZEIj4jprXwmcsVqMa9sUFtZ7ic8 V7dqVDOyg3/fV2fEvXfKw== Message-ID: <46769B76.60502@delphij.net> Date: Mon, 18 Jun 2007 22:49:26 +0800 From: Xin LI User-Agent: Thunderbird 2.0.0.4 (X11/20070615) MIME-Version: 1.0 To: freebsd-current@FreeBSD.org, freebsd-fs@FreeBSD.org, jdp@FreeBSD.org X-Enigmail-Version: 0.95.1 OpenPGP: url=http://www.delphij.net/delphij.asc Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: Subject: Why vfs.timestamp_precision is set to 0 by default? 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, 18 Jun 2007 15:06:08 -0000 Hi, Recently while I'm looking into the VFS code I found that we set vfs.timestamp_precision to 0 by default. Is there any reason not to set this to, for instance 1 by default? My rough test indicates that the performance affect is almost negligible... Cheers, From owner-freebsd-fs@FreeBSD.ORG Mon Jun 18 16:05:51 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 42CF716A469; Mon, 18 Jun 2007 16:05:51 +0000 (UTC) (envelope-from brde@optusnet.com.au) Received: from mail35.syd.optusnet.com.au (mail35.syd.optusnet.com.au [211.29.133.51]) by mx1.freebsd.org (Postfix) with ESMTP id BA0D713C46A; Mon, 18 Jun 2007 16:05:50 +0000 (UTC) (envelope-from brde@optusnet.com.au) Received: from c220-239-235-248.carlnfd3.nsw.optusnet.com.au (c220-239-235-248.carlnfd3.nsw.optusnet.com.au [220.239.235.248]) by mail35.syd.optusnet.com.au (8.13.1/8.13.1) with ESMTP id l5IG5a37017908 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Tue, 19 Jun 2007 02:05:38 +1000 Date: Tue, 19 Jun 2007 02:05:35 +1000 (EST) From: Bruce Evans X-X-Sender: bde@delplex.bde.org To: Xin LI In-Reply-To: <46769B76.60502@delphij.net> Message-ID: <20070619013303.F43847@delplex.bde.org> References: <46769B76.60502@delphij.net> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-fs@freebsd.org, jdp@freebsd.org, freebsd-current@freebsd.org Subject: Re: Why vfs.timestamp_precision is set to 0 by default? 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, 18 Jun 2007 16:05:51 -0000 On Mon, 18 Jun 2007, Xin LI wrote: > Recently while I'm looking into the VFS code I found that we set > vfs.timestamp_precision to 0 by default. Is there any reason not to set > this to, for instance 1 by default? My rough test indicates that the > performance affect is almost negligible... o 1 second is the historical default for ffs. o vfs.timestamp_precision is global, so changing it would change the default for ffs. o 1 is a magic number. Unfortunately, TSP_HZ is not visible outside of vfs_subr.c. o The TSP_SEC and TSP_HZ settings are efficient. The other might not be, depending on the speed of hardware timecounters. o TSP_HZ gives a much larger coherence bug than TSP_SEC. The timestamp is not the current time rounded down as it should be, but is a previous time rounded down. The previous time is updated at a frequency of at most HZ (at a lower frequency iff HZ > 1000 or a certain sysctl variable is set). suppose that its update frequency is precisely HZ. The TSP_SEC gives wrong results with a probablility of about (HZ - 0.5)/HZ, while TSP_GZ gives wrong results with a probablility of about 0.5. This is hard to fix for SMP without slowing down the timestamps. I sometimes use TSP_USEC to avoid seeing this bug reported by file times coherency tests. o No userland APIs and thus no utilities support setting times with the resolution given by TSP_NSEC. Bruce From owner-freebsd-fs@FreeBSD.ORG Mon Jun 18 17:00:23 2007 Return-Path: X-Original-To: freebsd-fs@FreeBSD.org Delivered-To: freebsd-fs@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 2B08716A41F; Mon, 18 Jun 2007 17:00:23 +0000 (UTC) (envelope-from jdp@polstra.com) Received: from rock.polstra.com (rock.polstra.com [64.119.0.113]) by mx1.freebsd.org (Postfix) with ESMTP id 097B513C45B; Mon, 18 Jun 2007 17:00:22 +0000 (UTC) (envelope-from jdp@polstra.com) Received: from [10.0.0.64] (adsl-sj-9-160.rockisland.net [64.119.9.160]) (authenticated bits=0) by rock.polstra.com (8.13.8/8.13.8) with ESMTP id l5IGiadf021386 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Mon, 18 Jun 2007 09:44:37 -0700 (PDT) (envelope-from jdp@polstra.com) Message-ID: <4676B674.4030104@polstra.com> Date: Mon, 18 Jun 2007 09:44:36 -0700 From: John Polstra User-Agent: Thunderbird 1.5.0.12 (Macintosh/20070509) MIME-Version: 1.0 To: Xin LI References: <46769B76.60502@delphij.net> In-Reply-To: <46769B76.60502@delphij.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Greylist: Sender succeeded SMTP AUTH authentication, not delayed by milter-greylist-3.0 (rock.polstra.com [64.119.0.113]); Mon, 18 Jun 2007 09:44:38 -0700 (PDT) Cc: freebsd-fs@FreeBSD.org, freebsd-current@FreeBSD.org Subject: Re: Why vfs.timestamp_precision is set to 0 by default? 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, 18 Jun 2007 17:00:23 -0000 Xin LI wrote: > Recently while I'm looking into the VFS code I found that we set > vfs.timestamp_precision to 0 by default. Is there any reason not to set > this to, for instance 1 by default? My rough test indicates that the > performance affect is almost negligible... If I remember correctly, I set the default to 0 for compatibility -- i.e., so that the fractional seconds would continue to be set to 0 as before. That was probably too conservative. John From owner-freebsd-fs@FreeBSD.ORG Wed Jun 20 06:54:33 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 7519416A421 for ; Wed, 20 Jun 2007 06:54:33 +0000 (UTC) (envelope-from gurdiga@gmail.com) Received: from wx-out-0506.google.com (wx-out-0506.google.com [66.249.82.224]) by mx1.freebsd.org (Postfix) with ESMTP id 35F8013C458 for ; Wed, 20 Jun 2007 06:54:33 +0000 (UTC) (envelope-from gurdiga@gmail.com) Received: by wx-out-0506.google.com with SMTP id h28so83575wxd for ; Tue, 19 Jun 2007 23:54:32 -0700 (PDT) DKIM-Signature: a=rsa-sha1; c=relaxed/relaxed; d=gmail.com; s=beta; h=domainkey-signature:received:received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=cp4Cmin1JUPjO3it+IN7cwF78yRYS+itHcxJE/OMnCHdhtCPFMWtoiayFiOdk6FVp44DbB2PK9BxbFaSOdfEgYaMyR8xa4tCh+QCm6npbTOelAQ0ptJCuxfMdP3owtWZBUL/Qh/EPXEC+wxfYNQNjroq1wVSDtbkWEFGdLeFnxo= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=kNdw0PTfO2nfjzOoqW90XlYSgLteQp7bYJgbqkNrsmInyomcQSEsjZEzCaucxH/GzYjBNgHiJ1Rtb7Ih8uyo5JzXQXUZPDD5d5mhQzNIIS4KlKIR8vubHGYNdKA3XIca+5Jh87+zn28fBSoMk7onmjGREgvc+tnSjCesdUUzZc8= Received: by 10.78.200.20 with SMTP id x20mr108444huf.1182321006320; Tue, 19 Jun 2007 23:30:06 -0700 (PDT) Received: by 10.78.194.12 with HTTP; Tue, 19 Jun 2007 23:30:06 -0700 (PDT) Message-ID: Date: Wed, 20 Jun 2007 09:30:06 +0300 From: "Vlad GURDIGA" To: freebsd-fs@freebsd.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: Subject: fs cache 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, 20 Jun 2007 06:54:33 -0000 Hello, I have FreeBSD 7-CURRENT and Ubuntu on the same computer but Firefox takes twice as long to start on a fresh boot. I've run some simple tests: - on FreeBSD it takes about 7 seconds on the first start and about 3 on subsequent startups; - on Ubuntu it takes about 3 seconds on the first start and about 1 on subsequent startups; The only difference I can see is that on Ubuntu, after first start of Firefox the memory use for cache is 22% vs. 0% on FreeBSD. My guess is that this is the cause of slower startups on FreeBSD. My question is: can I tune UFS2 in such a way that the most frequently used desktop applications would remain for a longer time in disk cache? In both cases I use GNOME 2.18, GNOME System Monitor 2.18, and Firefox 2. Both FreeBSD 7-CURRENT (src and ports tree) and Ubuntu 7.01 (2.6.20-16-generic kernel) are up to date. Both are SMP and 32bit. Here is the system configuration: - Intel DP965LT mother-board; - dual-core Pentium D 820; - 1GB of dual-channel-enabled DDR2 PC5300 at 667 MHz; - Seagate, BARRACUDA 7200.7 Plus, 160GB, ST3160827AS, 8M cache, with NCQ; From owner-freebsd-fs@FreeBSD.ORG Wed Jun 20 16:39:44 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 799A116A400 for ; Wed, 20 Jun 2007 16:39:44 +0000 (UTC) (envelope-from SRS0=5IyI=LU=ira.uka.de=esk@srs.kundenserver.de) Received: from moutng.kundenserver.de (moutng.kundenserver.de [212.227.126.174]) by mx1.freebsd.org (Postfix) with ESMTP id 10EB113C489 for ; Wed, 20 Jun 2007 16:39:43 +0000 (UTC) (envelope-from SRS0=5IyI=LU=ira.uka.de=esk@srs.kundenserver.de) Received: from [213.144.1.98] (helo=localhost) by mrelayeu.kundenserver.de (node=mrelayeu3) with ESMTP (Nemesis), id 0MKxQS-1I131J36fc-0008Dr; Wed, 20 Jun 2007 18:27:02 +0200 From: Espen Skoglund MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <18041.21810.297355.202403@gargle.gargle.HOWL> Date: Wed, 20 Jun 2007 18:26:26 +0200 To: freebsd-fs@freebsd.org X-Mailer: VM 7.17 under 21.4 (patch 20) "Double Solitaire" XEmacs Lucid X-Provags-ID: V01U2FsdGVkX1+exciM/yYG1NK3DCPMjpptvWVnwdidZYAdRB0 aslh6W5NKdEl5gp5IaMIEM17L+uHoz9+44K9M76R4le/71s9m0 Qqgl9NV5e+sT23B9NA4AA== Subject: Snapshot usage guidelines (to avoid stability issues) 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, 20 Jun 2007 16:39:44 -0000 Hi, A couple of days ago I decided to start using snapshots on my system. Knowing that the functionality has been available for quite some time now I (apparently wrongly) assumed that it was ready for production use. My bad. My system, a 6-STABLE from week and a half ago, uses two 250GB gstriped disks and has about 4-5 snapshots on one 215GB UFS partiton. This morning I learned that things had gone terribly wrong during some nightly cronjobs, hanging the whole system. Suspecting that snapshots were the culprit I soon learned after some investigation that the snapshot functionality wasn't nearly as stable as I had hoped for. Looking at PRs and mailing lists there seems to be mainly two outstanding stability issues with snapshots: a) snapshotted fs running full, and b) deleting large amount of files on an fs with multiple snapshots. The former issue, while certainly annoying, one could be able to work around. The latter issue, on the other hand, seems more like a definite show stopper. Am I right in inferring that the two above cases are main issues with snaphots at this time, or are there other known gotchas that I have to look out for. eSk From owner-freebsd-fs@FreeBSD.ORG Wed Jun 20 16:58:14 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id BEF6B16A400 for ; Wed, 20 Jun 2007 16:58:14 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from relay01.kiev.sovam.com (relay01.kiev.sovam.com [62.64.120.200]) by mx1.freebsd.org (Postfix) with ESMTP id 52D3C13C44B for ; Wed, 20 Jun 2007 16:58:14 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from [89.162.146.170] (helo=skuns.kiev.zoral.com.ua) by relay01.kiev.sovam.com with esmtps (TLSv1:AES256-SHA:256) (Exim 4.67) (envelope-from ) id 1I13VU-000K0P-5v for freebsd-fs@freebsd.org; Wed, 20 Jun 2007 19:58:13 +0300 Received: from deviant.kiev.zoral.com.ua (root@deviant.kiev.zoral.com.ua [10.1.1.148]) by skuns.kiev.zoral.com.ua (8.14.1/8.14.1) with ESMTP id l5KGvgTU041860 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Wed, 20 Jun 2007 19:57:43 +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 (8.14.1/8.14.1) with ESMTP id l5KGvmtJ081617; Wed, 20 Jun 2007 19:57:48 +0300 (EEST) (envelope-from kostikbel@gmail.com) Received: (from kostik@localhost) by deviant.kiev.zoral.com.ua (8.14.1/8.14.1/Submit) id l5KGvkOM081616; Wed, 20 Jun 2007 19:57:46 +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: Wed, 20 Jun 2007 19:57:46 +0300 From: Kostik Belousov To: Espen Skoglund Message-ID: <20070620165746.GX2268@deviant.kiev.zoral.com.ua> References: <18041.21810.297355.202403@gargle.gargle.HOWL> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="+hLoyg/derPMoKTw" Content-Disposition: inline In-Reply-To: <18041.21810.297355.202403@gargle.gargle.HOWL> User-Agent: Mutt/1.4.2.2i X-Virus-Scanned: ClamAV version 0.90.2, clamav-milter version 0.90.2 on skuns.kiev.zoral.com.ua X-Virus-Status: Clean X-Spam-Status: No, score=-1.4 required=5.0 tests=ALL_TRUSTED autolearn=failed version=3.1.8 X-Spam-Checker-Version: SpamAssassin 3.1.8 (2007-02-13) on skuns.kiev.zoral.com.ua X-Scanner-Signature: d3dfc5a0b247ea81d48b6a940fe6235f X-DrWeb-checked: yes X-SpamTest-Envelope-From: kostikbel@gmail.com X-SpamTest-Group-ID: 00000000 X-SpamTest-Header: Not Detected X-SpamTest-Info: Profiles 1162 [June 20 2007] X-SpamTest-Info: helo_type=3 X-SpamTest-Method: none X-SpamTest-Rate: 0 X-SpamTest-Status: Not detected X-SpamTest-Status-Extended: not_detected X-SpamTest-Version: SMTP-Filter Version 3.0.0 [0255], KAS30/Release Cc: freebsd-fs@freebsd.org Subject: Re: Snapshot usage guidelines (to avoid stability issues) 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, 20 Jun 2007 16:58:14 -0000 --+hLoyg/derPMoKTw Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Jun 20, 2007 at 06:26:26PM +0200, Espen Skoglund wrote: > Hi, >=20 > A couple of days ago I decided to start using snapshots on my system. > Knowing that the functionality has been available for quite some time > now I (apparently wrongly) assumed that it was ready for production > use. My bad. >=20 > My system, a 6-STABLE from week and a half ago, uses two 250GB > gstriped disks and has about 4-5 snapshots on one 215GB UFS partiton. > This morning I learned that things had gone terribly wrong during some > nightly cronjobs, hanging the whole system. Suspecting that snapshots > were the culprit I soon learned after some investigation that the > snapshot functionality wasn't nearly as stable as I had hoped for. >=20 > Looking at PRs and mailing lists there seems to be mainly two > outstanding stability issues with snapshots: a) snapshotted fs running > full, and b) deleting large amount of files on an fs with multiple > snapshots. The former issue, while certainly annoying, one could be > able to work around. The latter issue, on the other hand, seems more > like a definite show stopper. >=20 > Am I right in inferring that the two above cases are main issues with > snaphots at this time, or are there other known gotchas that I have to > look out for. About the issue b). Are you system sources before or after 2007-06-11 10:53:48 UTC ? Or simply show me the version of sys/ufs/ffs/ffs_snapshot.c. If it is less then 1.103.2.24, see developers handbook for instruction on reporting deadlocks. --+hLoyg/derPMoKTw Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (FreeBSD) iD8DBQFGeVyKC3+MBN1Mb4gRAsyuAKCr1dQUqYJ3nsknhei7o9vE75klFQCggNjP IPlWviBqi2ZxKmM81SFpE9c= =DjYU -----END PGP SIGNATURE----- --+hLoyg/derPMoKTw-- From owner-freebsd-fs@FreeBSD.ORG Wed Jun 20 17:02:27 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 6139F16A469 for ; Wed, 20 Jun 2007 17:02:27 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from relay01.kiev.sovam.com (relay01.kiev.sovam.com [62.64.120.200]) by mx1.freebsd.org (Postfix) with ESMTP id D312713C46C for ; Wed, 20 Jun 2007 17:02:26 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from [89.162.146.170] (helo=skuns.kiev.zoral.com.ua) by relay01.kiev.sovam.com with esmtps (TLSv1:AES256-SHA:256) (Exim 4.67) (envelope-from ) id 1I13ZW-000LaP-T8 for freebsd-fs@freebsd.org; Wed, 20 Jun 2007 20:02:26 +0300 Received: from deviant.kiev.zoral.com.ua (root@deviant.kiev.zoral.com.ua [10.1.1.148]) by skuns.kiev.zoral.com.ua (8.14.1/8.14.1) with ESMTP id l5KH26Hr041992 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Wed, 20 Jun 2007 20:02:06 +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 (8.14.1/8.14.1) with ESMTP id l5KH2CBM081687; Wed, 20 Jun 2007 20:02:12 +0300 (EEST) (envelope-from kostikbel@gmail.com) Received: (from kostik@localhost) by deviant.kiev.zoral.com.ua (8.14.1/8.14.1/Submit) id l5KH29Vf081686; Wed, 20 Jun 2007 20:02:09 +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: Wed, 20 Jun 2007 20:02:09 +0300 From: Kostik Belousov To: Espen Skoglund Message-ID: <20070620170209.GY2268@deviant.kiev.zoral.com.ua> References: <18041.21810.297355.202403@gargle.gargle.HOWL> <20070620165746.GX2268@deviant.kiev.zoral.com.ua> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="QfPW8fNxh+WKMpMU" Content-Disposition: inline In-Reply-To: <20070620165746.GX2268@deviant.kiev.zoral.com.ua> User-Agent: Mutt/1.4.2.2i X-Virus-Scanned: ClamAV version 0.90.2, clamav-milter version 0.90.2 on skuns.kiev.zoral.com.ua X-Virus-Status: Clean X-Spam-Status: No, score=-1.4 required=5.0 tests=ALL_TRUSTED autolearn=failed version=3.1.8 X-Spam-Checker-Version: SpamAssassin 3.1.8 (2007-02-13) on skuns.kiev.zoral.com.ua X-Scanner-Signature: 5e2df25549de819b25d1bfd51e9f52eb X-DrWeb-checked: yes X-SpamTest-Envelope-From: kostikbel@gmail.com X-SpamTest-Group-ID: 00000000 X-SpamTest-Header: Not Detected X-SpamTest-Info: Profiles 1162 [June 20 2007] X-SpamTest-Info: helo_type=3 X-SpamTest-Method: none X-SpamTest-Rate: 0 X-SpamTest-Status: Not detected X-SpamTest-Status-Extended: not_detected X-SpamTest-Version: SMTP-Filter Version 3.0.0 [0255], KAS30/Release Cc: freebsd-fs@freebsd.org Subject: Re: Snapshot usage guidelines (to avoid stability issues) 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, 20 Jun 2007 17:02:27 -0000 --QfPW8fNxh+WKMpMU Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Jun 20, 2007 at 07:57:46PM +0300, Kostik Belousov wrote: > On Wed, Jun 20, 2007 at 06:26:26PM +0200, Espen Skoglund wrote: > > Hi, > >=20 > > A couple of days ago I decided to start using snapshots on my system. > > Knowing that the functionality has been available for quite some time > > now I (apparently wrongly) assumed that it was ready for production > > use. My bad. > >=20 > > My system, a 6-STABLE from week and a half ago, uses two 250GB > > gstriped disks and has about 4-5 snapshots on one 215GB UFS partiton. > > This morning I learned that things had gone terribly wrong during some > > nightly cronjobs, hanging the whole system. Suspecting that snapshots > > were the culprit I soon learned after some investigation that the > > snapshot functionality wasn't nearly as stable as I had hoped for. > >=20 > > Looking at PRs and mailing lists there seems to be mainly two > > outstanding stability issues with snapshots: a) snapshotted fs running > > full, and b) deleting large amount of files on an fs with multiple > > snapshots. The former issue, while certainly annoying, one could be > > able to work around. The latter issue, on the other hand, seems more > > like a definite show stopper. > >=20 > > Am I right in inferring that the two above cases are main issues with > > snaphots at this time, or are there other known gotchas that I have to > > look out for. > About the issue b). Are you system sources before or after 2007-06-11 > 10:53:48 UTC ? Or simply show me the version of sys/ufs/ffs/ffs_snapshot.= c. >=20 > If it is less then 1.103.2.24, see developers handbook for instruction on shall be "equal to 1.103.2.24" > reporting deadlocks. >=20 --QfPW8fNxh+WKMpMU Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (FreeBSD) iD8DBQFGeV2QC3+MBN1Mb4gRAqlQAJ0ZYgIE+XLOWMzQrsfgDhphwXBQiACgjebD SV3Ga92+mDnqApRLi5vYLRw= =TnPy -----END PGP SIGNATURE----- --QfPW8fNxh+WKMpMU-- From owner-freebsd-fs@FreeBSD.ORG Wed Jun 20 17:20:34 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 021AB16A46F for ; Wed, 20 Jun 2007 17:20:34 +0000 (UTC) (envelope-from db@danielbond.org) Received: from mail.nsn.no (mailtwo.nsn.no [62.89.38.161]) by mx1.freebsd.org (Postfix) with SMTP id 5657013C455 for ; Wed, 20 Jun 2007 17:20:33 +0000 (UTC) (envelope-from db@danielbond.org) Received: (qmail 24480 invoked by uid 0); 20 Jun 2007 16:53:51 -0000 Received: from unknown (HELO ?172.16.3.90?) (85.95.44.187) by mail.nsn.no with SMTP; 20 Jun 2007 16:53:51 -0000 Message-ID: <46795B9F.8030108@danielbond.org> Date: Wed, 20 Jun 2007 18:53:51 +0200 From: Daniel Bond User-Agent: Thunderbird 1.5.0.12 (Windows/20070509) MIME-Version: 1.0 To: Vlad GURDIGA References: In-Reply-To: X-Enigmail-Version: 0.94.2.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org Subject: Re: fs cache 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, 20 Jun 2007 17:20:34 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Vlad GURDIGA wrote: > Hello, > > I have FreeBSD 7-CURRENT and Ubuntu on the same computer but Firefox > takes twice as long to start on a fresh boot. I've run some simple > tests: > - on FreeBSD it takes about 7 seconds on the first start and about 3 > on subsequent startups; > - on Ubuntu it takes about 3 seconds on the first start and about 1 on > subsequent startups; > > The only difference I can see is that on Ubuntu, after first start of > Firefox the memory use for cache is 22% vs. 0% on FreeBSD. My guess is > that this is the cause of slower startups on FreeBSD. > > My question is: can I tune UFS2 in such a way that the most frequently > used desktop applications would remain for a longer time in disk > cache? > > In both cases I use GNOME 2.18, GNOME System Monitor 2.18, and Firefox 2. > Both FreeBSD 7-CURRENT (src and ports tree) and Ubuntu 7.01 > (2.6.20-16-generic kernel) are up to date. Both are SMP and 32bit. > Here is the system configuration: > - Intel DP965LT mother-board; > - dual-core Pentium D 820; > - 1GB of dual-channel-enabled DDR2 PC5300 at 667 MHz; > - Seagate, BARRACUDA 7200.7 Plus, 160GB, ST3160827AS, 8M cache, with NCQ; > _______________________________________________ > 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" Hi, I would think it loads faster in linux due to a linux-feature called prelink. Most common applications make use of shared libraries. These shared libraries need to be loaded into memory at runtime and the various symbol references need to be resolved. For most small programs this dynamic linking is very quick. But for programs written in C++ and that have many library dependencies, the dynamic linking can take a fair amount of time. Prelinking does this in advance of starting the program, but it requires that user runs "prelink" every time libraries are updated. I think it is the effect of prelinking you are noticing here, ubuntu has it on by default as far as I know, and I guess that the package-manager does the prelinking for the user. - -CURRENT also has some extra debugging in kernel that slows things down. - -DB. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iD8DBQFGeVufUR3pKhqN0EoRAjKUAJ9/SAten1JcZWTkCgAludzhZhi11ACeMtr/ hn827NyiaVQAJApUbIctJaw= =ScVy -----END PGP SIGNATURE----- From owner-freebsd-fs@FreeBSD.ORG Wed Jun 20 18:23:34 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id AA66516A400 for ; Wed, 20 Jun 2007 18:23:34 +0000 (UTC) (envelope-from freebsd-fs@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.freebsd.org (Postfix) with ESMTP id 618D513C44B for ; Wed, 20 Jun 2007 18:23:34 +0000 (UTC) (envelope-from freebsd-fs@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1I14GT-0002aG-Lo for freebsd-fs@freebsd.org; Wed, 20 Jun 2007 19:46:45 +0200 Received: from 78-0-78-228.adsl.net.t-com.hr ([78.0.78.228]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 20 Jun 2007 19:46:45 +0200 Received: from ivoras by 78-0-78-228.adsl.net.t-com.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 20 Jun 2007 19:46:45 +0200 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-fs@freebsd.org From: Ivan Voras Date: Wed, 20 Jun 2007 19:31:35 +0200 Lines: 35 Message-ID: References: Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig0E208D8A37F367437639C9C3" X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: 78-0-78-228.adsl.net.t-com.hr User-Agent: Thunderbird 1.5.0.12 (Windows/20070509) In-Reply-To: X-Enigmail-Version: 0.94.3.0 Sender: news Subject: Re: fs cache 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, 20 Jun 2007 18:23:34 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig0E208D8A37F367437639C9C3 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Vlad GURDIGA wrote: > Hello, >=20 > I have FreeBSD 7-CURRENT and Ubuntu on the same computer but Firefox > takes twice as long to start on a fresh boot. I've run some simple > tests: > - on FreeBSD it takes about 7 seconds on the first start and about 3 > on subsequent startups; > - on Ubuntu it takes about 3 seconds on the first start and about 1 on > subsequent startups; Do you have debugging disabled in your 7-CURRENT? You should at least disable WITNESS and INVARIANTS in the kernel configuration. --------------enig0E208D8A37F367437639C9C3 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.4 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iD8DBQFGeWR3ldnAQVacBcgRAgpnAJ9Iif+K/acIgJkJ9ryeYh1DoWq7SgCfZ9Yx PGWDAMyVWnndl2uhUFv6b4E= =oLl+ -----END PGP SIGNATURE----- --------------enig0E208D8A37F367437639C9C3-- From owner-freebsd-fs@FreeBSD.ORG Wed Jun 20 19:36:37 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 9D28516A41F for ; Wed, 20 Jun 2007 19:36:37 +0000 (UTC) (envelope-from SRS0=5IyI=LU=ira.uka.de=esk@srs.kundenserver.de) Received: from moutng.kundenserver.de (moutng.kundenserver.de [212.227.126.174]) by mx1.freebsd.org (Postfix) with ESMTP id 317AE13C448 for ; Wed, 20 Jun 2007 19:36:36 +0000 (UTC) (envelope-from SRS0=5IyI=LU=ira.uka.de=esk@srs.kundenserver.de) Received: from [213.144.1.98] (helo=localhost) by mrelayeu.kundenserver.de (node=mrelayeu8) with ESMTP (Nemesis), id 0ML31I-1I15yB3hKr-00045m; Wed, 20 Jun 2007 21:36:34 +0200 From: Espen Skoglund MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <18041.33127.677804.653910@gargle.gargle.HOWL> Date: Wed, 20 Jun 2007 21:35:03 +0200 To: Kostik Belousov In-Reply-To: <20070620165746.GX2268@deviant.kiev.zoral.com.ua> References: <18041.21810.297355.202403@gargle.gargle.HOWL> <20070620165746.GX2268@deviant.kiev.zoral.com.ua> X-Mailer: VM 7.17 under 21.4 (patch 20) "Double Solitaire" XEmacs Lucid X-Provags-ID: V01U2FsdGVkX18ZXf4HfkAEDfFO2Mm1nVzer/m701slsnbeMdR yhhgbUs/CGWcnvAsdrKnR89PKiOZgs2izkNZrRLnqlnArO1S/r DrEZiquQ5megPa/yQBErQ== Cc: freebsd-fs@freebsd.org, Espen Skoglund Subject: Re: Snapshot usage guidelines (to avoid stability issues) 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, 20 Jun 2007 19:36:37 -0000 [Kostik Belousov] >> Looking at PRs and mailing lists there seems to be mainly two >> outstanding stability issues with snapshots: a) snapshotted fs >> running full, and b) deleting large amount of files on an fs with >> multiple snapshots. The former issue, while certainly annoying, >> one could be able to work around. The latter issue, on the other >> hand, seems more like a definite show stopper. >> >> Am I right in inferring that the two above cases are main issues >> with snaphots at this time, or are there other known gotchas that I >> have to look out for. > About the issue b). Are you system sources before or after > 2007-06-11 10:53:48 UTC ? Or simply show me the version of > sys/ufs/ffs/ffs_snapshot.c. > If it is less then 1.103.2.24, see developers handbook for > instruction on reporting deadlocks. Ok. Thanks. Looking at the CVS logs after the hangup I wasn't sure whether the last commits addressed any of my problems. My kernel was from June 9, so I just missed the update you refer to. Unfortunately I didn't have any debug options turned on in my kernel. Also, I wasn't able to log into the system in any way so there was not much information I could gather. Will try the update once I find a suitable time that doesn't mess up my/our work schedule. If the update does indeed solve problem (b) then I can actually make use of snapshots. Huzzah! eSk From owner-freebsd-fs@FreeBSD.ORG Wed Jun 20 22:45:38 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 264FD16A46C for ; Wed, 20 Jun 2007 22:45:37 +0000 (UTC) (envelope-from cristi@net.utcluj.ro) Received: from bavaria.utcluj.ro (bavaria.utcluj.ro [193.226.5.35]) by mx1.freebsd.org (Postfix) with ESMTP id 3FF3F13C457 for ; Wed, 20 Jun 2007 22:45:37 +0000 (UTC) (envelope-from cristi@net.utcluj.ro) Received: from localhost (localhost [127.0.0.1]) by bavaria.utcluj.ro (Postfix) with ESMTP id DDFA65082A; Thu, 21 Jun 2007 01:45:35 +0300 (EEST) X-Virus-Scanned: by the daemon playing with your mail on bavaria.utcluj.ro Received: from bavaria.utcluj.ro ([127.0.0.1]) by localhost (bavaria.utcluj.ro [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id B0pc6fi4uy4g; Thu, 21 Jun 2007 01:45:32 +0300 (EEST) Received: from [172.27.2.200] (c7.campus.utcluj.ro [193.226.6.226]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by bavaria.utcluj.ro (Postfix) with ESMTP id BE32450821; Thu, 21 Jun 2007 01:45:32 +0300 (EEST) Message-ID: <4679AE0C.5040306@net.utcluj.ro> Date: Thu, 21 Jun 2007 01:45:32 +0300 From: Cristian KLEIN Organization: Data Communication Center - Technical University of Cluj-Napoca User-Agent: Thunderbird 1.5.0.12 (X11/20070604) MIME-Version: 1.0 To: Kostik Belousov References: <18041.21810.297355.202403@gargle.gargle.HOWL> <20070620165746.GX2268@deviant.kiev.zoral.com.ua> In-Reply-To: <20070620165746.GX2268@deviant.kiev.zoral.com.ua> X-Enigmail-Version: 0.94.0.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org, Espen Skoglund Subject: Re: Snapshot usage guidelines (to avoid stability issues) 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, 20 Jun 2007 22:45:38 -0000 Kostik Belousov wrote: > On Wed, Jun 20, 2007 at 06:26:26PM +0200, Espen Skoglund wrote: >> Hi, >> >> A couple of days ago I decided to start using snapshots on my system. >> Knowing that the functionality has been available for quite some time >> now I (apparently wrongly) assumed that it was ready for production >> use. My bad. >> >> My system, a 6-STABLE from week and a half ago, uses two 250GB >> gstriped disks and has about 4-5 snapshots on one 215GB UFS partiton. >> This morning I learned that things had gone terribly wrong during some >> nightly cronjobs, hanging the whole system. Suspecting that snapshots >> were the culprit I soon learned after some investigation that the >> snapshot functionality wasn't nearly as stable as I had hoped for. >> >> Looking at PRs and mailing lists there seems to be mainly two >> outstanding stability issues with snapshots: a) snapshotted fs running >> full, and b) deleting large amount of files on an fs with multiple >> snapshots. The former issue, while certainly annoying, one could be >> able to work around. The latter issue, on the other hand, seems more >> like a definite show stopper. >> >> Am I right in inferring that the two above cases are main issues with >> snaphots at this time, or are there other known gotchas that I have to >> look out for. > About the issue b). Are you system sources before or after 2007-06-11 > 10:53:48 UTC ? Or simply show me the version of sys/ufs/ffs/ffs_snapshot.c. > > If it is less then 1.103.2.24, see developers handbook for instruction on > reporting deadlocks. > Do you think that 1.103.2.24 might solve this http://lists.freebsd.org/pipermail/freebsd-fs/2007-May/003161.html ? From owner-freebsd-fs@FreeBSD.ORG Thu Jun 21 00:57:28 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 69D4E16A468 for ; Thu, 21 Jun 2007 00:57:28 +0000 (UTC) (envelope-from tom.hurst@clara.net) Received: from spork.qfe3.net (spork.qfe3.net [212.13.207.101]) by mx1.freebsd.org (Postfix) with ESMTP id 2F36913C469 for ; Thu, 21 Jun 2007 00:57:27 +0000 (UTC) (envelope-from tom.hurst@clara.net) Received: from [81.104.144.87] (helo=voi.aagh.net) by spork.qfe3.net with esmtp (Exim 4.66 (FreeBSD)) (envelope-from ) id 1I1AeU-000Lgk-Gv; Thu, 21 Jun 2007 01:35:58 +0100 Received: from freaky by voi.aagh.net with local (Exim 4.67 (FreeBSD)) (envelope-from ) id 1I1AeU-000F4z-8R; Thu, 21 Jun 2007 01:35:58 +0100 Date: Thu, 21 Jun 2007 01:35:58 +0100 From: Thomas Hurst To: Vlad GURDIGA Message-ID: <20070621003558.GA55731@voi.aagh.net> Mail-Followup-To: Vlad GURDIGA , freebsd-fs@freebsd.org References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: Organization: Not much. User-Agent: Mutt/1.5.15 (2007-04-06) Sender: Thomas Hurst Cc: freebsd-fs@freebsd.org Subject: Re: fs cache 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, 21 Jun 2007 00:57:28 -0000 * Vlad GURDIGA (gurdiga@gmail.com) wrote: > The only difference I can see is that on Ubuntu, after first start of > Firefox the memory use for cache is 22% vs. 0% on FreeBSD. My guess is > that this is the cause of slower startups on FreeBSD. If you mean the "Cache" value in top, that's quite normal; "Cache" in FreeBSD doesn't mean quite the same as it does in Linux -- it's just one of several queues VM pages churn through depending on usage patterns and memory pressure. Most cached data will tend to reside in "Inact", where it's ready for quick use and modification, and it only cycles to "Cache" when the VM decides it's worth making clean (flushing to backing store if necessary) and marking read-only so it can be reused quickly (i.e. without touching a disk). And yes, Ubuntu doubtless does fancy prelinking/binding magic. This is a project idea listed on http://www.freebsd.org/projects/ideas/ and has had several attempts in the past from the look of it. -- Thomas 'Freaky' Hurst http://hur.st/ From owner-freebsd-fs@FreeBSD.ORG Thu Jun 21 09:03:53 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 4001016A41F for ; Thu, 21 Jun 2007 09:03:53 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from relay02.kiev.sovam.com (relay02.kiev.sovam.com [62.64.120.197]) by mx1.freebsd.org (Postfix) with ESMTP id CBC5F13C455 for ; Thu, 21 Jun 2007 09:03:52 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from [89.162.146.170] (helo=skuns.kiev.zoral.com.ua) by relay02.kiev.sovam.com with esmtps (TLSv1:AES256-SHA:256) (Exim 4.67) (envelope-from ) id 1I1IZy-000ALI-3f for freebsd-fs@freebsd.org; Thu, 21 Jun 2007 12:03:51 +0300 Received: from deviant.kiev.zoral.com.ua (root@deviant.kiev.zoral.com.ua [10.1.1.148]) by skuns.kiev.zoral.com.ua (8.14.1/8.14.1) with ESMTP id l5L93T4A066438 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Thu, 21 Jun 2007 12:03:29 +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 (8.14.1/8.14.1) with ESMTP id l5L93Z8O046362; Thu, 21 Jun 2007 12:03:35 +0300 (EEST) (envelope-from kostikbel@gmail.com) Received: (from kostik@localhost) by deviant.kiev.zoral.com.ua (8.14.1/8.14.1/Submit) id l5L93XCm046361; Thu, 21 Jun 2007 12:03:33 +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: Thu, 21 Jun 2007 12:03:33 +0300 From: Kostik Belousov To: Cristian KLEIN Message-ID: <20070621090333.GA2268@deviant.kiev.zoral.com.ua> References: <18041.21810.297355.202403@gargle.gargle.HOWL> <20070620165746.GX2268@deviant.kiev.zoral.com.ua> <4679AE0C.5040306@net.utcluj.ro> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="Vwd26Opu41siI++W" Content-Disposition: inline In-Reply-To: <4679AE0C.5040306@net.utcluj.ro> User-Agent: Mutt/1.4.2.2i X-Virus-Scanned: ClamAV version 0.90.2, clamav-milter version 0.90.2 on skuns.kiev.zoral.com.ua X-Virus-Status: Clean X-Spam-Status: No, score=-1.4 required=5.0 tests=ALL_TRUSTED autolearn=failed version=3.1.8 X-Spam-Checker-Version: SpamAssassin 3.1.8 (2007-02-13) on skuns.kiev.zoral.com.ua X-Scanner-Signature: 96b5a640d20a32298b7e0b1f479135d9 X-DrWeb-checked: yes X-SpamTest-Envelope-From: kostikbel@gmail.com X-SpamTest-Group-ID: 00000000 X-SpamTest-Header: Not Detected X-SpamTest-Info: Profiles 1162 [June 20 2007] X-SpamTest-Info: helo_type=3 X-SpamTest-Method: none X-SpamTest-Rate: 0 X-SpamTest-Status: Not detected X-SpamTest-Status-Extended: not_detected X-SpamTest-Version: SMTP-Filter Version 3.0.0 [0255], KAS30/Release Cc: freebsd-fs@freebsd.org, Espen Skoglund Subject: Re: Snapshot usage guidelines (to avoid stability issues) 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, 21 Jun 2007 09:03:53 -0000 --Vwd26Opu41siI++W Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Thu, Jun 21, 2007 at 01:45:32AM +0300, Cristian KLEIN wrote: > Kostik Belousov wrote: > > On Wed, Jun 20, 2007 at 06:26:26PM +0200, Espen Skoglund wrote: > >> Hi, > >> > >> A couple of days ago I decided to start using snapshots on my system. > >> Knowing that the functionality has been available for quite some time > >> now I (apparently wrongly) assumed that it was ready for production > >> use. My bad. > >> > >> My system, a 6-STABLE from week and a half ago, uses two 250GB > >> gstriped disks and has about 4-5 snapshots on one 215GB UFS partiton. > >> This morning I learned that things had gone terribly wrong during some > >> nightly cronjobs, hanging the whole system. Suspecting that snapshots > >> were the culprit I soon learned after some investigation that the > >> snapshot functionality wasn't nearly as stable as I had hoped for. > >> > >> Looking at PRs and mailing lists there seems to be mainly two > >> outstanding stability issues with snapshots: a) snapshotted fs running > >> full, and b) deleting large amount of files on an fs with multiple > >> snapshots. The former issue, while certainly annoying, one could be > >> able to work around. The latter issue, on the other hand, seems more > >> like a definite show stopper. > >> > >> Am I right in inferring that the two above cases are main issues with > >> snaphots at this time, or are there other known gotchas that I have to > >> look out for. > > About the issue b). Are you system sources before or after 2007-06-11 > > 10:53:48 UTC ? Or simply show me the version of sys/ufs/ffs/ffs_snapsho= t.c. > >=20 > > If it is less then 1.103.2.24, see developers handbook for instruction = on > > reporting deadlocks. > >=20 >=20 > Do you think that 1.103.2.24 might solve this > http://lists.freebsd.org/pipermail/freebsd-fs/2007-May/003161.html ? I very much doubt it. AFAIR, I asked at least ddb backtrace for the crash, and you did not answered. --Vwd26Opu41siI++W Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (FreeBSD) iD8DBQFGej7kC3+MBN1Mb4gRAifUAJ46RwdwbsbAWtavTgZpb7NzC2psPQCgqLny 0G0/tpm9ALfalyHgHAYr3WY= =3+qz -----END PGP SIGNATURE----- --Vwd26Opu41siI++W-- From owner-freebsd-fs@FreeBSD.ORG Thu Jun 21 09:32:48 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 038E416A46B for ; Thu, 21 Jun 2007 09:32:48 +0000 (UTC) (envelope-from cristi@net.utcluj.ro) Received: from bavaria.utcluj.ro (bavaria.utcluj.ro [193.226.5.35]) by mx1.freebsd.org (Postfix) with ESMTP id ADEB213C448 for ; Thu, 21 Jun 2007 09:32:47 +0000 (UTC) (envelope-from cristi@net.utcluj.ro) Received: from localhost (localhost [127.0.0.1]) by bavaria.utcluj.ro (Postfix) with ESMTP id 5C46650853; Thu, 21 Jun 2007 12:32:46 +0300 (EEST) X-Virus-Scanned: by the daemon playing with your mail on bavaria.utcluj.ro Received: from bavaria.utcluj.ro ([127.0.0.1]) by localhost (bavaria.utcluj.ro [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id TddlB8QkqtZQ; Thu, 21 Jun 2007 12:32:43 +0300 (EEST) Received: from [10.132.7.254] (hades.eduroam.int.utcluj.ro [10.132.7.254]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by bavaria.utcluj.ro (Postfix) with ESMTP id E2AC450865; Thu, 21 Jun 2007 12:32:42 +0300 (EEST) Message-ID: <467A45B8.3070303@net.utcluj.ro> Date: Thu, 21 Jun 2007 12:32:40 +0300 From: Cristian KLEIN Organization: Data Communication Center - Technical University of Cluj-Napoca User-Agent: Thunderbird 1.5.0.12 (X11/20070604) MIME-Version: 1.0 To: Kostik Belousov References: <18041.21810.297355.202403@gargle.gargle.HOWL> <20070620165746.GX2268@deviant.kiev.zoral.com.ua> <4679AE0C.5040306@net.utcluj.ro> <20070621090333.GA2268@deviant.kiev.zoral.com.ua> In-Reply-To: <20070621090333.GA2268@deviant.kiev.zoral.com.ua> X-Enigmail-Version: 0.94.0.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org, Espen Skoglund Subject: Re: Snapshot usage guidelines (to avoid stability issues) 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, 21 Jun 2007 09:32:48 -0000 Kostik Belousov wrote: > On Thu, Jun 21, 2007 at 01:45:32AM +0300, Cristian KLEIN wrote: >> Kostik Belousov wrote: >>> On Wed, Jun 20, 2007 at 06:26:26PM +0200, Espen Skoglund wrote: >>>> Hi, >>>> >>>> A couple of days ago I decided to start using snapshots on my system. >>>> Knowing that the functionality has been available for quite some time >>>> now I (apparently wrongly) assumed that it was ready for production >>>> use. My bad. >>>> >>>> My system, a 6-STABLE from week and a half ago, uses two 250GB >>>> gstriped disks and has about 4-5 snapshots on one 215GB UFS partiton. >>>> This morning I learned that things had gone terribly wrong during some >>>> nightly cronjobs, hanging the whole system. Suspecting that snapshots >>>> were the culprit I soon learned after some investigation that the >>>> snapshot functionality wasn't nearly as stable as I had hoped for. >>>> >>>> Looking at PRs and mailing lists there seems to be mainly two >>>> outstanding stability issues with snapshots: a) snapshotted fs running >>>> full, and b) deleting large amount of files on an fs with multiple >>>> snapshots. The former issue, while certainly annoying, one could be >>>> able to work around. The latter issue, on the other hand, seems more >>>> like a definite show stopper. >>>> >>>> Am I right in inferring that the two above cases are main issues with >>>> snaphots at this time, or are there other known gotchas that I have to >>>> look out for. >>> About the issue b). Are you system sources before or after 2007-06-11 >>> 10:53:48 UTC ? Or simply show me the version of sys/ufs/ffs/ffs_snapshot.c. >>> >>> If it is less then 1.103.2.24, see developers handbook for instruction on >>> reporting deadlocks. >>> >> Do you think that 1.103.2.24 might solve this >> http://lists.freebsd.org/pipermail/freebsd-fs/2007-May/003161.html ? > I very much doubt it. AFAIR, I asked at least ddb backtrace for the crash, > and you did not answered. I'm really sorry, but I wasn't able to reproduce the problem on another system. I tried taking / deleting many snapshots while running bonnie++, but the panic would not occur. I have 1,7mil inodes (4% utilization) on the server where the crash occured. Might this be a prerequisite of the panic? From owner-freebsd-fs@FreeBSD.ORG Thu Jun 21 10:10:51 2007 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 2B96616A46C for ; Thu, 21 Jun 2007 10:10:51 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from relay02.kiev.sovam.com (relay02.kiev.sovam.com [62.64.120.197]) by mx1.freebsd.org (Postfix) with ESMTP id B7F8913C4BD for ; Thu, 21 Jun 2007 10:10:50 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from [89.162.146.170] (helo=skuns.kiev.zoral.com.ua) by relay02.kiev.sovam.com with esmtps (TLSv1:AES256-SHA:256) (Exim 4.67) (envelope-from ) id 1I1Jck-000EZr-Kv for freebsd-fs@freebsd.org; Thu, 21 Jun 2007 13:10:49 +0300 Received: from deviant.kiev.zoral.com.ua (root@deviant.kiev.zoral.com.ua [10.1.1.148]) by skuns.kiev.zoral.com.ua (8.14.1/8.14.1) with ESMTP id l5LAASXR067911 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Thu, 21 Jun 2007 13:10:28 +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 (8.14.1/8.14.1) with ESMTP id l5LAAY0U061027; Thu, 21 Jun 2007 13:10:34 +0300 (EEST) (envelope-from kostikbel@gmail.com) Received: (from kostik@localhost) by deviant.kiev.zoral.com.ua (8.14.1/8.14.1/Submit) id l5LAAYjS061026; Thu, 21 Jun 2007 13:10:34 +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: Thu, 21 Jun 2007 13:10:34 +0300 From: Kostik Belousov To: Cristian KLEIN Message-ID: <20070621101034.GB2268@deviant.kiev.zoral.com.ua> References: <18041.21810.297355.202403@gargle.gargle.HOWL> <20070620165746.GX2268@deviant.kiev.zoral.com.ua> <4679AE0C.5040306@net.utcluj.ro> <20070621090333.GA2268@deviant.kiev.zoral.com.ua> <467A45B8.3070303@net.utcluj.ro> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="2tb6s275ZjQu9Nb2" Content-Disposition: inline In-Reply-To: <467A45B8.3070303@net.utcluj.ro> User-Agent: Mutt/1.4.2.2i X-Virus-Scanned: ClamAV version 0.90.2, clamav-milter version 0.90.2 on skuns.kiev.zoral.com.ua X-Virus-Status: Clean X-Spam-Status: No, score=-1.4 required=5.0 tests=ALL_TRUSTED autolearn=failed version=3.1.8 X-Spam-Checker-Version: SpamAssassin 3.1.8 (2007-02-13) on skuns.kiev.zoral.com.ua X-Scanner-Signature: efe3bc1504fa577d936f03857ce6b673 X-DrWeb-checked: yes X-SpamTest-Envelope-From: kostikbel@gmail.com X-SpamTest-Group-ID: 00000000 X-SpamTest-Header: Not Detected X-SpamTest-Info: Profiles 1162 [June 20 2007] X-SpamTest-Info: helo_type=3 X-SpamTest-Method: none X-SpamTest-Rate: 0 X-SpamTest-Status: Not detected X-SpamTest-Status-Extended: not_detected X-SpamTest-Version: SMTP-Filter Version 3.0.0 [0255], KAS30/Release Cc: freebsd-fs@freebsd.org, Espen Skoglund Subject: Re: Snapshot usage guidelines (to avoid stability issues) 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, 21 Jun 2007 10:10:51 -0000 --2tb6s275ZjQu9Nb2 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Thu, Jun 21, 2007 at 12:32:40PM +0300, Cristian KLEIN wrote: > Kostik Belousov wrote: > > On Thu, Jun 21, 2007 at 01:45:32AM +0300, Cristian KLEIN wrote: > >> Kostik Belousov wrote: > >>> On Wed, Jun 20, 2007 at 06:26:26PM +0200, Espen Skoglund wrote: > >>>> Hi, > >>>> > >>>> A couple of days ago I decided to start using snapshots on my system. > >>>> Knowing that the functionality has been available for quite some time > >>>> now I (apparently wrongly) assumed that it was ready for production > >>>> use. My bad. > >>>> > >>>> My system, a 6-STABLE from week and a half ago, uses two 250GB > >>>> gstriped disks and has about 4-5 snapshots on one 215GB UFS partiton. > >>>> This morning I learned that things had gone terribly wrong during so= me > >>>> nightly cronjobs, hanging the whole system. Suspecting that snapsho= ts > >>>> were the culprit I soon learned after some investigation that the > >>>> snapshot functionality wasn't nearly as stable as I had hoped for. > >>>> > >>>> Looking at PRs and mailing lists there seems to be mainly two > >>>> outstanding stability issues with snapshots: a) snapshotted fs runni= ng > >>>> full, and b) deleting large amount of files on an fs with multiple > >>>> snapshots. The former issue, while certainly annoying, one could be > >>>> able to work around. The latter issue, on the other hand, seems more > >>>> like a definite show stopper. > >>>> > >>>> Am I right in inferring that the two above cases are main issues with > >>>> snaphots at this time, or are there other known gotchas that I have = to > >>>> look out for. > >>> About the issue b). Are you system sources before or after 2007-06-11 > >>> 10:53:48 UTC ? Or simply show me the version of sys/ufs/ffs/ffs_snaps= hot.c. > >>> > >>> If it is less then 1.103.2.24, see developers handbook for instructio= n on > >>> reporting deadlocks. > >>> > >> Do you think that 1.103.2.24 might solve this > >> http://lists.freebsd.org/pipermail/freebsd-fs/2007-May/003161.html ? > > I very much doubt it. AFAIR, I asked at least ddb backtrace for the cra= sh, > > and you did not answered. >=20 > I'm really sorry, but I wasn't able to reproduce the problem on another > system. I tried taking / deleting many snapshots while running bonnie++, > but the panic would not occur. >=20 > I have 1,7mil inodes (4% utilization) on the server where the crash > occured. Might this be a prerequisite of the panic? It may be related to inode/cyl groups density ratio. --2tb6s275ZjQu9Nb2 Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (FreeBSD) iD8DBQFGek6ZC3+MBN1Mb4gRAstNAKC5IbY1VwR4Jw4zztHl5JmcTdoe/wCbB57x WHUI39TyrcDwt5DPVPV8BPk= =Kp/i -----END PGP SIGNATURE----- --2tb6s275ZjQu9Nb2--