From owner-freebsd-fs@FreeBSD.ORG Sun Oct 31 05:59:51 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C5B0A106564A; Sun, 31 Oct 2010 05:59:51 +0000 (UTC) (envelope-from avg@icyb.net.ua) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id D5E918FC08; Sun, 31 Oct 2010 05:59:50 +0000 (UTC) Received: from porto.topspin.kiev.ua (porto-e.starpoint.kiev.ua [212.40.38.100]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id HAA29149; Sun, 31 Oct 2010 07:59:45 +0200 (EET) (envelope-from avg@icyb.net.ua) Received: from localhost.topspin.kiev.ua ([127.0.0.1]) by porto.topspin.kiev.ua with esmtp (Exim 4.34 (FreeBSD)) id 1PCQxE-000OpJ-RK; Sun, 31 Oct 2010 07:59:44 +0200 Message-ID: <4CCD05CF.8080301@icyb.net.ua> Date: Sun, 31 Oct 2010 07:59:43 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.12) Gecko/20101029 Lightning/1.0b2 Thunderbird/3.1.6 MIME-Version: 1.0 To: Kostik Belousov References: <4CCAF0EB.4080001@icyb.net.ua> <20101029175105.GB18613@two.kliksys.ru> <4CCBD443.7010305@icyb.net.ua> <4CCBD46E.9030200@icyb.net.ua> <4CCBD661.3000204@freebsd.org> <4CCBEAF6.2030408@freebsd.org> <20101030101254.GB79691@two.kliksys.ru> <4CCBF45C.4080208@icyb.net.ua> <20101030112520.GD79691@two.kliksys.ru> <4CCC2F2A.7020809@icyb.net.ua> <20101030233739.GE2392@deviant.kiev.zoral.com.ua> In-Reply-To: <20101030233739.GE2392@deviant.kiev.zoral.com.ua> X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org, freebsd-stable@freebsd.org Subject: Re: 8.1-STABLE: zfs and sendfile: problem still exists 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, 31 Oct 2010 05:59:51 -0000 on 31/10/2010 02:37 Kostik Belousov said the following: > On Sat, Oct 30, 2010 at 05:43:54PM +0300, Andriy Gapon wrote: >> on 30/10/2010 14:25 Artemiev Igor said the following: >>> On Sat, Oct 30, 2010 at 01:33:00PM +0300, Andriy Gapon wrote: >>>> on 30/10/2010 13:12 Artemiev Igor said the following: >>>>> On Sat, Oct 30, 2010 at 12:52:54PM +0300, Andriy Gapon wrote: >>>>> >>>>>> Heh, next try. >>>>> >>>>> Got a panic, "vm_page_unwire: invalid wire count: 0" >>>> >>>> Oh, thank you for testing - forgot another piece (VM_ALLOC_WIRE for vm_page_alloc): >>> >>> Yep, it work. But VM_ALLOC_WIRE not exists in RELENG_8, therefore i slightly modified your patch: >> >> I apologize for my haste, it should have been VM_ALLOC_WIRED. >> Here is a corrected patch: >> Index: sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_vnops.c >> =================================================================== >> --- sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_vnops.c (revision 214318) >> +++ sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_vnops.c (working copy) >> @@ -67,6 +67,7 @@ >> #include >> #include >> #include >> +#include >> >> /* >> * Programming rules. >> @@ -464,7 +465,7 @@ >> uiomove_fromphys(&m, off, bytes, uio); >> VM_OBJECT_LOCK(obj); >> vm_page_wakeup(m); >> - } else if (m != NULL && uio->uio_segflg == UIO_NOCOPY) { >> + } else if (uio->uio_segflg == UIO_NOCOPY) { >> /* >> * The code below is here to make sendfile(2) work >> * correctly with ZFS. As pointed out by ups@ >> @@ -474,9 +475,23 @@ >> */ >> KASSERT(off == 0, >> ("unexpected offset in mappedread for sendfile")); >> - if (vm_page_sleep_if_busy(m, FALSE, "zfsmrb")) >> + if (m != NULL && vm_page_sleep_if_busy(m, FALSE, "zfsmrb")) >> goto again; >> - vm_page_busy(m); >> + if (m == NULL) { >> + m = vm_page_alloc(obj, OFF_TO_IDX(start), >> + VM_ALLOC_NOBUSY | VM_ALLOC_WIRED | VM_ALLOC_NORMAL); >> + if (m == NULL) { >> + VM_OBJECT_UNLOCK(obj); >> + VM_WAIT; >> + VM_OBJECT_LOCK(obj); >> + goto again; >> + } >> + } else { >> + vm_page_lock_queues(); >> + vm_page_wire(m); >> + vm_page_unlock_queues(); >> + } >> + vm_page_io_start(m); > Why wiring the page if it is busied ? Eh? Because it is not? -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Sun Oct 31 06:09:14 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id E5A9F1065673; Sun, 31 Oct 2010 06:09:14 +0000 (UTC) (envelope-from avg@icyb.net.ua) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id 049378FC12; Sun, 31 Oct 2010 06:09:13 +0000 (UTC) Received: from porto.topspin.kiev.ua (porto-e.starpoint.kiev.ua [212.40.38.100]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id IAA29229; Sun, 31 Oct 2010 08:09:09 +0200 (EET) (envelope-from avg@icyb.net.ua) Received: from localhost.topspin.kiev.ua ([127.0.0.1]) by porto.topspin.kiev.ua with esmtp (Exim 4.34 (FreeBSD)) id 1PCR6K-000Opx-Rt; Sun, 31 Oct 2010 08:09:08 +0200 Message-ID: <4CCD0804.8010703@icyb.net.ua> Date: Sun, 31 Oct 2010 08:09:08 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.12) Gecko/20101029 Lightning/1.0b2 Thunderbird/3.1.6 MIME-Version: 1.0 To: Artemiev Igor References: <4CCAF0EB.4080001@icyb.net.ua> <20101029175105.GB18613@two.kliksys.ru> <4CCBD443.7010305@icyb.net.ua> <4CCBD46E.9030200@icyb.net.ua> <4CCBD661.3000204@freebsd.org> <4CCBEAF6.2030408@freebsd.org> <20101030101254.GB79691@two.kliksys.ru> <4CCBF45C.4080208@icyb.net.ua> <20101030112520.GD79691@two.kliksys.ru> <4CCC2F2A.7020809@icyb.net.ua> <20101030190120.GA80301@two.kliksys.ru> In-Reply-To: <20101030190120.GA80301@two.kliksys.ru> X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org, freebsd-stable@freebsd.org Subject: Re: 8.1-STABLE: zfs and sendfile: problem still exists 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, 31 Oct 2010 06:09:15 -0000 on 30/10/2010 22:01 Artemiev Igor said the following: > On Sat, Oct 30, 2010 at 05:43:54PM +0300, Andriy Gapon wrote: > >> I apologize for my haste, it should have been VM_ALLOC_WIRED. > > Ok, applied and tested under some load(~1200 active connections, outgoing > ~80MB/s). Patch work as expected and i has noted no side effects. Just one > question - should grow Active memory counter, if some pages is "hot"(during > multiple sendfile on one file)? Pages used by sendfile are marked as Inactive for faster reclamation on demand. -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Sun Oct 31 09:02:49 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id DAAA4106566C; Sun, 31 Oct 2010 09:02:49 +0000 (UTC) (envelope-from alexz@visp.ru) Received: from mail.visp.ru (srv1.visp.ru [91.215.204.2]) by mx1.freebsd.org (Postfix) with ESMTP id 8BB238FC19; Sun, 31 Oct 2010 09:02:47 +0000 (UTC) Received: from 91-215-205-255.static.visp.ru ([91.215.205.255] helo=zagrebin) by mail.visp.ru with esmtp (Exim 4.72 (FreeBSD)) (envelope-from ) id 1PCToL-0000tt-3X; Sun, 31 Oct 2010 12:02:45 +0300 From: "Alexander Zagrebin" To: "'Andriy Gapon'" References: <4CCAF0EB.4080001@icyb.net.ua> <20101029175105.GB18613@two.kliksys.ru> <4CCBD443.7010305@icyb.net.ua><4CCBD46E.9030200@icyb.net.ua> <4CCBD661.3000204@freebsd.org><4CCBEAF6.2030408@freebsd.org> <20101030101254.GB79691@two.kliksys.ru> <4CCBF45C.4080208@icyb.net.ua> <20101030112520.GD79691@two.kliksys.ru> <4CCC2F2A.7020809@icyb.net.ua><20101030190120.GA80301@two.kliksys.ru> <4CCD0804.8010703@icyb.net.ua> Date: Sun, 31 Oct 2010 12:02:44 +0300 Keywords: freebsd-fs Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="koi8-r" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook 11 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.5512 In-Reply-To: <4CCD0804.8010703@icyb.net.ua> Thread-Index: Act4wku/wmVwJWj2TD2hR3M6uk44wAAEHgaA Cc: freebsd-fs@freebsd.org, freebsd-stable@freebsd.org Subject: RE: 8.1-STABLE: zfs and sendfile: problem still exists 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, 31 Oct 2010 09:02:49 -0000 > >> I apologize for my haste, it should have been VM_ALLOC_WIRED. > > > > Ok, applied and tested under some load(~1200 active > connections, outgoing > > ~80MB/s). Patch work as expected and i has noted no side > effects. Just one > > question - should grow Active memory counter, if some pages > is "hot"(during > > multiple sendfile on one file)? > > Pages used by sendfile are marked as Inactive for faster > reclamation on demand. I have a question. When we transfer a file via sendfile, then current code allocates a memory, marked inactive. For example, if the file has size 100 MB, then 100 MB of memory will be allocated. If we have to transfer this file again later, then this memory will used as cache, and no disk io will be required. The memory will be freed if file will be deleted or operating system will need an additional memory. I have correctly understood? If it so, the i continue... Such behaviour is good if we have files with relatively small size. Suppose we have to transfer file with large size (for example, greater than amount of physical memory). While transfering, the inactive memory will grow, pressing the ARC. When size of the ARC will fall to its minimum (vfs.zfs.arc_min), then inactive memory will be reused. So, when transfer is complete, we have: 1. No free memory 2. Size of the ARC has minimal size (it is bad) 3. Inactive memory contains the _tail_ of the file only (it is bad too) Now if we have to transfer this file again, then 1. there is no (or few) file's data in ARC (ARC too small) 2. The inactive memory doesn't contain a head part of the file So the file's data will read from a disk again and again... Also i've noticed that inactive memory frees relatively slowly, so if there is a frequent access to large files, then system will run at very unoptimal conditions. It's imho... Can you comment this? -- Alexander Zagrebin From owner-freebsd-fs@FreeBSD.ORG Sun Oct 31 09:47:23 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 7B3FB1065670; Sun, 31 Oct 2010 09:47:23 +0000 (UTC) (envelope-from ronald-freebsd8@klop.yi.org) Received: from smtp-out2.tiscali.nl (smtp-out2.tiscali.nl [195.241.79.177]) by mx1.freebsd.org (Postfix) with ESMTP id 085F78FC0A; Sun, 31 Oct 2010 09:47:22 +0000 (UTC) Received: from [212.123.145.58] (helo=sjakie.klop.ws) by smtp-out2.tiscali.nl with esmtp (Exim) (envelope-from ) id 1PCUVV-0005qu-PV; Sun, 31 Oct 2010 10:47:21 +0100 Received: from 212-123-145-58.ip.telfort.nl (localhost [127.0.0.1]) by sjakie.klop.ws (Postfix) with ESMTP id 2FDE3E08D; Sun, 31 Oct 2010 10:47:14 +0100 (CET) Content-Type: text/plain; charset=us-ascii; format=flowed; delsp=yes To: "'Andriy Gapon'" , "Alexander Zagrebin" References: <4CCAF0EB.4080001@icyb.net.ua> <20101029175105.GB18613@two.kliksys.ru> <4CCBD443.7010305@icyb.net.ua> <4CCBD46E.9030200@icyb.net.ua> <4CCBD661.3000204@freebsd.org> <4CCBEAF6.2030408@freebsd.org> <20101030101254.GB79691@two.kliksys.ru> <4CCBF45C.4080208@icyb.net.ua> <20101030112520.GD79691@two.kliksys.ru> <4CCC2F2A.7020809@icyb.net.ua> <20101030190120.GA80301@two.kliksys.ru> <4CCD0804.8010703@icyb.net.ua> Date: Sun, 31 Oct 2010 10:47:13 +0100 MIME-Version: 1.0 From: "Ronald Klop" Message-ID: In-Reply-To: User-Agent: Opera Mail/10.62 (FreeBSD) Content-Transfer-Encoding: quoted-printable Cc: freebsd-fs@freebsd.org, freebsd-stable@freebsd.org Subject: Re: 8.1-STABLE: zfs and sendfile: problem still exists 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, 31 Oct 2010 09:47:23 -0000 On Sun, 31 Oct 2010 10:02:44 +0100, Alexander Zagrebin =20 wrote: >> >> I apologize for my haste, it should have been VM_ALLOC_WIRED. >> > >> > Ok, applied and tested under some load(~1200 active >> connections, outgoing >> > ~80MB/s). Patch work as expected and i has noted no side >> effects. Just one >> > question - should grow Active memory counter, if some pages >> is "hot"(during >> > multiple sendfile on one file)? >> >> Pages used by sendfile are marked as Inactive for faster >> reclamation on demand. > > I have a question. > When we transfer a file via sendfile, then current code allocates > a memory, marked inactive. For example, if the file has size 100 MB, > then 100 MB of memory will be allocated. > If we have to transfer this file again later, then this memory will use= d > as cache, and no disk io will be required. > The memory will be freed if file will be deleted or operating system > will need an additional memory. > I have correctly understood? > If it so, the i continue... > Such behaviour is good if we have files with relatively small size. > Suppose we have to transfer file with large size (for example, greater > than amount of physical memory). > While transfering, the inactive memory will grow, pressing the ARC. > When size of the ARC will fall to its minimum (vfs.zfs.arc_min), then > inactive memory will be reused. > So, when transfer is complete, we have: > 1. No free memory > 2. Size of the ARC has minimal size (it is bad) > 3. Inactive memory contains the _tail_ of the file only (it is bad too) > Now if we have to transfer this file again, then > 1. there is no (or few) file's data in ARC (ARC too small) > 2. The inactive memory doesn't contain a head part of the file > So the file's data will read from a disk again and again... > Also i've noticed that inactive memory frees relatively slowly, > so if there is a frequent access to large files, then system will run > at very unoptimal conditions. > It's imho... > Can you comment this? > Add more RAM? From owner-freebsd-fs@FreeBSD.ORG Sun Oct 31 09:56:33 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 10C39106566C for ; Sun, 31 Oct 2010 09:56:33 +0000 (UTC) (envelope-from freebsd-listen@fabiankeil.de) Received: from smtprelay03.ispgateway.de (smtprelay03.ispgateway.de [80.67.29.28]) by mx1.freebsd.org (Postfix) with ESMTP id 56C838FC0A for ; Sun, 31 Oct 2010 09:56:32 +0000 (UTC) Received: from [87.78.57.188] (helo=r500.local) by smtprelay03.ispgateway.de with esmtpsa (TLSv1:AES128-SHA:128) (Exim 4.68) (envelope-from ) id 1PCUQV-0007kF-Qa for freebsd-fs@freebsd.org; Sun, 31 Oct 2010 10:42:12 +0100 Date: Sun, 31 Oct 2010 10:42:09 +0100 From: Fabian Keil To: freebsd-fs@freebsd.org Message-ID: <20101031104209.771cc47e@r500.local> In-Reply-To: References: X-Mailer: Claws Mail 3.7.6 (GTK+ 2.20.1; amd64-portbld-freebsd9.0) X-PGP-KEY-URL: http://www.fabiankeil.de/gpg-keys/freebsd-listen-2008-08-18.asc Mime-Version: 1.0 Content-Type: multipart/signed; micalg=PGP-SHA1; boundary="Sig_//nUatHWA_bdzcjmJ_IYD4LJ"; protocol="application/pgp-signature" X-Df-Sender: 775067 Subject: Re: ZFS inresponsive. 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, 31 Oct 2010 09:56:33 -0000 --Sig_//nUatHWA_bdzcjmJ_IYD4LJ Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Peter Ankerst=E5l wrote: > I accidentally aborted a zfs send mid-tranfer. >=20 > Now the receiveing side cant do anything with the affected filesystem. bo= th zfs list and zfs destroy hangs. > How can I fix this? I can list other filesystems without a problem but a = general list or any command concerning > the one the got broken in transer hangs the zfs command. I occasionally see this, too, when sending snapshots to zpools on USB disks using geli. If the device gets lost in transfer, general zfs and zpool commands hang: Oct 18 17:09:28 r500 sudo: fk : TTY=3Dpts/9 ; PWD=3D/home/fk ; USER= =3Droot ; COMMAND=3D/sbin/geli attach -k /home/fk/geli-keys/poppstar.key /d= ev/label/poppstar Oct 18 17:09:34 r500 sudo: fk : TTY=3Dpts/9 ; PWD=3D/home/fk ; USER= =3Droot ; COMMAND=3D/sbin/zpool import poppstar Oct 18 17:09:34 r500 kernel: GEOM_ELI: Device label/poppstar.eli created. Oct 18 17:09:34 r500 kernel: GEOM_ELI: Encryption: AES-CBC 128 Oct 18 17:09:34 r500 kernel: GEOM_ELI: Crypto: software Oct 18 17:09:35 r500 kernel: (cd0:ahcich1:0:0:0): SCSI status error Oct 18 17:09:35 r500 kernel: (cd0:ahcich1:0:0:0): Requesting SCSI sense data Oct 18 17:09:35 r500 kernel: (cd0:ahcich1:0:0:0): SCSI status error Oct 18 17:09:35 r500 kernel: (cd0:ahcich1:0:0:0): READ CAPACITY. CDB: 25 0 = 0 0 0 0 0 0 0 0=20 Oct 18 17:09:35 r500 kernel: (cd0:ahcich1:0:0:0): CAM status: SCSI Status E= rror Oct 18 17:09:35 r500 kernel: (cd0:ahcich1:0:0:0): SCSI status: Check Condit= ion Oct 18 17:09:35 r500 kernel: (cd0:ahcich1:0:0:0): SCSI sense: NOT READY asc= :3a,1 (Medium not present - tray closed) Oct 18 17:09:35 r500 kernel: (cd0:ahcich1:0:0:0): Error 6, Unretryable error Oct 18 17:09:58 r500 sudo: fk : TTY=3Dpts/9 ; PWD=3D/home/fk ; USER= =3Droot ; COMMAND=3D/sbin/zfs create poppstar/dvds/sliders Oct 18 17:10:32 r500 sudo: fk : TTY=3Dpts/9 ; PWD=3D/home/fk ; USER= =3Droot ; COMMAND=3D/sbin/zfs send wde2/dvds/sliders/season-1-2@2009-12-05 Oct 18 17:10:32 r500 sudo: fk : TTY=3Dpts/9 ; PWD=3D/home/fk ; USER= =3Droot ; COMMAND=3D/sbin/zfs receive -v poppstar/dvds/sliders/season-1-2 Oct 18 17:38:06 r500 sudo: fk : TTY=3Dpts/9 ; PWD=3D/home/fk ; USER= =3Droot ; COMMAND=3D/sbin/zfs receive -v poppstar/dvds/sliders/season-3 Oct 18 17:38:06 r500 sudo: fk : TTY=3Dpts/9 ; PWD=3D/home/fk ; USER= =3Droot ; COMMAND=3D/sbin/zfs send wde2/dvds/sliders/season-3@2009-03-28 Oct 18 17:39:47 r500 kernel: acpi_lid0: Lid closed Oct 18 18:13:19 r500 kernel: acpi_lid0: Lid opened Oct 18 18:22:56 r500 sudo: fk : TTY=3Dpts/9 ; PWD=3D/home/fk ; USER= =3Droot ; COMMAND=3D/sbin/zfs send wde2/dvds/sliders/season-4@2009-12-05 Oct 18 18:22:56 r500 sudo: fk : TTY=3Dpts/9 ; PWD=3D/home/fk ; USER= =3Droot ; COMMAND=3D/sbin/zfs receive -v poppstar/dvds/sliders/season-4 Oct 18 18:33:05 r500 kernel: ugen3.3: at usbus3 (disconnected) Oct 18 18:33:05 r500 kernel: umass2: at uhub3, port 1, addr 3 (disconnected) Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): SCSI status error Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Requesting SCSI sense = data Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): AutoSense failed Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Error 5, Unretryable e= rror Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D5). label/poppstar.eli[WRITE(offset=3D362645020672, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D5). label/poppstar.eli[WRITE(offset=3D362645151744, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D5). label/poppstar.eli[WRITE(offset=3D362645282816, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D5). label/poppstar.eli[WRITE(offset=3D362645413888, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D5). label/poppstar.eli[WRITE(offset=3D362645544960, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D5). label/poppstar.eli[WRITE(offset=3D362645676032, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D5). label/poppstar.eli[WRITE(offset=3D362645807104, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D5). label/poppstar.eli[WRITE(offset=3D362645938176, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D5). label/poppstar.eli[WRITE(offset=3D362646069248, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D5). label/poppstar.eli[WRITE(offset=3D362644889600, length=3D131072)] Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Selection timeout Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Retrying command Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Selection timeout Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Retrying command Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Selection timeout Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Retrying command Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Selection timeout Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Retrying command Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): lost device Oct 18 18:33:05 r500 kernel: (pass4:umass-sim2:2:0:0): lost device Oct 18 18:33:05 r500 kernel: (pass4:umass-sim2:2:0:0): removing device entry Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Error 6, Unretryable e= rror Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0):G EOM_ELIInvalidating p= ack:=20 Oct 18 18:33:05 r500 kernel: g_eli_read_done() failed label/poppstar.eli[RE= AD(offset=3D2000398327808, length=3D8192)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: g_eli_read_done() failed label/popps= tar.eli[READ(offset=3D270336, length=3D8192)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: g_eli_read_done() failed label/popps= tar.eli[READ(offset=3D2000398589952, length=3D8192)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D6). label/poppstar.eli[WRITE(offset=3D362646200320, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D6). label/poppstar.eli[WRITE(offset=3D362646331392, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D6). label/poppstar.eli[WRITE(offset=3D362646593536, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D6). label/poppstar.eli[WRITE(offset=3D362646724608, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D6). label/poppstar.eli[WRITE(offset=3D362646462464, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D6). label/poppstar.eli[WRITE(offset=3D362646855680, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D6). label/poppstar.eli[WRITE(offset=3D362646986752, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D6). label/poppstar.eli[WRITE(offset=3D362647117824, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D6). label/poppstar.eli[WRITE(offset=3D362647248896, length=3D131072)] Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error= =3D6). label/poppstar.eli[WRITE(offset=3D362647379968, length=3D131072)] Oct 18 18:33:05 r500 root: ZFS: vdev I/O failure, zpool=3Dpoppstar path=3D/= dev/label/poppstar.eli offset=3D2000398327808 size=3D8192 error=3D6 Oct 18 18:33:05 r500 root: ZFS: vdev I/O failure, zpool=3Dpoppstar path=3D/= dev/label/poppstar.eli offset=3D270336 size=3D8192 error=3D6 Oct 18 18:33:05 r500 root: ZFS: vdev I/O failure, zpool=3Dpoppstar path=3D/= dev/label/poppstar.eli offset=3D2000398589952 size=3D8192 error=3D6 Oct 18 18:33:05 r500 root: ZFS: zpool I/O failure, zpool=3Dpoppstar error= =3D6 Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): Synchronize cache fail= ed, status =3D=3D 0xa, scsi status =3D=3D 0x0 Oct 18 18:33:05 r500 kernel: (da2:umass-sim2:2:0:0): removing device entry Oct 18 18:33:05 r500 root: ZFS: zpool I/O failure, zpool=3Dpoppstar error= =3D6 Oct 18 18:33:05 r500 last message repeated 151 times Oct 18 18:33:05 r500 root: ZFS: zpool I/O failure, zpool=3Dpoppstar error= =3D28 Oct 18 18:33:06 r500 last message repeated 161 times Oct 18 18:33:06 r500 root: ZFS: vdev I/O failure, zpool=3Dpoppstar path=3D = offset=3D size=3D error=3D Oct 18 18:33:06 r500 root: Unknown USB device: vendor 0x13fd product 0x1240= bus uhub3 Oct 18 18:33:06 r500 kernel: ugen3.3: at usbus3 Oct 18 18:33:06 r500 kernel: umass2: on usbus3 Oct 18 18:33:06 r500 kernel: umass2: SCSI over Bulk-Only; quirks =3D 0x0000 Oct 18 18:33:08 r500 kernel: umass2:4:2:-1: Attached to scbus4 Oct 18 18:33:08 r500 kernel: pass4 at umass-sim2 bus 2 scbus4 target 0 lun 0 Oct 18 18:33:08 r500 kernel: pass4: Fixed Direct Ac= cess SCSI-4 device=20 Oct 18 18:33:08 r500 kernel: pass4: Serial Number 395857304652454620202020 Oct 18 18:33:08 r500 kernel: pass4: 40.000MB/s transfers Oct 18 18:33:08 r500 kernel: GEOM: new disk da2 Oct 18 18:33:08 r500 kernel: da2 at umass-sim2 bus 2 scbus4 target 0 lun 0 Oct 18 18:33:08 r500 kernel: da2: Fixed Direct Acce= ss SCSI-4 device=20 Oct 18 18:33:08 r500 kernel: da2: Serial Number 395857304652454620202020 Oct 18 18:33:08 r500 kernel: da2: 40.000MB/s transfers Oct 18 18:33:08 r500 kernel: da2: 1907729MB (3907029168 512 byte sectors: 2= 55H 63S/T 243201C) Oct 18 18:34:02 r500 sudo: fk : TTY=3Dpts/14 ; PWD=3D/home/fk ; USER= =3Droot ; COMMAND=3D/sbin/zpool list Oct 18 18:34:02 r500 root: ZFS: zpool I/O failure, zpool=3Dpoppstar error= =3D6 Oct 18 18:34:02 r500 root: ZFS: vdev I/O failure, zpool=3Dpoppstar path=3D = offset=3D size=3D error=3D Oct 18 18:36:34 r500 kernel: ugen3.3: at usbus3 (disconnected) Oct 18 18:36:34 r500 kernel: umass2: at uhub3, port 1, addr 3 (disconnected) Oct 18 18:36:34 r500 kernel: (da2:umass-sim2:2:0:0): lost device Oct 18 18:36:34 r500 kernel: (da2:umass-sim2:2:0:0): removing device entry Oct 18 18:36:34 r500 kernel: (pass4:umass-sim2:2:0:0): lost device Oct 18 18:36:34 r500 kernel: (pass4:umass-sim2:2:0:0): removing device entry Oct 18 18:36:44 r500 root: Unknown USB device: vendor 0x13fd product 0x1240= bus uhub3 Oct 18 18:36:44 r500 kernel: ugen3.3: at usbus3 Oct 18 18:36:44 r500 kernel: umass2: on usbus3 Oct 18 18:36:44 r500 kernel: umass2: SCSI over Bulk-Only; quirks =3D 0x0000 Oct 18 18:36:46 r500 kernel: umass2:4:2:-1: Attached to scbus4 Oct 18 18:36:46 r500 kernel: pass4 at umass-sim2 bus 2 scbus4 target 0 lun 0 Oct 18 18:36:46 r500 kernel: pass4: Fixed Direct Ac= cess SCSI-4 device=20 Oct 18 18:36:46 r500 kernel: pass4: Serial Number 395857304652454620202020 Oct 18 18:36:46 r500 kernel: pass4: 40.000MB/s transfers Oct 18 18:36:46 r500 kernel: GEOM: new disk da2 Oct 18 18:36:46 r500 kernel: da2 at umass-sim2 bus 2 scbus4 target 0 lun 0 Oct 18 18:36:46 r500 kernel: da2: Fixed Direct Acce= ss SCSI-4 device=20 Oct 18 18:36:46 r500 kernel: da2: Serial Number 395857304652454620202020 Oct 18 18:36:46 r500 kernel: da2: 40.000MB/s transfers Oct 18 18:36:46 r500 kernel: da2: 1907729MB (3907029168 512 byte sectors: 2= 55H 63S/T 243201C) Oct 18 18:36:46 r500 kernel: ugen3.3: at usbus3 (disconnected) Oct 18 18:36:46 r500 kernel: umass2: at uhub3, port 1, addr 3 (disconnected) Oct 18 18:36:46 r500 kernel: ugen7.3: at usbus7 (disconne= cted) Oct 18 18:36:46 r500 kernel: umass1: at uhub7, port 1, addr 3 (disconnected) Oct 18 18:36:46 r500 kernel: (da2:umass-sim2:2:0:0): lost device Oct 18 18:36:46 r500 kernel: (da2:umass-sim2:2:0:0): removing device entry Oct 18 18:36:46 r500 kernel: (pass4:umass-sim2:2:0:0): lost device Oct 18 18:36:46 r500 kernel: (pass4:umass-sim2:2:0:0): removing device entry Oct 18 18:36:46 r500 kernel: (da1:umass-sim1:1:0:0): lost device Oct 18 18:36:46 r500 kernel: (pass3:umass-sim1:1:0:0): lost device Oct 18 18:36:46 r500 kernel: (pass3:umass-sim1:1:0:0): removing device entry Oct 18 18:36:46 r500 kernel: (da1:umass-sim1:1:0:0): Synchronize cache fail= ed, status =3D=3D 0xa, scsi status =3D=3D 0x0 Oct 18 18:36:46 r500 kernel: (da1:umass-sim1:1:0:0): removing device entry Oct 18 18:36:46 r500 kernel: ugen7.2: at usbus7 (disconne= cted) Oct 18 18:36:46 r500 kernel: umass0: at uhub7, port 2, addr 2 (disconnected) Oct 18 18:36:46 r500 kernel: (da0:umass-sim0:0:0:0): lost device Oct 18 18:36:46 r500 kernel: (pass2:umass-sim0:0:0:0): lost device Oct 18 18:36:46 r500 kernel: (pass2:umass-sim0:0:0:0): removing device entry Oct 18 18:36:46 r500 kernel: (da0:umass-sim0:0:0:0): Synchronize cache fail= ed, status =3D=3D 0xa, scsi status =3D=3D 0x0 Oct 18 18:36:46 r500 kernel: (da0:umass-sim0:0:0:0): removing device entry Oct 18 18:36:54 r500 root: ZFS: zpool I/O failure, zpool=3Dwde2 error=3D28 Oct 18 18:36:54 r500 last message repeated 3 times Oct 18 18:36:54 r500 root: ZFS: vdev I/O failure, zpool=3Dwde2 path=3D offs= et=3D size=3D error=3D Oct 18 18:36:54 r500 root: ZFS: zpool I/O failure, zpool=3Dwde3 error=3D28 Oct 18 18:36:54 r500 last message repeated 3 times Oct 18 18:36:54 r500 root: ZFS: vdev I/O failure, zpool=3Dwde3 path=3D offs= et=3D size=3D error=3D fk@r500 ~ $ps waux | grep \ [z] root 5501 0.0 0.1 13364 1288 9 I+ 6:22PM 0:00.01 sudo zfs= receive -v poppstar/dvds/sliders/season-4 root 5502 0.0 0.1 18944 1312 9 D+ 6:22PM 0:21.73 zfs rece= ive -v poppstar/dvds/sliders/season-4 fk 4711 0.0 0.1 19980 1364 11 D+ 5:10PM 0:01.03 zpool io= stat poppstar 1 root 5947 0.0 0.1 13364 1728 14 I+ 6:34PM 0:00.01 sudo zpo= ol list root 5948 0.0 0.1 19980 1760 14 D+ 6:34PM 0:00.01 zpool li= st fk 5990 0.0 0.1 19980 1744 16 D+ 6:36PM 0:00.01 zpool li= st -H -o name fk@r500 ~ $sudo procstat -kk `pgrep zfs` PID TID COMM TDNAME KSTACK = =20 5502 100519 zfs - mi_switch+0x176 sleepq_wait+= 0x42 _cv_wait+0x129 txg_wait_synced+0x7c dmu_tx_assign+0x16c dmu_recv_strea= m+0x125f zfs_ioc_recv+0x282 zfsdev_ioctl+0x8f devfs_ioctl_f+0x7b kern_ioctl= +0x102 ioctl+0xfd syscallenter+0x331 syscall+0x4b Xfast_syscall+0xe2=20 fk@r500 ~ $sudo procstat -kk `pgrep zpool` PID TID COMM TDNAME KSTACK = =20 5990 100507 zpool - mi_switch+0x176 sleepq_wait+= 0x42 _sx_xlock_hard+0x3c2 _sx_xlock+0x6e spa_all_configs+0xbf zfs_ioc_pool_= configs+0x29 zfsdev_ioctl+0x8f devfs_ioctl_f+0x7b kern_ioctl+0x102 ioctl+0x= fd syscallenter+0x331 syscall+0x4b Xfast_syscall+0xe2=20 5948 100292 zpool - mi_switch+0x176 sleepq_wait+= 0x42 _cv_wait+0x129 zio_wait+0x61 dbuf_read+0x39a dnode_hold_impl+0xf0 dmu_= buf_hold+0x34 zap_lockdir+0x52 zap_cursor_retrieve+0x194 spa_prop_get+0x26f= zfs_ioc_pool_get_props+0xb2 zfsdev_ioctl+0x8f devfs_ioctl_f+0x7b kern_ioct= l+0x102 ioctl+0xfd syscallenter+0x331 syscall+0x4b Xfast_syscall+0xe2=20 4711 100269 zpool - mi_switch+0x176 sleepq_wait+= 0x42 _sx_xlock_hard+0x3c2 _sx_xlock+0x6e spa_open_common+0x76 spa_get_stats= +0x42 zfs_ioc_pool_stats+0x2c zfsdev_ioctl+0x8f devfs_ioctl_f+0x7b kern_ioc= tl+0x102 ioctl+0xfd syscallenter+0x331 syscall+0x4b Xfast_syscall+0xe2=20 At the time I've been using: FreeBSD r500.local 9.0-CURRENT FreeBSD 9.0-CURRENT #193 r+3be3a96: Sun Oct = 17 12:51:52 CEST 2010 fk@r500.local:/usr/obj/usr/src/sys/ZOEY amd64 with ZFS pool version 15, but I saw the problem with earlier FreeBSD and ZFS versions, too. Fabian --Sig_//nUatHWA_bdzcjmJ_IYD4LJ Content-Type: application/pgp-signature; name=signature.asc Content-Disposition: attachment; filename=signature.asc -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.16 (FreeBSD) iEYEARECAAYFAkzNOfgACgkQBYqIVf93VJ0KfwCcDApuTT8QkxyMXt6HLEMOeslR kVAAoINh2rLwsOyXgcP+5uH1vjvZv3pN =ue8o -----END PGP SIGNATURE----- --Sig_//nUatHWA_bdzcjmJ_IYD4LJ-- From owner-freebsd-fs@FreeBSD.ORG Sun Oct 31 12:05:19 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 71289106566B for ; Sun, 31 Oct 2010 12:05:19 +0000 (UTC) (envelope-from thomas.e.zander@googlemail.com) Received: from mail-vw0-f54.google.com (mail-vw0-f54.google.com [209.85.212.54]) by mx1.freebsd.org (Postfix) with ESMTP id 2B1148FC15 for ; Sun, 31 Oct 2010 12:05:18 +0000 (UTC) Received: by vws12 with SMTP id 12so2414588vws.13 for ; Sun, 31 Oct 2010 05:05:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=googlemail.com; s=gamma; h=domainkey-signature:mime-version:received:received:in-reply-to :references:date:message-id:subject:from:to:content-type; bh=uz49CGp63W0R5sIVrnyxOjTsBCeK/mczki62daNWYoE=; b=aIZN5zdx9BLjdxLTb6PMtNrtoHLCJ4wqLL+1TEq4tourm6otd6shwX1ytgHJsuARYJ sdDhHI98sfKZpXAFHxGaC5ce5R95lB2ANqeLR5rGlPguTeq3ekmn03LjzzaygwJ46Fm+ MORRP662Mg2rP7A1TmGt7QN3+8FfJtONGCPYo= DomainKey-Signature: a=rsa-sha1; c=nofws; d=googlemail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :content-type; b=d3Whs+yiWGiT18NjgHO7UznmQMPLQMhXiyRWulDS2Wgc9VNm3bDQsKJbEaURaqCTUL QMQeqsS4m1FpbfIyQS8ePZbGPNy++sF4mEVS5JW0ANGe5frI0XgF411D7v0o511payjl hi/dnrDKXfBbEZFXjrg0fixK+whmu6R5UufHg= MIME-Version: 1.0 Received: by 10.224.208.1 with SMTP id ga1mr7876173qab.111.1288525310721; Sun, 31 Oct 2010 04:41:50 -0700 (PDT) Received: by 10.229.249.135 with HTTP; Sun, 31 Oct 2010 04:41:50 -0700 (PDT) In-Reply-To: <20101031104209.771cc47e@r500.local> References: <20101031104209.771cc47e@r500.local> Date: Sun, 31 Oct 2010 12:41:50 +0100 Message-ID: From: Thomas Zander To: freebsd-fs@freebsd.org Content-Type: text/plain; charset=ISO-8859-1 Subject: Re: ZFS inresponsive. 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, 31 Oct 2010 12:05:19 -0000 On Sun, Oct 31, 2010 at 10:42, Fabian Keil wrote: > Oct 18 18:33:05 r500 kernel: GEOM_ELI: Crypto WRITE request failed (error=5). label/poppstar.eli[WRITE(offset=362645020672, length=131072)] Same here, same setup. ZFS, GELI, USB. Occasionally this happens, haven't found a way to reliably trigger it yet. However, what seems to (more or less) reliably work is to trigger a failed crypto READ request when copying files from a ZFS-GELI-USB pool to a FAT formatted USB stick. If that happens, I have to reboot as the ZFS-GELI-USB pool is no longer functioning properly. This is on a recent 8-STABLE amd64 box, but it has always been that way since I am using zpools on USB disks on FreeBSD. Riggs From owner-freebsd-fs@FreeBSD.ORG Sun Oct 31 18:20:21 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 0114B1065672 for ; Sun, 31 Oct 2010 18:20:21 +0000 (UTC) (envelope-from james-freebsd-fs2@jrv.org) Received: from mail.jrv.org (adsl-70-243-84-13.dsl.austtx.swbell.net [70.243.84.13]) by mx1.freebsd.org (Postfix) with ESMTP id 97D418FC21 for ; Sun, 31 Oct 2010 18:20:20 +0000 (UTC) Received: from kremvax.housenet.jrv (kremvax.housenet.jrv [192.168.3.124]) by mail.jrv.org (8.14.3/8.14.3) with ESMTP id o9VIKGPM035952; Sun, 31 Oct 2010 13:20:16 -0500 (CDT) (envelope-from james-freebsd-fs2@jrv.org) Authentication-Results: mail.jrv.org; domainkeys=pass (testing) header.from=james-freebsd-fs2@jrv.org DomainKey-Signature: a=rsa-sha1; s=enigma; d=jrv.org; c=nofws; q=dns; h=message-id:date:from:user-agent:mime-version:to:cc:subject: references:in-reply-to:content-type:content-transfer-encoding; b=UKBNnE7HyLCNePhAWPRTB0sosHqmKlXmdnFNF7Wxp/j4qO03yjLzGMzHTWByAh8o/ P8puj9+rkA/wBo5jC3odR5NWtPY/NEucihfPX6dV1WN5+S1CogU6TL3Ff08XVKB3YbO 9Va9gX+lskUQcGc6rxIsFWMmHSFE6b/Ym3md9k0= Message-ID: <4CCDB360.50609@jrv.org> Date: Sun, 31 Oct 2010 13:20:16 -0500 From: "James R. Van Artsdalen" User-Agent: Thunderbird 2.0.0.24 (Macintosh/20100228) MIME-Version: 1.0 To: Thomas Zander References: <20101031104209.771cc47e@r500.local> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org Subject: Re: ZFS inresponsive. 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, 31 Oct 2010 18:20:21 -0000 Thomas Zander wrote: > Same here, same setup. ZFS, GELI, USB. It is not a good idea to use USB disks with ZFS. It can cause pool loss. Many (most?) USB enclosures use USB<->SATA chips that discard the SYNC/FLUSH command to the disk. As a result this opens a window of time where disk writes might be reordered in a way that cause the ZFS structures to become corrupted. There's no problem in normal operation but there may be a failure if there is a power loss. The log entries in Fabian's note look like a USB SYNC/FLASH failure to me - that USB enclosure should not be used with ZFS. At one time there was talk of "deferred reallocation" in ZFS which would deal with broken USB enclosures but I don't know if Sun ever got around to this. From owner-freebsd-fs@FreeBSD.ORG Sun Oct 31 20:03:16 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 32C9B106564A for ; Sun, 31 Oct 2010 20:03:16 +0000 (UTC) (envelope-from csalgau-br@bitdefender.com) Received: from mail.bitdefender.com (mail.bitdefender.com [91.199.104.2]) by mx1.freebsd.org (Postfix) with ESMTP id 625238FC14 for ; Sun, 31 Oct 2010 20:03:14 +0000 (UTC) Received: (qmail 24657 invoked from network); 31 Oct 2010 21:36:33 +0200 Received: from bitdefender.is.ew.ro (HELO ?192.168.70.65?) (csalgau@bitdefender.com@81.181.91.206) by mail.bitdefender.com with AES256-SHA encrypted SMTP; 31 Oct 2010 21:36:32 +0200 Date: Sun, 31 Oct 2010 21:36:27 +0200 From: Mihai-Catalin Salgau Organization: S.C. Bitdefender S.R.L. X-Priority: 3 (Normal) Message-ID: <47023445.20101031213627@bitdefender.com> To: freebsd-fs In-Reply-To: References: MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-BitDefender-Spam: No (0) X-BitDefender-SpamStamp: v1, build 2.8.97.113122, SQMD Hits: none, rbl score: 0(0), bayes score: 500(0), pbayes score: 500(0), neunet score: 0(0), flags: [NN_S_HOW_TO_VDA; NN_LEGIT_BITDEFENDER], SQMD: 3c6becbf19241d5a1b50a3c3f4fc148d.fuzzy.fzrbl.org, total: 0(775) X-BitDefender-Scanner: Clean, Agent: BitDefender qmail 3.1.0 on elfie.dsd.hq, sigver: 7.34496 Subject: Re: How to run ZFS Test Suite (ztest)? 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, 31 Oct 2010 20:03:16 -0000 > Attempting to run it on 8.1-R drops the error: > %ztest > Assertion failed: (abstime > 0), file > /usr/src/cddl/lib/libzpool/../../../cddl/contrib/opensolaris/lib/libzpool= /common/kernel.c, > line 309. > Abort (core dumped) > Thanks. +1 too was on 8.0-RELEASE and getting a "child died with signal 11" every time. now I'm getting this assertion on 8-STABLE From owner-freebsd-fs@FreeBSD.ORG Mon Nov 1 07:31:01 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 45C1C1065670; Mon, 1 Nov 2010 07:31:01 +0000 (UTC) (envelope-from avg@icyb.net.ua) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id 39B6E8FC13; Mon, 1 Nov 2010 07:30:59 +0000 (UTC) Received: from porto.topspin.kiev.ua (porto-e.starpoint.kiev.ua [212.40.38.100]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id JAA14454; Mon, 01 Nov 2010 09:30:55 +0200 (EET) (envelope-from avg@icyb.net.ua) Received: from localhost.topspin.kiev.ua ([127.0.0.1]) by porto.topspin.kiev.ua with esmtp (Exim 4.34 (FreeBSD)) id 1PCor1-0002e8-9c; Mon, 01 Nov 2010 09:30:55 +0200 Message-ID: <4CCE6CAD.30304@icyb.net.ua> Date: Mon, 01 Nov 2010 09:30:53 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.12) Gecko/20101029 Lightning/1.0b2 Thunderbird/3.1.6 MIME-Version: 1.0 To: Alexander Zagrebin References: <4CCAF0EB.4080001@icyb.net.ua> <20101029175105.GB18613@two.kliksys.ru> <4CCBD443.7010305@icyb.net.ua><4CCBD46E.9030200@icyb.net.ua> <4CCBD661.3000204@freebsd.org><4CCBEAF6.2030408@freebsd.org> <20101030101254.GB79691@two.kliksys.ru> <4CCBF45C.4080208@icyb.net.ua> <20101030112520.GD79691@two.kliksys.ru> <4CCC2F2A.7020809@icyb.net.ua><20101030190120.GA80301@two.kliksys.ru> <4CCD0804.8010703@icyb.net.ua> In-Reply-To: X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=KOI8-R Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org, freebsd-stable@freebsd.org Subject: Re: 8.1-STABLE: zfs and sendfile: problem still exists 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, 01 Nov 2010 07:31:01 -0000 on 31/10/2010 11:02 Alexander Zagrebin said the following: > I have a question. > When we transfer a file via sendfile, then current code allocates > a memory, marked inactive. For example, if the file has size 100 MB, > then 100 MB of memory will be allocated. > If we have to transfer this file again later, then this memory will used > as cache, and no disk io will be required. > The memory will be freed if file will be deleted or operating system > will need an additional memory. > I have correctly understood? > If it so, the i continue... > Such behaviour is good if we have files with relatively small size. > Suppose we have to transfer file with large size (for example, greater > than amount of physical memory). > While transfering, the inactive memory will grow, pressing the ARC. > When size of the ARC will fall to its minimum (vfs.zfs.arc_min), then > inactive memory will be reused. > So, when transfer is complete, we have: > 1. No free memory > 2. Size of the ARC has minimal size (it is bad) > 3. Inactive memory contains the _tail_ of the file only (it is bad too) > Now if we have to transfer this file again, then > 1. there is no (or few) file's data in ARC (ARC too small) > 2. The inactive memory doesn't contain a head part of the file > So the file's data will read from a disk again and again... > Also i've noticed that inactive memory frees relatively slowly, > so if there is a frequent access to large files, then system will run > at very unoptimal conditions. > It's imho... > Can you comment this? > First and foremost, the double-caching issue for ZFS+sendfile on FreeBSD is still there and no resolution for this issue is on horizon. So, you have to account for the fact that twice as much memory is needed for this use-case. Whether you plan your system, or configure it, or tune it. Second, with recent head and stable/8 ARC should not be the primary victim of memory pressure; ARC reclaim thread and the page daemon should cooperate in freeing/recycling memory. Nothing much to add. -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Mon Nov 1 08:28:08 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 486F7106566B for ; Mon, 1 Nov 2010 08:28:08 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (60.wheelsystems.com [83.12.187.60]) by mx1.freebsd.org (Postfix) with ESMTP id E5C6C8FC14 for ; Mon, 1 Nov 2010 08:27:58 +0000 (UTC) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id AFFF945C9C; Mon, 1 Nov 2010 09:27:56 +0100 (CET) Received: from localhost (chello089073192049.chello.pl [89.73.192.49]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id DF4D345B36; Mon, 1 Nov 2010 09:27:50 +0100 (CET) Date: Mon, 1 Nov 2010 09:27:11 +0100 From: Pawel Jakub Dawidek To: "James R. Van Artsdalen" Message-ID: <20101101082711.GG2160@garage.freebsd.pl> References: <20101031104209.771cc47e@r500.local> <4CCDB360.50609@jrv.org> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="9Iq5ULCa7nGtWwZS" Content-Disposition: inline In-Reply-To: <4CCDB360.50609@jrv.org> User-Agent: Mutt/1.4.2.3i X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 9.0-CURRENT amd64 X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-0.6 required=4.5 tests=BAYES_00,RCVD_IN_SORBS_DUL autolearn=no version=3.0.4 Cc: freebsd-fs@freebsd.org Subject: Re: ZFS inresponsive. 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, 01 Nov 2010 08:28:08 -0000 --9Iq5ULCa7nGtWwZS Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sun, Oct 31, 2010 at 01:20:16PM -0500, James R. Van Artsdalen wrote: > Thomas Zander wrote: > > Same here, same setup. ZFS, GELI, USB. >=20 > It is not a good idea to use USB disks with ZFS. It can cause pool loss. >=20 > Many (most?) USB enclosures use USB<->SATA chips that discard the > SYNC/FLUSH command to the disk. As a result this opens a window of time > where disk writes might be reordered in a way that cause the ZFS > structures to become corrupted. There's no problem in normal operation > but there may be a failure if there is a power loss. >=20 > The log entries in Fabian's note look like a USB SYNC/FLASH failure to > me - that USB enclosure should not be used with ZFS. >=20 > At one time there was talk of "deferred reallocation" in ZFS which would > deal with broken USB enclosures but I don't know if Sun ever got around > to this. Yes, it is implemented in new ZFS. Blocks are not reused for next three transaction groups and one can import a pool by falling back to the last working transaction group if the most recent one is corrupted. --=20 Pawel Jakub Dawidek http://www.wheelsystems.com pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --9Iq5ULCa7nGtWwZS Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.14 (FreeBSD) iEYEARECAAYFAkzOed8ACgkQForvXbEpPzRjrwCg6vBC8ojXRxBCrM+nWIyBmWRa UScAoK+tDi2QjskEOXN+I4M3FDVOURA1 =yllR -----END PGP SIGNATURE----- --9Iq5ULCa7nGtWwZS-- From owner-freebsd-fs@FreeBSD.ORG Mon Nov 1 10:39:48 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 299AD106564A; Mon, 1 Nov 2010 10:39:48 +0000 (UTC) (envelope-from wjw@digiware.nl) Received: from mail.digiware.nl (mail.ip6.digiware.nl [IPv6:2001:4cb8:1:106::2]) by mx1.freebsd.org (Postfix) with ESMTP id AE9848FC08; Mon, 1 Nov 2010 10:39:47 +0000 (UTC) Received: from localhost (localhost.digiware.nl [127.0.0.1]) by mail.digiware.nl (Postfix) with ESMTP id B9613153434; Mon, 1 Nov 2010 11:39:45 +0100 (CET) X-Virus-Scanned: amavisd-new at digiware.nl Received: from mail.digiware.nl ([127.0.0.1]) by localhost (rack1.digiware.nl [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id sr-RcVERgydU; Mon, 1 Nov 2010 11:39:43 +0100 (CET) Received: from [127.0.0.1] (opteron [192.168.10.67]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (No client certificate requested) by mail.digiware.nl (Postfix) with ESMTPSA id 91FBC153433; Mon, 1 Nov 2010 11:39:43 +0100 (CET) Message-ID: <4CCE98ED.6010002@digiware.nl> Date: Mon, 01 Nov 2010 11:39:41 +0100 From: Willem Jan Withagen User-Agent: Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.2.12) Gecko/20101027 Lightning/1.0b2 Thunderbird/3.1.6 MIME-Version: 1.0 To: Andriy Gapon References: <4CCAF0EB.4080001@icyb.net.ua> <20101029175105.GB18613@two.kliksys.ru> <4CCBD443.7010305@icyb.net.ua><4CCBD46E.9030200@icyb.net.ua> <4CCBD661.3000204@freebsd.org><4CCBEAF6.2030408@freebsd.org> <20101030101254.GB79691@two.kliksys.ru> <4CCBF45C.4080208@icyb.net.ua> <20101030112520.GD79691@two.kliksys.ru> <4CCC2F2A.7020809@icyb.net.ua><20101030190120.GA80301@two.kliksys.ru> <4CCD0804.8010703@icyb.net.ua> <4CCE6CAD.30304@icyb.net.ua> In-Reply-To: <4CCE6CAD.30304@icyb.net.ua> Content-Type: text/plain; charset=KOI8-R; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org, freebsd-stable@freebsd.org Subject: Re: 8.1-STABLE: zfs and sendfile: problem still exists 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, 01 Nov 2010 10:39:48 -0000 On 2010-11-01 8:30, Andriy Gapon wrote: > First and foremost, the double-caching issue for ZFS+sendfile on FreeBSD is > still there and no resolution for this issue is on horizon. So, you have to > account for the fact that twice as much memory is needed for this use-case. > Whether you plan your system, or configure it, or tune it. > > Second, with recent head and stable/8 ARC should not be the primary victim of > memory pressure; ARC reclaim thread and the page daemon should cooperate in > freeing/recycling memory. > > Nothing much to add. Although this discussion started due to issues with serving files thru web-typish services, there are more apps that use sendfile. For one, I noticed that I had once enabled sendfile in my Samba config. As per this discussion I saw little advantage in keeping it that way...... But I'm open for other suggestions. --WjW From owner-freebsd-fs@FreeBSD.ORG Mon Nov 1 10:42:50 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5A2121065694 for ; Mon, 1 Nov 2010 10:42:50 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (60.wheelsystems.com [83.12.187.60]) by mx1.freebsd.org (Postfix) with ESMTP id 072788FC1A for ; Mon, 1 Nov 2010 10:42:49 +0000 (UTC) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id 44A9D45CAC; Mon, 1 Nov 2010 11:42:48 +0100 (CET) Received: from localhost (chello089073192049.chello.pl [89.73.192.49]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id E67FB45B36; Mon, 1 Nov 2010 11:42:42 +0100 (CET) Date: Mon, 1 Nov 2010 11:42:03 +0100 From: Pawel Jakub Dawidek To: App Deb Message-ID: <20101101104203.GH2160@garage.freebsd.pl> References: Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="fmEUq8M7S0s+Fl0V" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.3i X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 9.0-CURRENT amd64 X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-0.6 required=4.5 tests=BAYES_00,RCVD_IN_SORBS_DUL autolearn=no version=3.0.4 Cc: freebsd-fs Subject: Re: How to run ZFS Test Suite (ztest)? 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, 01 Nov 2010 10:42:50 -0000 --fmEUq8M7S0s+Fl0V Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, Oct 29, 2010 at 10:53:38PM +0300, App Deb wrote: > Attempting to run it on 8.1-R drops the error: >=20 > %ztest > Assertion failed: (abstime > 0), file > /usr/src/cddl/lib/libzpool/../../../cddl/contrib/opensolaris/lib/libzpool= /common/kernel.c, > line 309. > Abort (core dumped) Should be now fixed in r214622 and r214623. Thank you for the report. --=20 Pawel Jakub Dawidek http://www.wheelsystems.com pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --fmEUq8M7S0s+Fl0V Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.14 (FreeBSD) iEYEARECAAYFAkzOmXsACgkQForvXbEpPzQfzgCeJOdApP/yKFNIMD3IH5qSfGbP qqIAn27FzSTClmzskSWjQ90rnBJkjYbI =fYgG -----END PGP SIGNATURE----- --fmEUq8M7S0s+Fl0V-- From owner-freebsd-fs@FreeBSD.ORG Mon Nov 1 11:06:56 2010 Return-Path: Delivered-To: freebsd-fs@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 97EEB1065670 for ; Mon, 1 Nov 2010 11:06:56 +0000 (UTC) (envelope-from owner-bugmaster@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 6004A8FC28 for ; Mon, 1 Nov 2010 11:06:56 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA1B6ufI019158 for ; Mon, 1 Nov 2010 11:06:56 GMT (envelope-from owner-bugmaster@FreeBSD.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA1B6tHw019156 for freebsd-fs@FreeBSD.org; Mon, 1 Nov 2010 11:06:55 GMT (envelope-from owner-bugmaster@FreeBSD.org) Date: Mon, 1 Nov 2010 11:06:55 GMT Message-Id: <201011011106.oA1B6tHw019156@freefall.freebsd.org> X-Authentication-Warning: freefall.freebsd.org: gnats set sender to owner-bugmaster@FreeBSD.org using -f From: FreeBSD bugmaster To: freebsd-fs@FreeBSD.org Cc: Subject: Current problem reports assigned to freebsd-fs@FreeBSD.org 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, 01 Nov 2010 11:06:56 -0000 Note: to view an individual PR, use: http://www.freebsd.org/cgi/query-pr.cgi?pr=(number). The following is a listing of current problems submitted by FreeBSD users. These represent problem reports covering all versions including experimental development code and obsolete releases. S Tracker Resp. Description -------------------------------------------------------------------------------- o kern/151648 fs [zfs] disk wait bug o kern/151629 fs [fs] [patch] Skip empty directory entries during name o kern/151326 fs [nfs] nfs exports fail if netgroups contain duplicate o kern/151226 fs [zfs] can't delete zfs snapshot o kern/151111 fs [zfs] vnodes leakage during zfs unmount o kern/151082 fs [zfs] [patch] sappend-flaged files on ZFS not working o kern/150796 fs [panic] [suj] [ufs] [softupdates] Panic on portbuild o kern/150503 fs [zfs] ZFS disks are UNAVAIL and corrupted after reboot o kern/150501 fs [zfs] ZFS vdev failure vdev.bad_label on amd64 o kern/150390 fs [zfs] zfs deadlock when arcmsr reports drive faulted o kern/150336 fs [nfs] mountd/nfsd became confused; refused to reload n o kern/150207 fs zpool(1): zpool import -d /dev tries to open weird dev o kern/149855 fs [gvinum] growfs causes fsck to report errors in Filesy o kern/149495 fs [zfs] chflags sappend on zfs not working right o kern/149208 fs mksnap_ffs(8) hang/deadlock o kern/149173 fs [patch] [zfs] make OpenSolaris installa o kern/149022 fs [hang] File system operations hangs with suspfs state o kern/149015 fs [zfs] [patch] misc fixes for ZFS code to build on Glib o kern/149014 fs [zfs] [patch] declarations in ZFS libraries/utilities o kern/149013 fs [zfs] [patch] make ZFS makefiles use the libraries fro o kern/148504 fs [zfs] ZFS' zpool does not allow replacing drives to be o kern/148490 fs [zfs]: zpool attach - resilver bidirectionally, and re o kern/148368 fs [zfs] ZFS hanging forever on 8.1-PRERELEASE o bin/148296 fs [zfs] [loader] [patch] Very slow probe in /usr/src/sys o kern/148204 fs [nfs] UDP NFS causes overload o kern/148138 fs [zfs] zfs raidz pool commands freeze o kern/147903 fs [zfs] [panic] Kernel panics on faulty zfs device o kern/147881 fs [zfs] [patch] ZFS "sharenfs" doesn't allow different " o kern/147790 fs [zfs] zfs set acl(mode|inherit) fails on existing zfs o kern/147560 fs [zfs] [boot] Booting 8.1-PRERELEASE raidz system take o kern/147420 fs [ufs] [panic] ufs_dirbad, nullfs, jail panic (corrupt o kern/146941 fs [zfs] [panic] Kernel Double Fault - Happens constantly o kern/146786 fs [zfs] zpool import hangs with checksum errors o kern/146708 fs [ufs] [panic] Kernel panic in softdep_disk_write_compl o kern/146528 fs [zfs] Severe memory leak in ZFS on i386 o kern/146502 fs [nfs] FreeBSD 8 NFS Client Connection to Server o kern/146375 fs [nfs] [patch] Typos in macro variables names in sys/fs s kern/145712 fs [zfs] cannot offline two drives in a raidz2 configurat o kern/145411 fs [xfs] [panic] Kernel panics shortly after mounting an o bin/145309 fs bsdlabel: Editing disk label invalidates the whole dev o kern/145272 fs [zfs] [panic] Panic during boot when accessing zfs on o kern/145246 fs [ufs] dirhash in 7.3 gratuitously frees hashes when it o kern/145238 fs [zfs] [panic] kernel panic on zpool clear tank o kern/145229 fs [zfs] Vast differences in ZFS ARC behavior between 8.0 o kern/145189 fs [nfs] nfsd performs abysmally under load o kern/144929 fs [ufs] [lor] vfs_bio.c + ufs_dirhash.c o kern/144458 fs [nfs] [patch] nfsd fails as a kld p kern/144447 fs [zfs] sharenfs fsunshare() & fsshare_main() non functi o kern/144416 fs [panic] Kernel panic on online filesystem optimization s kern/144415 fs [zfs] [panic] kernel panics on boot after zfs crash o kern/144234 fs [zfs] Cannot boot machine with recent gptzfsboot code o kern/143825 fs [nfs] [panic] Kernel panic on NFS client o bin/143572 fs [zfs] zpool(1): [patch] The verbose output from iostat o kern/143345 fs [ext2fs] [patch] extfs minor header cleanups to better o kern/143212 fs [nfs] NFSv4 client strange work ... o kern/143184 fs [zfs] [lor] zfs/bufwait LOR o kern/142924 fs [ext2fs] [patch] Small cleanup for the inode struct in o kern/142914 fs [zfs] ZFS performance degradation over time o kern/142878 fs [zfs] [vfs] lock order reversal o kern/142597 fs [ext2fs] ext2fs does not work on filesystems with real o kern/142489 fs [zfs] [lor] allproc/zfs LOR o kern/142466 fs Update 7.2 -> 8.0 on Raid 1 ends with screwed raid [re o kern/142401 fs [ntfs] [patch] Minor updates to NTFS from NetBSD o kern/142306 fs [zfs] [panic] ZFS drive (from OSX Leopard) causes two o kern/142068 fs [ufs] BSD labels are got deleted spontaneously o kern/141897 fs [msdosfs] [panic] Kernel panic. msdofs: file name leng o kern/141463 fs [nfs] [panic] Frequent kernel panics after upgrade fro o kern/141305 fs [zfs] FreeBSD ZFS+sendfile severe performance issues ( o kern/141091 fs [patch] [nullfs] fix panics with DIAGNOSTIC enabled o kern/141086 fs [nfs] [panic] panic("nfs: bioread, not dir") on FreeBS o kern/141010 fs [zfs] "zfs scrub" fails when backed by files in UFS2 o kern/140888 fs [zfs] boot fail from zfs root while the pool resilveri o kern/140661 fs [zfs] [patch] /boot/loader fails to work on a GPT/ZFS- o kern/140640 fs [zfs] snapshot crash o kern/140134 fs [msdosfs] write and fsck destroy filesystem integrity o kern/140068 fs [smbfs] [patch] smbfs does not allow semicolon in file o kern/139725 fs [zfs] zdb(1) dumps core on i386 when examining zpool c o kern/139715 fs [zfs] vfs.numvnodes leak on busy zfs o bin/139651 fs [nfs] mount(8): read-only remount of NFS volume does n o kern/139597 fs [patch] [tmpfs] tmpfs initializes va_gen but doesn't u o kern/139564 fs [zfs] [panic] 8.0-RC1 - Fatal trap 12 at end of shutdo o kern/139407 fs [smbfs] [panic] smb mount causes system crash if remot o kern/138790 fs [zfs] ZFS ceases caching when mem demand is high o kern/138662 fs [panic] ffs_blkfree: freeing free block o kern/138421 fs [ufs] [patch] remove UFS label limitations o kern/138202 fs mount_msdosfs(1) see only 2Gb o kern/136968 fs [ufs] [lor] ufs/bufwait/ufs (open) o kern/136945 fs [ufs] [lor] filedesc structure/ufs (poll) o kern/136944 fs [ffs] [lor] bufwait/snaplk (fsync) o kern/136873 fs [ntfs] Missing directories/files on NTFS volume o kern/136865 fs [nfs] [patch] NFS exports atomic and on-the-fly atomic o kern/136470 fs [nfs] Cannot mount / in read-only, over NFS o kern/135667 fs [lor] LORs causing ufs filesystem corruption on XEN Do o kern/135546 fs [zfs] zfs.ko module doesn't ignore zpool.cache filenam o kern/135469 fs [ufs] [panic] kernel crash on md operation in ufs_dirb o kern/135050 fs [zfs] ZFS clears/hides disk errors on reboot o kern/134491 fs [zfs] Hot spares are rather cold... o kern/133676 fs [smbfs] [panic] umount -f'ing a vnode-based memory dis o kern/133614 fs [panic] panic: ffs_truncate: read-only filesystem o kern/133174 fs [msdosfs] [patch] msdosfs must support utf-encoded int o kern/132960 fs [ufs] [panic] panic:ffs_blkfree: freeing free frag o kern/132397 fs reboot causes filesystem corruption (failure to sync b o kern/132331 fs [ufs] [lor] LOR ufs and syncer o kern/132237 fs [msdosfs] msdosfs has problems to read MSDOS Floppy o kern/132145 fs [panic] File System Hard Crashes o kern/131441 fs [unionfs] [nullfs] unionfs and/or nullfs not combineab o kern/131360 fs [nfs] poor scaling behavior of the NFS server under lo o kern/131342 fs [nfs] mounting/unmounting of disks causes NFS to fail o bin/131341 fs makefs: error "Bad file descriptor" on the mount poin o kern/130920 fs [msdosfs] cp(1) takes 100% CPU time while copying file o kern/130210 fs [nullfs] Error by check nullfs o kern/129760 fs [nfs] after 'umount -f' of a stale NFS share FreeBSD l o kern/129488 fs [smbfs] Kernel "bug" when using smbfs in smbfs_smb.c: o kern/129231 fs [ufs] [patch] New UFS mount (norandom) option - mostly o kern/129152 fs [panic] non-userfriendly panic when trying to mount(8) f kern/128829 fs smbd(8) causes periodic panic on 7-RELEASE o kern/127787 fs [lor] [ufs] Three LORs: vfslock/devfs/vfslock, ufs/vfs o bin/127270 fs fsck_msdosfs(8) may crash if BytesPerSec is zero o kern/127029 fs [panic] mount(8): trying to mount a write protected zi o kern/126287 fs [ufs] [panic] Kernel panics while mounting an UFS file o kern/125895 fs [ffs] [panic] kernel: panic: ffs_blkfree: freeing free s kern/125738 fs [zfs] [request] SHA256 acceleration in ZFS p kern/124621 fs [ext3] [patch] Cannot mount ext2fs partition f bin/124424 fs [zfs] zfs(8): zfs list -r shows strange snapshots' siz o kern/123939 fs [msdosfs] corrupts new files o kern/122380 fs [ffs] ffs_valloc:dup alloc (Soekris 4801/7.0/USB Flash o bin/122172 fs [fs]: amd(8) automount daemon dies on 6.3-STABLE i386, o bin/121898 fs [nullfs] pwd(1)/getcwd(2) fails with Permission denied o bin/121779 fs [ufs] snapinfo(8) (and related tools?) only work for t o bin/121366 fs [zfs] [patch] Automatic disk scrubbing from periodic(8 o bin/121072 fs [smbfs] mount_smbfs(8) cannot normally convert the cha f kern/120991 fs [panic] [ffs] [snapshot] System crashes when manipulat o kern/120483 fs [ntfs] [patch] NTFS filesystem locking changes o kern/120482 fs [ntfs] [patch] Sync style changes between NetBSD and F f kern/119735 fs [zfs] geli + ZFS + samba starting on boot panics 7.0-B o kern/118912 fs [2tb] disk sizing/geometry problem with large array o kern/118713 fs [minidump] [patch] Display media size required for a k o bin/118249 fs mv(1): moving a directory changes its mtime o kern/118107 fs [ntfs] [panic] Kernel panic when accessing a file at N o kern/117954 fs [ufs] dirhash on very large directories blocks the mac o bin/117315 fs [smbfs] mount_smbfs(8) and related options can't mount o kern/117314 fs [ntfs] Long-filename only NTFS fs'es cause kernel pani o kern/117158 fs [zfs] zpool scrub causes panic if geli vdevs detach on o bin/116980 fs [msdosfs] [patch] mount_msdosfs(8) resets some flags f o conf/116931 fs lack of fsck_cd9660 prevents mounting iso images with p kern/116608 fs [msdosfs] [patch] msdosfs fails to check mount options o kern/116583 fs [ffs] [hang] System freezes for short time when using o kern/116170 fs [panic] Kernel panic when mounting /tmp f kern/115645 fs [ffs] [snapshots] [panic] lockmgr: thread 0xc4c00d80, o bin/115361 fs [zfs] mount(8) gets into a state where it won't set/un o kern/114955 fs [cd9660] [patch] [request] support for mask,dirmask,ui o kern/114847 fs [ntfs] [patch] [request] dirmask support for NTFS ala o kern/114676 fs [ufs] snapshot creation panics: snapacct_ufs2: bad blo o bin/114468 fs [patch] [request] add -d option to umount(8) to detach o kern/113852 fs [smbfs] smbfs does not properly implement DFS referral o bin/113838 fs [patch] [request] mount(8): add support for relative p o bin/113049 fs [patch] [request] make quot(8) use getopt(3) and show o kern/112658 fs [smbfs] [patch] smbfs and caching problems (resolves b o kern/111843 fs [msdosfs] Long Names of files are incorrectly created o kern/111782 fs [ufs] dump(8) fails horribly for large filesystems s bin/111146 fs [2tb] fsck(8) fails on 6T filesystem o kern/109024 fs [msdosfs] [iconv] mount_msdosfs: msdosfs_iconv: Operat o kern/109010 fs [msdosfs] can't mv directory within fat32 file system o bin/107829 fs [2TB] fdisk(8): invalid boundary checking in fdisk / w o kern/106107 fs [ufs] left-over fsck_snapshot after unfinished backgro o kern/106030 fs [ufs] [panic] panic in ufs from geom when a dead disk o kern/104406 fs [ufs] Processes get stuck in "ufs" state under persist o kern/104133 fs [ext2fs] EXT2FS module corrupts EXT2/3 filesystems o kern/103035 fs [ntfs] Directories in NTFS mounted disc images appear o kern/101324 fs [smbfs] smbfs sometimes not case sensitive when it's s o kern/99290 fs [ntfs] mount_ntfs ignorant of cluster sizes s bin/97498 fs [request] newfs(8) has no option to clear the first 12 o kern/97377 fs [ntfs] [patch] syntax cleanup for ntfs_ihash.c o kern/95222 fs [iso9660] File sections on ISO9660 level 3 CDs ignored o kern/94849 fs [ufs] rename on UFS filesystem is not atomic o bin/94810 fs fsck(8) incorrectly reports 'file system marked clean' o kern/94769 fs [ufs] Multiple file deletions on multi-snapshotted fil o kern/94733 fs [smbfs] smbfs may cause double unlock o bin/94635 fs snapinfo(8)/libufs only works for disk-backed filesyst o kern/93942 fs [vfs] [patch] panic: ufs_dirbad: bad dir (patch from D o kern/92272 fs [ffs] [hang] Filling a filesystem while creating a sna o kern/91134 fs [smbfs] [patch] Preserve access and modification time a kern/90815 fs [smbfs] [patch] SMBFS with character conversions somet o kern/88657 fs [smbfs] windows client hang when browsing a samba shar o kern/88555 fs [panic] ffs_blkfree: freeing free frag on AMD 64 o kern/88266 fs [smbfs] smbfs does not implement UIO_NOCOPY and sendfi o bin/87966 fs [patch] newfs(8): introduce -A flag for newfs to enabl o kern/87859 fs [smbfs] System reboot while umount smbfs. o kern/86587 fs [msdosfs] rm -r /PATH fails with lots of small files o bin/85494 fs fsck_ffs: unchecked use of cg_inosused macro etc. f kern/85326 fs [smbfs] [panic] saving a file via samba to an overquot o kern/80088 fs [smbfs] Incorrect file time setting on NTFS mounted vi o bin/74779 fs Background-fsck checks one filesystem twice and omits o kern/73484 fs [ntfs] Kernel panic when doing `ls` from the client si o bin/73019 fs [ufs] fsck_ufs(8) cannot alloc 607016868 bytes for ino o kern/71774 fs [ntfs] NTFS cannot "see" files on a WinXP filesystem o bin/70600 fs fsck(8) throws files away when it can't grow lost+foun o kern/68978 fs [panic] [ufs] crashes with failing hard disk, loose po o kern/65920 fs [nwfs] Mounted Netware filesystem behaves strange o kern/65901 fs [smbfs] [patch] smbfs fails fsx write/truncate-down/tr o kern/61503 fs [smbfs] mount_smbfs does not work as non-root o kern/55617 fs [smbfs] Accessing an nsmb-mounted drive via a smb expo o kern/51685 fs [hang] Unbounded inode allocation causes kernel to loc o kern/51583 fs [nullfs] [patch] allow to work with devices and socket o kern/36566 fs [smbfs] System reboot with dead smb mount and umount o kern/33464 fs [ufs] soft update inconsistencies after system crash o bin/27687 fs fsck(8) wrapper is not properly passing options to fsc o kern/18874 fs [2TB] 32bit NFS servers export wrong negative values t 208 problems total. From owner-freebsd-fs@FreeBSD.ORG Mon Nov 1 20:01:12 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 0B091106566B for ; Mon, 1 Nov 2010 20:01:12 +0000 (UTC) (envelope-from csalgau-br@bitdefender.com) Received: from mail.bitdefender.com (mail.bitdefender.com [91.199.104.2]) by mx1.freebsd.org (Postfix) with ESMTP id 3B0C28FC1B for ; Mon, 1 Nov 2010 20:01:10 +0000 (UTC) Received: (qmail 7836 invoked from network); 1 Nov 2010 22:01:08 +0200 Received: from 79-112-63-218.iasi.fiberlink.ro (HELO CSalgau3.mshome.net) (csalgau@bitdefender.com@79.112.63.218) by mail.bitdefender.com with AES256-SHA encrypted SMTP; 1 Nov 2010 22:01:07 +0200 Date: Mon, 1 Nov 2010 22:00:18 +0200 From: Mihai-Catalin Salgau Organization: S.C. Bitdefender S.R.L. X-Priority: 3 (Normal) Message-ID: <354971554.20101101220018@bitdefender.com> To: freebsd-fs In-Reply-To: <20101101104203.GH2160@garage.freebsd.pl> References: <20101101104203.GH2160@garage.freebsd.pl> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-BitDefender-Spam: No (0) X-BitDefender-SpamStamp: v1, build 2.8.97.113122, SQMD Hits: InvalidIPBytes34 97.47.107.105, rbl score: 0(0), bayes score: 500(0), pbayes score: 500(0), neunet score: 0(0), flags: [NN_S_HOW_TO_VDA; NN_LEGIT_BITDEFENDER], SQMD: ef52ac2905c913c33601e87649f3514c.fuzzy.fzrbl.org, total: 0(775) X-BitDefender-Scanner: Clean, Agent: BitDefender qmail 3.1.0 on elfie.dsd.hq, sigver: 7.34496 Subject: Re: How to run ZFS Test Suite (ztest)? 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, 01 Nov 2010 20:01:12 -0000 Hello Pawel, Monday, November 1, 2010, 12:42:03 PM, you wrote: > On Fri, Oct 29, 2010 at 10:53:38PM +0300, App Deb wrote: >> Attempting to run it on 8.1-R drops the error: >>=20 >> %ztest >> Assertion failed: (abstime > 0), file >> /usr/src/cddl/lib/libzpool/../../../cddl/contrib/opensolaris/lib/libzpoo= l/common/kernel.c, >> line 309. >> Abort (core dumped) > Should be now fixed in r214622 and r214623. > Thank you for the report. Thanks. Any chance of seeing these MFCed? --=20 Mihai-Catalin Salgau Virus Analyst BitDefender Iasi ------------------------------ Email: csalgau@bitdefender.com Phone: +40 727 388 826 ------------------------------ From owner-freebsd-fs@FreeBSD.ORG Mon Nov 1 20:23:34 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 1D20E1065674 for ; Mon, 1 Nov 2010 20:23:34 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta14.westchester.pa.mail.comcast.net (qmta14.westchester.pa.mail.comcast.net [76.96.59.212]) by mx1.freebsd.org (Postfix) with ESMTP id BAB3A8FC0A for ; Mon, 1 Nov 2010 20:23:33 +0000 (UTC) Received: from omta07.westchester.pa.mail.comcast.net ([76.96.62.59]) by qmta14.westchester.pa.mail.comcast.net with comcast id RrwX1f0081GhbT85EwPZvb; Mon, 01 Nov 2010 20:23:33 +0000 Received: from koitsu.dyndns.org ([98.248.41.155]) by omta07.westchester.pa.mail.comcast.net with comcast id RwPY1f00H3LrwQ23TwPZvZ; Mon, 01 Nov 2010 20:23:33 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id AFB229B422; Mon, 1 Nov 2010 13:23:31 -0700 (PDT) Date: Mon, 1 Nov 2010 13:23:31 -0700 From: Jeremy Chadwick To: Mihai-Catalin Salgau Message-ID: <20101101202331.GA31463@icarus.home.lan> References: <20101101104203.GH2160@garage.freebsd.pl> <354971554.20101101220018@bitdefender.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <354971554.20101101220018@bitdefender.com> User-Agent: Mutt/1.5.21 (2010-09-15) Cc: freebsd-fs Subject: Re: How to run ZFS Test Suite (ztest)? 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, 01 Nov 2010 20:23:34 -0000 On Mon, Nov 01, 2010 at 10:00:18PM +0200, Mihai-Catalin Salgau wrote: > Hello Pawel, > > Monday, November 1, 2010, 12:42:03 PM, you wrote: > > > On Fri, Oct 29, 2010 at 10:53:38PM +0300, App Deb wrote: > >> Attempting to run it on 8.1-R drops the error: > >> > >> %ztest > >> Assertion failed: (abstime > 0), file > >> /usr/src/cddl/lib/libzpool/../../../cddl/contrib/opensolaris/lib/libzpool/common/kernel.c, > >> line 309. > >> Abort (core dumped) > > > Should be now fixed in r214622 and r214623. > > > Thank you for the report. > > Thanks. > Any chance of seeing these MFCed? The commits are here, and are very easy/simple: r214623: http://freshbsd.org/2010/11/01/10/42/14 r214622: http://freshbsd.org/2010/11/01/10/41/05 I'd recommend hand-applying them and testing on RELENG_8 first and report back to us. You will probably have to rebuild/install libzpool, just as a FYI. -- | Jeremy Chadwick jdc@parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB | From owner-freebsd-fs@FreeBSD.ORG Tue Nov 2 17:51:32 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id CFEE610656A4 for ; Tue, 2 Nov 2010 17:51:32 +0000 (UTC) (envelope-from mi+thun@aldan.algebra.com) Received: from mail2.timeinc.net (mail2.timeinc.net [64.236.74.30]) by mx1.freebsd.org (Postfix) with ESMTP id 7BF258FC1D for ; Tue, 2 Nov 2010 17:51:31 +0000 (UTC) Received: from mail.timeinc.net (mail.timeinc.net [64.12.55.166]) by mail2.timeinc.net (8.13.8/8.13.8) with ESMTP id oA2HVOuo021802 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO) for ; Tue, 2 Nov 2010 13:31:24 -0400 Received: from ws-mteterin.dev.pathfinder.com (ws-mteterin.dev.pathfinder.com [209.251.223.173]) by mail.timeinc.net (8.13.8/8.13.8) with SMTP id oA2HVO8W004856 for ; Tue, 2 Nov 2010 13:31:24 -0400 Message-ID: <4CD04AEC.8040607@aldan.algebra.com> Date: Tue, 02 Nov 2010 13:31:24 -0400 From: "Mikhail T." Organization: Virtual Estates, Inc. User-Agent: Mozilla/5.0 (X11; U; Linux i686; uk; rv:1.9.2.11) Gecko/20101013 Lightning/1.0b2 Thunderbird/3.1.5 MIME-Version: 1.0 To: fs@freebsd.org Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Subject: Using an SSD "disk" for / 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, 02 Nov 2010 17:51:32 -0000 Hello! I'm setting up a new system and would like to use a moderate (64Gb or 128Gb) SSD-drive to boot from. This will house /, /var, /home, and the /usr/local and thus see plenty of activity, whenever src and ports are updated, or "world" is remade, or packages are upgraded. I'm hoping, these operations would be much faster, than with a regular HDD. However, people mention, that SSDs develop /severe/ performance degradation if written to A LOT -- unless some SDD-specific operation (TRIM) is used, but not all Operating Systems support that... Does FreeBSD-8? Is that sufficient, or will an SSD degrade quickly anyway? Does anyone use an SSD under FreeBSD? Which brand/model? Are you happy with it? Also, what parameters should I give to newfs? SSDs' characteristics seem rather different from HDDs', so it is unlikely, that newfs' defaults will be optimal for an SSD... Would a different filesystem (ZFS?) be a better choice, than FFS, for these devices? Other thoughts? Thank you very much! Yours, -mi From owner-freebsd-fs@FreeBSD.ORG Tue Nov 2 18:00:41 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id E90EC106566C for ; Tue, 2 Nov 2010 18:00:41 +0000 (UTC) (envelope-from davidc@acns.ab.ca) Received: from mail.acns.ab.ca (mail.acns.ab.ca [204.191.24.183]) by mx1.freebsd.org (Postfix) with ESMTP id C96338FC1C for ; Tue, 2 Nov 2010 18:00:41 +0000 (UTC) Received: from [192.168.2.108] (dhcp8.acns.ab.ca [192.168.2.108]) by r2.acns.ab.ca (Postfix) with ESMTPA id 9AEA533CF5 for ; Tue, 2 Nov 2010 11:45:16 -0600 (MDT) Message-ID: <4CD04E21.7010907@acns.ab.ca> Date: Tue, 02 Nov 2010 11:45:05 -0600 From: Chad David User-Agent: Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.2.12) Gecko/20101027 Lightning/1.0b2 Thunderbird/3.1.6 MIME-Version: 1.0 To: fs@freebsd.org Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Subject: Skeleton Filesystem 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, 02 Nov 2010 18:00:42 -0000 I'm porting our filesystem from Solaris to FreeBSD, and part of that effort is getting back into FreeBSD and getting familiar with VFS. I've been writing a simple module that focuses on the VFS interfaces themselves, and not the underlying fileystem implementation in the hope of ending up with a concise but complete skeleton that can be used as a reference, and potentially a learning tool. I have permission from my current employer to release this code, and am wondering if there is any interest from others? If there isn't, I'll just focus on my port any leave you guys alone. If there is, I can make the code available and spend more effort on documenting the flow and logic. What I'm hoping for is feedback from people (who are maybe not experts already) on what is clear and what is not. If the code is straight forward, it should be useful as a starting point for others, or even just as a reference for the curious. Anyway, if you are interested feel free to contact me, and I'd be happy to make the code available. Thanks. Chad From owner-freebsd-fs@FreeBSD.ORG Tue Nov 2 18:16:33 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 56B6B1065697 for ; Tue, 2 Nov 2010 18:16:33 +0000 (UTC) (envelope-from julian@freebsd.org) Received: from out-0.mx.aerioconnect.net (out-0-26.mx.aerioconnect.net [216.240.47.86]) by mx1.freebsd.org (Postfix) with ESMTP id 39EE18FC15 for ; Tue, 2 Nov 2010 18:16:32 +0000 (UTC) Received: from idiom.com (postfix@mx0.idiom.com [216.240.32.160]) by out-0.mx.aerioconnect.net (8.13.8/8.13.8) with ESMTP id oA2I0CJY008488; Tue, 2 Nov 2010 11:00:12 -0700 X-Client-Authorized: MaGic Cook1e X-Client-Authorized: MaGic Cook1e Received: from julian-mac.elischer.org (h-67-100-89-137.snfccasy.static.covad.net [67.100.89.137]) by idiom.com (Postfix) with ESMTP id 7039F2D6015; Tue, 2 Nov 2010 11:00:11 -0700 (PDT) Message-ID: <4CD051A9.7090200@freebsd.org> Date: Tue, 02 Nov 2010 11:00:09 -0700 From: Julian Elischer User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.4; en-US; rv:1.9.2.12) Gecko/20101027 Thunderbird/3.1.6 MIME-Version: 1.0 To: "Mikhail T." References: <4CD04AEC.8040607@aldan.algebra.com> In-Reply-To: <4CD04AEC.8040607@aldan.algebra.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Scanned-By: MIMEDefang 2.67 on 216.240.47.51 Cc: fs@freebsd.org Subject: Re: Using an SSD "disk" for / 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, 02 Nov 2010 18:16:33 -0000 On 11/2/10 10:31 AM, Mikhail T. wrote: > Hello! > > I'm setting up a new system and would like to use a moderate (64Gb > or 128Gb) SSD-drive to boot from. > > This will house /, /var, /home, and the /usr/local and thus see > plenty of activity, whenever src and ports are updated, or "world" > is remade, or packages are upgraded. I'm hoping, these operations > would be much faster, than with a regular HDD. > > However, people mention, that SSDs develop /severe/ performance > degradation if written to A LOT -- unless some SDD-specific > operation (TRIM) is used, but not all Operating Systems support > that... Does FreeBSD-8? Is that sufficient, or will an SSD degrade > quickly anyway? there are trim patches but not in the OS by default as yet. > > Does anyone use an SSD under FreeBSD? Which brand/model? Are you > happy with it? I don't use it for / it's a waste.. / is usually not such a high priority in terms of performance etc.. usually I use flash for data regions. > > Also, what parameters should I give to newfs? SSDs' characteristics > seem rather different from HDDs', so it is unlikely, that newfs' > defaults will be optimal for an SSD... Would a different filesystem > (ZFS?) be a better choice, than FFS, for these devices? > > Other thoughts? Thank you very much! Yours, > > -mi > > _______________________________________________ > 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 Tue Nov 2 18:16:36 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 645781065670 for ; Tue, 2 Nov 2010 18:16:36 +0000 (UTC) (envelope-from avg@icyb.net.ua) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id B1D968FC1B for ; Tue, 2 Nov 2010 18:16:35 +0000 (UTC) Received: from odyssey.starpoint.kiev.ua (alpha-e.starpoint.kiev.ua [212.40.38.101]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id UAA17406; Tue, 02 Nov 2010 20:16:30 +0200 (EET) (envelope-from avg@icyb.net.ua) Message-ID: <4CD0557D.1070901@icyb.net.ua> Date: Tue, 02 Nov 2010 20:16:29 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.11) Gecko/20101021 Lightning/1.0b2 Thunderbird/3.1.5 MIME-Version: 1.0 To: Chad David References: <4CD04E21.7010907@acns.ab.ca> In-Reply-To: <4CD04E21.7010907@acns.ab.ca> X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: fs@freebsd.org Subject: Re: Skeleton Filesystem 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, 02 Nov 2010 18:16:36 -0000 on 02/11/2010 19:45 Chad David said the following: > > I'm porting our filesystem from Solaris to FreeBSD, and part of that effort is > getting back into FreeBSD and getting familiar with VFS. > > I've been writing a simple module that focuses on the VFS interfaces themselves, > and not the underlying fileystem implementation in the hope of ending up with a > concise but complete skeleton that can be used as a reference, and potentially a > learning tool. > > I have permission from my current employer to release this code, and am wondering > if there is any interest from others? If there isn't, I'll just focus on my port > any leave you guys alone. If there is, I can make the code available and spend > more effort on documenting the flow and logic. > > What I'm hoping for is feedback from people (who are maybe not experts already) on > what is clear and what is not. If the code is straight forward, it should be > useful as a starting point for others, or even just as a reference for the curious. > > Anyway, if you are interested feel free to contact me, and I'd be happy to make > the code available. That sounds terribly useful for different uses, please share it! I myself took a shot at this although in much more primitive from [avgfs :-)]. Thanks! -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Tue Nov 2 18:28:05 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 81338106564A for ; Tue, 2 Nov 2010 18:28:05 +0000 (UTC) (envelope-from freebsd-fs@m.gmane.org) Received: from lo.gmane.org (lo.gmane.org [80.91.229.12]) by mx1.freebsd.org (Postfix) with ESMTP id 31BDA8FC18 for ; Tue, 2 Nov 2010 18:28:04 +0000 (UTC) Received: from list by lo.gmane.org with local (Exim 4.69) (envelope-from ) id 1PDLaV-0004EJ-Kh for freebsd-fs@freebsd.org; Tue, 02 Nov 2010 19:28:03 +0100 Received: from firewall.andxor.it ([195.223.2.2]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Tue, 02 Nov 2010 19:28:03 +0100 Received: from lapo by firewall.andxor.it with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Tue, 02 Nov 2010 19:28:03 +0100 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-fs@freebsd.org From: Lapo Luchini Date: Tue, 02 Nov 2010 19:27:51 +0100 Lines: 29 Message-ID: <4CD05827.9040903@lapo.it> References: <49BAD057.6060602@jrv.org> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@dough.gmane.org X-Gmane-NNTP-Posting-Host: firewall.andxor.it User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.1.15) Gecko/20101102 SeaMonkey/2.0.10 In-Reply-To: <49BAD057.6060602@jrv.org> X-Enigmail-Version: 1.0.1 OpenPGP: id=C8F252FB Cc: Luigi Lauro Subject: Re: ZFS recv doesn't properly skip existing snapshots 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, 02 Nov 2010 18:28:05 -0000 James R. Van Artsdalen wrote: > I'm working on a way to keep a remote pool in sync with a local pool > using zfs send/recv. [...] > It appears "zfs recv" is supposed to simply skip any snapshot it already > has [...] But instead "zfs recv" appears to never get in > sync with the input stream again and simple exits. I have come to the same conclusions, it seems to me that it follows a "fail fast" approach and simply closes after the first "ignore", even though the could be useful data afterwards. In this thread http://opensolaris.org/jive/thread.jspa?threadID=116790 they're asking the O.P. "why are you sending the wrong initial snap?" which applies to the case of sending a single filesystem, but as you correctly pointed out when sending "zfs send -RI" an inconsistent state can be reached even using the "correct" inizial snapshot, which might exist on some of the sub-filesystems and not on the others. I wonder if it might be as simple as removing the "fail fast" exit code which I thin might be used after the "already exists; ignoring" warning, but I still have to find the place in the code that is printed. Oh, on 8-STABLE it is printed in line 1885 of /usr/src/cddl/contrib/opensolaris/lib/libzfs/common/libzfs_sendrecv.c and the is no "fail fast" at all, so I guess it is failing (without verbose errors) in recv_skip(). -- Lapo Luchini - http://lapo.it/ From owner-freebsd-fs@FreeBSD.ORG Tue Nov 2 19:53:54 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 1BFD8106564A for ; Tue, 2 Nov 2010 19:53:54 +0000 (UTC) (envelope-from julian@freebsd.org) Received: from out-0.mx.aerioconnect.net (out-0-27.mx.aerioconnect.net [216.240.47.87]) by mx1.freebsd.org (Postfix) with ESMTP id F2BA88FC1D for ; Tue, 2 Nov 2010 19:53:53 +0000 (UTC) Received: from idiom.com (postfix@mx0.idiom.com [216.240.32.160]) by out-0.mx.aerioconnect.net (8.13.8/8.13.8) with ESMTP id oA2JrpF8014423; Tue, 2 Nov 2010 12:53:51 -0700 X-Client-Authorized: MaGic Cook1e X-Client-Authorized: MaGic Cook1e Received: from julian-mac.elischer.org (h-67-100-89-137.snfccasy.static.covad.net [67.100.89.137]) by idiom.com (Postfix) with ESMTP id D073A2D601A; Tue, 2 Nov 2010 12:53:49 -0700 (PDT) Message-ID: <4CD06C4B.80100@freebsd.org> Date: Tue, 02 Nov 2010 12:53:47 -0700 From: Julian Elischer User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.4; en-US; rv:1.9.2.12) Gecko/20101027 Thunderbird/3.1.6 MIME-Version: 1.0 To: "Mikhail T." References: <4CD04AEC.8040607@aldan.algebra.com> <4CD051A9.7090200@freebsd.org> <4CD0660E.2000102@aldan.algebra.com> In-Reply-To: <4CD0660E.2000102@aldan.algebra.com> Content-Type: text/plain; charset=KOI8-R; format=flowed Content-Transfer-Encoding: 8bit X-Scanned-By: MIMEDefang 2.67 on 216.240.47.51 Cc: fs@freebsd.org Subject: Re: Using an SSD "disk" for / 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, 02 Nov 2010 19:53:54 -0000 On 11/2/10 12:27 PM, Mikhail T. wrote: > 02.11.2010 14:00, Julian Elischer ÎÁÐÉÓÁ×(ÌÁ): >> there are trim patches but not in the OS by default as yet. > Would the patches apply to RELENG_8 today, or do they require some > 9-only feature(s)? >>> Does anyone use an SSD under FreeBSD? Which brand/model? Are you >>> happy with it? >> ... >> usually I use flash for data regions. > And? Do you use the TRIM-patches? Does performance stay high with > time -- with or without TRIM? Do you use FFS or some other > file-system? If FFS, are you relying on newfs' defaults? I'm not the person to talk to because I work fo rFusion-io (flash storage). I use our cards.. > > Thank you! Yours, > > -mi > >>> Also, what parameters should I give to newfs? SSDs' >>> characteristics seem rather different from HDDs', so it is >>> unlikely, that newfs' defaults will be optimal for an SSD... Would >>> a different filesystem (ZFS?) be a better choice, > From owner-freebsd-fs@FreeBSD.ORG Tue Nov 2 21:52:46 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C2149106564A; Tue, 2 Nov 2010 21:52:46 +0000 (UTC) (envelope-from fjwcash@gmail.com) Received: from mail-gw0-f54.google.com (mail-gw0-f54.google.com [74.125.83.54]) by mx1.freebsd.org (Postfix) with ESMTP id 68F958FC08; Tue, 2 Nov 2010 21:52:46 +0000 (UTC) Received: by gwj16 with SMTP id 16so252898gwj.13 for ; Tue, 02 Nov 2010 14:52:45 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:received:in-reply-to :references:date:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=9QYKjd2uod7lsxVBjQP0IhlOal77FKpB0gA+dbdQtRU=; b=euUXKh5FXoTXVUynedn/5BVfFe8BIC70fghoA7B4dzhQxDtx3NC1dZYikvdVBBKu3o P147M83IGlhGif6M9Oeu69BSViLq2Uh4BcN/KXcVydYUG5uu/ltZ+OY/eoi9+AZ+633V 5nn5xwwf8hKIwU+abISlzx2n9fmBfm+fOSgso= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=Iy/Zw9bhmfeiHrvMKOwTLUyQNW6KCLA6MSo7v1AIM45PIb+jbaLc/Vn3WWR+K2FA5I SmnIR5R9NgCS+nT8B1BEqkCKfRfgC4+H2Jd5IKbfh3g4ZoxB3OFfPu3Le5tu2NwVXoV9 88t9/auWjODaZE6bOeH/HY4+dqHl/V41ALCnw= MIME-Version: 1.0 Received: by 10.91.24.17 with SMTP id b17mr2025646agj.192.1288734765442; Tue, 02 Nov 2010 14:52:45 -0700 (PDT) Received: by 10.90.97.7 with HTTP; Tue, 2 Nov 2010 14:52:45 -0700 (PDT) In-Reply-To: <20101016222833.GA6765@garage.freebsd.pl> References: <20101016222833.GA6765@garage.freebsd.pl> Date: Tue, 2 Nov 2010 14:52:45 -0700 Message-ID: From: Freddie Cash To: Pawel Jakub Dawidek Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-fs@freebsd.org Subject: Re: Converting a non-HAST ZFS pool to a HAST pool 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, 02 Nov 2010 21:52:46 -0000 On Sat, Oct 16, 2010 at 3:28 PM, Pawel Jakub Dawidek wrot= e: > On Fri, Oct 15, 2010 at 11:37:34AM -0700, Freddie Cash wrote: >> Has anyone looked into, attempted, or considered converting a non-HAST >> ZFS pool configuration into a HAST one? =C2=A0While the pool is live and >> the server is in use. =C2=A0Would it even be possible? >> >> For example, would the following work (in a pool with a single raidz2 >> vdev, where the underlying GEOM provider is glabel) >> =C2=A0 - zpool offline 1 drive =C2=A0(pool is now running degraded) >> =C2=A0 - configure hastd in master mode with a single provider using the >> "offline" disk (hast metadata takes the place of glabel metadata) > > HAST metadata takes much more space than glabel metadata. The latter > takes only one sector, while the former depends on provider size, but we > have to keep entire extent bitmap there, so definitely more than one > sector. Okay, so converting a non-HAST ZFS setup to a HAST setup using the same drives won't work. Any reason that it wouldn't work when replacing the drives with larger ones= ? - zpool offline poolname label/disk01 - physically replace drive - glabel drive as disk01 - configure hast to use label/disk01 - zpool replace poolname label/drive01 hast/drive01 I can't think of any reason why it would fail, since the hast device will be twice as large as the non-hast device it's replacing. But thought I'd double-check, just to be safe. :) Granted, doing it this way would required a *long* initial sync, as there's currently 18 TB of data in the pool. And more going in every day. So it might be better to start fresh. --=20 Freddie Cash fjwcash@gmail.com From owner-freebsd-fs@FreeBSD.ORG Tue Nov 2 22:07:42 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D69D1106566C for ; Tue, 2 Nov 2010 22:07:42 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (60.wheelsystems.com [83.12.187.60]) by mx1.freebsd.org (Postfix) with ESMTP id 7A75F8FC08 for ; Tue, 2 Nov 2010 22:07:42 +0000 (UTC) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id 5EB2A45CA6; Tue, 2 Nov 2010 23:07:40 +0100 (CET) Received: from localhost (chello089073192049.chello.pl [89.73.192.49]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id D6B4F45B36; Tue, 2 Nov 2010 23:07:34 +0100 (CET) Date: Tue, 2 Nov 2010 23:06:57 +0100 From: Pawel Jakub Dawidek To: Freddie Cash Message-ID: <20101102220657.GC2051@garage.freebsd.pl> References: <20101016222833.GA6765@garage.freebsd.pl> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="adJ1OR3c6QgCpb/j" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.3i X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 9.0-CURRENT amd64 X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-0.6 required=4.5 tests=BAYES_00,RCVD_IN_SORBS_DUL autolearn=no version=3.0.4 Cc: freebsd-fs@freebsd.org Subject: Re: Converting a non-HAST ZFS pool to a HAST pool 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, 02 Nov 2010 22:07:42 -0000 --adJ1OR3c6QgCpb/j Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Tue, Nov 02, 2010 at 02:52:45PM -0700, Freddie Cash wrote: > Okay, so converting a non-HAST ZFS setup to a HAST setup using the > same drives won't work. >=20 > Any reason that it wouldn't work when replacing the drives with larger on= es? >=20 > - zpool offline poolname label/disk01 > - physically replace drive > - glabel drive as disk01 > - configure hast to use label/disk01 > - zpool replace poolname label/drive01 hast/drive01 >=20 > I can't think of any reason why it would fail, since the hast device > will be twice as large as the non-hast device it's replacing. But > thought I'd double-check, just to be safe. :) Yes, this should work. > Granted, doing it this way would required a *long* initial sync, as > there's currently 18 TB of data in the pool. And more going in every > day. So it might be better to start fresh. If you mean HAST initial sync, then this should be now improved in r214284: Before this change on first connect between primary and secondary we initialize all the data. This is huge waste of time and resources if there were no writes yet, as there is no real data to synchronize. Optimize this by sending "virgin" argument to secondary, which gives it a hint that synchronization is not needed. In the common case (where noth nodes are configured at the same time) instead of synchronizing everything, we don't synchronize at all. The change is not yet merged to stable/8, AFAIR, but this will happen today or tomorrow. You still need to wait for ZFS to copy the data over to the new vdev. --=20 Pawel Jakub Dawidek http://www.wheelsystems.com pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --adJ1OR3c6QgCpb/j Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.14 (FreeBSD) iEYEARECAAYFAkzQi4AACgkQForvXbEpPzSk2gCcDf0SA7iyDVUHV7jnSnQi4fYZ m10AoL/pad/aTU0PcZ5EhDr+dSzgm6aZ =Dr3l -----END PGP SIGNATURE----- --adJ1OR3c6QgCpb/j-- From owner-freebsd-fs@FreeBSD.ORG Tue Nov 2 19:27:12 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C75BA1065674 for ; Tue, 2 Nov 2010 19:27:12 +0000 (UTC) (envelope-from mi+thun@aldan.algebra.com) Received: from mail2.timeinc.net (mail2.timeinc.net [64.236.74.30]) by mx1.freebsd.org (Postfix) with ESMTP id 6E69A8FC27 for ; Tue, 2 Nov 2010 19:27:11 +0000 (UTC) Received: from mail.timeinc.net (mail.timeinc.net [64.12.55.166]) by mail2.timeinc.net (8.13.8/8.13.8) with ESMTP id oA2JRB58019769 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Tue, 2 Nov 2010 15:27:11 -0400 Received: from ws-mteterin.dev.pathfinder.com (ws-mteterin.dev.pathfinder.com [209.251.223.173]) by mail.timeinc.net (8.13.8/8.13.8) with SMTP id oA2JRAvC018230; Tue, 2 Nov 2010 15:27:11 -0400 Message-ID: <4CD0660E.2000102@aldan.algebra.com> Date: Tue, 02 Nov 2010 15:27:10 -0400 From: "Mikhail T." Organization: Virtual Estates, Inc. User-Agent: Mozilla/5.0 (X11; U; Linux i686; uk; rv:1.9.2.11) Gecko/20101013 Lightning/1.0b2 Thunderbird/3.1.5 MIME-Version: 1.0 To: Julian Elischer References: <4CD04AEC.8040607@aldan.algebra.com> <4CD051A9.7090200@freebsd.org> In-Reply-To: <4CD051A9.7090200@freebsd.org> Content-Type: text/plain; charset=KOI8-R; format=flowed Content-Transfer-Encoding: 8bit X-Mailman-Approved-At: Tue, 02 Nov 2010 22:08:08 +0000 Cc: fs@freebsd.org Subject: Re: Using an SSD "disk" for / 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, 02 Nov 2010 19:27:12 -0000 02.11.2010 14:00, Julian Elischer ÎÁÐÉÓÁ×(ÌÁ): > there are trim patches but not in the OS by default as yet. Would the patches apply to RELENG_8 today, or do they require some 9-only feature(s)? >> Does anyone use an SSD under FreeBSD? Which brand/model? Are you >> happy with it? > ... > usually I use flash for data regions. And? Do you use the TRIM-patches? Does performance stay high with time -- with or without TRIM? Do you use FFS or some other file-system? If FFS, are you relying on newfs' defaults? Thank you! Yours, -mi >> Also, what parameters should I give to newfs? SSDs' characteristics >> seem rather different from HDDs', so it is unlikely, that newfs' >> defaults will be optimal for an SSD... Would a different filesystem >> (ZFS?) be a better choice, From owner-freebsd-fs@FreeBSD.ORG Tue Nov 2 22:29:55 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 16637106566C; Tue, 2 Nov 2010 22:29:55 +0000 (UTC) (envelope-from fjwcash@gmail.com) Received: from mail-yw0-f54.google.com (mail-yw0-f54.google.com [209.85.213.54]) by mx1.freebsd.org (Postfix) with ESMTP id AF04F8FC0A; Tue, 2 Nov 2010 22:29:54 +0000 (UTC) Received: by ywh2 with SMTP id 2so4223063ywh.13 for ; Tue, 02 Nov 2010 15:29:54 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:received:in-reply-to :references:date:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=tIZ0YbyALF4du71yK4RiNb7IiS2NkApV0d2sXDf5K2k=; b=KKAGEFVlPxLqw//UNogV0lYuPcHVMAua5G8xC27U+TtJttWykJtNCZzbu69CvDEv74 IorqZvIkFQYuW6W6cRil3Qg9UH/I4UFrDpX2ipTESZqzv0W/Kcxum1gtHMfLXilGr4IH iozjmosGVMzrBNthM+xsrWTvKvnTo5ZV5aNyg= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=axHbckEriDZj2zmR4pYcqMuQyi9dI6i9RcKq4SA5gpgiKNmIHPq8NlZmMSpRIswU86 jCUzrl74940cHy0BzFLpwyYae0izH/MO5RCG1Oa3xPVxDUzR5yqpAlCZIEyYMgcpaxC8 qf0hVWmMP4jq56ojtbYOHYpHV4oKsxJpFJ3w4= MIME-Version: 1.0 Received: by 10.90.4.26 with SMTP id 26mr2088325agd.84.1288736993065; Tue, 02 Nov 2010 15:29:53 -0700 (PDT) Received: by 10.90.97.7 with HTTP; Tue, 2 Nov 2010 15:29:52 -0700 (PDT) In-Reply-To: <20101102220657.GC2051@garage.freebsd.pl> References: <20101016222833.GA6765@garage.freebsd.pl> <20101102220657.GC2051@garage.freebsd.pl> Date: Tue, 2 Nov 2010 15:29:52 -0700 Message-ID: From: Freddie Cash To: Pawel Jakub Dawidek Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-fs@freebsd.org Subject: Re: Converting a non-HAST ZFS pool to a HAST pool 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, 02 Nov 2010 22:29:55 -0000 On Tue, Nov 2, 2010 at 3:06 PM, Pawel Jakub Dawidek wrote= : > On Tue, Nov 02, 2010 at 02:52:45PM -0700, Freddie Cash wrote: >> Okay, so converting a non-HAST ZFS setup to a HAST setup using the >> same drives won't work. >> >> Any reason that it wouldn't work when replacing the drives with larger o= nes? >> >> =C2=A0- zpool offline poolname label/disk01 >> =C2=A0- physically replace drive >> =C2=A0- glabel drive as disk01 >> =C2=A0- configure hast to use label/disk01 >> =C2=A0- zpool replace poolname label/drive01 hast/drive01 >> >> I can't think of any reason why it would fail, since the hast device >> will be twice as large as the non-hast device it's replacing. =C2=A0But >> thought I'd double-check, just to be safe. =C2=A0:) > > Yes, this should work. > >> Granted, doing it this way would required a *long* initial sync, as >> there's currently 18 TB of data in the pool. =C2=A0And more going in eve= ry >> day. =C2=A0So it might be better to start fresh. > > If you mean HAST initial sync, then this should be now improved in > r214284: > > =C2=A0 =C2=A0 =C2=A0 =C2=A0Before this change on first connect between pr= imary and > =C2=A0 =C2=A0 =C2=A0 =C2=A0secondary we initialize all the data. This is = huge waste of time > =C2=A0 =C2=A0 =C2=A0 =C2=A0and resources if there were no writes yet, as = there is no real > =C2=A0 =C2=A0 =C2=A0 =C2=A0data to synchronize. > > =C2=A0 =C2=A0 =C2=A0 =C2=A0Optimize this by sending "virgin" argument to = secondary, which > =C2=A0 =C2=A0 =C2=A0 =C2=A0gives it a hint that synchronization is not ne= eded. > > =C2=A0 =C2=A0 =C2=A0 =C2=A0In the common case (where noth nodes are confi= gured at the same > =C2=A0 =C2=A0 =C2=A0 =C2=A0time) instead of synchronizing everything, we = don't synchronize > =C2=A0 =C2=A0 =C2=A0 =C2=A0at all. > > The change is not yet merged to stable/8, AFAIR, but this will happen > today or tomorrow. > > You still need to wait for ZFS to copy the data over to the new vdev. Ah, I see what you mean. I was originally thinking of replacing the drives in the "master" server, then configuring the "slave" server, and then syncing the two. Which would take aeons to do. Instead, it can be done in a piecemeal fashion: - configure slave server using new hardware (all 1 TB drives, for example= ) - replace 1 drive in master server, configure drive as a HAST device - use the HAST device to replace the non-HAST device in the ZFS pool, which causes ZFS to resilver it - this would then start a HAST sync *of just that one drive* - wait for resilver and sync to complete - replace next drive in master server - same process as above - repeat until all drives in master server are replaced with larger drives, using /dev/hast/* devices At that point, the master server should be using all HAST devices to form the ZFS pool, and have a bunch of extra free space as a bonus. *And*, the HAST devices should be all sync'd up with the slave server. During this process, I'd have to make sure that no automatic fail-over is setup, as it needs to sync master-->slave first. But, once the sync is done, then the CARP setup and fail-over can be done. --=20 Freddie Cash fjwcash@gmail.com From owner-freebsd-fs@FreeBSD.ORG Tue Nov 2 23:01:14 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 90462106566C for ; Tue, 2 Nov 2010 23:01:14 +0000 (UTC) (envelope-from julian@freebsd.org) Received: from out-0.mx.aerioconnect.net (out-0-31.mx.aerioconnect.net [216.240.47.91]) by mx1.freebsd.org (Postfix) with ESMTP id 70FE18FC15 for ; Tue, 2 Nov 2010 23:01:14 +0000 (UTC) Received: from idiom.com (postfix@mx0.idiom.com [216.240.32.160]) by out-0.mx.aerioconnect.net (8.13.8/8.13.8) with ESMTP id oA2N16HA023577; Tue, 2 Nov 2010 16:01:06 -0700 X-Client-Authorized: MaGic Cook1e X-Client-Authorized: MaGic Cook1e Received: from julian-mac.elischer.org (h-67-100-89-137.snfccasy.static.covad.net [67.100.89.137]) by idiom.com (Postfix) with ESMTP id AA2672D601B; Tue, 2 Nov 2010 16:01:05 -0700 (PDT) Message-ID: <4CD09830.3030400@freebsd.org> Date: Tue, 02 Nov 2010 16:01:04 -0700 From: Julian Elischer User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.4; en-US; rv:1.9.2.12) Gecko/20101027 Thunderbird/3.1.6 MIME-Version: 1.0 To: "Mikhail T." References: <4CD04AEC.8040607@aldan.algebra.com> <4CD051A9.7090200@freebsd.org> <4CD0660E.2000102@aldan.algebra.com> <4CD06C4B.80100@freebsd.org> <4CD0895A.5030402@aldan.algebra.com> In-Reply-To: <4CD0895A.5030402@aldan.algebra.com> Content-Type: text/plain; charset=KOI8-R; format=flowed Content-Transfer-Encoding: 8bit X-Scanned-By: MIMEDefang 2.67 on 216.240.47.51 Cc: fs@freebsd.org Subject: Re: Using an SSD "disk" for / 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, 02 Nov 2010 23:01:14 -0000 On 11/2/10 2:57 PM, Mikhail T. wrote: > 02.11.2010 15:53, Julian Elischer ÎÁÐÉÓÁ×(ÌÁ): >>> And? Do you use the TRIM-patches? Does performance stay high with >>> time -- with or without TRIM? Do you use FFS or some other >>> file-system? If FFS, are you relying on newfs' defaults? >> >> I'm not the person to talk to because I work fo rFusion-io (flash >> storage). I use our cards.. > Are you not at liberty to share the experiences with those cards? Our FreeBSD driver is limited a bit by the geom code but we get about 500MB/sec writes on the slower cards and about 800MB/sec on the faster cards, (per card). with 800MB/sec read on both I think from memory (I don't have a slower one). That's with larger sequential writes (32KB +) and reads. With smaller ones the transaction overhead comes in and I have had trouble getting over 120,000 transactions per second with 512 byte records. (slower machines would get smaller numbers).120,000 tps at 1/2 k each is only 60MB/sec. So you see what you are doing can greatly change the performance you get. Our FreeBSD driver doesn't support trim yet as we haven't had a lot of call for it. but it will 'eventually' when we get the time. Our cards are probably too expensive for personal use however. On a more general direction however, regarding all SSDs and flash based devices there are some characteristics that are just true across the board due to the nature of flash memory. On any flash drive, when the housekeeping kicks in, you find that the steady state write speed drops because it has to spend some of it's internal resources on housekeeping. Trim is definitely not a requirement for a root partition. They don't move very fast.. :-/ > Even if you > can't comment on quality, you can still talk about (un)importance of > TRIM-support > as well as about fine-tuning FS-parameters, no? Trim support is important in long-running situations where the drive is going to use up it's 'reserve' capacity fairly quickly. Because flash needs to be erased in large trunks, you need to move stuff around fairly regularly "behind the back of the OS". The more 'free' space the drive has to work with the more efficiently it can do that and so the less of it's resources it has to use for that purpose and the more resources are left for servicing user/OS requests. If it can add the file-system's free space to it's own spare space (thereby making the spare space effectively larger) it can be a lot more efficient and thus you get better performance. However if you are not pushing the drive hard enough to make it use up its spare space, (continuous writes for example) then trim will not have much effect. In other words if the inbuilt housekeeping code can keep up with your write requirements then trim will not make much of a difference.. For example if you have fast work for 15 seconds and then let it sit idle for a couple of minutes, it SHOULD have done enough housekeeping in that period so that when you start writing again, it has enough spare space to quickly store your new data without getting bottle-necked behind the housekeeper. If you run out of your 'spare space' then you depend on the speed of the housekeeper to free up new space for you. Trim can also help by adding the trimmed area to that 'spare space' number so it takes LONGER until you start to depend on the housekeeper. You can always increase the steady state speed of a flash drive by, "never" writing to part of it.. e.g. newfs a smaller filesystem than the drive. but if you "ever" write to the excess part you will need to either use trim to reclaim that space or low-level reformat the drive. The space beyond the filesystem will 'effectively' be added to the drive spare space until it is written to. I've seen this mentioned several times on various SSD lists and sites.. I can make no recomendations as I don't track them > > Thanks! Yours, > > -mi > From owner-freebsd-fs@FreeBSD.ORG Tue Nov 2 23:51:07 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id CD598106564A for ; Tue, 2 Nov 2010 23:51:07 +0000 (UTC) (envelope-from dougb@FreeBSD.org) Received: from mail2.fluidhosting.com (mx23.fluidhosting.com [204.14.89.6]) by mx1.freebsd.org (Postfix) with ESMTP id 7500F8FC14 for ; Tue, 2 Nov 2010 23:51:07 +0000 (UTC) Received: (qmail 4578 invoked by uid 399); 2 Nov 2010 23:51:05 -0000 Received: from localhost (HELO doug-optiplex.ka9q.net) (dougb@dougbarton.us@127.0.0.1) by localhost with ESMTPAM; 2 Nov 2010 23:51:05 -0000 X-Originating-IP: 127.0.0.1 X-Sender: dougb@dougbarton.us Message-ID: <4CD0A3E8.4080304@FreeBSD.org> Date: Tue, 02 Nov 2010 16:51:04 -0700 From: Doug Barton Organization: http://SupersetSolutions.com/ User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.12) Gecko/20101028 Thunderbird/3.1.6 MIME-Version: 1.0 To: freebsd-fs@freebsd.org References: <20100929031825.L683@besplex.bde.org> <20100929084801.M948@besplex.bde.org> <20100929041650.GA1553@aditya> <201009290917.05269.jhb@freebsd.org> <20100929202526.GA1564@aditya> In-Reply-To: <20100929202526.GA1564@aditya> X-Enigmail-Version: 1.1.2 OpenPGP: id=1A1ABC84 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: ext2fs now extremely slow 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, 02 Nov 2010 23:51:07 -0000 On 09/29/10 13:25, Aditya Sarawgi wrote: > [snip] >>> I see what you are saying. The gap of 8 block between the files >>> is due to the old preallocation which used to allocate additional >>> 8 blocks in advance for a particular inode when allocating a block >>> for it. The gap between blocks of the same file shouldn't be there >>> too. Both of these cases should be removed. I will look into this >>> during this week. The slowness is also due to lack of preallocation >>> in the new code. >> >> One of the GSoC students worked on a patch to add preallocation back to >> ext2fs this summer. Would you be interested in reviewing and/or testing >> that patch? (I've attached it). Here is his original e-mail: > [snip] > > Hi John, > > I did a review of Zheng Liu's reservation window patch last week and > I suggested him a few changes. Otherwise the code looks awesome. > But it would be great if someone else can review the patch too and if > everything goes well, we should merge this to HEAD. > For the ext4 part, I still have to review his patches and I am planning > to do it soon. Zheng is planning to have a separate module for ext4, > and it does make sense. We are aiming at bringing ext4 to a usable state > for 9-RELEASE (atleast read-only). Is anything happening with this? I recently built a new system that is multi-booting windows, freebsd, and ubuntu. I chose ext[23]fs for my /home partition so that I could share unix'y stuff between freebsd and linux, but I'm having both performance and stability problems, and today (fortunately for the first time, and fortunately recoverable) I had actual data loss. I'm happy to be a guinea pig for new code if people are reasonably sure that it will help, but if the situation doesn't improve I will have to reformat. On a related note, is there any way to use the journaling features of ext3fs in FreeBSD? When I boot the linux partition it's treating the fs as ext3fs, but AFAICS we only have ext2fs capabilities. FWIW, the reason I chose ext2fs is that linux doesn't have reliable r/w support for ufs, and there are really good drivers to mount ext2fs partitions in windows; which we also don't have for ufs. Doug -- Nothin' ever doesn't change, but nothin' changes much. -- OK Go Breadth of IT experience, and depth of knowledge in the DNS. Yours for the right price. :) http://SupersetSolutions.com/ From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 01:11:47 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 1DF7B106566C for ; Wed, 3 Nov 2010 01:11:47 +0000 (UTC) (envelope-from csalgau-br@bitdefender.com) Received: from mail.bitdefender.com (mail.bitdefender.com [91.199.104.2]) by mx1.freebsd.org (Postfix) with ESMTP id 461CC8FC16 for ; Wed, 3 Nov 2010 01:11:45 +0000 (UTC) Received: (qmail 32636 invoked from network); 3 Nov 2010 03:11:43 +0200 Received: from 79-112-63-218.iasi.fiberlink.ro (HELO CSalgau3.mshome.net) (csalgau@bitdefender.com@79.112.63.218) by mail.bitdefender.com with AES256-SHA encrypted SMTP; 3 Nov 2010 03:11:42 +0200 Date: Wed, 3 Nov 2010 03:11:38 +0200 From: Mihai-Catalin Salgau X-Priority: 3 (Normal) Message-ID: <1591425455.20101103031138@bitdefender.com> To: freebsd-fs In-Reply-To: <20101101202331.GA31463@icarus.home.lan> References: <20101101104203.GH2160@garage.freebsd.pl> <354971554.20101101220018@bitdefender.com> <20101101202331.GA31463@icarus.home.lan> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-BitDefender-Spam: No (0) X-BitDefender-SpamStamp: v1, build 2.8.97.113122, SQMD Hits: InvalidIPBytes34 97.41.112.104, rbl score: 0(0), bayes score: 500(0), pbayes score: 500(0), neunet score: 0(0), flags: [NN_S_HOW_TO_VDA; NN_LEGIT_BITDEFENDER], SQMD: f51575d66f19c6e65959ccf068128fc0.fuzzy.fzrbl.org, total: 0(775) X-BitDefender-Scanner: Clean, Agent: BitDefender qmail 3.1.0 on elfie.dsd.hq, sigver: 7.34496 Subject: Re: How to run ZFS Test Suite (ztest)? 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, 03 Nov 2010 01:11:47 -0000 Hello Jeremy, Monday, November 1, 2010, 10:23:31 PM, you wrote: > The commits are here, and are very easy/simple: > r214623: http://freshbsd.org/2010/11/01/10/42/14 > r214622: http://freshbsd.org/2010/11/01/10/41/05 > I'd recommend hand-applying them and testing on RELENG_8 first and > report back to us. You will probably have to rebuild/install libzpool, > just as a FYI. Thanks. Sorry for the delay. I forgot to post back. The patches are ok, but it seams it landed me back where 8.0-RELEASE was. I've tried this on three amd64 systems running on 8.1-STABLE #2: Mon Nov 1= 02:11:22 UTC 2010 or near. # ztest -V 5 vdevs, 7 datasets, 23 threads, 300 seconds... child died with signal 11 there is virtually 0 load on the system when running this From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 03:05:18 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id EBB33106564A for ; Wed, 3 Nov 2010 03:05:17 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta01.emeryville.ca.mail.comcast.net (qmta01.emeryville.ca.mail.comcast.net [76.96.30.16]) by mx1.freebsd.org (Postfix) with ESMTP id CA0E68FC08 for ; Wed, 3 Nov 2010 03:05:17 +0000 (UTC) Received: from omta13.emeryville.ca.mail.comcast.net ([76.96.30.52]) by qmta01.emeryville.ca.mail.comcast.net with comcast id SCV61f00617UAYkA1T5Hf5; Wed, 03 Nov 2010 03:05:17 +0000 Received: from koitsu.dyndns.org ([98.248.41.155]) by omta13.emeryville.ca.mail.comcast.net with comcast id ST5G1f0053LrwQ28ZT5GKV; Wed, 03 Nov 2010 03:05:16 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id F21F29B422; Tue, 2 Nov 2010 20:05:15 -0700 (PDT) Date: Tue, 2 Nov 2010 20:05:15 -0700 From: Jeremy Chadwick To: "Mikhail T." Message-ID: <20101103030515.GA61758@icarus.home.lan> References: <4CD04AEC.8040607@aldan.algebra.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4CD04AEC.8040607@aldan.algebra.com> User-Agent: Mutt/1.5.21 (2010-09-15) Cc: fs@freebsd.org Subject: Re: Using an SSD "disk" for / 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, 03 Nov 2010 03:05:18 -0000 On Tue, Nov 02, 2010 at 01:31:24PM -0400, Mikhail T. wrote: > I'm setting up a new system and would like to use a moderate (64Gb > or 128Gb) SSD-drive to boot from. > > This will house /, /var, /home, and the /usr/local and thus see > plenty of activity, whenever src and ports are updated, or "world" > is remade, or packages are upgraded. I'm hoping, these operations > would be much faster, than with a regular HDD. > > However, people mention, that SSDs develop /severe/ performance > degradation if written to A LOT -- unless some SDD-specific > operation (TRIM) is used, but not all Operating Systems support > that... Does FreeBSD-8? Is that sufficient, or will an SSD degrade > quickly anyway? > > Does anyone use an SSD under FreeBSD? Which brand/model? Are you > happy with it? > > Also, what parameters should I give to newfs? SSDs' characteristics > seem rather different from HDDs', so it is unlikely, that newfs' > defaults will be optimal for an SSD... Would a different filesystem > (ZFS?) be a better choice, than FFS, for these devices? Yes, I use SSDs as the OS disk. Depending on the system's needs, I use one of the following models: - Intel X25-V 40GB - Intel X25-M 80GB The reason I go with Intel disks is because they dominate all other SSD brands when it comes to IOPS. I'm less interested in sequential throughput in this particular case. I also go with Intel because I have a pretty severe dislike for OCZ products (and that's my problem/issue not yours). I use UFS2 + softupdates on all filesystems on the SSDs (except for the root filesystem, which lacks SU). Those filesystems are /, swap, /usr, /tmp, and /var. I do not do any "tuning" of the filesystems either, so I imagine there's room for speed improvements there as well. As for the performance: it's something you'll have to see for yourself. The performance is outright amazing when it comes to administrative tasks (OS installation, newfs, massive copies of data to/from the SSD, updating /usr/src and /usr/ports, etc.). Try a build/install world or kernel sometime on an SSD and watch your terminal. You'll be pretty impressed. Our systems which use SSDs *always* have at least one mechanical HDD included in the system (in fact usually 3, using ZFS raidz1). These are used for things like /var/mail and /home. As for TRIM and the like -- yes, that's a concern of mine as well, but for right now I just monitor the SSDs with smartmontools 5.40 and smartctl -a. If I had to make a recommendation of which drive to get, I would say get a drive that offers at least 80GB. I have to make some sacrifices with the 40GB. Having swap and /var (thus /var/crash) that's big enough to handle a kernel panic is important to me, so effectively the more RAM's in the machine the bigger the SSD needs to be. 80GB seems to be okay for our setups. -- | Jeremy Chadwick jdc@parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB | From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 10:38:04 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 8355B106566C for ; Wed, 3 Nov 2010 10:38:04 +0000 (UTC) (envelope-from dan.naumov@gmail.com) Received: from mail-bw0-f54.google.com (mail-bw0-f54.google.com [209.85.214.54]) by mx1.freebsd.org (Postfix) with ESMTP id 15DB48FC1B for ; Wed, 3 Nov 2010 10:38:03 +0000 (UTC) Received: by bwz3 with SMTP id 3so395253bwz.13 for ; Wed, 03 Nov 2010 03:38:03 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:received:date:message-id :subject:from:to:content-type; bh=AeUyX+JguuE5GoUkh8DkO8cvzfhbqiQuDijbY3SgW2M=; b=LlQXRK6M+WP1Tr2nEuQ7omTiNUgljADImGwkz7dBqercqWuMwgp0kbr/Yo+YPVmPt7 3Gh796R7OKvIt0pZAs+kEHMcdNzenEPVovKLiPI5ixhONEyFYUEpukIDW8IHM3iTac+U IK+5Jw02GzgW2cPbHhmnZ1hZEsiZf4Bnn3m3w= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:date:message-id:subject:from:to:content-type; b=KPFvD/q8tPj3cZp6Bd+lagAE4o/jyEyN7dk1IcfFO+9LhYnPDAfkwRViUbsihGdjiS 5i6WwTdP7lxCWE2ZqTp6u0iXrBG76k9QVPF5VN+7E6pC7uRnC3VoHakvFx08vMzmiSbT NdaZRByk4zOgq33pC69rtEcZ5oZmA9ZNajzi8= MIME-Version: 1.0 Received: by 10.204.113.74 with SMTP id z10mr637082bkp.25.1288778837616; Wed, 03 Nov 2010 03:07:17 -0700 (PDT) Received: by 10.204.71.138 with HTTP; Wed, 3 Nov 2010 03:07:17 -0700 (PDT) Date: Wed, 3 Nov 2010 12:07:17 +0200 Message-ID: From: Dan Naumov To: freebsd-fs@freebsd.org Content-Type: text/plain; charset=ISO-8859-1 Subject: regarding kern/148655 fix for 8.1 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: Wed, 03 Nov 2010 10:38:04 -0000 http://www.freebsd.org/cgi/query-pr.cgi?pr=148655 When is the fix getting backported from -STABLE to 8.1 as an errata fix? A lot of people cannot and will not update to 8.1 before this is fixed and no, "just track -STABLE" is not a valid answer. - Sincerely, Dan Naumov From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 10:58:40 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 54E111065670 for ; Wed, 3 Nov 2010 10:58:40 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta13.emeryville.ca.mail.comcast.net (qmta13.emeryville.ca.mail.comcast.net [76.96.27.243]) by mx1.freebsd.org (Postfix) with ESMTP id 3AE0B8FC20 for ; Wed, 3 Nov 2010 10:58:39 +0000 (UTC) Received: from omta11.emeryville.ca.mail.comcast.net ([76.96.30.36]) by qmta13.emeryville.ca.mail.comcast.net with comcast id SavN1f0010mlR8UADayfoK; Wed, 03 Nov 2010 10:58:39 +0000 Received: from koitsu.dyndns.org ([98.248.41.155]) by omta11.emeryville.ca.mail.comcast.net with comcast id Saye1f0063LrwQ28Xayf5b; Wed, 03 Nov 2010 10:58:39 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id 8EAD19B422; Wed, 3 Nov 2010 03:58:38 -0700 (PDT) Date: Wed, 3 Nov 2010 03:58:38 -0700 From: Jeremy Chadwick To: Dan Naumov Message-ID: <20101103105838.GA70884@icarus.home.lan> References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Cc: freebsd-fs@freebsd.org Subject: Re: regarding kern/148655 fix for 8.1 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: Wed, 03 Nov 2010 10:58:40 -0000 On Wed, Nov 03, 2010 at 12:07:17PM +0200, Dan Naumov wrote: > http://www.freebsd.org/cgi/query-pr.cgi?pr=148655 > > When is the fix getting backported from -STABLE to 8.1 as an errata > fix? A lot of people cannot and will not update to 8.1 before this is > fixed and no, "just track -STABLE" is not a valid answer. I'm not sure how much traction you'll get with that statement, but for what it's worth, I agree. The severity of the situation in the PR is extremely high, and the repercussions if experienced are bad. This *is* something that should be backported to the RELENG_8_1 branch. -- | Jeremy Chadwick jdc@parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB | From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 13:15:25 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5D9661065672; Wed, 3 Nov 2010 13:15:25 +0000 (UTC) (envelope-from petefrench@ticketswitch.com) Received: from constantine.ticketswitch.com (constantine.ticketswitch.com [IPv6:2002:57e0:1d4e:1::3]) by mx1.freebsd.org (Postfix) with ESMTP id 239BB8FC19; Wed, 3 Nov 2010 13:15:25 +0000 (UTC) Received: from dilbert.rattatosk ([10.64.50.6] helo=dilbert.ticketswitch.com) by constantine.ticketswitch.com with esmtps (TLSv1:AES256-SHA:256) (Exim 4.69 (FreeBSD)) (envelope-from ) id 1PDdBT-000DOX-ON; Wed, 03 Nov 2010 13:15:23 +0000 Received: from petefrench by dilbert.ticketswitch.com with local (Exim 4.72 (FreeBSD)) (envelope-from ) id 1PDdBT-000FY1-NT; Wed, 03 Nov 2010 13:15:23 +0000 Date: Wed, 03 Nov 2010 13:15:23 +0000 Message-Id: To: fjwcash@gmail.com, pjd@freebsd.org In-Reply-To: From: Pete French Cc: freebsd-fs@freebsd.org Subject: Re: Converting a non-HAST ZFS pool to a HAST pool 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, 03 Nov 2010 13:15:25 -0000 > Okay, so converting a non-HAST ZFS setup to a HAST setup using the > same drives won't work. See my post on the same subject - this is not true depending on how you have your non-hast setup configured. I migrated from gmirror to hast quite happily with no downtime. > Any reason that it wouldn't work when replacing the drives with larger ones? That will work fine - effectyively it's what I did as the drives were larger under hast than under gmirror. -pete. From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 13:25:20 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 44E561065673 for ; Wed, 3 Nov 2010 13:25:20 +0000 (UTC) (envelope-from luke@foolishgames.com) Received: from qmta03.emeryville.ca.mail.comcast.net (qmta03.emeryville.ca.mail.comcast.net [76.96.30.32]) by mx1.freebsd.org (Postfix) with ESMTP id 21D508FC08 for ; Wed, 3 Nov 2010 13:25:20 +0000 (UTC) Received: from omta17.emeryville.ca.mail.comcast.net ([76.96.30.73]) by qmta03.emeryville.ca.mail.comcast.net with comcast id SdA11f0061afHeLA3dCAtd; Wed, 03 Nov 2010 13:12:10 +0000 Received: from stargazer.midnightbsd.org ([70.91.226.201]) by omta17.emeryville.ca.mail.comcast.net with comcast id SdC81f0084MLobJ8ddC9BW; Wed, 03 Nov 2010 13:12:10 +0000 Received: from [10.1.10.166] ([10.1.10.166]) (authenticated bits=0) by stargazer.midnightbsd.org (8.14.4/8.14.4) with ESMTP id oA3DC6vV040846 (version=TLSv1/SSLv3 cipher=AES128-SHA bits=128 verify=NOT); Wed, 3 Nov 2010 09:12:08 -0400 (EDT) (envelope-from luke@foolishgames.com) X-Habeas-Swe-2: brightly anticipated In-Reply-To: <4CD04AEC.8040607@aldan.algebra.com> X-Habeas-Swe-7: warrant mark warrants that this is a Habeas Compliant X-Habeas-Swe-4: Copyright 2002 Habeas (tm) X-Habeas-Swe-1: winter into spring Mime-Version: 1.0 (Apple Message framework v1081) X-Habeas-Swe-9: mark in spam to . Date: Wed, 3 Nov 2010 09:12:06 -0400 X-Habeas-Swe-6: email in exchange for a license for this Habeas Message-Id: <190E58BD-6D27-4522-848D-C7E04FEC4B98@foolishgames.com> To: "Mikhail T." X-Habeas-Swe-3: like Habeas SWE (tm) Content-Transfer-Encoding: quoted-printable From: Lucas Holt References: <4CD04AEC.8040607@aldan.algebra.com> X-Habeas-Swe-8: Message (HCM) and not spam. Please report use of this Content-Type: text/plain; charset=us-ascii X-Habeas-Swe-5: Sender Warranted Email (SWE) (tm). The sender of this X-Mailer: Apple Mail (2.1081) Cc: fs@freebsd.org Subject: Re: Using an SSD "disk" for / 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, 03 Nov 2010 13:25:20 -0000 On Nov 2, 2010, at 1:31 PM, Mikhail T. wrote: > Hello! >=20 > I'm setting up a new system and would like to use a moderate (64Gb or = 128Gb) SSD-drive to boot from. >=20 > This will house /, /var, /home, and the /usr/local and thus see plenty = of activity, whenever src and ports are updated, or "world" is remade, = or packages are upgraded. I'm hoping, these operations would be much = faster, than with a regular HDD. >=20 > However, people mention, that SSDs develop /severe/ performance = degradation if written to A LOT -- unless some SDD-specific operation = (TRIM) is used, but not all Operating Systems support that... Does = FreeBSD-8? Is that sufficient, or will an SSD degrade quickly anyway? >=20 > Does anyone use an SSD under FreeBSD? Which brand/model? Are you happy = with it? I setup a pfsense system at work with an Intel SSD. It was overkill, = but we wanted high uptime. It was well worth the money. Not all SSDs = are created equal. Early this year, I built a server with an Imation = 32GB SSD as a boot drive and it failed on me within 3 months. I could = read the data off it, but it was no longer writable. Don't get cheap if = you go with SSD. It burned me. =20 Lucas Holt Luke@FoolishGames.com ________________________________________________________ MidnightBSD.org (Free OS) JustJournal.com (Free blogging) From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 13:35:02 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 1FBCE106566C for ; Wed, 3 Nov 2010 13:35:02 +0000 (UTC) (envelope-from petefrench@ticketswitch.com) Received: from constantine.ticketswitch.com (constantine.ticketswitch.com [IPv6:2002:57e0:1d4e:1::3]) by mx1.freebsd.org (Postfix) with ESMTP id D4E358FC0C for ; Wed, 3 Nov 2010 13:35:01 +0000 (UTC) Received: from dilbert.rattatosk ([10.64.50.6] helo=dilbert.ticketswitch.com) by constantine.ticketswitch.com with esmtps (TLSv1:AES256-SHA:256) (Exim 4.69 (FreeBSD)) (envelope-from ) id 1PDdUQ-000DUu-T0; Wed, 03 Nov 2010 13:34:58 +0000 Received: from petefrench by dilbert.ticketswitch.com with local (Exim 4.72 (FreeBSD)) (envelope-from ) id 1PDdUQ-000Fbg-S5; Wed, 03 Nov 2010 13:34:58 +0000 Date: Wed, 03 Nov 2010 13:34:58 +0000 Message-Id: To: fs@freebsd.org, mi+thun@aldan.algebra.com In-Reply-To: <4CD04AEC.8040607@aldan.algebra.com> From: Pete French Cc: Subject: Re: Using an SSD "disk" for / 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, 03 Nov 2010 13:35:02 -0000 > I'm setting up a new system and would like to use a moderate (64Gb or > 128Gb) SSD-drive to boot from. .... > Does anyone use an SSD under FreeBSD? Which brand/model? Are you happy > with it? I boot a server from a Compact Flash drive connected to a CF->SATA adaptor. Its only 4GB, enough to boot, and then all my read/write partititons come from several terrabytes of attached zpool. It works excellently, and was very cheap to setup. Performance is fine as you are almost never writing to the flash drive. The only time I notice the slowdown is when doing an installworld or installkernel. -pete. From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 14:18:52 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 88B4D1065674 for ; Wed, 3 Nov 2010 14:18:52 +0000 (UTC) (envelope-from gljennjohn@googlemail.com) Received: from mail-fx0-f54.google.com (mail-fx0-f54.google.com [209.85.161.54]) by mx1.freebsd.org (Postfix) with ESMTP id 13F688FC17 for ; Wed, 3 Nov 2010 14:18:51 +0000 (UTC) Received: by fxm17 with SMTP id 17so503830fxm.13 for ; Wed, 03 Nov 2010 07:18:50 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=googlemail.com; s=gamma; h=domainkey-signature:received:received:date:from:to:cc:subject :message-id:in-reply-to:references:reply-to:x-mailer:mime-version :content-type:content-transfer-encoding; bh=6dogMHilY1RlfPAJCJObai5OwL5XpqgXIUUsBjV8n8U=; b=FI+DrpZ2ex3qWFeNG/Q3Y4uD0PuEMPdkQfR3abLotW5l9rqpxD6MHVCAsDzSwPV6ix +B7fnwz1cKmJXb5hPpdHI2BCraIpAx0xfR4+DdzFdWFIlTmrC1FxcvMF9JzVQD3PvgP1 zkpKjHsQYXGlBHkSlrZ+dv+8/iB6KUhclVktM= DomainKey-Signature: a=rsa-sha1; c=nofws; d=googlemail.com; s=gamma; h=date:from:to:cc:subject:message-id:in-reply-to:references:reply-to :x-mailer:mime-version:content-type:content-transfer-encoding; b=O15yAkfvzegVZ9V6TV2y6AotMcN0SNtxfe0mIWINI3NOx74jVHtUMvlqwjU2g9k4Ju dtBfDe8GQY/2qhah2HRa+bsY6UwekKBNn8MxOa5z/JP1CvhgPZ0uyB7fdEvPAa8kD9kA zssnmxoLON9Vk5ofLu7kYviwozkqy6fMsr2fs= Received: by 10.223.74.15 with SMTP id s15mr3069343faj.28.1288792438123; Wed, 03 Nov 2010 06:53:58 -0700 (PDT) Received: from ernst.jennejohn.org (p578E2EF4.dip.t-dialin.net [87.142.46.244]) by mx.google.com with ESMTPS id u8sm3684727fah.12.2010.11.03.06.53.56 (version=TLSv1/SSLv3 cipher=RC4-MD5); Wed, 03 Nov 2010 06:53:56 -0700 (PDT) Date: Wed, 3 Nov 2010 14:53:54 +0100 From: Gary Jennejohn To: Jeremy Chadwick Message-ID: <20101103145354.0cbd8ae0@ernst.jennejohn.org> In-Reply-To: <20101103105838.GA70884@icarus.home.lan> References: <20101103105838.GA70884@icarus.home.lan> X-Mailer: Claws Mail 3.7.6 (GTK+ 2.18.7; amd64-portbld-freebsd9.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org, Dan Naumov Subject: Re: regarding kern/148655 fix for 8.1 X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: gljennjohn@googlemail.com List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 03 Nov 2010 14:18:52 -0000 On Wed, 3 Nov 2010 03:58:38 -0700 Jeremy Chadwick wrote: > On Wed, Nov 03, 2010 at 12:07:17PM +0200, Dan Naumov wrote: > > http://www.freebsd.org/cgi/query-pr.cgi?pr=148655 > > > > When is the fix getting backported from -STABLE to 8.1 as an errata > > fix? A lot of people cannot and will not update to 8.1 before this is > > fixed and no, "just track -STABLE" is not a valid answer. > > I'm not sure how much traction you'll get with that statement, but for > what it's worth, I agree. The severity of the situation in the PR is > extremely high, and the repercussions if experienced are bad. This *is* > something that should be backported to the RELENG_8_1 branch. > Considering that 8.2 is a ways off I also tend to agree. But that sort of in-your-face demand for action won't make any friends among the committers, you can bet on that. -- Gary Jennejohn From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 14:48:46 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4FA04106564A for ; Wed, 3 Nov 2010 14:48:46 +0000 (UTC) (envelope-from dan.naumov@gmail.com) Received: from mail-yx0-f182.google.com (mail-yx0-f182.google.com [209.85.213.182]) by mx1.freebsd.org (Postfix) with ESMTP id F35178FC08 for ; Wed, 3 Nov 2010 14:48:45 +0000 (UTC) Received: by yxl31 with SMTP id 31so521004yxl.13 for ; Wed, 03 Nov 2010 07:48:45 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:received:in-reply-to :references:date:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=Bb0JvzzM84059qLjF+s+H1uoY/IAAMA2RKwFw3iwmR0=; b=KDneGT2mjX8ibROGmghpFlQ6VB+F6t0PfpVkdAGtWruZs4sb/Qi24viDhSPGPtYcYm fCrKsTQmnUTVU2RgdEHqv6tKhlq4VGBGegc2v6h4e3IOhCB2ZQ23bsP2xkr6xpniYdPP Ob9znl6PLO9satT1nvc1o58V2pFvT/XBXQUcY= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=ZrFcxLUMhOyXulOOwk1wNQHUqnRvobT2SwNJK0BzCdbgPUn7Eb2CLq1ZFrhO/DPnRk l6Uyr2KVkOrf+r8i1aoEWN1042PAfvlNWtfbmfJsD7RaV2G9/7EmFQiV8A27q3/uDczi Z2cZ9tlb/uprlbaXItvQbY5dTNmT1G41tBVqM= MIME-Version: 1.0 Received: by 10.204.116.141 with SMTP id m13mr6439285bkq.187.1288795724300; Wed, 03 Nov 2010 07:48:44 -0700 (PDT) Received: by 10.204.71.138 with HTTP; Wed, 3 Nov 2010 07:48:44 -0700 (PDT) In-Reply-To: <20101103145354.0cbd8ae0@ernst.jennejohn.org> References: <20101103105838.GA70884@icarus.home.lan> <20101103145354.0cbd8ae0@ernst.jennejohn.org> Date: Wed, 3 Nov 2010 16:48:44 +0200 Message-ID: From: Dan Naumov To: gljennjohn@googlemail.com Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: freebsd-fs@freebsd.org Subject: Re: regarding kern/148655 fix for 8.1 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: Wed, 03 Nov 2010 14:48:46 -0000 >> I'm not sure how much traction you'll get with that statement, but for >> what it's worth, I agree. =A0The severity of the situation in the PR is >> extremely high, and the repercussions if experienced are bad. =A0This *i= s* >> something that should be backported to the RELENG_8_1 branch. >> > > Considering that 8.2 is a ways off I also tend to agree. > > But that sort of in-your-face demand for action won't make any friends > among the committers, you can bet on that. I am not entirely sure why my question was understood as some kind of aggression, that was certainly not my intention. > When is the fix getting backported from -STABLE to 8.1 as an errata fix? I think this a normal, valid question? > A lot of people cannot and will not update to 8.1 before this is fixed This is a simple fact. > and no, "just track -STABLE" is not a valid answer Just pre-empting the usual expected "just update to -STABLE to get your fix" responces. This is not a valid solution for a lot of users out there. - Sincerely, Dan Naumov From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 16:23:05 2010 Return-Path: Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id E469E106566C for ; Wed, 3 Nov 2010 16:23:05 +0000 (UTC) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (lurza.secnetix.de [IPv6:2a01:170:102f::2]) by mx1.freebsd.org (Postfix) with ESMTP id 612A18FC15 for ; Wed, 3 Nov 2010 16:23:05 +0000 (UTC) Received: from lurza.secnetix.de (localhost [127.0.0.1]) by lurza.secnetix.de (8.14.3/8.14.3) with ESMTP id oA3GMmC5032478; Wed, 3 Nov 2010 17:23:03 +0100 (CET) (envelope-from oliver.fromme@secnetix.de) Received: (from olli@localhost) by lurza.secnetix.de (8.14.3/8.14.3/Submit) id oA3GMl8o032477; Wed, 3 Nov 2010 17:22:47 +0100 (CET) (envelope-from olli) Date: Wed, 3 Nov 2010 17:22:47 +0100 (CET) Message-Id: <201011031622.oA3GMl8o032477@lurza.secnetix.de> From: Oliver Fromme To: freebsd-fs@FreeBSD.ORG, dan.naumov@gmail.com, gljennjohn@googlemail.com In-Reply-To: X-Newsgroups: list.freebsd-fs User-Agent: tin/1.8.3-20070201 ("Scotasay") (UNIX) (FreeBSD/6.4-PRERELEASE-20080904 (i386)) MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.3.5 (lurza.secnetix.de [127.0.0.1]); Wed, 03 Nov 2010 17:23:03 +0100 (CET) Cc: Subject: Re: regarding kern/148655 fix for 8.1 X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: freebsd-fs@FreeBSD.ORG, dan.naumov@gmail.com, gljennjohn@googlemail.com List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 03 Nov 2010 16:23:06 -0000 Dan Naumov wrote: > I am not entirely sure why my question was understood as some kind of > aggression, that was certainly not my intention. > > > When is the fix getting backported from -STABLE to 8.1 as an errata fix? > I think this a normal, valid question? By asking "when" you imply that you expect it to be backported. You're not asking for it to be backported. That's a difference. Note that the PR was closed (already two months ago), which usually means that no further merges are planned. If you want the patch to be merged to another branch, like releng/8.1, you should rather ask for it to be merged, not ask "when" it will be merged. The likely answer to the latter might be "never". > > A lot of people cannot and will not update to 8.1 before this is fixed > This is a simple fact. No, it's a guess. How many is "a lot of"? > > and no, "just track -STABLE" is not a valid answer > Just pre-empting the usual expected "just update to -STABLE to get > your fix" responces. This is not a valid solution for a lot of users > out there. I don't think that "a lot of" users of FreeBSD 8.0-Release are booting off a ZFS raidz or mirror (which is officially supported since 8.1 only!) *AND* are unable to update to stable/8 *AND* are unable to wait for 8.2 which isn't that far away in the future. I don't think that issuing a fix for releng/8.1 is really required. Even if it's only a 3-lines patch, making changes to a release branch is a very delicate matter that requires careful testing to make sure that nothing breaks. This is usually only warranted for security issues and critical bugs (like kernel panics) that affect a significant number of FreeBSD users. Best regards Oliver -- Oliver Fromme, secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing b. M. Handelsregister: Registergericht Muenchen, HRA 74606, Geschäftsfuehrung: secnetix Verwaltungsgesellsch. mbH, Handelsregister: Registergericht Mün- chen, HRB 125758, Geschäftsführer: Maik Bachmann, Olaf Erb, Ralf Gebhart FreeBSD-Dienstleistungen, -Produkte und mehr: http://www.secnetix.de/bsd "In My Egoistical Opinion, most people's C programs should be indented six feet downward and covered with dirt." -- Blair P. Houghton From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 16:28:42 2010 Return-Path: Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 3113B1065672 for ; Wed, 3 Nov 2010 16:28:42 +0000 (UTC) (envelope-from avg@icyb.net.ua) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id 782F18FC15 for ; Wed, 3 Nov 2010 16:28:41 +0000 (UTC) Received: from odyssey.starpoint.kiev.ua (alpha-e.starpoint.kiev.ua [212.40.38.101]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id SAA11221; Wed, 03 Nov 2010 18:28:38 +0200 (EET) (envelope-from avg@icyb.net.ua) Message-ID: <4CD18DB6.5010006@icyb.net.ua> Date: Wed, 03 Nov 2010 18:28:38 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.11) Gecko/20101021 Lightning/1.0b2 Thunderbird/3.1.5 MIME-Version: 1.0 To: dan.naumov@gmail.com References: <201011031622.oA3GMl8o032477@lurza.secnetix.de> In-Reply-To: <201011031622.oA3GMl8o032477@lurza.secnetix.de> X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: freebsd-fs@FreeBSD.ORG, Oliver Fromme Subject: Re: regarding kern/148655 fix for 8.1 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: Wed, 03 Nov 2010 16:28:42 -0000 on 03/11/2010 18:22 Oliver Fromme said the following: > Dan Naumov wrote: > > I am not entirely sure why my question was understood as some kind of > > aggression, that was certainly not my intention. > > > > > When is the fix getting backported from -STABLE to 8.1 as an errata fix? > > I think this a normal, valid question? > > By asking "when" you imply that you expect it to be backported. > You're not asking for it to be backported. That's a difference. > > Note that the PR was closed (already two months ago), which > usually means that no further merges are planned. If you want > the patch to be merged to another branch, like releng/8.1, > you should rather ask for it to be merged, not ask "when" it > will be merged. The likely answer to the latter might be > "never". Oliver made some good points overall, to which I might only add that such decisions are made by Release Engineering team. So a request like this should go to them (re@), not to a mailing list where technical details of filesystem development and usage are typically discussed. -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 18:04:19 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 8BF5F106566B for ; Wed, 3 Nov 2010 18:04:19 +0000 (UTC) (envelope-from tevans.uk@googlemail.com) Received: from mail-qw0-f54.google.com (mail-qw0-f54.google.com [209.85.216.54]) by mx1.freebsd.org (Postfix) with ESMTP id 45BAE8FC18 for ; Wed, 3 Nov 2010 18:04:18 +0000 (UTC) Received: by qwg8 with SMTP id 8so288465qwg.13 for ; Wed, 03 Nov 2010 11:04:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=googlemail.com; s=gamma; h=domainkey-signature:mime-version:received:received:in-reply-to :references:date:message-id:subject:from:to:cc:content-type; bh=RLVc/Ezbc1mv9EXHGmBQj8EZv58f6OHju89HkLmWrtk=; b=ib5QUNdiXclirPhHgnOAFRMcy983IWiJUvrZtNL/U9Lce62ZfcU036EOsTRR0ZSCE9 By3ciCyClS/RpBh6Qwy1rpVih1kKb+Peg7AW2X7KIL+2UgNWd1KiGbCc8js9RG5BxuNy Ixkpj8LtKxOJHF7t4ivRVwsAJjBOordRwhTrQ= DomainKey-Signature: a=rsa-sha1; c=nofws; d=googlemail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; b=HKAZ5RibdlyjUe7NOq/3gPkFli3SyuDpr/2aQOa5sBVUhGwyV2fRbuYZqe4puvSkCw amiXWGjIQWZmIAmgNEv8ZYJV7iy9SiWtaymbx9peAfxUYlPblgCuiPpDUy+es2TwuY/h vM68scYGuzFxRcqLvV4mO0dLukRIjd66G8Nmg= MIME-Version: 1.0 Received: by 10.224.207.131 with SMTP id fy3mr10324782qab.185.1288805975327; Wed, 03 Nov 2010 10:39:35 -0700 (PDT) Received: by 10.229.182.18 with HTTP; Wed, 3 Nov 2010 10:39:35 -0700 (PDT) In-Reply-To: References: <4CD04AEC.8040607@aldan.algebra.com> Date: Wed, 3 Nov 2010 17:39:35 +0000 Message-ID: From: Tom Evans To: Pete French Content-Type: text/plain; charset=UTF-8 Cc: mi+thun@aldan.algebra.com, fs@freebsd.org Subject: Re: Using an SSD "disk" for / 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, 03 Nov 2010 18:04:19 -0000 On Wed, Nov 3, 2010 at 1:34 PM, Pete French wrote: > I boot a server from a Compact Flash drive connected to a CF->SATA > adaptor. Its only 4GB, enough to boot, and then all my read/write > partititons come from several terrabytes of attached zpool. It > works excellently, and was very cheap to setup. Performance is > fine as you are almost never writing to the flash drive. The only > time I notice the slowdown is when doing an installworld or installkernel. > > -pete. > When you set up your disks like this, where do you put your swap? For my home ZFS server - which has a tank with two raidz pools, each with 6 disks in - I partitioned the first 6 disks into 2 partitions, a 6 GB chunk at the start, and the remaining data used for zfs. I then use 3 of the disks first partition in a gmirror UFS root partition, and the other 3 as swap. Cheers Tom From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 18:50:09 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 16CAE1065696 for ; Wed, 3 Nov 2010 18:50:09 +0000 (UTC) (envelope-from fjwcash@gmail.com) Received: from mail-gw0-f54.google.com (mail-gw0-f54.google.com [74.125.83.54]) by mx1.freebsd.org (Postfix) with ESMTP id 8D60D8FC23 for ; Wed, 3 Nov 2010 18:50:08 +0000 (UTC) Received: by gwj16 with SMTP id 16so763546gwj.13 for ; Wed, 03 Nov 2010 11:50:07 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:received:in-reply-to :references:date:message-id:subject:from:to:content-type; bh=PHPsMlHCEEQHYWuL2F6zy70BetebOaCEDedyMFv9vi4=; b=neR/OOFRm7TDXWqrUI3tYB8NGGvD/xBD2q3LfyeLY/NoIH8q/9JxwQi5MGLGMhbfF5 xqWLGNgJrxniyAFNrC1AWruj7lruNXTkovWfztnQJDFLsEgzWyAx9dpuHfYiPUMItJN9 6HliN2rYudheLO4BKVWobB8H0yNxOQFBB3RYA= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :content-type; b=FCgJORXOlOvb3DmV451OQ+OYk42XTJOiY1yGeqTsYe4O3X+w7jTkR1ih4W1cs/l2q3 3ofZUCmauBxlq5l9tDZ0/DYZN6l4sZUmdvbvCX3Zz+6X7tezT37PA173p6bCppHRl3U6 mg2oZIvPIB3EYx11G7/8vvWQlZIvYauh/7Z00= MIME-Version: 1.0 Received: by 10.90.4.26 with SMTP id 26mr1334563agd.84.1288808468420; Wed, 03 Nov 2010 11:21:08 -0700 (PDT) Received: by 10.90.97.7 with HTTP; Wed, 3 Nov 2010 11:21:08 -0700 (PDT) In-Reply-To: References: <4CD04AEC.8040607@aldan.algebra.com> Date: Wed, 3 Nov 2010 11:21:08 -0700 Message-ID: From: Freddie Cash To: fs@freebsd.org Content-Type: text/plain; charset=UTF-8 Cc: Subject: Re: Using an SSD "disk" for / 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, 03 Nov 2010 18:50:09 -0000 On Wed, Nov 3, 2010 at 10:39 AM, Tom Evans wrote: > On Wed, Nov 3, 2010 at 1:34 PM, Pete French wrote: >> I boot a server from a Compact Flash drive connected to a CF->SATA >> adaptor. Its only 4GB, enough to boot, and then all my read/write >> partititons come from several terrabytes of attached zpool. It >> works excellently, and was very cheap to setup. Performance is >> fine as you are almost never writing to the flash drive. The only >> time I notice the slowdown is when doing an installworld or installkernel. > > When you set up your disks like this, where do you put your swap? > > For my home ZFS server - which has a tank with two raidz pools, each > with 6 disks in - I partitioned the first 6 disks into 2 partitions, a > 6 GB chunk at the start, and the remaining data used for zfs. I then > use 3 of the disks first partition in a gmirror UFS root partition, > and the other 3 as swap. We do something similar to Pete: - 2x CompactFlash disks in CF-to-SATA adapters, gmirror'd together for the OS - bunch of SATA disks configured via ZFS, for everything else But, we add an SSD for L2ARC use, with 8 GB partitioned off for swap. Thus, the CF disks are basically read-only except for installworld/kernel and the odd config file update. -- Freddie Cash fjwcash@gmail.com From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 18:50:34 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C79DC10656A6; Wed, 3 Nov 2010 18:50:34 +0000 (UTC) (envelope-from olivier@gid0.org) Received: from mail-iw0-f182.google.com (mail-iw0-f182.google.com [209.85.214.182]) by mx1.freebsd.org (Postfix) with ESMTP id 8E8AB8FC22; Wed, 3 Nov 2010 18:50:34 +0000 (UTC) Received: by iwn39 with SMTP id 39so1030742iwn.13 for ; Wed, 03 Nov 2010 11:50:34 -0700 (PDT) MIME-Version: 1.0 Received: by 10.231.19.74 with SMTP id z10mr4240703iba.120.1288808895749; Wed, 03 Nov 2010 11:28:15 -0700 (PDT) Received: by 10.231.172.202 with HTTP; Wed, 3 Nov 2010 11:28:15 -0700 (PDT) In-Reply-To: <20100831215915.GE1932@garage.freebsd.pl> References: <20100831215915.GE1932@garage.freebsd.pl> Date: Wed, 3 Nov 2010 19:28:15 +0100 Message-ID: From: Olivier Smedts To: Pawel Jakub Dawidek Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: freebsd-fs@freebsd.org, freebsd-current@freebsd.org Subject: Re: ZFS v28 is ready for wider testing. 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, 03 Nov 2010 18:50:34 -0000 2010/8/31 Pawel Jakub Dawidek : > Hello. > > I'd like to give you ZFS v28 for testing. If you are neither brave nor > mad, you can stop here. > > The patchset is very experimental. It can eat your cookie and hurt your > teddy bear, so be warned. Don't try it for anything except testing. > > This patchset is also a message we, as the FreeBSD project, would like > to send to our users: Eventhough OpenSolaris is dead, the ZFS file > system is going to stay in FreeBSD. At this point we have quite a few > developers involved in ZFS on FreeBSD as well as serveral companies. > We are also looking forward to work with IllumOS. > > So, what this new ZFS brings? > > - Data deduplication. Read more here: > > =A0 =A0 =A0 =A0http://blogs.sun.com/bonwick/entry/zfs_dedup > > - Triple parity RAIDZ (RAIDZ3). Read more here: > > =A0 =A0 =A0 =A0http://dtrace.org/blogs/ahl/2009/07/21/triple-parity-raid-= z/ > > - zfs diff. Read more here: > > =A0 =A0 =A0 =A0http://arc.opensolaris.org/caselog/PSARC/2010/105/20100328= _tim.haley > > - zpool split. Read more here: > > =A0 =A0 =A0 =A0http://arc.opensolaris.org/caselog/PSARC/2009/511/20090924= _mark.musante > > - Snapshot holds. Read more here: > > =A0 =A0 =A0 =A0http://arc.opensolaris.org/caselog/PSARC/2009/297/20090511= _chris.kirby > > - zpool import -F. Allows to rewind corrupted pool to earlier > =A0transaction group. > > - Possibility to import pool in read-only mode. > > And much, much more, including plenty of preformance improvements and bug > fixes. > > So test whatever you can and report back. Look for regressions, strange > behaviour, missing features, deadlocks, livelocks, preformance > degradation, etc. > > The boot code is not updated at all, so booting off of ZFS doesn't > currently work. > > The patch is against today's FreeBSD HEAD. > > The patch enables (in sys/modules/zfs/Makefile) ZFS internal debugging, > please don't turn it off. Also, compile your kernel with the following > options: > > =A0 =A0 =A0 =A0options =A0 =A0 =A0 =A0 KDB > =A0 =A0 =A0 =A0options =A0 =A0 =A0 =A0 DDB > =A0 =A0 =A0 =A0options =A0 =A0 =A0 =A0 INVARIANTS > =A0 =A0 =A0 =A0options =A0 =A0 =A0 =A0 INVARIANT_SUPPORT > =A0 =A0 =A0 =A0options =A0 =A0 =A0 =A0 WITNESS > =A0 =A0 =A0 =A0options =A0 =A0 =A0 =A0 WITNESS_SKIPSPIN > =A0 =A0 =A0 =A0options =A0 =A0 =A0 =A0 DEBUG_LOCKS > =A0 =A0 =A0 =A0options =A0 =A0 =A0 =A0 DEBUG_VFS_LOCKS > > Ignore all the LOR (Lock Order Reversal) reports from WITNESS. There will > be plenty of those, and you'll desperately want to report them, but pleas= e > don't. > > The best way to report a problem is to answer to this e-mail with as shor= t > as possible procedure of how to reproduce it and debugging info. I'd > prefer textdump if possible. Below you can find quick procedure how to > setup textdumps: > > =A0 =A0 =A0 =A0Choose spare/swap disk/partition in your system, let's say= it is > =A0 =A0 =A0 =A0/dev/ad0s1b. > > =A0 =A0 =A0 =A0Add the following line to /etc/fstab: > > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0/dev/ad0s1b =A0 =A0 none =A0 =A0swap =A0 = =A0sw =A0 =A0 =A00 =A0 =A0 =A0 0 > > =A0 =A0 =A0 =A0Add the following line to /etc/rc.conf: > > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0ddb_enable=3D"YES" > > =A0 =A0 =A0 =A0Run the following commands: > > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0# /etc/rc.d/swap1 start > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0# /etc/rc.d/dumpon start > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0# /etc/rc.d/ddb start > > =A0 =A0 =A0 =A0This will setup swap, mark it as dump device and setup som= e DDB > =A0 =A0 =A0 =A0scripts. Or you can just reboot. > > =A0 =A0 =A0 =A0Now when your system panic or deadlock, enter DDB and call= the > =A0 =A0 =A0 =A0following command: > > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0ddb> run kdb.enter.panic > > =A0 =A0 =A0 =A0It will execute all the commands I need, dump them in text= format to > =A0 =A0 =A0 =A0your swap device and reboot machine. > > =A0 =A0 =A0 =A0After the reboot, you should find textdump.tar.0 file in /= var/crash/ > =A0 =A0 =A0 =A0directory. This is the debug info I need. > > End of textdumps procedure. > > Ok, now that I know you read everything carefully, here is the patch: > > =A0 =A0 =A0 =A0http://people.freebsd.org/~pjd/patches/zfs_20100831.patch.= bz2 Hello, Any status update on this ? I regularly check http://people.freebsd.org/~pjd/patches/ to see if there's an updated version of your patch. 2 months old is quite a bit for -CURRENT, which often receives commits on zfs&co parts. Thanks for all your work on FreeBSD (not only ZFS). > > Good luck! >:> > > -- > Pawel Jakub Dawidek =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 http://ww= w.wheelsystems.com > pjd@FreeBSD.org =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 http:= //www.FreeBSD.org > FreeBSD committer =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 Am I Ev= il? Yes, I Am! > --=20 Olivier Smedts=A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 = =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0=A0 _ =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0= =A0 ASCII ribbon campaign ( ) e-mail: olivier@gid0.org=A0 =A0 =A0 =A0 - against HTML email & vCards=A0 X www: http://www.gid0.org=A0 =A0 - against proprietary attachments / \ =A0 "Il y a seulement 10 sortes de gens dans le monde : =A0 ceux qui comprennent le binaire, =A0 et ceux qui ne le comprennent pas." From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 19:35:27 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 1957A106566C for ; Wed, 3 Nov 2010 19:35:27 +0000 (UTC) (envelope-from ronald-freebsd8@klop.yi.org) Received: from smtp-out1.tiscali.nl (smtp-out1.tiscali.nl [195.241.79.176]) by mx1.freebsd.org (Postfix) with ESMTP id C792D8FC12 for ; Wed, 3 Nov 2010 19:35:26 +0000 (UTC) Received: from [212.123.145.58] (helo=sjakie.klop.ws) by smtp-out1.tiscali.nl with esmtp (Exim) (envelope-from ) id 1PDj7F-00071F-MP for freebsd-fs@freebsd.org; Wed, 03 Nov 2010 20:35:25 +0100 Received: from 212-123-145-58.ip.telfort.nl (localhost [127.0.0.1]) by sjakie.klop.ws (Postfix) with ESMTP id C305E184FD for ; Wed, 3 Nov 2010 20:35:21 +0100 (CET) Content-Type: text/plain; charset=us-ascii; format=flowed; delsp=yes To: freebsd-fs@freebsd.org References: <4CD04AEC.8040607@aldan.algebra.com> Date: Wed, 03 Nov 2010 20:35:21 +0100 MIME-Version: 1.0 From: "Ronald Klop" Message-ID: In-Reply-To: User-Agent: Opera Mail/10.63 (FreeBSD) Content-Transfer-Encoding: quoted-printable Subject: Re: Using an SSD "disk" for / 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, 03 Nov 2010 19:35:27 -0000 On Wed, 03 Nov 2010 18:39:35 +0100, Tom Evans = =20 wrote: > On Wed, Nov 3, 2010 at 1:34 PM, Pete French =20 > wrote: >> I boot a server from a Compact Flash drive connected to a CF->SATA >> adaptor. Its only 4GB, enough to boot, and then all my read/write >> partititons come from several terrabytes of attached zpool. It >> works excellently, and was very cheap to setup. Performance is >> fine as you are almost never writing to the flash drive. The only >> time I notice the slowdown is when doing an installworld or =20 >> installkernel. >> >> -pete. >> > > When you set up your disks like this, where do you put your swap? > > For my home ZFS server - which has a tank with two raidz pools, each > with 6 disks in - I partitioned the first 6 disks into 2 partitions, a > 6 GB chunk at the start, and the remaining data used for zfs. I then > use 3 of the disks first partition in a gmirror UFS root partition, > and the other 3 as swap. > > Cheers > > Tom Why do you need swap if the server is doing file serving only? You will =20 have more fun if you add more RAM then when you add more swap. Ronald. From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 20:17:23 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 51192106566B for ; Wed, 3 Nov 2010 20:17:23 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta09.emeryville.ca.mail.comcast.net (qmta09.emeryville.ca.mail.comcast.net [76.96.30.96]) by mx1.freebsd.org (Postfix) with ESMTP id 34C098FC0A for ; Wed, 3 Nov 2010 20:17:22 +0000 (UTC) Received: from omta11.emeryville.ca.mail.comcast.net ([76.96.30.36]) by qmta09.emeryville.ca.mail.comcast.net with comcast id Sea11f0060mlR8UA9kHN2j; Wed, 03 Nov 2010 20:17:22 +0000 Received: from koitsu.dyndns.org ([98.248.41.155]) by omta11.emeryville.ca.mail.comcast.net with comcast id SkHM1f00F3LrwQ28XkHMV7; Wed, 03 Nov 2010 20:17:22 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id 92D9C9B422; Wed, 3 Nov 2010 13:17:21 -0700 (PDT) Date: Wed, 3 Nov 2010 13:17:21 -0700 From: Jeremy Chadwick To: Ronald Klop Message-ID: <20101103201721.GA80732@icarus.home.lan> References: <4CD04AEC.8040607@aldan.algebra.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Cc: freebsd-fs@freebsd.org Subject: Re: Using an SSD "disk" for / 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, 03 Nov 2010 20:17:23 -0000 On Wed, Nov 03, 2010 at 08:35:21PM +0100, Ronald Klop wrote: > On Wed, 03 Nov 2010 18:39:35 +0100, Tom Evans > wrote: > > >On Wed, Nov 3, 2010 at 1:34 PM, Pete French > > wrote: > >>I boot a server from a Compact Flash drive connected to a CF->SATA > >>adaptor. Its only 4GB, enough to boot, and then all my read/write > >>partititons come from several terrabytes of attached zpool. It > >>works excellently, and was very cheap to setup. Performance is > >>fine as you are almost never writing to the flash drive. The only > >>time I notice the slowdown is when doing an installworld or > >>installkernel. > >> > >>-pete. > >> > > > >When you set up your disks like this, where do you put your swap? > > > >For my home ZFS server - which has a tank with two raidz pools, each > >with 6 disks in - I partitioned the first 6 disks into 2 partitions, a > >6 GB chunk at the start, and the remaining data used for zfs. I then > >use 3 of the disks first partition in a gmirror UFS root partition, > >and the other 3 as swap. > > Why do you need swap if the server is doing file serving only? You > will have more fun if you add more RAM then when you add more swap. Well, in my case, I'm equally concerned about memory exhaustion (sometimes programs do spiral out of control!), in addition to the need for a dump device in the case of a kernel panic. Pete's situation and needs are different from mine, but those are the two focal points I have when it comes to swap and /var's size. -- | Jeremy Chadwick jdc@parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB | From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 21:24:58 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id CE8C91065670; Wed, 3 Nov 2010 21:24:58 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (60.wheelsystems.com [83.12.187.60]) by mx1.freebsd.org (Postfix) with ESMTP id 775268FC1F; Wed, 3 Nov 2010 21:24:57 +0000 (UTC) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id 6620845C89; Wed, 3 Nov 2010 22:24:56 +0100 (CET) Received: from localhost (chello089073192049.chello.pl [89.73.192.49]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id 48A8A45C98; Wed, 3 Nov 2010 22:24:51 +0100 (CET) Date: Wed, 3 Nov 2010 22:24:11 +0100 From: Pawel Jakub Dawidek To: Olivier Smedts Message-ID: <20101103212411.GE13266@garage.freebsd.pl> References: <20100831215915.GE1932@garage.freebsd.pl> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="NGIwU0kFl1Z1A3An" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.3i X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 9.0-CURRENT amd64 X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-0.6 required=4.5 tests=BAYES_00,RCVD_IN_SORBS_DUL autolearn=no version=3.0.4 Cc: freebsd-fs@freebsd.org, freebsd-current@freebsd.org Subject: Re: ZFS v28 is ready for wider testing. 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, 03 Nov 2010 21:24:58 -0000 --NGIwU0kFl1Z1A3An Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Nov 03, 2010 at 07:28:15PM +0100, Olivier Smedts wrote: > > =A0 =A0 =A0 =A0http://people.freebsd.org/~pjd/patches/zfs_20100831.patc= h.bz2 >=20 > Hello, >=20 > Any status update on this ? I regularly check > http://people.freebsd.org/~pjd/patches/ to see if there's an updated > version of your patch. 2 months old is quite a bit for -CURRENT, which > often receives commits on zfs&co parts. >=20 > Thanks for all your work on FreeBSD (not only ZFS). It took a while, but I should have something new shortly. I recently finished boot support for v28 (the most missing feature in the previous patch?) and will work on new patch soon. I'm heading to meetBSD California tomorrow and I'll be back in a week, so nothing will happen till then for sure. --=20 Pawel Jakub Dawidek http://www.wheelsystems.com pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --NGIwU0kFl1Z1A3An Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.14 (FreeBSD) iEYEARECAAYFAkzR0vsACgkQForvXbEpPzRDTACeN9wKLtXdkNvZfOUQd8i5yiiA Z2cAnjuf0GPnJn4anBzumqJyxfTg7OI1 =jmof -----END PGP SIGNATURE----- --NGIwU0kFl1Z1A3An-- From owner-freebsd-fs@FreeBSD.ORG Wed Nov 3 23:38:17 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id AFC6A106564A for ; Wed, 3 Nov 2010 23:38:17 +0000 (UTC) (envelope-from sarawgi.aditya@gmail.com) Received: from mail-iw0-f182.google.com (mail-iw0-f182.google.com [209.85.214.182]) by mx1.freebsd.org (Postfix) with ESMTP id 759FC8FC12 for ; Wed, 3 Nov 2010 23:38:17 +0000 (UTC) Received: by iwn39 with SMTP id 39so1278138iwn.13 for ; Wed, 03 Nov 2010 16:38:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:received:in-reply-to :references:date:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=F6OJ+eWd3HX4ChCApyQwwfJIzvJjyWu7CnNkJWszYMk=; b=h+WOpdv2Jvbiy+IsW2885Jke/1Se9K4s543+dJMtrjgJ1+Ja7Hgruw0unu8nGs4/I2 u1eSZCxwjw5aVh12TT55uzQbQx0f0B53amsAH5iQQWMGx+E/2j6g99rZZMoHEzDw4okX faH3fQ67W1cPsaQO6o98YXl4ZYbC+NDQinTbc= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=XGWHtGsCjItc5ppvTsH7AW8ZlZFRQO5D4MvuFBlfXSm1W8UD1hE2qnMyMy/8ZLXcJl FO8ohRvrmPJ6i0+IgZTump91O5bveRndsJoZwrEXETeLboiMbciSgAcCVQzw3DOGNEcg Bi8OQoDetHMZ92/f3YPMvkNYuJj/0/3Ff8ysY= MIME-Version: 1.0 Received: by 10.42.169.130 with SMTP id b2mr681321icz.403.1288827496805; Wed, 03 Nov 2010 16:38:16 -0700 (PDT) Received: by 10.231.253.81 with HTTP; Wed, 3 Nov 2010 16:38:16 -0700 (PDT) In-Reply-To: <4CD0A3E8.4080304@FreeBSD.org> References: <20100929031825.L683@besplex.bde.org> <20100929084801.M948@besplex.bde.org> <20100929041650.GA1553@aditya> <201009290917.05269.jhb@freebsd.org> <20100929202526.GA1564@aditya> <4CD0A3E8.4080304@FreeBSD.org> Date: Thu, 4 Nov 2010 05:08:16 +0530 Message-ID: From: Aditya Sarawgi To: Doug Barton Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: fs@freebsd.org Subject: Re: ext2fs now extremely slow 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, 03 Nov 2010 23:38:17 -0000 On Wed, Nov 3, 2010 at 5:21 AM, Doug Barton wrote: > On 09/29/10 13:25, Aditya Sarawgi wrote: >> >> [snip] >>>> >>>> I see what you are saying. The gap of 8 block between the files >>>> is due to the old preallocation which used to allocate additional >>>> 8 blocks in advance for a particular inode when allocating a block >>>> for it. The gap between blocks of the same file shouldn't be there >>>> too. Both of these cases should be removed. I will look into this >>>> during this week. The slowness is also due to lack of preallocation >>>> in the new code. >>> >>> One of the GSoC students worked on a patch to add preallocation back to >>> ext2fs this summer. =A0Would you be interested in reviewing and/or test= ing >>> that patch? =A0(I've attached it). =A0Here is his original e-mail: >> >> [snip] >> >> Hi John, >> >> I did a review of Zheng Liu's reservation window patch last week and >> I suggested him a few changes. Otherwise the code looks awesome. >> But it would be great if someone else can review the patch too and if >> everything goes well, we should merge this to HEAD. >> For the ext4 part, I still have to review his patches and I am planning >> to do it soon. Zheng is planning to have a separate module for ext4, >> and it does make sense. We are aiming at bringing ext4 to a usable state >> for 9-RELEASE (atleast read-only). > > Is anything happening with this? =A0I recently built a new system that is > multi-booting windows, freebsd, and ubuntu. I chose ext[23]fs for my /hom= e > partition so that I could share unix'y stuff between freebsd and linux, b= ut > I'm having both performance and stability problems, and today (fortunatel= y > for the first time, and fortunately recoverable) I had actual data loss. = I'm > happy to be a guinea pig for new code if people are reasonably sure that = it > will help, but if the situation doesn't improve I will have to reformat. > Are you suffering from these problems on CURRENT ? Can you please elaborate on the performance and stability issue you are facing ? Any specific scenar= io ? You can test Zheng's preallocation patch for ext2fs, there is a serious lack of testers for that. > On a related note, is there any way to use the journaling features of ext= 3fs > in FreeBSD? When I boot the linux partition it's treating the fs as ext3f= s, > but AFAICS we only have ext2fs capabilities. > Journaling is difficult to bring in, especially if one is planning to have a BSDL version. > FWIW, the reason I chose ext2fs is that linux doesn't have reliable r/w > support for ufs, and there are really good drivers to mount ext2fs > partitions in windows; which we also don't have for ufs. > > > Doug > > -- > > =A0 =A0 =A0 =A0Nothin' ever doesn't change, but nothin' changes much. > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0-- OK Go > > =A0 =A0 =A0 =A0Breadth of IT experience, and depth of knowledge in the DN= S. > =A0 =A0 =A0 =A0Yours for the right price. =A0:) =A0http://SupersetSolutio= ns.com/ > > _______________________________________________ > 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" > --=20 Cheers, Aditya Sarawgi From owner-freebsd-fs@FreeBSD.ORG Thu Nov 4 01:10:10 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D13B61065672 for ; Thu, 4 Nov 2010 01:10:10 +0000 (UTC) (envelope-from dougb@FreeBSD.org) Received: from mail2.fluidhosting.com (mx23.fluidhosting.com [204.14.89.6]) by mx1.freebsd.org (Postfix) with ESMTP id 777208FC08 for ; Thu, 4 Nov 2010 01:10:10 +0000 (UTC) Received: (qmail 908 invoked by uid 399); 4 Nov 2010 00:43:27 -0000 Received: from localhost (HELO doug-optiplex.ka9q.net) (dougb@dougbarton.us@127.0.0.1) by localhost with ESMTPAM; 4 Nov 2010 00:43:27 -0000 X-Originating-IP: 127.0.0.1 X-Sender: dougb@dougbarton.us Message-ID: <4CD201AE.3040409@FreeBSD.org> Date: Wed, 03 Nov 2010 17:43:26 -0700 From: Doug Barton Organization: http://SupersetSolutions.com/ User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.12) Gecko/20101028 Thunderbird/3.1.6 MIME-Version: 1.0 To: Aditya Sarawgi References: <20100929031825.L683@besplex.bde.org> <20100929084801.M948@besplex.bde.org> <20100929041650.GA1553@aditya> <201009290917.05269.jhb@freebsd.org> <20100929202526.GA1564@aditya> <4CD0A3E8.4080304@FreeBSD.org> In-Reply-To: X-Enigmail-Version: 1.1.2 OpenPGP: id=1A1ABC84 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: fs@freebsd.org Subject: Re: ext2fs now extremely slow 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, 04 Nov 2010 01:10:11 -0000 On 11/03/10 16:38, Aditya Sarawgi wrote: > On Wed, Nov 3, 2010 at 5:21 AM, Doug Barton wrote: >> Is anything happening with this? I recently built a new system that is >> multi-booting windows, freebsd, and ubuntu. I chose ext[23]fs for my /home >> partition so that I could share unix'y stuff between freebsd and linux, but >> I'm having both performance and stability problems, and today (fortunately >> for the first time, and fortunately recoverable) I had actual data loss. I'm >> happy to be a guinea pig for new code if people are reasonably sure that it >> will help, but if the situation doesn't improve I will have to reformat. >> > > Are you suffering from these problems on CURRENT ? Yes. > Can you please elaborate > on the performance and stability issue you are facing ? Any specific scenario ? What I did was create a fairly large (37G) /home and put all the stuff I'd like to have access to from all 3 systems, like svn, my ports tree, etc. I also ended up putting my obj directory there because I created my /usr/local a little smaller than I should have and after installing gnome I ran out of room. :) I should also point out that this is on a brand new desktop system that was donated by a FreeBSD user. It's a C2D running at 3.17G, 4G RAM, and a fast 250G disk. I'm running amd64 -current. Everything disk intensive (updating ports with csup, updating my svn trees, etc.) is slower on this system than it was on my laptop where all the same stuff was on UFS2. Bruce's message that started this thread alluded to the problems, my experience has been similar. Regarding stability, sometimes (but not always) when I'm doing the above listed disk-intensive things on an otherwise idle system I've had the system lock up. Not panic, not reboot, just wedge. I'm running X when this happens, so I'm not 100% sure that the disk activity is the culprit, but it seems very suspicious. Yesterday was a very bad day, I had to do 3 tries to get all the way through a buildworld/kernel, mostly because the last 2 crashes resulted in my /usr/src (which is actually /home/svn/head) and /usr/obj (/home/obj-9) directories getting corrupted respectively. Today (running r214694) has actually been quite good, although I haven't tried a buildworld yet. > You can test Zheng's preallocation patch for ext2fs, there is a > serious lack of testers for that. I would be happy to do that, but my reading of this thread last month didn't produce a clear "try this version of the patch" neon sign. Various people referred to suggestions, updates, etc. If someone could provide a URL for the right patch to try, as well as a suggestion for benchmarking methodology, I'll be glad to do so. >> On a related note, is there any way to use the journaling features of ext3fs >> in FreeBSD? When I boot the linux partition it's treating the fs as ext3fs, >> but AFAICS we only have ext2fs capabilities. >> > > Journaling is difficult to bring in, especially if one is planning to > have a BSDL version. Ok. I can live with accessing the stuff as ext2 from FreeBSD, and I can even live with a minor performance penalty. What I can't live with is instability and/or data corruption; and it should go without saying that our users should not have to live with that either. Thanks for the response, Doug -- Nothin' ever doesn't change, but nothin' changes much. -- OK Go Breadth of IT experience, and depth of knowledge in the DNS. Yours for the right price. :) http://SupersetSolutions.com/ From owner-freebsd-fs@FreeBSD.ORG Thu Nov 4 07:49:06 2010 Return-Path: Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id B33501065670; Thu, 4 Nov 2010 07:49:06 +0000 (UTC) (envelope-from avg@icyb.net.ua) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id B5D738FC21; Thu, 4 Nov 2010 07:49:05 +0000 (UTC) Received: from porto.topspin.kiev.ua (porto-e.starpoint.kiev.ua [212.40.38.100]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id JAA21122; Thu, 04 Nov 2010 09:49:03 +0200 (EET) (envelope-from avg@icyb.net.ua) Received: from localhost.topspin.kiev.ua ([127.0.0.1]) by porto.topspin.kiev.ua with esmtp (Exim 4.34 (FreeBSD)) id 1PDuZD-000Dhk-1R; Thu, 04 Nov 2010 09:49:03 +0200 Message-ID: <4CD2656D.8050701@icyb.net.ua> Date: Thu, 04 Nov 2010 09:49:01 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.12) Gecko/20101029 Lightning/1.0b2 Thunderbird/3.1.6 MIME-Version: 1.0 To: freebsd-current@FreeBSD.ORG, freebsd-fs@FreeBSD.ORG X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=X-VIET-VPS Content-Transfer-Encoding: 7bit Cc: Subject: processes stuck on a vnode lock 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, 04 Nov 2010 07:49:06 -0000 I see a few processes stuck on the same vnode, trying to take or to upgrade to an exclusive lock on it, while the lock data suggests that it is already shared-locked. The vnode is a root vnode of one of ZFS filesystems (it's not a global root). I couldn't find any (other) threads that could actually hold the vnode lock, but lock shared count is suspiciously or coincidentally the same as number of threads in zfs_root call. Relevant data dump: 1125 100129 mountd - mi_switch sleepq_switch sleepq_wait __lockmgr_args vop_stdlock VOP_LOCK1_APV _vn_lock zfs_root lookup namei getfh syscallenter syscall Xfast_syscall 1135 100209 nfsd nfsd: service mi_switch sleepq_switch sleepq_wait __lockmgr_args vop_stdlock VOP_LOCK1_APV _vn_lock zfs_fhtovp nfsrv_fhtovp nfsrv_readdirplus nfssvc_program svc_run_internal svc_thread_start fork_exit fork_trampoline 39672 100779 find - mi_switch sleepq_switch sleepq_wait __lockmgr_args vop_stdlock VOP_LOCK1_APV _vn_lock zfs_root lookup namei vn_open_cred vn_open kern_openat kern_open open syscallenter syscall Xfast_syscall 61414 100769 smbd - mi_switch sleepq_switch sleepq_wait __lockmgr_args vop_stdlock VOP_LOCK1_APV _vn_lock cache_lookup vfs_cache_lookup VOP_LOOKUP_APV lookup namei vn_open_cred vn_open kern_openat kern_open open syscallenter 61644 100525 smbd - mi_switch sleepq_switch sleepq_wait __lockmgr_args vop_stdlock VOP_LOCK1_APV _vn_lock cache_lookup vfs_cache_lookup VOP_LOOKUP_APV lookup namei vn_open_cred vn_open kern_openat kern_open open syscallenter 61645 100504 smbd - mi_switch sleepq_switch sleepq_wait __lockmgr_args vop_stdlock VOP_LOCK1_APV _vn_lock cache_lookup vfs_cache_lookup VOP_LOOKUP_APV lookup namei vn_open_cred vn_open kern_openat kern_open open syscallenter 61646 100822 smbd - mi_switch sleepq_switch sleepq_wait __lockmgr_args vop_stdlock VOP_LOCK1_APV _vn_lock cache_lookup vfs_cache_lookup VOP_LOOKUP_APV lookup namei vn_open_cred vn_open kern_openat kern_open open syscallenter ====================================================================== (kgdb) tid 100779 [Switching to thread 521 (Thread 100779)]#0 sched_switch (td=0xffffff0051e59450, newtd=0xffffff0001a4c450, flags=Variable "flags" is not available. ) at /usr/src/sys/kern/sched_ule.c:1851 1851 cpuid = PCPU_GET(cpuid); (kgdb) bt #0 sched_switch (td=0xffffff0051e59450, newtd=0xffffff0001a4c450, flags=Variable "flags" is not available. ) at /usr/src/sys/kern/sched_ule.c:1851 #1 0xffffffff8038631e in mi_switch (flags=Variable "flags" is not available. ) at /usr/src/sys/kern/kern_synch.c:449 #2 0xffffffff803bd87b in sleepq_switch (wchan=Variable "wchan" is not available. ) at /usr/src/sys/kern/subr_sleepqueue.c:538 #3 0xffffffff803be5a5 in sleepq_wait (wchan=0xffffff000a3e4098, pri=80) at /usr/src/sys/kern/subr_sleepqueue.c:617 #4 0xffffffff80362d62 in __lockmgr_args (lk=0xffffff000a3e4098, flags=524288, ilk=0xffffff000a3e40c8, wmesg=Variable "wmesg" is not available. ) at /usr/src/sys/kern/kern_lock.c:218 #5 0xffffffff804037f1 in vop_stdlock (ap=Variable "ap" is not available. ) at lockmgr.h:97 #6 0xffffffff805bd322 in VOP_LOCK1_APV (vop=0xffffffff807e2580, a=0xffffff8126ec05b0) at vnode_if.c:1988 #7 0xffffffff80422d98 in _vn_lock (vp=0xffffff000a3e4000, flags=524288, file=0xffffffff80b23c58 "/usr/src/sys/modules/zfs/../../cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_vfsops.c", line=1305) at vnode_if.h:859 #8 0xffffffff80abd185 in zfs_root (vfsp=Variable "vfsp" is not available. ) at /usr/src/sys/modules/zfs/../../cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_vfsops.c:1305 #9 0xffffffff80408323 in lookup (ndp=0xffffff8126ec09a0) at /usr/src/sys/kern/vfs_lookup.c:785 #10 0xffffffff80408f0f in namei (ndp=0xffffff8126ec09a0) at /usr/src/sys/kern/vfs_lookup.c:273 #11 0xffffffff80422120 in vn_open_cred (ndp=0xffffff8126ec09a0, flagp=0xffffff8126ec099c, cmode=2432, vn_open_flags=Variable "vn_open_flags" is not available. ) at /usr/src/sys/kern/vfs_vnops.c:189 #12 0xffffffff804223cc in vn_open (ndp=Variable "ndp" is not available. ) at /usr/src/sys/kern/vfs_vnops.c:95 #13 0xffffffff80420b9d in kern_openat (td=0xffffff0051e59450, fd=-100, path=0x800c61100 , pathseg=UIO_USERSPACE, flags=131077, mode=13052800) at /usr/src/sys/kern/vfs_syscalls.c:1083 #14 0xffffffff80420f19 in kern_open (td=Variable "td" is not available. ) at /usr/src/sys/kern/vfs_syscalls.c:1039 #15 0xffffffff80420f38 in open (td=Variable "td" is not available. ) at /usr/src/sys/kern/vfs_syscalls.c:1015 #16 0xffffffff803c0f8e in syscallenter (td=0xffffff0051e59450, sa=0xffffff8126ec0bb0) at /usr/src/sys/kern/subr_trap.c:318 #17 0xffffffff8055b5f1 in syscall (frame=0xffffff8126ec0c40) at /usr/src/sys/amd64/amd64/trap.c:939 #18 0xffffffff80546262 in Xfast_syscall () at /usr/src/sys/amd64/amd64/exception.S:381 #19 0x000000080073489c in ?? () Previous frame inner to this frame (corrupt stack?) (kgdb) fr 4 #4 0xffffffff80362d62 in __lockmgr_args (lk=0xffffff000a3e4098, flags=524288, ilk=0xffffff000a3e40c8, wmesg=Variable "wmesg" is not available. ) at /usr/src/sys/kern/kern_lock.c:218 218 sleepq_wait(&lk->lock_object, pri); (kgdb) p *lk $3 = {lock_object = {lo_name = 0xffffffff80b267b0 "zfs", lo_flags = 91947008, lo_data = 0, lo_witness = 0x0}, lk_lock = 37, lk_exslpfail = 0, lk_timo = 51, lk_pri = 80} (kgdb) p/x lk->lk_lock $7 = 0x25 ===================================================================== (kgdb) p *dvp $8 = {v_type = VDIR, v_tag = 0xffffffff80b267b0 "zfs", v_op = 0xffffffff80b2c780, v_data = 0xffffff000a2c8840, v_mount = 0xffffff000a3e92f8, v_nmntvnodes = {tqe_next = 0xffffff000a3e3d20, tqe_prev = 0xffffff000a3e9358}, v_un = {vu_mount = 0x0, vu_socket = 0x0, vu_cdev = 0x0, vu_fifoinfo = 0x0, vu_yield = 0}, v_hashlist = {le_next = 0x0, le_prev = 0x0}, v_hash = 0, v_cache_src = {lh_first = 0x0}, v_cache_dst = { tqh_first = 0x0, tqh_last = 0xffffff000a3e4060}, v_cache_dd = 0x0, v_cstart = 0, v_lasta = 0, v_lastw = 0, v_clen = 0, v_lock = {lock_object = { lo_name = 0xffffffff80b267b0 "zfs", lo_flags = 91947008, lo_data = 0, lo_witness = 0x0}, lk_lock = 37, lk_exslpfail = 0, lk_timo = 51, lk_pri = 80}, v_interlock = {lock_object = {lo_name = 0xffffffff8064ecf9 "vnode interlock", lo_flags = 16973824, lo_data = 0, lo_witness = 0x0}, mtx_lock = 4}, v_vnlock = 0xffffff000a3e4098, v_holdcnt = 16, v_usecount = 16, v_iflag = 0, v_vflag = 1, v_writecount = 0, v_freelist = { tqe_next = 0x0, tqe_prev = 0x0}, v_bufobj = {bo_mtx = {lock_object = {lo_name = 0xffffffff8064ed09 "bufobj interlock", lo_flags = 16973824, lo_data = 0, lo_witness = 0x0}, mtx_lock = 4}, bo_clean = {bv_hd = {tqh_first = 0x0, tqh_last = 0xffffff000a3e4140}, bv_root = 0x0, bv_cnt = 0}, bo_dirty = {bv_hd = {tqh_first = 0x0, tqh_last = 0xffffff000a3e4160}, bv_root = 0x0, bv_cnt = 0}, bo_numoutput = 0, bo_flag = 0, bo_ops = 0xffffffff807df2a0, bo_bsize = 131072, bo_object = 0xffffff0123507000, bo_synclist = {le_next = 0x0, le_prev = 0x0}, bo_private = 0xffffff000a3e4000, __bo_vnode = 0xffffff000a3e4000}, v_pollinfo = 0xffffff00658778c0, v_label = 0x0, v_lockf = 0x0} -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Thu Nov 4 12:44:39 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 7B605106564A for ; Thu, 4 Nov 2010 12:44:39 +0000 (UTC) (envelope-from petefrench@ticketswitch.com) Received: from constantine.ticketswitch.com (constantine.ticketswitch.com [IPv6:2002:57e0:1d4e:1::3]) by mx1.freebsd.org (Postfix) with ESMTP id 414558FC08 for ; Thu, 4 Nov 2010 12:44:39 +0000 (UTC) Received: from dilbert.rattatosk ([10.64.50.6] helo=dilbert.ticketswitch.com) by constantine.ticketswitch.com with esmtps (TLSv1:AES256-SHA:256) (Exim 4.69 (FreeBSD)) (envelope-from ) id 1PDzB9-000KKg-SU; Thu, 04 Nov 2010 12:44:31 +0000 Received: from petefrench by dilbert.ticketswitch.com with local (Exim 4.72 (FreeBSD)) (envelope-from ) id 1PDzB9-000IVX-RL; Thu, 04 Nov 2010 12:44:31 +0000 Date: Thu, 04 Nov 2010 12:44:31 +0000 Message-Id: To: tevans.uk@googlemail.com In-Reply-To: From: Pete French Cc: mi+thun@aldan.algebra.com, fs@freebsd.org Subject: Re: Using an SSD "disk" for / 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, 04 Nov 2010 12:44:39 -0000 > When you set up your disks like this, where do you put your swap? If I want swap I use a zvol on the pool - if you set the zfs porperty 'org.freebsd:swap' to 'on' then it will swaap to it quite happily. But in actual practice I usually stuff the machine with RAM and run without swap enabled. In the case of the specific machine in question it just does simple low volume file serving and has 44GB in it, which is plenty for a ZFS fileserver. -pete. From owner-freebsd-fs@FreeBSD.ORG Thu Nov 4 14:29:40 2010 Return-Path: Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 372271065675 for ; Thu, 4 Nov 2010 14:29:40 +0000 (UTC) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (lurza.secnetix.de [IPv6:2a01:170:102f::2]) by mx1.freebsd.org (Postfix) with ESMTP id 925778FC1A for ; Thu, 4 Nov 2010 14:29:39 +0000 (UTC) Received: from lurza.secnetix.de (localhost [127.0.0.1]) by lurza.secnetix.de (8.14.3/8.14.3) with ESMTP id oA4ETNdn088126; Thu, 4 Nov 2010 15:29:38 +0100 (CET) (envelope-from oliver.fromme@secnetix.de) Received: (from olli@localhost) by lurza.secnetix.de (8.14.3/8.14.3/Submit) id oA4ETMsV088125; Thu, 4 Nov 2010 15:29:22 +0100 (CET) (envelope-from olli) Date: Thu, 4 Nov 2010 15:29:22 +0100 (CET) Message-Id: <201011041429.oA4ETMsV088125@lurza.secnetix.de> From: Oliver Fromme To: freebsd-fs@FreeBSD.ORG, freebsd@jdc.parodius.com In-Reply-To: <20101103030515.GA61758@icarus.home.lan> X-Newsgroups: list.freebsd-fs User-Agent: tin/1.8.3-20070201 ("Scotasay") (UNIX) (FreeBSD/6.4-PRERELEASE-20080904 (i386)) MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.3.5 (lurza.secnetix.de [127.0.0.1]); Thu, 04 Nov 2010 15:29:38 +0100 (CET) Cc: Subject: Re: Using an SSD "disk" for / X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: freebsd-fs@FreeBSD.ORG, freebsd@jdc.parodius.com List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 04 Nov 2010 14:29:40 -0000 Jeremy Chadwick wrote: > As for the performance: it's something you'll have to see for yourself. > The performance is outright amazing when it comes to administrative > tasks (OS installation, newfs, massive copies of data to/from the SSD, > updating /usr/src and /usr/ports, etc.). Try a build/install world or > kernel sometime on an SSD and watch your terminal. You'll be pretty > impressed. What kind of tuning do you apply to those file systems? I'm asking because I can't really reproduce those results. On a machine with plenty of RAM I've created memory disks for obj and src, which should at least be as fast (probably even faster) than an SSD. Buildworld was somewhat faster, compared to standard (well-tuned) UFS+SU filesystems on a fast SATA HDD, but not _that_ much faster. In fact the difference was small enough that I stopped using memory disks and returned to using UFS+SU+noatime (and a few other tuning options) on a HDD. So, if you experience a _dramatic_ speed-up when using SSDs for buildworld, I would really very much like to know why this is the case, and what kind of tuning you performed. Best regards Oliver -- Oliver Fromme, secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing b. M. Handelsregister: Registergericht Muenchen, HRA 74606, Geschäftsfuehrung: secnetix Verwaltungsgesellsch. mbH, Handelsregister: Registergericht Mün- chen, HRB 125758, Geschäftsführer: Maik Bachmann, Olaf Erb, Ralf Gebhart FreeBSD-Dienstleistungen, -Produkte und mehr: http://www.secnetix.de/bsd "A language that doesn't have everything is actually easier to program in than some that do." -- Dennis M. Ritchie From owner-freebsd-fs@FreeBSD.ORG Thu Nov 4 14:35:45 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id ACA631065672 for ; Thu, 4 Nov 2010 14:35:45 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta01.westchester.pa.mail.comcast.net (qmta01.westchester.pa.mail.comcast.net [76.96.62.16]) by mx1.freebsd.org (Postfix) with ESMTP id 58DEF8FC08 for ; Thu, 4 Nov 2010 14:35:44 +0000 (UTC) Received: from omta23.westchester.pa.mail.comcast.net ([76.96.62.74]) by qmta01.westchester.pa.mail.comcast.net with comcast id Sywv1f0031c6gX8512bl43; Thu, 04 Nov 2010 14:35:45 +0000 Received: from koitsu.dyndns.org ([98.248.41.155]) by omta23.westchester.pa.mail.comcast.net with comcast id T2bk1f0053LrwQ23j2bksu; Thu, 04 Nov 2010 14:35:45 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id F3E729B422; Thu, 4 Nov 2010 07:35:42 -0700 (PDT) Date: Thu, 4 Nov 2010 07:35:42 -0700 From: Jeremy Chadwick To: freebsd-fs@FreeBSD.ORG Message-ID: <20101104143542.GA628@icarus.home.lan> References: <20101103030515.GA61758@icarus.home.lan> <201011041429.oA4ETMsV088125@lurza.secnetix.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <201011041429.oA4ETMsV088125@lurza.secnetix.de> User-Agent: Mutt/1.5.21 (2010-09-15) Cc: Subject: Re: Using an SSD "disk" for / 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, 04 Nov 2010 14:35:45 -0000 On Thu, Nov 04, 2010 at 03:29:22PM +0100, Oliver Fromme wrote: > Jeremy Chadwick wrote: > > As for the performance: it's something you'll have to see for yourself. > > The performance is outright amazing when it comes to administrative > > tasks (OS installation, newfs, massive copies of data to/from the SSD, > > updating /usr/src and /usr/ports, etc.). Try a build/install world or > > kernel sometime on an SSD and watch your terminal. You'll be pretty > > impressed. > > What kind of tuning do you apply to those file systems? > > I'm asking because I can't really reproduce those results. > On a machine with plenty of RAM I've created memory disks > for obj and src, which should at least be as fast (probably > even faster) than an SSD. Buildworld was somewhat faster, > compared to standard (well-tuned) UFS+SU filesystems on a > fast SATA HDD, but not _that_ much faster. In fact the > difference was small enough that I stopped using memory > disks and returned to using UFS+SU+noatime (and a few other > tuning options) on a HDD. > > So, if you experience a _dramatic_ speed-up when using SSDs > for buildworld, I would really very much like to know why > this is the case, and what kind of tuning you performed. Literally: absolutely no tuning. I treat the SSD the exact same as I would a standard mechanical HDD: install FreeBSD on it, and that's that. I imagine the performance difference greatly depends on what SSD you're actually using. Again, the Intel drives have the highest IOPS out there (at least in the consumer-grade market), and I can't justify the cost of an SLC-based drive, so I stick to MLC. Possibly you and I have different interpretation of what "dramatic" means? :-) My opinion is that cutting 6-7 full minutes off a buildworld is pretty dramatic. -- | Jeremy Chadwick jdc@parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB | From owner-freebsd-fs@FreeBSD.ORG Thu Nov 4 14:45:29 2010 Return-Path: Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D3DEC106564A; Thu, 4 Nov 2010 14:45:29 +0000 (UTC) (envelope-from avg@icyb.net.ua) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id CCD3E8FC1A; Thu, 4 Nov 2010 14:45:28 +0000 (UTC) Received: from odyssey.starpoint.kiev.ua (alpha-e.starpoint.kiev.ua [212.40.38.101]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id QAA27911; Thu, 04 Nov 2010 16:45:26 +0200 (EET) (envelope-from avg@icyb.net.ua) Message-ID: <4CD2C706.6000100@icyb.net.ua> Date: Thu, 04 Nov 2010 16:45:26 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.11) Gecko/20101021 Lightning/1.0b2 Thunderbird/3.1.5 MIME-Version: 1.0 To: freebsd-current@FreeBSD.ORG, freebsd-fs@FreeBSD.ORG References: <4CD2656D.8050701@icyb.net.ua> In-Reply-To: <4CD2656D.8050701@icyb.net.ua> X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=x-viet-vps Content-Transfer-Encoding: 7bit Cc: Subject: Re: processes stuck on a vnode lock 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, 04 Nov 2010 14:45:29 -0000 on 04/11/2010 09:49 Andriy Gapon said the following: > > I see a few processes stuck on the same vnode, trying to take or to upgrade to > an exclusive lock on it, while the lock data suggests that it is already > shared-locked. The vnode is a root vnode of one of ZFS filesystems (it's not a > global root). > > I couldn't find any (other) threads that could actually hold the vnode lock, but > lock shared count is suspiciously or coincidentally the same as number of > threads in zfs_root call. BTW, I still have the system alive and online, so if anyone has ideas I can try them. -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Thu Nov 4 16:56:17 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C7B5C106566B; Thu, 4 Nov 2010 16:56:17 +0000 (UTC) (envelope-from avg@freebsd.org) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id 70B638FC0A; Thu, 4 Nov 2010 16:56:15 +0000 (UTC) Received: from odyssey.starpoint.kiev.ua (alpha-e.starpoint.kiev.ua [212.40.38.101]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id SAA29317; Thu, 04 Nov 2010 18:56:11 +0200 (EET) (envelope-from avg@freebsd.org) Message-ID: <4CD2E5AA.1090208@freebsd.org> Date: Thu, 04 Nov 2010 18:56:10 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.11) Gecko/20101021 Lightning/1.0b2 Thunderbird/3.1.5 MIME-Version: 1.0 To: Kostik Belousov , Pawel Jakub Dawidek , Alan Cox References: <4C91F031.1010801@freebsd.org> <20101010134717.GA59922@deviant.kiev.zoral.com.ua> In-Reply-To: <20101010134717.GA59922@deviant.kiev.zoral.com.ua> X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org Subject: Re: vop_getpages for zfs 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, 04 Nov 2010 16:56:18 -0000 on 10/10/2010 16:47 Kostik Belousov said the following: > I think that readahead requests should be satisfied, if possible. Esp. > in the case the readahead does not cause additional i/o. So, per Kostik's suggestion, here is patch for your review and testing: http://people.freebsd.org/~avg/zfs_getpages.2.diff The patch tries to fill as many of the passed in pages as possible as long as that can be done from a block (or even two blocks) that has to be read to fill the requested page. This means that the optimization kicks in only if a vnode has a block size greater than the page size. I mentioned "two blocks" above because I tried to optimize the case when, for example, block size is 6KB and page size is 4KB and the requested page covers parts of two adjacent blocks (e.g. range from 4KB to 8KB). Not sure if this was worth the trouble. In other words, the code tries to avoid reading more blocks than is strictly required, because additional blocks may be far apart on a disk and thus read latency could get increased. You will also notice that I added vop_bmap method to ZFS vops. This is needed to satisfy logic in vnode_pager_haspage(); otherwise, for example, vm_fault() would never request any additional pages besides the required one. zfs_bmap() implementation is really simple - it returns zeros for a_runp and a_runb (and some reasonable-ish but unused values in other fields), and vnode_pager_haspage() figures out number of eligible pages from the block size (f_iosize actually[*]) and the page size. Now, that ZFS has vop_getpages method, it is safe to provide this dummy-ish implementation of vop_bmap, because this operation would not be called by any other place but vnode_pager_haspage(). Code from vfs_bio.c and vfs_cluster.c is never called for ZFS, because it doesn't use the buffer cache layer. [*] There is a few interesting questions with respect to f_iosize usage in vnode_pager_haspage() and ZFS. For one, ZFS has a variable block size and f_iosize for ZFS has a currently configured maximum block ('record' in ZFS terms) size. This should not result in non-optimal behavior for files with smaller block sizes, because those files would have smaller sizes too (within the block size). Unless, of course, recordsize property is modified after some files are created on a ZFS filesystem. In that case there could be large files with some smaller (previously maximum) block size; or files with a block size larger than the current recordsize == f_iosize. So, such situations may lead to sub-optimal performance. Another issue related to the above is that f_iosize for ZFS can change on the fly when an administrators runs zfs set recordsize=NNN, and that may happen concurrently with vnode_pager_haspage() using f_iosize for its calculations. Not sure how to handle this correctly. I will appreciate your comment comments, test reports, reviews and suggestions. Thanks a lot! -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Thu Nov 4 18:23:48 2010 Return-Path: Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 645B01065673 for ; Thu, 4 Nov 2010 18:23:48 +0000 (UTC) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (lurza.secnetix.de [IPv6:2a01:170:102f::2]) by mx1.freebsd.org (Postfix) with ESMTP id D51F08FC0A for ; Thu, 4 Nov 2010 18:23:47 +0000 (UTC) Received: from lurza.secnetix.de (localhost [127.0.0.1]) by lurza.secnetix.de (8.14.3/8.14.3) with ESMTP id oA4INT2A097845; Thu, 4 Nov 2010 19:23:44 +0100 (CET) (envelope-from oliver.fromme@secnetix.de) Received: (from olli@localhost) by lurza.secnetix.de (8.14.3/8.14.3/Submit) id oA4INTIL097844; Thu, 4 Nov 2010 19:23:29 +0100 (CET) (envelope-from olli) Date: Thu, 4 Nov 2010 19:23:29 +0100 (CET) Message-Id: <201011041823.oA4INTIL097844@lurza.secnetix.de> From: Oliver Fromme To: freebsd-fs@FreeBSD.ORG, freebsd@jdc.parodius.com In-Reply-To: <20101104143542.GA628@icarus.home.lan> X-Newsgroups: list.freebsd-fs User-Agent: tin/1.8.3-20070201 ("Scotasay") (UNIX) (FreeBSD/6.4-PRERELEASE-20080904 (i386)) MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.3.5 (lurza.secnetix.de [127.0.0.1]); Thu, 04 Nov 2010 19:23:45 +0100 (CET) Cc: Subject: Re: Using an SSD "disk" for / X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: freebsd-fs@FreeBSD.ORG, freebsd@jdc.parodius.com List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 04 Nov 2010 18:23:48 -0000 Jeremy Chadwick wrote: > On Thu, Nov 04, 2010 at 03:29:22PM +0100, Oliver Fromme wrote: > > What kind of tuning do you apply to those file systems? > > > > I'm asking because I can't really reproduce those results. > > On a machine with plenty of RAM I've created memory disks > > for obj and src, which should at least be as fast (probably > > even faster) than an SSD. Buildworld was somewhat faster, > > compared to standard (well-tuned) UFS+SU filesystems on a > > fast SATA HDD, but not _that_ much faster. In fact the > > difference was small enough that I stopped using memory > > disks and returned to using UFS+SU+noatime (and a few other > > tuning options) on a HDD. > > > > So, if you experience a _dramatic_ speed-up when using SSDs > > for buildworld, I would really very much like to know why > > this is the case, and what kind of tuning you performed. > > Literally: absolutely no tuning. I treat the SSD the exact same as I > would a standard mechanical HDD: install FreeBSD on it, and that's that. > > I imagine the performance difference greatly depends on what SSD you're > actually using. Again, the Intel drives have the highest IOPS out there > (at least in the consumer-grade market), and I can't justify the cost of > an SLC-based drive, so I stick to MLC. > > Possibly you and I have different interpretation of what "dramatic" > means? :-) My opinion is that cutting 6-7 full minutes off a > buildworld is pretty dramatic. Well, here are some hard numbers: With /usr/src and /usr/obj both on the same SATA-300 HDD, a buildworld takes 10 minutes and 13 seconds. With /usr/src and /usr/obj on separate memory disks, a buildworld takes 10 minutes and 4 seconds. This is stable/8 with empty /etc/src.conf, i.e. a complete buildworld. The machine is an AMD Phenom II X6 (hexacore). I think 10:13 vs. 10:04 is not "dramatic". I don't think there's a way I can cut 6-7 minutes from that with current (and affordable) hardware. Best regards Oliver -- Oliver Fromme, secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing b. M. Handelsregister: Registergericht Muenchen, HRA 74606, Geschäftsfuehrung: secnetix Verwaltungsgesellsch. mbH, Handelsregister: Registergericht Mün- chen, HRB 125758, Geschäftsführer: Maik Bachmann, Olaf Erb, Ralf Gebhart FreeBSD-Dienstleistungen, -Produkte und mehr: http://www.secnetix.de/bsd "C is quirky, flawed, and an enormous success." -- Dennis M. Ritchie. From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 07:32:58 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id DBE52106566B; Fri, 5 Nov 2010 07:32:58 +0000 (UTC) (envelope-from linimon@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id B0C978FC19; Fri, 5 Nov 2010 07:32:58 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA57Ww45007283; Fri, 5 Nov 2010 07:32:58 GMT (envelope-from linimon@freefall.freebsd.org) Received: (from linimon@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA57WwPr007279; Fri, 5 Nov 2010 07:32:58 GMT (envelope-from linimon) Date: Fri, 5 Nov 2010 07:32:58 GMT Message-Id: <201011050732.oA57WwPr007279@freefall.freebsd.org> To: linimon@FreeBSD.org, freebsd-bugs@FreeBSD.org, freebsd-fs@FreeBSD.org From: linimon@FreeBSD.org Cc: Subject: Re: kern/151845: [smbfs] [patch] smbfs should be upgraded to support Unicode 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, 05 Nov 2010 07:32:58 -0000 Old Synopsis: smbfs should be upgraded to support Unicode New Synopsis: [smbfs] [patch] smbfs should be upgraded to support Unicode Responsible-Changed-From-To: freebsd-bugs->freebsd-fs Responsible-Changed-By: linimon Responsible-Changed-When: Fri Nov 5 07:32:24 UTC 2010 Responsible-Changed-Why: Over to maintainer(s). http://www.freebsd.org/cgi/query-pr.cgi?pr=151845 From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 07:39:15 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5C2A0106564A; Fri, 5 Nov 2010 07:39:15 +0000 (UTC) (envelope-from avg@freebsd.org) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id 7537C8FC08; Fri, 5 Nov 2010 07:39:14 +0000 (UTC) Received: from porto.topspin.kiev.ua (porto-e.starpoint.kiev.ua [212.40.38.100]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id JAA08050; Fri, 05 Nov 2010 09:39:13 +0200 (EET) (envelope-from avg@freebsd.org) Received: from localhost.topspin.kiev.ua ([127.0.0.1]) by porto.topspin.kiev.ua with esmtp (Exim 4.34 (FreeBSD)) id 1PEGtE-000HWJ-No; Fri, 05 Nov 2010 09:39:12 +0200 Message-ID: <4CD3B4A0.6060207@freebsd.org> Date: Fri, 05 Nov 2010 09:39:12 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.12) Gecko/20101029 Lightning/1.0b2 Thunderbird/3.1.6 MIME-Version: 1.0 To: freebsd-current@freebsd.org, freebsd-fs@freebsd.org References: <4CD2656D.8050701@icyb.net.ua> <4CD2C706.6000100@icyb.net.ua> In-Reply-To: <4CD2C706.6000100@icyb.net.ua> X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=x-viet-vps Content-Transfer-Encoding: 7bit Cc: Subject: Re: processes stuck on a vnode lock 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, 05 Nov 2010 07:39:15 -0000 on 04/11/2010 16:45 Andriy Gapon said the following: > on 04/11/2010 09:49 Andriy Gapon said the following: >> >> I see a few processes stuck on the same vnode, trying to take or to upgrade to >> an exclusive lock on it, while the lock data suggests that it is already >> shared-locked. The vnode is a root vnode of one of ZFS filesystems (it's not a >> global root). >> >> I couldn't find any (other) threads that could actually hold the vnode lock, but >> lock shared count is suspiciously or coincidentally the same as number of >> threads in zfs_root call. > > BTW, I still have the system alive and online, so if anyone has ideas I can try them. > The kernel is not live now, but I have saved it and vmcore of the system. Kostik, just a pure guesswork here - could r214049 have something to do with this? I looked at the change and it looks completely correct - I don't think that a vnode lock can be leaked by that code. But, OTOH, it has some special handling for VV_ROOT, it's in NFS code and and it's in a right time-frame, so just asking. Here's a link to the start of this report thread: http://thread.gmane.org/gmane.os.freebsd.devel.file-systems/10659/focus=128893 -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 07:52:29 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 97220106567A; Fri, 5 Nov 2010 07:52:29 +0000 (UTC) (envelope-from linimon@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 07BB38FC14; Fri, 5 Nov 2010 07:52:29 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA57qSs9031232; Fri, 5 Nov 2010 07:52:28 GMT (envelope-from linimon@freefall.freebsd.org) Received: (from linimon@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA57qS7Y031228; Fri, 5 Nov 2010 07:52:28 GMT (envelope-from linimon) Date: Fri, 5 Nov 2010 07:52:28 GMT Message-Id: <201011050752.oA57qS7Y031228@freefall.freebsd.org> To: linimon@FreeBSD.org, freebsd-bugs@FreeBSD.org, freebsd-fs@FreeBSD.org From: linimon@FreeBSD.org Cc: Subject: Re: kern/151905: [zfs] page fault under load in /sbin/zfs 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, 05 Nov 2010 07:52:29 -0000 Synopsis: [zfs] page fault under load in /sbin/zfs Responsible-Changed-From-To: freebsd-bugs->freebsd-fs Responsible-Changed-By: linimon Responsible-Changed-When: Fri Nov 5 07:52:17 UTC 2010 Responsible-Changed-Why: Over to maintainer(s). http://www.freebsd.org/cgi/query-pr.cgi?pr=151905 From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 07:54:04 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 220141065672; Fri, 5 Nov 2010 07:54:04 +0000 (UTC) (envelope-from linimon@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id EB15D8FC14; Fri, 5 Nov 2010 07:54:03 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA57s3PZ031358; Fri, 5 Nov 2010 07:54:03 GMT (envelope-from linimon@freefall.freebsd.org) Received: (from linimon@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA57s3EP031353; Fri, 5 Nov 2010 07:54:03 GMT (envelope-from linimon) Date: Fri, 5 Nov 2010 07:54:03 GMT Message-Id: <201011050754.oA57s3EP031353@freefall.freebsd.org> To: linimon@FreeBSD.org, freebsd-bugs@FreeBSD.org, freebsd-fs@FreeBSD.org From: linimon@FreeBSD.org Cc: Subject: Re: kern/151910: [zfs] booting from raidz/raidz2 on ciss(4) doesn't work 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, 05 Nov 2010 07:54:04 -0000 Synopsis: [zfs] booting from raidz/raidz2 on ciss(4) doesn't work Responsible-Changed-From-To: freebsd-bugs->freebsd-fs Responsible-Changed-By: linimon Responsible-Changed-When: Fri Nov 5 07:53:13 UTC 2010 Responsible-Changed-Why: not sure if this is a zfs problem or a ciss problem, but make a guess and assign. Committers, feel free to reassign it if wrong. http://www.freebsd.org/cgi/query-pr.cgi?pr=151910 From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 07:57:10 2010 Return-Path: Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 117B1106566C for ; Fri, 5 Nov 2010 07:57:10 +0000 (UTC) (envelope-from olli@lurza.secnetix.de) Received: from lurza.secnetix.de (lurza.secnetix.de [IPv6:2a01:170:102f::2]) by mx1.freebsd.org (Postfix) with ESMTP id 843538FC15 for ; Fri, 5 Nov 2010 07:57:09 +0000 (UTC) Received: from lurza.secnetix.de (localhost [127.0.0.1]) by lurza.secnetix.de (8.14.3/8.14.3) with ESMTP id oA57uqBl030091; Fri, 5 Nov 2010 08:57:08 +0100 (CET) (envelope-from oliver.fromme@secnetix.de) Received: (from olli@localhost) by lurza.secnetix.de (8.14.3/8.14.3/Submit) id oA57uqdW030090; Fri, 5 Nov 2010 08:56:52 +0100 (CET) (envelope-from olli) Date: Fri, 5 Nov 2010 08:56:52 +0100 (CET) Message-Id: <201011050756.oA57uqdW030090@lurza.secnetix.de> From: Oliver Fromme To: freebsd-fs@FreeBSD.ORG, freebsd@jdc.parodius.com In-Reply-To: <201011041823.oA4INTIL097844@lurza.secnetix.de> X-Newsgroups: list.freebsd-fs User-Agent: tin/1.8.3-20070201 ("Scotasay") (UNIX) (FreeBSD/6.4-PRERELEASE-20080904 (i386)) MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.3.5 (lurza.secnetix.de [127.0.0.1]); Fri, 05 Nov 2010 08:57:08 +0100 (CET) Cc: Subject: Re: Using an SSD "disk" for / X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: freebsd-fs@FreeBSD.ORG, freebsd@jdc.parodius.com List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 05 Nov 2010 07:57:10 -0000 Oliver Fromme wrote: > With /usr/src and /usr/obj both on the same SATA-300 HDD, > a buildworld takes 10 minutes and 13 seconds. > > With /usr/src and /usr/obj on separate memory disks, > a buildworld takes 10 minutes and 4 seconds. > > This is stable/8 with empty /etc/src.conf, i.e. a complete > buildworld. The machine is an AMD Phenom II X6 (hexacore). I think I should give some more information about the system that I used for the test. The HDD is accessed via ahci(4) and ada(4) with NCQ. This might make a small difference, though I haven't benchmarked it. src and obj are mounted with noatime. In the memory disk case, src was even mounted read-only, and obj was mounted async. I made sure that there was no swapping / page-out activity during the memory disk test, so all the data really stayed in RAM (which should be even faster than an SSD, I assume). The system was otherwise idle, gstat(8) basically showed nothing on ada0 during the memory disk test. The following sysctl tunings are in effect: vfs.hirunningspace=8388608 vfs.lorunningspace=1048576 vfs.read_max=32 vfs.ufs.dirhash_maxmem=33554432 kern.sched.preempt_thresh=220 (I've got more things in /etc/sysctl.conf, but the rest shouldn't affect file system performance or buildworld, I think.) The kernel is running with HZ=300 (unfortunately HZ isn't dynamic in FreeBSD, so I'm using 300 as a trade-off). AUDIT and MAC are disabled. Best regards Oliver -- Oliver Fromme, secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing b. M. Handelsregister: Registergericht Muenchen, HRA 74606, Geschäftsfuehrung: secnetix Verwaltungsgesellsch. mbH, Handelsregister: Registergericht Mün- chen, HRB 125758, Geschäftsführer: Maik Bachmann, Olaf Erb, Ralf Gebhart FreeBSD-Dienstleistungen, -Produkte und mehr: http://www.secnetix.de/bsd "When your hammer is C++, everything begins to look like a thumb." -- Steve Haflich, in comp.lang.c++ From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 11:02:29 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C5C71106564A; Fri, 5 Nov 2010 11:02:29 +0000 (UTC) (envelope-from linimon@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 9B5FE8FC0C; Fri, 5 Nov 2010 11:02:29 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA5B2TuN009745; Fri, 5 Nov 2010 11:02:29 GMT (envelope-from linimon@freefall.freebsd.org) Received: (from linimon@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA5B2Tkq009741; Fri, 5 Nov 2010 11:02:29 GMT (envelope-from linimon) Date: Fri, 5 Nov 2010 11:02:29 GMT Message-Id: <201011051102.oA5B2Tkq009741@freefall.freebsd.org> To: linimon@FreeBSD.org, freebsd-bugs@FreeBSD.org, freebsd-fs@FreeBSD.org From: linimon@FreeBSD.org Cc: Subject: Re: kern/151942: [zfs] panic during ls(1) zfs snapshot directory 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, 05 Nov 2010 11:02:29 -0000 Synopsis: [zfs] panic during ls(1) zfs snapshot directory Responsible-Changed-From-To: freebsd-bugs->freebsd-fs Responsible-Changed-By: linimon Responsible-Changed-When: Fri Nov 5 11:02:08 UTC 2010 Responsible-Changed-Why: Over to maintainer(s). http://www.freebsd.org/cgi/query-pr.cgi?pr=151942 From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 11:05:06 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id F2323106567A; Fri, 5 Nov 2010 11:05:06 +0000 (UTC) (envelope-from linimon@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id C78328FC0A; Fri, 5 Nov 2010 11:05:06 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA5B56Lw010064; Fri, 5 Nov 2010 11:05:06 GMT (envelope-from linimon@freefall.freebsd.org) Received: (from linimon@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA5B5628010060; Fri, 5 Nov 2010 11:05:06 GMT (envelope-from linimon) Date: Fri, 5 Nov 2010 11:05:06 GMT Message-Id: <201011051105.oA5B5628010060@freefall.freebsd.org> To: linimon@FreeBSD.org, freebsd-i386@FreeBSD.org, freebsd-fs@FreeBSD.org From: linimon@FreeBSD.org Cc: Subject: Re: kern/151330: [zfs] will unshare all zfs filesystem after execute a "zfs clone" 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, 05 Nov 2010 11:05:07 -0000 Old Synopsis: will unshare all zfs filesystem after execute a "zfs clone" New Synopsis: [zfs] will unshare all zfs filesystem after execute a "zfs clone" Responsible-Changed-From-To: freebsd-i386->freebsd-fs Responsible-Changed-By: linimon Responsible-Changed-When: Fri Nov 5 11:04:47 UTC 2010 Responsible-Changed-Why: This does not sound i386-specific. http://www.freebsd.org/cgi/query-pr.cgi?pr=151330 From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 11:09:38 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 7DC4B106566C; Fri, 5 Nov 2010 11:09:38 +0000 (UTC) (envelope-from linimon@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 533958FC14; Fri, 5 Nov 2010 11:09:38 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA5B9cIe010288; Fri, 5 Nov 2010 11:09:38 GMT (envelope-from linimon@freefall.freebsd.org) Received: (from linimon@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA5B9co4010284; Fri, 5 Nov 2010 11:09:38 GMT (envelope-from linimon) Date: Fri, 5 Nov 2010 11:09:38 GMT Message-Id: <201011051109.oA5B9co4010284@freefall.freebsd.org> To: linimon@FreeBSD.org, freebsd-i386@FreeBSD.org, freebsd-fs@FreeBSD.org From: linimon@FreeBSD.org Cc: Subject: Re: kern/151251: [ufs] Can not create files on filesystem with heavy usage 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, 05 Nov 2010 11:09:38 -0000 Old Synopsis: Can not create files on filesystem with heavy usage New Synopsis: [ufs] Can not create files on filesystem with heavy usage Responsible-Changed-From-To: freebsd-i386->freebsd-fs Responsible-Changed-By: linimon Responsible-Changed-When: Fri Nov 5 11:07:46 UTC 2010 Responsible-Changed-Why: possibly a UFS problem? Someone with a filesystem clue should tell me how to categorize this one. http://www.freebsd.org/cgi/query-pr.cgi?pr=151251 From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 12:00:22 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 8B6C710656B0 for ; Fri, 5 Nov 2010 12:00:22 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 54ACE8FC25 for ; Fri, 5 Nov 2010 12:00:22 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA5C0M9R062480 for ; Fri, 5 Nov 2010 12:00:22 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA5C0Md5062470; Fri, 5 Nov 2010 12:00:22 GMT (envelope-from gnats) Date: Fri, 5 Nov 2010 12:00:22 GMT Message-Id: <201011051200.oA5C0Md5062470@freefall.freebsd.org> To: freebsd-fs@FreeBSD.org From: Oliver Fromme Cc: Subject: Re: kern/151251: [ufs] Can not create files on filesystem with heavy usage X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Oliver Fromme List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 05 Nov 2010 12:00:22 -0000 The following reply was made to PR kern/151251; it has been noted by GNATS. From: Oliver Fromme To: bug-followup@FreeBSD.org, vermaden@interia.pl Cc: Subject: Re: kern/151251: [ufs] Can not create files on filesystem with heavy usage Date: Fri, 5 Nov 2010 12:53:41 +0100 (CET) vermaden wrote: > /usr/mail/DOMAIN/USER@DOMAIN/new # :> asd > /usr/mail/DOMAIN/USER@DOMAIN/new # echo $? > > /usr/mail/DOMAIN/USER@DOMAIN/new # ls asd > ls: asd: No such file or directory > /usr/mail/DOMAIN/USER@DOMAIN/new # echo $? > 1 > > If I reboot, everything goes back to normal and I can create files there: > /usr/mail/DOMAIN/USER@DOMAIN/new # :> asd > /usr/mail/DOMAIN/USER@DOMAIN/new # echo $? > > /usr/mail/DOMAIN/USER@DOMAIN/new # ls asd > asd > /usr/mail/DOMAIN/USER@DOMAIN/new # echo $? > Could it be that there is a problem with your shell? For successful completion, "$?" should contain the value 0, not an empty string. This looks fishy. One possibility is that your shell is malfunctioning because of a resource shortage and insufficient error checking. But that's just a wild guess. Please use plain /bin/sh to make sure that the shell is not causing (or hiding) any problems. If you still get exactly the same results, something really strange must be going on. By the way, I noticed that your machine (2.3 GHz Xeon) has only 320 MB RAM, which isn't exactly plenty, depending on the things that are running (you mentioned "heavy usage"). Could it be that you're running out of memory? (Although the symptoms aren't typical.) Best regards Oliver -- Oliver Fromme, secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing b. M. Handelsregister: Registergericht Muenchen, HRA 74606, Geschäftsfuehrung: secnetix Verwaltungsgesellsch. mbH, Handelsregister: Registergericht Mün- chen, HRB 125758, Geschäftsführer: Maik Bachmann, Olaf Erb, Ralf Gebhart FreeBSD-Dienstleistungen, -Produkte und mehr: http://www.secnetix.de/bsd "Documentation is like sex; when it's good, it's very, very good, and when it's bad, it's better than nothing." -- Dick Brandon From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 13:20:10 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D9CC7106566C for ; Fri, 5 Nov 2010 13:20:10 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id ADF248FC1C for ; Fri, 5 Nov 2010 13:20:10 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA5DKAqD047386 for ; Fri, 5 Nov 2010 13:20:10 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA5DKA8o047385; Fri, 5 Nov 2010 13:20:10 GMT (envelope-from gnats) Date: Fri, 5 Nov 2010 13:20:10 GMT Message-Id: <201011051320.oA5DKA8o047385@freefall.freebsd.org> To: freebsd-fs@FreeBSD.org From: Andriy Gapon Cc: Subject: Re: kern/151910: [zfs] booting from raidz/raidz2 on ciss(4) doesn't work X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Andriy Gapon List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 05 Nov 2010 13:20:10 -0000 The following reply was made to PR kern/151910; it has been noted by GNATS. From: Andriy Gapon To: bug-followup@FreeBSD.org, am@raisa.eu.org Cc: Subject: Re: kern/151910: [zfs] booting from raidz/raidz2 on ciss(4) doesn't work Date: Fri, 05 Nov 2010 15:17:05 +0200 8.1 release had a bug which prevented booting from raidz. Please see http://www.freebsd.org/cgi/query-pr.cgi?pr=148655 -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 13:20:12 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 9586D1065670 for ; Fri, 5 Nov 2010 13:20:12 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 69ECF8FC1A for ; Fri, 5 Nov 2010 13:20:12 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA5DKCU5047397 for ; Fri, 5 Nov 2010 13:20:12 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA5DKCd1047396; Fri, 5 Nov 2010 13:20:12 GMT (envelope-from gnats) Date: Fri, 5 Nov 2010 13:20:12 GMT Message-Id: <201011051320.oA5DKCd1047396@freefall.freebsd.org> To: freebsd-fs@FreeBSD.org From: Andriy Gapon Cc: Subject: Re: kern/151905: [zfs] page fault under load in /sbin/zfs X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Andriy Gapon List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 05 Nov 2010 13:20:12 -0000 The following reply was made to PR kern/151905; it has been noted by GNATS. From: Andriy Gapon To: bug-followup@FreeBSD.org, csalgau-br@bitdefender.com Cc: Subject: Re: kern/151905: [zfs] page fault under load in /sbin/zfs Date: Fri, 05 Nov 2010 15:18:41 +0200 Judging from the screenshot the panic is in fuse_statfs. So, most likely it's a fuse problem, not ZFS. -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 15:10:11 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 414EE106566C for ; Fri, 5 Nov 2010 15:10:11 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 14F998FC18 for ; Fri, 5 Nov 2010 15:10:11 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA5FAA7b065145 for ; Fri, 5 Nov 2010 15:10:10 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA5FAAmh065142; Fri, 5 Nov 2010 15:10:10 GMT (envelope-from gnats) Date: Fri, 5 Nov 2010 15:10:10 GMT Message-Id: <201011051510.oA5FAAmh065142@freefall.freebsd.org> To: freebsd-fs@FreeBSD.org From: "Emil Smolenski" Cc: Subject: Re: kern/151910: [zfs] booting from raidz/raidz2 on ciss(4) doesn't work X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Emil Smolenski List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 05 Nov 2010 15:10:11 -0000 The following reply was made to PR kern/151910; it has been noted by GNATS. From: "Emil Smolenski" To: bug-followup@freebsd.org, am@raisa.eu.org Cc: Subject: Re: kern/151910: [zfs] booting from raidz/raidz2 on ciss(4) doesn't work Date: Fri, 05 Nov 2010 15:45:39 +0100 Please see at "Originator" field in both PRs. I'm familiar with PR 148655 very well. Problem in PR 148655 is related to booting from _degraded_ raidz/raidz2/mirror. In this PR we have problem with booting from _non_degraded_ raidz/raidz2 and only when ciss(4) is used. Mirror-based configurations, SATA disks, USB sticks, other RAID controllers are all OK. Of course I tested 8.1-STABLE (from Oct) and 8.0-RELEASE (where PR 148655 is not applicable) but there were no difference -- still can't boot from raidz or raidz2. Thanks. -- am From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 15:20:13 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 3A9F51065679 for ; Fri, 5 Nov 2010 15:20:13 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 0E1C08FC0C for ; Fri, 5 Nov 2010 15:20:13 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA5FKC4b075692 for ; Fri, 5 Nov 2010 15:20:12 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA5FKCqN075691; Fri, 5 Nov 2010 15:20:12 GMT (envelope-from gnats) Date: Fri, 5 Nov 2010 15:20:12 GMT Message-Id: <201011051520.oA5FKCqN075691@freefall.freebsd.org> To: freebsd-fs@FreeBSD.org From: Guido Falsi Cc: Subject: Re: kern/151910: [zfs] booting from raidz/raidz2 on ciss(4) doesn't work X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Guido Falsi List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 05 Nov 2010 15:20:13 -0000 The following reply was made to PR kern/151910; it has been noted by GNATS. From: Guido Falsi To: bug-followup@FreeBSD.org, am@raisa.eu.org Cc: Subject: Re: kern/151910: [zfs] booting from raidz/raidz2 on ciss(4) doesn't work Date: Fri, 5 Nov 2010 16:18:48 +0100 I can confirm this same problem with similar hardware. At present I'm booting this machine from an USB stick. Hope this helps give this PR some traction. -- Guido Falsi From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 15:50:08 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5F14E1065693 for ; Fri, 5 Nov 2010 15:50:08 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 327968FC1C for ; Fri, 5 Nov 2010 15:50:08 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA5Fo86W005189 for ; Fri, 5 Nov 2010 15:50:08 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA5Fo8Gc005187; Fri, 5 Nov 2010 15:50:08 GMT (envelope-from gnats) Date: Fri, 5 Nov 2010 15:50:08 GMT Message-Id: <201011051550.oA5Fo8Gc005187@freefall.freebsd.org> To: freebsd-fs@FreeBSD.org From: Mihai-Catalin Salgau Cc: Subject: Re: kern/151905: [zfs] page fault under load in /sbin/zfs X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Mihai-Catalin Salgau List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 05 Nov 2010 15:50:08 -0000 The following reply was made to PR kern/151905; it has been noted by GNATS. From: Mihai-Catalin Salgau To: bug-followup@FreeBSD.org, csalgau-br@bitdefender.com Cc: Subject: Re: kern/151905: [zfs] page fault under load in /sbin/zfs Date: Fri, 5 Nov 2010 17:22:21 +0200 Hello Bug-followup, You're right. I totally missed that. I was used to not getting the stack in 8.0-RELEASE and I mostly skipped i= t. Could having an unmounted fuse device reading from a file in a zfs file s= ystem during a destroy operation cause this? =20 Thanks From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 17:40:10 2010 Return-Path: Delivered-To: freebsd-fs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 61976106564A for ; Fri, 5 Nov 2010 17:40:10 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 308468FC0A for ; Fri, 5 Nov 2010 17:40:10 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id oA5He9Fe020128 for ; Fri, 5 Nov 2010 17:40:09 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id oA5He9pq020127; Fri, 5 Nov 2010 17:40:09 GMT (envelope-from gnats) Date: Fri, 5 Nov 2010 17:40:09 GMT Message-Id: <201011051740.oA5He9pq020127@freefall.freebsd.org> To: freebsd-fs@FreeBSD.org From: Andriy Gapon Cc: Subject: Re: kern/151910: [zfs] booting from raidz/raidz2 on ciss(4) doesn't work X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Andriy Gapon List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 05 Nov 2010 17:40:10 -0000 The following reply was made to PR kern/151910; it has been noted by GNATS. From: Andriy Gapon To: Emil Smolenski Cc: bug-followup@FreeBSD.org Subject: Re: kern/151910: [zfs] booting from raidz/raidz2 on ciss(4) doesn't work Date: Fri, 05 Nov 2010 19:38:26 +0200 on 05/11/2010 17:10 Emil Smolenski said the following: > The following reply was made to PR kern/151910; it has been noted by GNATS. > > From: "Emil Smolenski" > To: bug-followup@freebsd.org, am@raisa.eu.org > Cc: > Subject: Re: kern/151910: [zfs] booting from raidz/raidz2 on ciss(4) doesn't > work > Date: Fri, 05 Nov 2010 15:45:39 +0100 > > Please see at "Originator" field in both PRs. I'm familiar with PR 148655 > very well. > > Problem in PR 148655 is related to booting from _degraded_ > raidz/raidz2/mirror. In this PR we have problem with booting from > _non_degraded_ raidz/raidz2 and only when ciss(4) is used. Mirror-based > configurations, SATA disks, USB sticks, other RAID controllers are all OK. > > Of course I tested 8.1-STABLE (from Oct) and 8.0-RELEASE (where PR 148655 > is not applicable) but there were no difference -- still can't boot from > raidz or raidz2. Apologies for missing that important information. It looks like this might be some exotic issue about ciss, BIOS (and ciss's option ROM) and how our boot code accesses/enumerates BIOS-visible disks. -- Andriy Gapon From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 21:16:16 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D6BDD106564A; Fri, 5 Nov 2010 21:16:16 +0000 (UTC) (envelope-from rmacklem@uoguelph.ca) Received: from esa-jnhn.mail.uoguelph.ca (esa-jnhn.mail.uoguelph.ca [131.104.91.44]) by mx1.freebsd.org (Postfix) with ESMTP id 70D9A8FC0A; Fri, 5 Nov 2010 21:16:16 +0000 (UTC) X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: ApwEAGYR1EyDaFvO/2dsb2JhbACDKJ80qwOQboJ0gWFzBIpW X-IronPort-AV: E=Sophos;i="4.58,305,1286164800"; d="scan'208";a="99793894" Received: from erie.cs.uoguelph.ca (HELO zcs3.mail.uoguelph.ca) ([131.104.91.206]) by esa-jnhn-pri.mail.uoguelph.ca with ESMTP; 05 Nov 2010 17:16:04 -0400 Received: from zcs3.mail.uoguelph.ca (localhost.localdomain [127.0.0.1]) by zcs3.mail.uoguelph.ca (Postfix) with ESMTP id 173D7B3F56; Fri, 5 Nov 2010 17:16:04 -0400 (EDT) Date: Fri, 5 Nov 2010 17:16:04 -0400 (EDT) From: Rick Macklem To: Andriy Gapon Message-ID: <1090600565.181851.1288991764084.JavaMail.root@erie.cs.uoguelph.ca> In-Reply-To: <4CD3B4A0.6060207@freebsd.org> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="----=_Part_181850_1076044894.1288991764083" X-Originating-IP: [99.225.56.115] X-Mailer: Zimbra 6.0.7_GA_2476.RHEL4 (ZimbraWebClient - IE8 (Win)/6.0.7_GA_2473.RHEL4_64) Cc: freebsd-fs@freebsd.org, freebsd-current@freebsd.org Subject: Re: processes stuck on a vnode lock 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, 05 Nov 2010 21:16:16 -0000 ------=_Part_181850_1076044894.1288991764083 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit > on 04/11/2010 16:45 Andriy Gapon said the following: > > on 04/11/2010 09:49 Andriy Gapon said the following: > >> > >> I see a few processes stuck on the same vnode, trying to take or to > >> upgrade to > >> an exclusive lock on it, while the lock data suggests that it is > >> already > >> shared-locked. The vnode is a root vnode of one of ZFS filesystems > >> (it's not a > >> global root). > >> > >> I couldn't find any (other) threads that could actually hold the > >> vnode lock, but > >> lock shared count is suspiciously or coincidentally the same as > >> number of > >> threads in zfs_root call. > > > > BTW, I still have the system alive and online, so if anyone has > > ideas I can try them. > > > > The kernel is not live now, but I have saved it and vmcore of the > system. > > Kostik, > > just a pure guesswork here - could r214049 have something to do with > this? > I looked at the change and it looks completely correct - I don't think > that a > vnode lock can be leaked by that code. But, OTOH, it has some special > handling > for VV_ROOT, it's in NFS code and and it's in a right time-frame, so > just asking. > You could try the attached patch which seems to have worked for Josh Carroll, who had a similar problem with stable/8. rick ------=_Part_181850_1076044894.1288991764083 Content-Type: text/x-patch; name=nfs_serv.patch Content-Transfer-Encoding: base64 Content-Disposition: attachment; filename=nfs_serv.patch LS0tIG5mc19zZXJ2LmMuc2F2CTIwMTAtMTEtMDUgMDg6MTU6NTcuMDAwMDAwMDAwIC0wNDAwCisr KyBuZnNfc2Vydi5jCTIwMTAtMTEtMDUgMDg6MTg6NDAuMDAwMDAwMDAwIC0wNDAwCkBAIC0zMjUy LDcgKzMyNTIsNyBAQAogCQkJbmZocC0+ZmhfZnNpZCA9IG52cC0+dl9tb3VudC0+bW50X3N0YXQu Zl9mc2lkOwogCQkJaWYgKChlcnJvcjEgPSBWT1BfVlBUT0ZIKG52cCwgJm5maHAtPmZoX2ZpZCkp ID09IDApCiAJCQkJZXJyb3IxID0gVk9QX0dFVEFUVFIobnZwLCB2YXAsIGNyZWQpOwotCQkJaWYg KHZwID09IG52cCkKKwkJCWlmICh1c2V2Z2V0ID09IDAgJiYgdnAgPT0gbnZwKQogCQkJCXZ1bnJl ZihudnApOwogCQkJZWxzZQogCQkJCXZwdXQobnZwKTsK ------=_Part_181850_1076044894.1288991764083-- From owner-freebsd-fs@FreeBSD.ORG Fri Nov 5 22:17:04 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 2B9D5106564A; Fri, 5 Nov 2010 22:17:04 +0000 (UTC) (envelope-from jhellenthal@gmail.com) Received: from mail-qw0-f54.google.com (mail-qw0-f54.google.com [209.85.216.54]) by mx1.freebsd.org (Postfix) with ESMTP id 970588FC15; Fri, 5 Nov 2010 22:17:03 +0000 (UTC) Received: by qwg8 with SMTP id 8so2895833qwg.13 for ; Fri, 05 Nov 2010 15:17:02 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:sender:message-id:date:from :organization:user-agent:mime-version:to:cc:subject:references :in-reply-to:x-enigmail-version:content-type :content-transfer-encoding; bh=7ULa/k5SQ++P3qGEml2YWgl+NizjJxNwTYKhLLziKyw=; b=h24eh/EIQFbbqrIOaYkaJzWPvj4PJs2B45ByyFhyKRIw1Uwm7jXE//wC6GmLytTTop y+Xx+iXIUr9xTve9bEIUiH5VGKa7LuhIIbImNpO5Fe1ZlUrxiT29GZYNowZmcPzFpxUB MwES72URSiwfjMMao8y707FufEJehtSE5IFo8= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=sender:message-id:date:from:organization:user-agent:mime-version:to :cc:subject:references:in-reply-to:x-enigmail-version:content-type :content-transfer-encoding; b=Kp45dVRu5DfkWzUO9hi/ICGKI2AZe9j1GI+5ao9RU7yBoFUlk3yl5r4U8cEjg01ISb 2AbWQsGU4aUmqe1AwTtPOuaaqH+e567zYjuhZMxeURMKqqVoUFsHsk064lvn2FTQYUD/ 9z5GHL9WDTD/CldRpCU0FOB6Ep7/jyaOS8uCY= Received: by 10.224.173.26 with SMTP id n26mr1423013qaz.360.1288995422643; Fri, 05 Nov 2010 15:17:02 -0700 (PDT) Received: from centel.dataix.local (adsl-99-181-136-243.dsl.klmzmi.sbcglobal.net [99.181.136.243]) by mx.google.com with ESMTPS id s34sm1824569qcp.32.2010.11.05.15.16.59 (version=SSLv3 cipher=RC4-MD5); Fri, 05 Nov 2010 15:17:01 -0700 (PDT) Sender: "J. Hellenthal" Message-ID: <4CD48259.6030402@DataIX.net> Date: Fri, 05 Nov 2010 18:16:57 -0400 From: jhell Organization: http://www.DataIX.net User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.9.2.12) Gecko/20101028 Lightning/1.0b1 Thunderbird MIME-Version: 1.0 To: Andriy Gapon References: <4C91F031.1010801@freebsd.org> <20101010134717.GA59922@deviant.kiev.zoral.com.ua> <4CD2E5AA.1090208@freebsd.org> In-Reply-To: <4CD2E5AA.1090208@freebsd.org> X-Enigmail-Version: 1.1.2 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Cc: Alan Cox , Pawel Jakub Dawidek , freebsd-fs@freebsd.org Subject: Re: vop_getpages for zfs 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, 05 Nov 2010 22:17:04 -0000 On 11/04/2010 12:56, Andriy Gapon wrote: > on 10/10/2010 16:47 Kostik Belousov said the following: >> I think that readahead requests should be satisfied, if possible. Esp. >> in the case the readahead does not cause additional i/o. > > So, per Kostik's suggestion, here is patch for your review and testing: > http://people.freebsd.org/~avg/zfs_getpages.2.diff > > The patch tries to fill as many of the passed in pages as possible as long as that > can be done from a block (or even two blocks) that has to be read to fill the > requested page. > This means that the optimization kicks in only if a vnode has a block size greater > than the page size. > I mentioned "two blocks" above because I tried to optimize the case when, for > example, block size is 6KB and page size is 4KB and the requested page covers > parts of two adjacent blocks (e.g. range from 4KB to 8KB). Not sure if this was > worth the trouble. > > In other words, the code tries to avoid reading more blocks than is strictly > required, because additional blocks may be far apart on a disk and thus read > latency could get increased. > > You will also notice that I added vop_bmap method to ZFS vops. > This is needed to satisfy logic in vnode_pager_haspage(); otherwise, for example, > vm_fault() would never request any additional pages besides the required one. > zfs_bmap() implementation is really simple - it returns zeros for a_runp and > a_runb (and some reasonable-ish but unused values in other fields), and > vnode_pager_haspage() figures out number of eligible pages from the block size > (f_iosize actually[*]) and the page size. > > Now, that ZFS has vop_getpages method, it is safe to provide this dummy-ish > implementation of vop_bmap, because this operation would not be called by any > other place but vnode_pager_haspage(). Code from vfs_bio.c and vfs_cluster.c is > never called for ZFS, because it doesn't use the buffer cache layer. > > [*] There is a few interesting questions with respect to f_iosize usage in > vnode_pager_haspage() and ZFS. > For one, ZFS has a variable block size and f_iosize for ZFS has a currently > configured maximum block ('record' in ZFS terms) size. This should not result in > non-optimal behavior for files with smaller block sizes, because those files would > have smaller sizes too (within the block size). > Unless, of course, recordsize property is modified after some files are created on > a ZFS filesystem. In that case there could be large files with some smaller > (previously maximum) block size; or files with a block size larger than the > current recordsize == f_iosize. So, such situations may lead to sub-optimal > performance. > Another issue related to the above is that f_iosize for ZFS can change on the fly > when an administrators runs zfs set recordsize=NNN, and that may happen > concurrently with vnode_pager_haspage() using f_iosize for its calculations. > Not sure how to handle this correctly. > > I will appreciate your comment comments, test reports, reviews and suggestions. > Thanks a lot! Hey Andriy Thought I would give you a heads up on this after seeing the post about zfs_getpages.diff. I patched up to this before after seeing it posted to @ and got reliable dumpage from it. Basically a vm_page_unwire fault or something like that. I believe the following is the backtrace from that. (kgdb) #0 doadump () at pcpu.h:231 #1 0x80675251 in boot (howto=260) at /usr/src/sys/kern/kern_shutdown.c:419 #2 0x806754e5 in panic (fmt=Variable "fmt" is not available. ) at /usr/src/sys/kern/kern_shutdown.c:592 #3 0x808e27ce in vm_page_unwire (m=0x816b46e0, activate=1) at /usr/src/sys/vm/vm_page.c:1564 #4 0x808d123a in vm_fault_unwire (map=0x81690088, start=2568372224, end=2568433664, fictitious=0) at /usr/src/sys/vm/vm_fault.c:1123 #5 0x808d8a33 in vm_map_delete (map=0x81690088, start=2568372224, end=2568433664) at /usr/src/sys/vm/vm_map.c:2619 #6 0x808d8d0d in vm_map_remove (map=0x81690088, start=2568372224, end=Variable "end" is not available. ) at /usr/src/sys/vm/vm_map.c:2801 #7 0x808d6360 in kmem_free (map=0x81690088, addr=2568372224, size=61440) at /usr/src/sys/vm/vm_kern.c:211 #8 0x808cb601 in page_free (mem=0x99164000, size=61440, flags=34 '"') at /usr/src/sys/vm/uma_core.c:1069 #9 0x808ccf92 in uma_large_free (slab=0x85be7e6c) at /usr/src/sys/vm/uma_core.c:3021 #10 0x8065f7a5 in free (addr=0x99164000, mtp=0x80d8e114) at /usr/src/sys/kern/kern_malloc.c:506 #11 0x80cd49db in zil_lwb_write_done () from /boot/kernel/zfs.ko #12 0x80cd99b1 in zio_done () from /boot/kernel/zfs.ko #13 0x80cd7d3a in zio_execute () from /boot/kernel/zfs.ko #14 0x80cd7f2e in zio_notify_parent () from /boot/kernel/zfs.ko #15 0x80cd9a31 in zio_done () from /boot/kernel/zfs.ko #16 0x80cd7d3a in zio_execute () from /boot/kernel/zfs.ko #17 0x80c6656b in taskq_run_safe () from /boot/kernel/zfs.ko #18 0x806af812 in taskqueue_run (queue=0x85a0ac40) at /usr/src/sys/kern/subr_taskqueue.c:239 #19 0x806afa07 in taskqueue_thread_loop (arg=0x85a3f830) at /usr/src/sys/kern/subr_taskqueue.c:360 #20 0x80647377 in fork_exit (callout=0x806af94a , arg=0x85a3f830, frame=0xb4439d38) at /usr/src/sys/kern/kern_fork.c:845 #21 0x809126a4 in fork_trampoline () at /usr/src/sys/i386/i386/exception.s:273 (kgdb) And that coincided with the dates that I added the patch once seeing it on the list. changeset: 351:f1ca4eb51520 user: J. Hellenthal date: Sun Oct 10 22:57:24 2010 -0400 summary: Remove the zfs_getpages patch from Andriy Gapon changeset: 350:bb885c047f0a user: J. Hellenthal date: Sun Oct 10 22:27:31 2010 -0400 summary: zfs_getpages improvement from Andriy Gapon If you would like I can patch back up to this patch to provide more information if its needed, but at the moment I do not have it available nor do I have the core that was generated. -- jhell,v From owner-freebsd-fs@FreeBSD.ORG Sat Nov 6 00:14:06 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5C979106566B; Sat, 6 Nov 2010 00:14:06 +0000 (UTC) (envelope-from mi+thunw@aldan.algebra.com) Received: from vms173013pub.verizon.net (vms173013pub.verizon.net [206.46.173.13]) by mx1.freebsd.org (Postfix) with ESMTP id 3A1118FC0C; Sat, 6 Nov 2010 00:14:06 +0000 (UTC) Received: from [192.168.1.9] ([unknown] [173.70.194.135]) by vms173013.mailsrvcs.net (Sun Java(tm) System Messaging Server 7u2-7.02 32bit (built Apr 16 2009)) with ESMTPA id <0LBF00IVEPTYSPW1@vms173013.mailsrvcs.net>; Fri, 05 Nov 2010 18:13:14 -0500 (CDT) Message-id: <4CD48F81.1080201@aldan.algebra.com> Date: Fri, 05 Nov 2010 19:13:05 -0400 From: "Mikhail T." User-Agent: Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.2.12) Gecko/20101027 Lightning/1.0b2 Thunderbird/3.1.6 MIME-version: 1.0 To: Julian Elischer References: <4CD04AEC.8040607@aldan.algebra.com> <4CD051A9.7090200@freebsd.org> <4CD0660E.2000102@aldan.algebra.com> <4CD06C4B.80100@freebsd.org> <4CD0895A.5030402@aldan.algebra.com> <4CD09830.3030400@freebsd.org> In-reply-to: <4CD09830.3030400@freebsd.org> Content-type: text/plain; charset=ISO-8859-1 Content-transfer-encoding: 7bit X-Mailman-Approved-At: Sat, 06 Nov 2010 03:07:45 +0000 Cc: fs@freebsd.org Subject: iozone-ing an SSD (Re: Using an SSD "disk" for /) 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, 06 Nov 2010 00:14:06 -0000 Hello! So, after an earlier inquiry, I went ahead and purchased an SSD (Crucial's CTFDDAC128MAG-1G1) and put it to some testing today. The computer is Dell Poweredge 2900, running FreeBSD-8.1/amd64 (the October 10th snapshot). Generic kernel. The system drive (for now) is traditional "real" HD -- a 15K RPM by Fujitsu (MAX3073RC), I ran `iozone -a' 4 times: 1. On /var/tmp -- freshly newfs-ed by the sysinstall on the Fujitsu drive (/dev/da0). 2. On the SSD (/dev/ad4) freshly newfs-ed by me without ANY options (no softupdates). 3. On the SSD (/dev/ad4) freshly newfs-ed by me with very large -e and -a options. Reading the man-page, I figured, any parameters mentioning "cylinders" can be set to very large values... 4. On the SSD (/dev/da1) connected to the server's mpt-controller, rather than the plain SATA port -- using the same filesystem created in 3. above (no reformatting). (The 2.5" can't be secured in the 3.5" slot and is simply hanging in the air on the SATA/SAS connectors.) The results can be found in 4 HTML files found at: http://aldan.algebra.com/~mi/io/ (The original iozone-created Excel files are there too.) They puzzle... Fujitsu, for example, is not an OBVIOUS loser -- it beats the SSD in a number of file-size record-length combinations. I also can't explain, the differences between different takes on the SSD. And, lastly, there is a surprising (to me) spike in "Record Rewrite" throughput -- for both SSD and HD -- for large files when the reclen is 64. Using reclen of 128 results in much worsening throughput -- especially for the Fujitsu. I wonder, if these data can be exploited to come up with better newfs parameters for the modern disks (SSD and not)... Comments? Thanks! -mi From owner-freebsd-fs@FreeBSD.ORG Sat Nov 6 19:00:36 2010 Return-Path: Delivered-To: fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 020C61065693; Sat, 6 Nov 2010 19:00:36 +0000 (UTC) (envelope-from mi+thunw@aldan.algebra.com) Received: from vms173013pub.verizon.net (vms173013pub.verizon.net [206.46.173.13]) by mx1.freebsd.org (Postfix) with ESMTP id D2F688FC18; Sat, 6 Nov 2010 19:00:35 +0000 (UTC) Received: from [192.168.1.9] ([unknown] [173.70.194.135]) by vms173013.mailsrvcs.net (Sun Java(tm) System Messaging Server 7u2-7.02 32bit (built Apr 16 2009)) with ESMTPA id <0LBH00EBK8SGD8D0@vms173013.mailsrvcs.net>; Sat, 06 Nov 2010 14:00:21 -0500 (CDT) Message-id: <4CD5A5B7.4040006@aldan.algebra.com> Date: Sat, 06 Nov 2010 15:00:07 -0400 From: "Mikhail T." User-Agent: Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.2.12) Gecko/20101027 Lightning/1.0b2 Thunderbird/3.1.6 MIME-version: 1.0 To: Julian Elischer References: <4CD04AEC.8040607@aldan.algebra.com> <4CD051A9.7090200@freebsd.org> <4CD0660E.2000102@aldan.algebra.com> <4CD06C4B.80100@freebsd.org> <4CD0895A.5030402@aldan.algebra.com> <4CD09830.3030400@freebsd.org> <4CD48F81.1080201@aldan.algebra.com> In-reply-to: <4CD48F81.1080201@aldan.algebra.com> Content-type: text/plain; charset=ISO-8859-1 Content-transfer-encoding: 7bit X-Mailman-Approved-At: Sat, 06 Nov 2010 19:33:18 +0000 Cc: fs@freebsd.org Subject: Re: iozone-ing an SSD (Re: Using an SSD "disk" for /) 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, 06 Nov 2010 19:00:36 -0000 On 11/5/2010 7:13 PM, Mikhail T. wrote: > The results can be found in 4 HTML files found at: > http://aldan.algebra.com/~mi/io/ (The original iozone-created Excel > files are there too.) I added some more iozone runs, as well as those of rawio. These are much fewer (as file-system parameters don't affect rawio) and easier to interpret: * It makes no difference to the SSD, whether your access is random or sequential * SSD clearly beats the HD in rawrite, although, at "only" 88Mb/sec, the results are far from the marketing... * SSD connected to plain SATA port strongly beats the same SSD connected to the fancy SAS controller (mpt) Yours, -mi