From owner-freebsd-geom@FreeBSD.ORG Sun Jan 7 00:52:56 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id DB51C16A412 for ; Sun, 7 Jan 2007 00:52:56 +0000 (UTC) (envelope-from r.c.ladan@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.171]) by mx1.freebsd.org (Postfix) with ESMTP id 7698F13C441 for ; Sun, 7 Jan 2007 00:52:56 +0000 (UTC) (envelope-from r.c.ladan@gmail.com) Received: by ug-out-1314.google.com with SMTP id o2so5329882uge for ; Sat, 06 Jan 2007 16:52:55 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:user-agent:mime-version:to:cc:subject:references:in-reply-to:x-enigmail-version:content-type; b=kg5kwOjVreWT5l/C5vUVtm5lzt8/dLX0cph6/1nOFccXN76kA2hJ95XyNapsM6uE42HFzwpymU1hs1jjH8V02sFoyRCjkiwd+S50MDPM2yFxeBvY7xzlnhQeEmXpUPXiSAbq2MJMsPKyEC4JakE9IJO5jx0+Mt7lk1IQTyBzOqA= Received: by 10.67.89.5 with SMTP id r5mr31603882ugl.1168131143354; Sat, 06 Jan 2007 16:52:23 -0800 (PST) Received: from ?192.168.123.201? ( [195.241.221.201]) by mx.google.com with ESMTP id s1sm31335775uge.2007.01.06.16.52.21; Sat, 06 Jan 2007 16:52:22 -0800 (PST) Message-ID: <45A04444.8010701@gmail.com> Date: Sun, 07 Jan 2007 01:52:20 +0100 From: Rene Ladan User-Agent: Thunderbird 1.5.0.9 (X11/20061224) MIME-Version: 1.0 To: freebsd-geom@freebsd.org References: <74225.1167686662@critter.freebsd.dk> <459D766B.9050304@gmail.com> In-Reply-To: <459D766B.9050304@gmail.com> X-Enigmail-Version: 0.94.0.0 Content-Type: multipart/mixed; boundary="------------010606090005080908030301" Cc: Poul-Henning Kamp Subject: Re: xbox360 extension for review/debug X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Jan 2007 00:52:56 -0000 This is a multi-part message in MIME format. --------------010606090005080908030301 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Rene Ladan schreef: > Poul-Henning Kamp schreef: >> In message <45996C4F.8070700@gmail.com>, Rene Ladan writes: >>> Hi, >>> >>> I've written an extension to /sys/geom/geom_mbr.c to slice up xbox360 >>> hard disks and memory units. The patch for revision 1.68 (i.e. CURRENT) >>> is at http://home.tisali.nl/rladan/freebsd/geom_mbr.c.diff >> This is wrong, you should make a geom_xbox360 class instead. >> > Ok, I made a geom_xbox360 class and restored geom_mbr.c > > The new class consists of three files at the above website. > > geom_xbox360.c : the class, put it in /sys/geom > geom_xbox360::Makefile : Makefile for /sys/modules/geom/geom_xbox360/ > Makefile.diff : patch for /sys/modules/geom/Makefile > > I've uploaded a new version of geom_xbox360.c. The class now works correctly except for: 1) If you kldload the class and plug in a physical medium afterwards, then pp->mediasize == 0 so the taste function fails. This does not happen if the medium is plugged in before the kldload or when using dd images using mdconfig. I think that the taste function is called before the physical medium (here da0) is properly initialized. MBR media don't suffer from this because mbr_taste() doesn't check pp->mediasize. A dmesg is attached. 2) Trying to kldunload the class before removing the (physical) medium results in g_event going haywire. But this might be on design according to Google. > Regards, > Rene -- GPG fingerprint = E738 5471 D185 7013 0EE0 4FC8 3C1D 6F83 12E1 84F6 (subkeys.pgp.net) "It won't fit on the line." -- me, 2001 --------------010606090005080908030301 Content-Type: text/plain; name="xbox360-dmesg.txt" Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="xbox360-dmesg.txt" umass0: on uhub4 umass0:0:0:-1: Attached to scbus0 (probe0:umass-sim0:0:0:0): Down reving Protocol Version from 2 to 0? (probe0:umass-sim0:0:0:0): Uninitialized Transport 5:26? pass0 at umass-sim0 bus 0 target 0 lun 0 pass0: Removable Simplified Direct Access SCSI-0 device pass0: Serial Number \M-{ pass0: 40.000MB/s transfers GEOM: new disk da0 da0 at umass-sim0 bus 0 target 0 lun 0 da0: Removable Simplified Direct Access SCSI-0 device da0: Serial Number \M-{ da0: 40.000MB/s transfers da0: 62MB (127232 512 byte sectors: 64H 32S/T 62C) # kldload geom_xbox360 mp=0xc5606d60 pp=0xc500c980 mp->name=XBOX360, pp->name=acd0 classname=ACD g_xbox360_taste: size = 8796093020160 mp=0xc5606d60 pp=0xc500cc00 mp->name=XBOX360, pp->name=ad0s2 classname=MBR g_xbox360_taste: size = 79135418880 mp=0xc5606d60 pp=0xc500cd00 mp->name=XBOX360, pp->name=ad0s1 classname=MBR g_xbox360_taste: size = 40896059904 mp=0xc5606d60 pp=0xc500c700 mp->name=XBOX360, pp->name=ad0s2f classname=BSD g_xbox360_taste: size = 70598388224 mp=0xc5606d60 pp=0xc500c200 mp->name=XBOX360, pp->name=ad0s2e classname=BSD g_xbox360_taste: size = 536870912 mp=0xc5606d60 pp=0xc500c300 mp->name=XBOX360, pp->name=ad0s2d classname=BSD g_xbox360_taste: size = 3203399680 mp=0xc5606d60 pp=0xc500c400 mp->name=XBOX360, pp->name=ad0s2c classname=BSD g_xbox360_taste: size = 79135418880 mp=0xc5606d60 pp=0xc500c500 mp->name=XBOX360, pp->name=ad0s2b classname=BSD g_xbox360_taste: size = 4259889152 mp=0xc5606d60 pp=0xc500c600 mp->name=XBOX360, pp->name=ad0s2a classname=BSD g_xbox360_taste: size = 536870912 mp=0xc5606d60 pp=0xc5147580 mp->name=XBOX360, pp->name=da0 classname=DISK g_xbox360_taste: size = 65142784 sectorsize = 512 mp=0xc5606d60 pp=0xc5081c80 mp->name=XBOX360, pp->name=cd0 classname=DISK g_xbox360_taste: size = 0 mp=0xc5606d60 pp=0xc5044500 mp->name=XBOX360, pp->name=ad0 classname=DISK g_xbox360_taste: size = 120034123776 mp=0xc5606d60 pp=0xc5653b00 mp->name=XBOX360, pp->name=da0s1 classname=XBOX360 mp=0xc5606d60 pp=0xc5082100 mp->name=XBOX360, pp->name=da0s2 classname=XBOX360 umass0: at uhub4 port 2 (addr 2) disconnected (da0:umass-sim0:0:0:0): lost device (da0:umass-sim0:0:0:0): removing device entry (pass0:umass-sim0:0:0:0): lost device (pass0:umass-sim0:0:0:0): removing device entry umass0: detached # reattach device with geom_xbox360 still loaded umass0: on uhub4 umass0:0:0:-1: Attached to scbus0 (probe0:umass-sim0:0:0:0): Down reving Protocol Version from 2 to 0? (probe0:umass-sim0:0:0:0): Uninitialized Transport 5:26? pass0 at umass-sim0 bus 0 target 0 lun 0 pass0: Removable Simplified Direct Access SCSI-0 device pass0: Serial Number \M-{ pass0: 40.000MB/s transfers GEOM: new disk da0 mp=0xc5606d60 pp=0xc5bbd380 mp->name=XBOX360, pp->name=da0 classname=DISK g_xbox360_taste: size = 0 <-- should be 65142784 ? da0 at umass-sim0 bus 0 target 0 lun 0 da0: Removable Simplified Direct Access SCSI-0 device da0: Serial Number \M-{ da0: 40.000MB/s transfers da0: 62MB (127232 512 byte sectors: 64H 32S/T 62C) # mdconfig -a -t vnode -f mc360.img , geom_xbox360 still loaded mp=0xc5606d60 pp=0xc5df3280 mp->name=XBOX360, pp->name=md0 classname=MD g_xbox360_taste: size = 65142784 sectorsize = 512 mp=0xc5606d60 pp=0xc534a880 mp->name=XBOX360, pp->name=md0s1 classname=XBOX360 mp=0xc5606d60 pp=0xc5df3a80 mp->name=XBOX360, pp->name=md0s2 classname=XBOX360 --------------010606090005080908030301-- From owner-freebsd-geom@FreeBSD.ORG Sun Jan 7 14:30:48 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 4EEB916A412 for ; Sun, 7 Jan 2007 14:30:48 +0000 (UTC) (envelope-from r.c.ladan@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.173]) by mx1.freebsd.org (Postfix) with ESMTP id CE88413C459 for ; Sun, 7 Jan 2007 14:30:47 +0000 (UTC) (envelope-from r.c.ladan@gmail.com) Received: by ug-out-1314.google.com with SMTP id o2so5366682uge for ; Sun, 07 Jan 2007 06:30:46 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:user-agent:mime-version:to:cc:subject:references:in-reply-to:x-enigmail-version:content-type:content-transfer-encoding; b=JPZAyYCiFwjlGp6n+lv98OV5D260MhkAfqeyOvuy80czJ7f7BWgR/9Rl8bOexRPyCvvJz/0kz+Bz2WWn3uYCj5nHliVkpBkLNHtAiiPuFDDfO5b0JDCKIVdR7j5bgd/1OyzlAeaz10LEgres5hUeC/ypJx1k0TUzFbswYuIyf0o= Received: by 10.66.248.5 with SMTP id v5mr32131719ugh.1168180214772; Sun, 07 Jan 2007 06:30:14 -0800 (PST) Received: from ?192.168.123.201? ( [195.241.221.201]) by mx.google.com with ESMTP id k2sm31915985ugf.2007.01.07.06.30.13; Sun, 07 Jan 2007 06:30:14 -0800 (PST) Message-ID: <45A103F4.5040108@gmail.com> Date: Sun, 07 Jan 2007 15:30:12 +0100 From: Rene Ladan User-Agent: Thunderbird 1.5.0.9 (X11/20061224) MIME-Version: 1.0 To: freebsd-geom@freebsd.org References: <74225.1167686662@critter.freebsd.dk> <459D766B.9050304@gmail.com> <45A04444.8010701@gmail.com> In-Reply-To: <45A04444.8010701@gmail.com> X-Enigmail-Version: 0.94.0.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: Poul-Henning Kamp Subject: pp->mediasize == 0 when reattaching physical medium ? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Jan 2007 14:30:48 -0000 Rene Ladan schreef: > Rene Ladan schreef: >> Poul-Henning Kamp schreef: >>> In message <45996C4F.8070700@gmail.com>, Rene Ladan writes: >>>> Hi, >>>> >>>> I've written an extension to /sys/geom/geom_mbr.c to slice up xbox360 >>>> hard disks and memory units. The patch for revision 1.68 (i.e. CURRENT) >>>> is at http://home.tisali.nl/rladan/freebsd/geom_mbr.c.diff >>> This is wrong, you should make a geom_xbox360 class instead. >>> >> Ok, I made a geom_xbox360 class and restored geom_mbr.c >> >> The new class consists of three files at the above website. >> >> geom_xbox360.c : the class, put it in /sys/geom >> geom_xbox360::Makefile : Makefile for /sys/modules/geom/geom_xbox360/ >> Makefile.diff : patch for /sys/modules/geom/Makefile >> >> > I've uploaded a new version of geom_xbox360.c. The class now works > correctly except for: > > 1) If you kldload the class and plug in a physical medium afterwards, > then pp->mediasize == 0 so the taste function fails. This does not > happen if the medium is plugged in before the kldload or when using dd > images using mdconfig. I think that the taste function is called before > the physical medium (here da0) is properly initialized. MBR media don't > suffer from this because mbr_taste() doesn't check pp->mediasize. A > dmesg is attached. > I am able to reproduce this with a standard USB 1 memory stick. The medium is correctly tasted when kldloading after the medium is plugged in, or when the class is kldloaded and you finish making the stick look like an xbox360 medium. I've uploaded a new version of the class, which enables experimenting with a normal USB stick, as explained at lines 53-56. I start to suspect that this is a bug in geom itself, should I send a PR ? Regards, Rene -- GPG fingerprint = E738 5471 D185 7013 0EE0 4FC8 3C1D 6F83 12E1 84F6 (subkeys.pgp.net) "It won't fit on the line." -- me, 2001 From owner-freebsd-geom@FreeBSD.ORG Sun Jan 7 15:46:39 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 2755616A412 for ; Sun, 7 Jan 2007 15:46:39 +0000 (UTC) (envelope-from phk@critter.freebsd.dk) Received: from phk.freebsd.dk (phk.freebsd.dk [130.225.244.222]) by mx1.freebsd.org (Postfix) with ESMTP id DD5B713C45E for ; Sun, 7 Jan 2007 15:46:38 +0000 (UTC) (envelope-from phk@critter.freebsd.dk) Received: from critter.freebsd.dk (critter.freebsd.dk [192.168.48.2]) by phk.freebsd.dk (Postfix) with ESMTP id 42BD61747B; Sun, 7 Jan 2007 15:46:37 +0000 (UTC) Received: from critter.freebsd.dk (localhost [127.0.0.1]) by critter.freebsd.dk (8.13.8/8.13.8) with ESMTP id l07FkTu9014693; Sun, 7 Jan 2007 15:46:29 GMT (envelope-from phk@critter.freebsd.dk) To: Rene Ladan From: "Poul-Henning Kamp" In-Reply-To: Your message of "Sun, 07 Jan 2007 15:30:12 +0100." <45A103F4.5040108@gmail.com> Date: Sun, 07 Jan 2007 15:46:29 +0000 Message-ID: <14692.1168184789@critter.freebsd.dk> Sender: phk@critter.freebsd.dk Cc: freebsd-geom@freebsd.org Subject: Re: pp->mediasize == 0 when reattaching physical medium ? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Jan 2007 15:46:39 -0000 In message <45A103F4.5040108@gmail.com>, Rene Ladan writes: >> 1) If you kldload the class and plug in a physical medium afterwards, >> then pp->mediasize == 0 so the taste function fails. That's a USB bug. -- Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 phk@FreeBSD.ORG | TCP/IP since RFC 956 FreeBSD committer | BSD since 4.3-tahoe Never attribute to malice what can adequately be explained by incompetence. From owner-freebsd-geom@FreeBSD.ORG Mon Jan 8 11:08:23 2007 Return-Path: X-Original-To: freebsd-geom@FreeBSD.org Delivered-To: freebsd-geom@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 251A116A403 for ; Mon, 8 Jan 2007 11:08:23 +0000 (UTC) (envelope-from owner-bugmaster@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [69.147.83.40]) by mx1.freebsd.org (Postfix) with ESMTP id 117A913C468 for ; Mon, 8 Jan 2007 11:08:23 +0000 (UTC) (envelope-from owner-bugmaster@FreeBSD.org) Received: from freefall.freebsd.org (linimon@localhost [127.0.0.1]) by freefall.freebsd.org (8.13.4/8.13.4) with ESMTP id l08B8MI3016465 for ; Mon, 8 Jan 2007 11:08:22 GMT (envelope-from owner-bugmaster@FreeBSD.org) Received: (from linimon@localhost) by freefall.freebsd.org (8.13.4/8.13.4/Submit) id l08B8JWQ016461 for freebsd-geom@FreeBSD.org; Mon, 8 Jan 2007 11:08:19 GMT (envelope-from owner-bugmaster@FreeBSD.org) Date: Mon, 8 Jan 2007 11:08:19 GMT Message-Id: <200701081108.l08B8JWQ016461@freefall.freebsd.org> X-Authentication-Warning: freefall.freebsd.org: linimon set sender to owner-bugmaster@FreeBSD.org using -f From: FreeBSD bugmaster To: freebsd-geom@FreeBSD.org Cc: Subject: Current problem reports assigned to you X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 08 Jan 2007 11:08:23 -0000 Current FreeBSD problem reports Critical problems Serious problems S Tracker Resp. Description -------------------------------------------------------------------------------- o kern/73177 geom kldload geom_* causes panic due to memory exhaustion o kern/76538 geom [gbde] nfs-write on gbde partition stalls and continue o kern/83464 geom [geom] [patch] Unhandled malloc failures within libgeo o kern/84556 geom [geom] GBDE-encrypted swap causes panic at shutdown o kern/87544 geom [gbde] mmaping large files on a gbde filesystem deadlo o kern/89102 geom [geom_vfs] [panic] panic when forced unmount FS from u o bin/90093 geom fdisk(8) incapable of altering in-core geometry o kern/90582 geom [geom_mirror] [panic] Restore cause panic string (ffs_ o kern/98034 geom [geom] dereference of NULL pointer in acd_geom_detach o kern/104389 geom [geom] [patch] sys/geom/geom_dump.c doesn't encode XML 10 problems total. Non-critical problems S Tracker Resp. Description -------------------------------------------------------------------------------- o bin/78131 geom gbde "destroy" not working. o kern/79251 geom [2TB] newfs fails on 2.6TB gbde device o kern/94632 geom [geom] Kernel output resets input while GELI asks for f kern/105390 geom [geli] filesystem on a md backed by sparse file with s 4 problems total. From owner-freebsd-geom@FreeBSD.ORG Mon Jan 8 21:39:29 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 1109016A403 for ; Mon, 8 Jan 2007 21:39:29 +0000 (UTC) (envelope-from ahnjoan@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.171]) by mx1.freebsd.org (Postfix) with ESMTP id 9E90013C448 for ; Mon, 8 Jan 2007 21:39:28 +0000 (UTC) (envelope-from ahnjoan@gmail.com) Received: by ug-out-1314.google.com with SMTP id o2so5668447uge for ; Mon, 08 Jan 2007 13:39:27 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=udD8VTKLl8bu9U/EblZvBwLkdLhfMD9OqrtXnHnaCE7012yteORWKXs662EWGcg9N8w6tmV5VGA+7fkutJgkJdY9c630BAfmrWRzl0qokORrWtiV4X/aJXI/lO9dS2vqwri/+oMGM1IXqIXr6P+eHph6P/lUNE9pMFsR+rFyKpU= Received: by 10.78.204.1 with SMTP id b1mr7095774hug.1168290619933; Mon, 08 Jan 2007 13:10:19 -0800 (PST) Received: by 10.78.11.6 with HTTP; Mon, 8 Jan 2007 13:10:19 -0800 (PST) Message-ID: <5e575c8a0701081310h4d59c6f7k31c5e31de9933754@mail.gmail.com> Date: Mon, 8 Jan 2007 16:10:19 -0500 From: "Ahnjoan Amous" To: freebsd-geom@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=WINDOWS-1252; format=flowed Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Subject: =?windows-1252?q?GEOM_mirror_performance_=96_slow?= X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 08 Jan 2007 21:39:29 -0000 While deploying 6.1-RELEASE I'm seeing slower than expected speed using geom mirror. Test 1. Outside of GEOM I'm able to write to both aacd2 and aacd3 concurrently and achieve between 41M =96 45M a second write speeds. (around 75M a second if I run the commands separately) Test 2. Inside a GEOM container but not mirrored (aacd2 =3D gm2, aacd3 =3D gm3) I'm able to write to both gm2 and gm3 concurrently and achieve between 40M =96 49M a second write speeds. (around 75M a second if I run the commands separately) Test 3. Inside a GEOM mirror (gm1 =3D aacd2 =3D aacd3) I'm able to achieve 23M a second. I'd love someones opinion as to if the speed I'm seeing using GEOM mirror is to be expected. FYI =96 The mirror was manually rebuilt and COMPLETE before tests were attempted on the mirror. *********************************************************************** *** Test 1. *** dd to devices mounted outside of geom > dd if=3D/dev/zero of=3D/data02/helloworld bs=3D8k count=3D100k & > dd if=3D/dev/zero of=3D/data03/helloworld bs=3D8k count=3D100k & 838860800 bytes transferred in 18.799345 secs (44621810 bytes/sec) ^^^^^^^^ 838860800 bytes transferred in 18.544963 secs (45233889 bytes/sec) ^^^^^^^^ > dd if=3D/dev/zero of=3D/data02/helloworld bs=3D1m count=3D800 & > dd if=3D/dev/zero of=3D/data03/helloworld bs=3D1m count=3D800 & 838860800 bytes transferred in 20.014247 secs (41913183 bytes/sec) ^^^^^^^^ 838860800 bytes transferred in 19.824656 secs (42314016 bytes/sec) ^^^^^^^^ **** setup info for test **** > df -k /dev/aacd2s1e 2026030 819620 1044328 44% /data02 /dev/aacd3s1e 2026030 819620 1044328 44% /data03 *********************************************************************** *** Test 2. *** dd to devices mounted as their own geom volumes > dd if=3D/dev/zero of=3D/data02/helloworld bs=3D8k count=3D100k & > dd if=3D/dev/zero of=3D/data03/helloworld bs=3D8k count=3D100k & 838860800 bytes transferred in 17.118679 secs (49002659 bytes/sec) ^^^^^^^^ 838860800 bytes transferred in 16.810787 secs (49900150 bytes/sec) ^^^^^^^^ > dd if=3D/dev/zero of=3D/data02/helloworld bs=3D1m count=3D800 & > dd if=3D/dev/zero of=3D/data03/helloworld bs=3D1m count=3D800 & 838860800 bytes transferred in 20.907455 secs (40122569 bytes/sec) ^^^^^^^^ 838860800 bytes transferred in 20.638277 secs (40645874 bytes/sec) ^^^^^^^^ **** setup info for test **** > df -k /dev/mirror/gm2 2026030 819620 1044328 44% /data02 /dev/mirror/gm3 2026030 819620 1044328 44% /data03 > gmirror list Geom name: gm2 1. Name: aacd2s1e Geom name: gm3 1. Name: aacd3s1e *********************************************************************** *** Test 3. *** dd to devices mounted as a geom mirror > dd if=3D/dev/zero of=3D/data01/helloworld bs=3D8k count=3D100k 838860800 bytes transferred in 35.622392 secs (23548694 bytes/sec) ^^^^^^^^ > dd if=3D/dev/zero of=3D/data01/helloworld bs=3D1m count=3D800 838860800 bytes transferred in 35.588491 secs (23571126 bytes/sec) ^^^^^^^^ **** setup info for test **** > df -k /dev/mirror/gm1 2026028 819620 1044326 44% /data01 > gmirror list Geom name: gm1 1. Name: aacd2s1e 2. Name: aacd3s1e From owner-freebsd-geom@FreeBSD.ORG Mon Jan 8 23:09:08 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id AAB7916A407 for ; Mon, 8 Jan 2007 23:09:08 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: from py-out-1112.google.com (py-out-1112.google.com [64.233.166.176]) by mx1.freebsd.org (Postfix) with ESMTP id 7091413C43E for ; Mon, 8 Jan 2007 23:09:08 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: by py-out-1112.google.com with SMTP id f31so4137945pyh for ; Mon, 08 Jan 2007 15:09:07 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=jgwoXbEPf4+6Q5UrhVTopBCc78Xmw8mhylm7oKZ1ALUSKjJvlFr+1VqjbI1roI6NLoUnDUTSnKAOjnQrDjHoY863vHlC753jG9DGdf1ZbL/vvDo61mRpzrlds85ALxgjhzs+ciyWYuRdOXtFje9OEIX8ZxCylFMr4xoINBIsIJU= Received: by 10.35.80.20 with SMTP id h20mr49772927pyl.1168296306111; Mon, 08 Jan 2007 14:45:06 -0800 (PST) Received: by 10.35.16.1 with HTTP; Mon, 8 Jan 2007 14:45:06 -0800 (PST) Message-ID: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> Date: Mon, 8 Jan 2007 19:45:06 -0300 From: "Fernan Aguero" To: geom@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline Cc: Subject: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 08 Jan 2007 23:09:08 -0000 Hi I'm trying to set up two disks to contain both gmirrored and gstriped slices. This is what I'm trying to achieve: adxs1, swap adxs2, gmirror adxs3, gstripe I already got the first and second slices set up (swap and gmirror containing the active, root partition), but I cannot seem to be able to set up s3 into a gstripped device. gama# gstripe label -v gs0 /dev/ad4s3 /dev/ad6s3 Can't store metadata on /dev/ad4s3: Operation not permitted. This might be because ad4s3 had been part of a gmirror device before I reorganized my disks and moved the mirror to the s2 slice. Gayn Winters suggested that: "The geom metadata is stored in the last block of the slice. Zero it as well and you can have a clean start." http://lists.freebsd.org/pipermail/freebsd-questions/2006-May/120950.html But now I wonder what is the magic incantation to run dd for targeting the last (sector?) of ad4s3? I imagine I have to use something like dd if=/dev/zero of=/dev/ad4s3? bs=512 count=1 but adding either skip=? or seek=? to taste. gama# fdisk -s /dev/ad4 /dev/ad4: 310101 cyl 16 hd 63 sec Part Start Size Type Flags 1: 63 16771041 0xa5 0x00 2: 16771923 146795229 0xa5 0x80 3: 146795292 188742708 0xa5 0x00 maybe I should skip (146795292 + 188742708 - 1) sectors? Fernan -- Fernan Aguero From owner-freebsd-geom@FreeBSD.ORG Mon Jan 8 23:44:33 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 0EDCD16A40F for ; Mon, 8 Jan 2007 23:44:33 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30310.mail.mud.yahoo.com (web30310.mail.mud.yahoo.com [209.191.69.72]) by mx1.freebsd.org (Postfix) with SMTP id ACA7413C44B for ; Mon, 8 Jan 2007 23:44:32 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 78306 invoked by uid 60001); 8 Jan 2007 23:17:51 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:X-YMail-OSG:Received:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=R9I6CqEN7TvkBVyNRlouRnRjsxLd1SEeQO5rf3Yx7jndfd1vkyoxumXxA1OW5iim7RNJJbyC87vnOnHnm5pZZSivwF5Fl/bL8N1FpgHYSG9rcbXwRDhJlb0K3Y9D2HzhCh9XdjSasVu3aJr/ryFLB9RKhTwR51XWv1EmoSld+6U= ; Message-ID: <20070108231751.78304.qmail@web30310.mail.mud.yahoo.com> X-YMail-OSG: W_BUM9cVM1mmaycW7y3SgeJV676s0pONLhlL_e9UjgYFLl0FNp2pWz_GHfeV1EleJxOvXvzpoG3uv2OHAGZQTxHRZD9aOYOn766zzkkWxEU4GQf1Eb6Gom9ahXr2ZVrT3DhkKW0DkoMs.w-- Received: from [213.54.175.5] by web30310.mail.mud.yahoo.com via HTTP; Mon, 08 Jan 2007 15:17:51 PST Date: Mon, 8 Jan 2007 15:17:51 -0800 (PST) From: "R. B. Riddick" To: Fernan Aguero , geom@freebsd.org In-Reply-To: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Cc: Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 08 Jan 2007 23:44:33 -0000 --- Fernan Aguero wrote: > I imagine I have to use something like > dd if=/dev/zero of=/dev/ad4s3? bs=512 count=1 > > but adding either skip=? or seek=? to taste. > > gama# fdisk -s /dev/ad4 > /dev/ad4: 310101 cyl 16 hd 63 sec > Part Start Size Type Flags > 1: 63 16771041 0xa5 0x00 > 2: 16771923 146795229 0xa5 0x80 > 3: 146795292 188742708 0xa5 0x00 > What about "dd if=/dev/zero of=/dev/ad4s3 oseek=188742707"? What does "gmirror status" say? I would remove the gmirror-s with "gmirror remove " (its easier than dd)... -Arne __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 00:18:39 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 5AE9116A412 for ; Tue, 9 Jan 2007 00:18:39 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (arm132.internetdsl.tpnet.pl [83.17.198.132]) by mx1.freebsd.org (Postfix) with ESMTP id EE8BA13C442 for ; Tue, 9 Jan 2007 00:18:38 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id 90B87487F3; Tue, 9 Jan 2007 00:51:16 +0100 (CET) Received: from localhost (154.81.datacomsa.pl [195.34.81.154]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id 985AA45696; Tue, 9 Jan 2007 00:51:12 +0100 (CET) Date: Tue, 9 Jan 2007 00:50:45 +0100 From: Pawel Jakub Dawidek To: "R. B. Riddick" Message-ID: <20070108235044.GB5165@garage.freebsd.pl> References: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> <20070108231751.78304.qmail@web30310.mail.mud.yahoo.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="nVMJ2NtxeReIH9PS" Content-Disposition: inline In-Reply-To: <20070108231751.78304.qmail@web30310.mail.mud.yahoo.com> X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 7.0-CURRENT i386 User-Agent: mutt-ng/devel-r804 (FreeBSD) X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-2.6 required=3.0 tests=BAYES_00 autolearn=ham version=3.0.4 Cc: geom@freebsd.org, Fernan Aguero Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 00:18:39 -0000 --nVMJ2NtxeReIH9PS Content-Type: text/plain; charset=iso-8859-2 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Jan 08, 2007 at 03:17:51PM -0800, R. B. Riddick wrote: > --- Fernan Aguero wrote: > > I imagine I have to use something like > > dd if=3D/dev/zero of=3D/dev/ad4s3? bs=3D512 count=3D1 > >=20 > > but adding either skip=3D? or seek=3D? to taste. > >=20 > > gama# fdisk -s /dev/ad4 > > /dev/ad4: 310101 cyl 16 hd 63 sec > > Part Start Size Type Flags > > 1: 63 16771041 0xa5 0x00 > > 2: 16771923 146795229 0xa5 0x80 > > 3: 146795292 188742708 0xa5 0x00 > >=20 > What about "dd if=3D/dev/zero of=3D/dev/ad4s3 oseek=3D188742707"? >=20 > What does "gmirror status" say? > I would remove the gmirror-s with "gmirror remove " = (its > easier than dd)... If there is a gmirror configured on adXs3, I'd suggest doing: # gmirror stop # gmirror clear adXs3 --=20 Pawel Jakub Dawidek http://www.wheel.pl pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --nVMJ2NtxeReIH9PS Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (FreeBSD) iD8DBQFFotjUForvXbEpPzQRAhSPAKCdIN1cmY1RPob/UIVO3k7TwMmN/gCg+Yvc ZbQMT52MPKPI0he6HRM7xv8= =anne -----END PGP SIGNATURE----- --nVMJ2NtxeReIH9PS-- From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 00:25:01 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id D4E9D16A403 for ; Tue, 9 Jan 2007 00:25:01 +0000 (UTC) (envelope-from gpalmer@freebsd.org) Received: from noop.in-addr.com (noop.in-addr.com [208.58.23.51]) by mx1.freebsd.org (Postfix) with ESMTP id 9908A13C442 for ; Tue, 9 Jan 2007 00:25:01 +0000 (UTC) (envelope-from gpalmer@freebsd.org) Received: from gjp by noop.in-addr.com with local (Exim 4.54 (FreeBSD)) id 1H44dR-000MF9-Vh; Mon, 08 Jan 2007 19:14:37 -0500 Date: Mon, 8 Jan 2007 19:14:37 -0500 From: Gary Palmer To: Fernan Aguero Message-ID: <20070109001437.GC97624@in-addr.com> Mail-Followup-To: Fernan Aguero , geom@freebsd.org References: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> Cc: geom@freebsd.org Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 00:25:01 -0000 On Mon, Jan 08, 2007 at 07:45:06PM -0300, Fernan Aguero wrote: > Hi > > I'm trying to set up two disks to contain both gmirrored and gstriped > slices. > > This is what I'm trying to achieve: > adxs1, swap > adxs2, gmirror > adxs3, gstripe > > I already got the first and second slices set up (swap and gmirror > containing > the active, root partition), but I cannot seem to be able to set up s3 into > a > gstripped device. > > gama# gstripe label -v gs0 /dev/ad4s3 /dev/ad6s3 > Can't store metadata on /dev/ad4s3: Operation not permitted. > > This might be because ad4s3 had been part of a gmirror device before I > reorganized my disks and moved the mirror to the s2 slice. > > Gayn Winters suggested that: > "The geom metadata is stored in the last block of the slice. Zero it as > well and you can have a clean start." > http://lists.freebsd.org/pipermail/freebsd-questions/2006-May/120950.html > > But now I wonder what is the magic incantation to run dd for targeting the > last > (sector?) of ad4s3? Any reason that "gstripe clear" or "gmirror clear" doesn't work? Thats what they're meant to do, as far as I know. From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 01:43:42 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 9E81916A40F for ; Tue, 9 Jan 2007 01:43:42 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: from nz-out-0506.google.com (nz-out-0506.google.com [64.233.162.233]) by mx1.freebsd.org (Postfix) with ESMTP id 5FF9E13C441 for ; Tue, 9 Jan 2007 01:43:42 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: by nz-out-0506.google.com with SMTP id i11so3782497nzh for ; Mon, 08 Jan 2007 17:43:39 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=qH+EhFMlDDQPRzR1j+olTP7KcUBv3v9yvoZAeDcEwtw+ks4GJ7mn/O0jigqql00eMzpQvLLSxwEyA2xf2UR3IXkLKj8YYAp278AISpTuMUU79bzS9QmlLZ75XaZczDkxih4AeGbYB4/lX22dMiYqlxYqto7FlFmKDAJAc7RHBCE= Received: by 10.35.27.2 with SMTP id e2mr49957994pyj.1168307019760; Mon, 08 Jan 2007 17:43:39 -0800 (PST) Received: by 10.35.16.1 with HTTP; Mon, 8 Jan 2007 17:43:39 -0800 (PST) Message-ID: <520894aa0701081743y49420d19u543e46edf7d61e79@mail.gmail.com> Date: Mon, 8 Jan 2007 22:43:39 -0300 From: "Fernan Aguero" To: "R. B. Riddick" In-Reply-To: <20070108231751.78304.qmail@web30310.mail.mud.yahoo.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> <20070108231751.78304.qmail@web30310.mail.mud.yahoo.com> Cc: geom@freebsd.org Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 01:43:42 -0000 On 1/8/07, R. B. Riddick wrote: > --- Fernan Aguero wrote: > > I imagine I have to use something like > > dd if=/dev/zero of=/dev/ad4s3? bs=512 count=1 > > > > but adding either skip=? or seek=? to taste. > > > > gama# fdisk -s /dev/ad4 > > /dev/ad4: 310101 cyl 16 hd 63 sec > > Part Start Size Type Flags > > 1: 63 16771041 0xa5 0x00 > > 2: 16771923 146795229 0xa5 0x80 > > 3: 146795292 188742708 0xa5 0x00 > > > What about "dd if=/dev/zero of=/dev/ad4s3 oseek=188742707"? gama# dd if=/dev/zero of=/dev/ad4s3 oseek=188742707 dd: /dev/ad4s3: Operation not permitted gama# whoami root > What does "gmirror status" say? gama# gmirror status Name Status Components mirror/gm0 COMPLETE ad4s2 ad6s2 As I said, I had (past time) a mirror on ad4s3/ad6s3, but I decided to resize s2 and s3, so I removed ad6s3 from the mirror, reformatted ad6 (dd bs=512 count=79 only) and moved all data in ad4s3 to it, but this time I put the active 'a' partition in the s2 slice. After doing this I rebooted mounting the root fs from ad6s2a and then I removed ad4s3 from the mirror and did the same reformatting with ad4. > I would remove the gmirror-s with "gmirror remove " (its > easier than dd)... IIRC this is what I did. -- Fernan Aguero From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 02:08:43 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 37FBE16A403 for ; Tue, 9 Jan 2007 02:08:43 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: from py-out-1112.google.com (py-out-1112.google.com [64.233.166.176]) by mx1.freebsd.org (Postfix) with ESMTP id EBE3D13C458 for ; Tue, 9 Jan 2007 02:08:42 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: by py-out-1112.google.com with SMTP id f31so4155737pyh for ; Mon, 08 Jan 2007 18:08:42 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=P5fk9gApXde0hmVFvFelWmgL6k+BgKzn3b8Oi9Icaf4JuhogkmfwVYC9xM1L7F4cBbvUK8UhXYBT3aLllgSu4jYkL5PBsuRnKrRbgJ6TaAt9AnttZXrCs0TCJ/WveIGJovL/oxrUIDA/xTfKYqbG0IiZgao365UAivd1SKDK9X8= Received: by 10.35.75.1 with SMTP id c1mr50028263pyl.1168308522188; Mon, 08 Jan 2007 18:08:42 -0800 (PST) Received: by 10.35.16.1 with HTTP; Mon, 8 Jan 2007 18:08:42 -0800 (PST) Message-ID: <520894aa0701081808k224709dbi3f36f0c1a703a70e@mail.gmail.com> Date: Mon, 8 Jan 2007 23:08:42 -0300 From: "Fernan Aguero" To: "Pawel Jakub Dawidek" In-Reply-To: <20070108235044.GB5165@garage.freebsd.pl> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> <20070108231751.78304.qmail@web30310.mail.mud.yahoo.com> <20070108235044.GB5165@garage.freebsd.pl> Cc: geom@freebsd.org, "R. B. Riddick" Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 02:08:43 -0000 On 1/8/07, Pawel Jakub Dawidek wrote: > On Mon, Jan 08, 2007 at 03:17:51PM -0800, R. B. Riddick wrote: > > --- Fernan Aguero wrote: > > > I imagine I have to use something like > > > dd if=/dev/zero of=/dev/ad4s3? bs=512 count=1 > > > > > > but adding either skip=? or seek=? to taste. > > > > > > gama# fdisk -s /dev/ad4 > > > /dev/ad4: 310101 cyl 16 hd 63 sec > > > Part Start Size Type Flags > > > 1: 63 16771041 0xa5 0x00 > > > 2: 16771923 146795229 0xa5 0x80 > > > 3: 146795292 188742708 0xa5 0x00 > > > > > What about "dd if=/dev/zero of=/dev/ad4s3 oseek=188742707"? > > > > What does "gmirror status" say? > > I would remove the gmirror-s with "gmirror remove " (its > > easier than dd)... > > If there is a gmirror configured on adXs3, I'd suggest doing: No, there's no mirror in adXs3 now ... there *was* a mirror on that slice before ... but ... I didn't zero the whole disk before reorganizing the slices and partitions, I resized s2 and s3, thus erasing the metadata on the old s2 slice (gstripe), but of course, this didn't affect the last sector of the last slice ... which is still there :) > # gmirror stop > # gmirror clear adXs3 I can't stop the gm0 mirror now, cause the root partition is mounted from it now. But although it doesn't have adXs3 listed as a consumer, I can why perhaps the fact that gmirror is loaded and running might be preventing operations that alter metadata (the old gmirror device was also named gm0 ... is this stored in the metadata and checked?) gama# gmirror status Name Status Components mirror/gm0 COMPLETE ad4s2 ad6s2 gama# gmirror clear ad4s3 Can't clear metadata on ad4s3: Operation not permitted. Not fully done. IIRC, I did gmirror remove gm0 ad4s3 before turning to reformat ad4 ... and according to gmirror(8): remove Remove the given component(s) from the mirror and clear meta-data on it. Now, what if I boot from ad6s2a (remove geom_gmirror_load="YES" from loader.conf, and change my fstab accordingly so that there's nothing 'active' or 'loaded') and try to clear ad4s3 again now? Fernan -- Fernan Aguero From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 02:13:16 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id BC24416A592 for ; Tue, 9 Jan 2007 02:13:16 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: from nz-out-0506.google.com (nz-out-0506.google.com [64.233.162.231]) by mx1.freebsd.org (Postfix) with ESMTP id 7E26613C448 for ; Tue, 9 Jan 2007 02:13:16 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: by nz-out-0506.google.com with SMTP id i11so3787633nzh for ; Mon, 08 Jan 2007 18:13:15 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=E1pc+hYX0r8zN8W2D6X6yG6xZs6DVj+sfanQdVchrj7R44bLpMj9r5kQBSzmcF7AJWLK+TzQ/ijIKTVkwp1gbU2UD5DE3dhO2hebLpQs7mHXhYuqgHLZSSU4AhggLcrv0kx+WRefpH45pKPsmXblNm0yQb45Ec82kg2OTEkSzLA= Received: by 10.35.60.15 with SMTP id n15mr50051772pyk.1168308795980; Mon, 08 Jan 2007 18:13:15 -0800 (PST) Received: by 10.35.16.1 with HTTP; Mon, 8 Jan 2007 18:13:15 -0800 (PST) Message-ID: <520894aa0701081813x3925b7f1r278785bb01f4232@mail.gmail.com> Date: Mon, 8 Jan 2007 23:13:15 -0300 From: "Fernan Aguero" To: "Fernan Aguero" , geom@freebsd.org In-Reply-To: <20070109001437.GC97624@in-addr.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> <20070109001437.GC97624@in-addr.com> Cc: Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 02:13:16 -0000 On 1/8/07, Gary Palmer wrote: > On Mon, Jan 08, 2007 at 07:45:06PM -0300, Fernan Aguero wrote: [snipped] > > gama# gstripe label -v gs0 /dev/ad4s3 /dev/ad6s3 > > Can't store metadata on /dev/ad4s3: Operation not permitted. > > > > This might be because ad4s3 had been part of a gmirror device before I > > reorganized my disks and moved the mirror to the s2 slice. [snipped] > Any reason that "gstripe clear" or "gmirror clear" doesn't work? Thats what > they're meant to do, as far as I know. because ad4s3 is no longer part of gm0? -- Fernan Aguero From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 02:27:48 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id C75C916A415 for ; Tue, 9 Jan 2007 02:27:48 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: from nz-out-0506.google.com (nz-out-0506.google.com [64.233.162.224]) by mx1.freebsd.org (Postfix) with ESMTP id 86BE413C44B for ; Tue, 9 Jan 2007 02:27:48 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: by nz-out-0506.google.com with SMTP id i11so3789891nzh for ; Mon, 08 Jan 2007 18:27:47 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=Zx7VoSFxDLtL5fjV+mUj8V8B2QO9KqeDk2+qa4FDTnjr4CP9LOqs5ftQG9N+aAOIqT6FqSvEKowky8VBbnwAcqMDmzgc9CNrPWk/SRFGjppmsTSf2GaUKbsvkuHnuUqlMKOLmzOE+V68P2HRgINIJDho0p7XLbNFodY8uggE3k8= Received: by 10.35.93.1 with SMTP id v1mr50095592pyl.1168309667766; Mon, 08 Jan 2007 18:27:47 -0800 (PST) Received: by 10.35.16.1 with HTTP; Mon, 8 Jan 2007 18:27:47 -0800 (PST) Message-ID: <520894aa0701081827i6bdc3428rbe104f12c3dbc542@mail.gmail.com> Date: Mon, 8 Jan 2007 23:27:47 -0300 From: "Fernan Aguero" To: "Pawel Jakub Dawidek" In-Reply-To: <520894aa0701081808k224709dbi3f36f0c1a703a70e@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> <20070108231751.78304.qmail@web30310.mail.mud.yahoo.com> <20070108235044.GB5165@garage.freebsd.pl> <520894aa0701081808k224709dbi3f36f0c1a703a70e@mail.gmail.com> Cc: geom@freebsd.org, "R. B. Riddick" Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 02:27:48 -0000 On 1/8/07, Fernan Aguero wrote: > > # gmirror stop > > # gmirror clear adXs3 > > I can't stop the gm0 mirror now, cause the root partition is mounted > from it now. But although it doesn't have adXs3 listed as a consumer, I can *see* (verb missing in my previous post) why perhaps > the fact that gmirror is loaded and running might be preventing operations that > alter metadata (the old gmirror device was also named gm0 ... is this stored in > the metadata and checked?) And no, I didn't specify that providers info should be hardcoded into the metadata (AFAIK, at least). -- Fernan Aguero From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 03:57:16 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 397DE16A403 for ; Tue, 9 Jan 2007 03:57:16 +0000 (UTC) (envelope-from ahnjoan@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.172]) by mx1.freebsd.org (Postfix) with ESMTP id C880313C43E for ; Tue, 9 Jan 2007 03:57:15 +0000 (UTC) (envelope-from ahnjoan@gmail.com) Received: by ug-out-1314.google.com with SMTP id o2so5743653uge for ; Mon, 08 Jan 2007 19:57:14 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=YUucRxxogA2tUHS0msiHWhB25JvjehX/xMyvP9yDx9gU1E5FTLvvePSeHVXJdmWzM/Ah5ZFCIvbWmt4RPNwHMPltL1/W1FME7QVpUQpx0T6kX81hkU0tA+wTe3S3VFPwMYALjSZhOdB23Bu+LlClPTLHiAhKoAwGBGBCwCLhLGI= Received: by 10.78.203.13 with SMTP id a13mr4364822hug.1168315034555; Mon, 08 Jan 2007 19:57:14 -0800 (PST) Received: by 10.78.11.6 with HTTP; Mon, 8 Jan 2007 19:57:14 -0800 (PST) Message-ID: <5e575c8a0701081957k43483e1ewf9b27022ae330d8a@mail.gmail.com> Date: Mon, 8 Jan 2007 22:57:14 -0500 From: "Ahnjoan Amous" To: freebsd-geom@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=WINDOWS-1252; format=flowed Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Subject: GEOM mirror performance - slow X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 03:57:16 -0000 I'm sorry about the double posting, I have switch e-mail clients and hope that the text is now understandable. While deploying 6.1-RELEASE I'm seeing slower than expected speed using geom mirror. Test 1. Outside of GEOM I'm able to write to both aacd2 and aacd3 concurrently and achieve between 41M =96 45M a second write speeds. (around 75M a second if I run the commands separately) Test 2. Inside a GEOM container but not mirrored (aacd2 =3D gm2, aacd3 =3D gm3) I'm able to write to both gm2 and gm3 concurrently and achieve between 40M =96 49M a second write speeds. (around 75M a second if I run the commands separately) Test 3. Inside a GEOM mirror (gm1 =3D aacd2 =3D aacd3) I'm able to achieve 23M a second. I'd love someones opinion as to if the speed I'm seeing using GEOM mirror is to be expected. FYI =96 The mirror was manually rebuilt and COMPLETE before tests were attempted on the mirror. *********************************************************************** *** Test 1. *** dd to devices mounted outside of geom > dd if=3D/dev/zero of=3D/data02/helloworld bs=3D8k count=3D100k & > dd if=3D/dev/zero of=3D/data03/helloworld bs=3D8k count=3D100k & 838860800 bytes transferred in 18.799345 secs (44621810 bytes/sec) ^^^^^^^^ 838860800 bytes transferred in 18.544963 secs (45233889 bytes/sec) ^^^^^^^^ > dd if=3D/dev/zero of=3D/data02/helloworld bs=3D1m count=3D800 & > dd if=3D/dev/zero of=3D/data03/helloworld bs=3D1m count=3D800 & 838860800 bytes transferred in 20.014247 secs (41913183 bytes/sec) ^^^^^^^^ 838860800 bytes transferred in 19.824656 secs (42314016 bytes/sec) ^^^^^^^^ **** setup info for test **** > df -k /dev/aacd2s1e 2026030 819620 1044328 44% /data02 /dev/aacd3s1e 2026030 819620 1044328 44% /data03 *********************************************************************** *** Test 2. *** dd to devices mounted as their own geom volumes > dd if=3D/dev/zero of=3D/data02/helloworld bs=3D8k count=3D100k & > dd if=3D/dev/zero of=3D/data03/helloworld bs=3D8k count=3D100k & 838860800 bytes transferred in 17.118679 secs (49002659 bytes/sec) ^^^^^^^^ 838860800 bytes transferred in 16.810787 secs (49900150 bytes/sec) ^^^^^^^^ > dd if=3D/dev/zero of=3D/data02/helloworld bs=3D1m count=3D800 & > dd if=3D/dev/zero of=3D/data03/helloworld bs=3D1m count=3D800 & 838860800 bytes transferred in 20.907455 secs (40122569 bytes/sec) ^^^^^^^^ 838860800 bytes transferred in 20.638277 secs (40645874 bytes/sec) ^^^^^^^^ **** setup info for test **** > df -k /dev/mirror/gm2 2026030 819620 1044328 44% /data02 /dev/mirror/gm3 2026030 819620 1044328 44% /data03 > gmirror list Geom name: gm2 1. Name: aacd2s1e Geom name: gm3 1. Name: aacd3s1e *********************************************************************** *** Test 3. *** dd to devices mounted as a geom mirror > dd if=3D/dev/zero of=3D/data01/helloworld bs=3D8k count=3D100k 838860800 bytes transferred in 35.622392 secs (23548694 bytes/sec) ^^^^^^^^ > dd if=3D/dev/zero of=3D/data01/helloworld bs=3D1m count=3D800 838860800 bytes transferred in 35.588491 secs (23571126 bytes/sec) ^^^^^^^^ **** setup info for test **** > df -k /dev/mirror/gm1 2026028 819620 1044326 44% /data01 > gmirror list Geom name: gm1 1. Name: aacd2s1e 2. Name: aacd3s1e From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 08:39:22 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 9F62B16A47C for ; Tue, 9 Jan 2007 08:39:22 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (arm132.internetdsl.tpnet.pl [83.17.198.132]) by mx1.freebsd.org (Postfix) with ESMTP id 42DEA13C461 for ; Tue, 9 Jan 2007 08:39:21 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id ED87A48803; Tue, 9 Jan 2007 09:39:19 +0100 (CET) Received: from localhost (pjd.wheel.pl [10.0.1.1]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id 11241487FD; Tue, 9 Jan 2007 09:39:14 +0100 (CET) Date: Tue, 9 Jan 2007 09:38:46 +0100 From: Pawel Jakub Dawidek To: Fernan Aguero Message-ID: <20070109083846.GA62430@garage.freebsd.pl> References: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> <20070109001437.GC97624@in-addr.com> <520894aa0701081813x3925b7f1r278785bb01f4232@mail.gmail.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="PNTmBPCT7hxwcZjr" Content-Disposition: inline In-Reply-To: <520894aa0701081813x3925b7f1r278785bb01f4232@mail.gmail.com> X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 7.0-CURRENT i386 User-Agent: mutt-ng/devel-r804 (FreeBSD) X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-5.9 required=3.0 tests=ALL_TRUSTED,BAYES_00 autolearn=ham version=3.0.4 Cc: geom@freebsd.org Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 08:39:22 -0000 --PNTmBPCT7hxwcZjr Content-Type: text/plain; charset=iso-8859-2 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Jan 08, 2007 at 11:13:15PM -0300, Fernan Aguero wrote: > On 1/8/07, Gary Palmer wrote: > >On Mon, Jan 08, 2007 at 07:45:06PM -0300, Fernan Aguero wrote: >=20 > [snipped] >=20 > >> gama# gstripe label -v gs0 /dev/ad4s3 /dev/ad6s3 > >> Can't store metadata on /dev/ad4s3: Operation not permitted. > >> > >> This might be because ad4s3 had been part of a gmirror device before I > >> reorganized my disks and moved the mirror to the s2 slice. >=20 > [snipped] >=20 > >Any reason that "gstripe clear" or "gmirror clear" doesn't work? Thats = what > >they're meant to do, as far as I know. >=20 > because ad4s3 is no longer part of gm0? You get "Operation not permitted." because someone already keep ad4s3 open for writing. Could you send output of 'sysctl -b kern.geom.confxml' so we can find out who? --=20 Pawel Jakub Dawidek http://www.wheel.pl pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --PNTmBPCT7hxwcZjr Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (FreeBSD) iD8DBQFFo1SWForvXbEpPzQRAl5kAKChuaa898+8rDeofMJS+QBSWCIydQCfRJy/ pUB6ObC9jDJaHUcv4MqI7Zk= =A7ig -----END PGP SIGNATURE----- --PNTmBPCT7hxwcZjr-- From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 10:12:22 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 1A33B16A40F for ; Tue, 9 Jan 2007 10:12:22 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (arm132.internetdsl.tpnet.pl [83.17.198.132]) by mx1.freebsd.org (Postfix) with ESMTP id 9E92413C461 for ; Tue, 9 Jan 2007 10:12:20 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id 593E248813; Tue, 9 Jan 2007 11:12:19 +0100 (CET) Received: from localhost (pjd.wheel.pl [10.0.1.1]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id 1DC2F45CD9; Tue, 9 Jan 2007 11:12:13 +0100 (CET) Date: Tue, 9 Jan 2007 11:11:45 +0100 From: Pawel Jakub Dawidek To: Ahnjoan Amous Message-ID: <20070109101144.GB62430@garage.freebsd.pl> References: <5e575c8a0701081957k43483e1ewf9b27022ae330d8a@mail.gmail.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="kORqDWCi7qDJ0mEj" Content-Disposition: inline In-Reply-To: <5e575c8a0701081957k43483e1ewf9b27022ae330d8a@mail.gmail.com> X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 7.0-CURRENT i386 User-Agent: mutt-ng/devel-r804 (FreeBSD) X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-5.9 required=3.0 tests=ALL_TRUSTED,BAYES_00 autolearn=ham version=3.0.4 Cc: freebsd-geom@freebsd.org Subject: Re: GEOM mirror performance - slow X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 10:12:22 -0000 --kORqDWCi7qDJ0mEj Content-Type: text/plain; charset=iso-8859-2 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Jan 08, 2007 at 10:57:14PM -0500, Ahnjoan Amous wrote: > I'm sorry about the double posting, I have switch e-mail clients and > hope that the text is now understandable. >=20 > While deploying 6.1-RELEASE I'm seeing slower than expected speed > using geom mirror. [...] Hard to say, really. It depends on many factors. On my test system: # dd if=3D/dev/zero of=3D/dev/ad4d bs=3D1m count=3D1000 &; dd if=3D/dev/ze= ro of=3D/dev/ad6d bs=3D1m count=3D1000 ad4d: 64.27MB/s ad6d: 61.49MB/s # gmirror label foo ad4d ad6d # dd if=3D/dev/zero of=3D/dev/mirror/foo bs=3D1m count=3D1000 mirror/foo: 61.26MB/s BUT disks can somehow interfere with each other (are on the same ATA channel, etc.). On this system I've this setup: ATA channel 2: Master: ad4 Serial ATA II Slave: ad5 Serial ATA II ATA channel 3: Master: ad6 Serial ATA II Slave: no device present As you saw above, I was using ad4 and ad6, which are on different ATA channels. When I do the same experiment for ad4 and ad5 I see worser results: # dd if=3D/dev/zero of=3D/dev/ad4d bs=3D1m count=3D1000 &; dd if=3D/dev/ze= ro of=3D/dev/ad5d bs=3D1m count=3D1000 ad4d: 59.55MB/s ad5d: 59.31MB/s # gmirror label foo ad4d ad5d # dd if=3D/dev/zero of=3D/dev/mirror/foo bs=3D1m count=3D1000 mirror/foo: 49.03MB/s So not ~40% slowdown as in your case, but still visible slowdown (~20%). --=20 Pawel Jakub Dawidek http://www.wheel.pl pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --kORqDWCi7qDJ0mEj Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (FreeBSD) iD8DBQFFo2pgForvXbEpPzQRAggTAJkB6etmnIJAegMbUgzs3omkJDmfLwCg3/3B St3K0GtfxPlKMNXoDMUBy1s= =5+aw -----END PGP SIGNATURE----- --kORqDWCi7qDJ0mEj-- From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 10:22:50 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id DD60316A415 for ; Tue, 9 Jan 2007 10:22:50 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30314.mail.mud.yahoo.com (web30314.mail.mud.yahoo.com [209.191.69.76]) by mx1.freebsd.org (Postfix) with SMTP id 8DABF13C448 for ; Tue, 9 Jan 2007 10:22:50 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 74405 invoked by uid 60001); 9 Jan 2007 10:22:49 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=ApqrD2j95EGJfrt/RlZyzo2Oy4kF6sSdNS69FdRHz6j/VCvAvxM4PlBs0xeMu0PCrtFYJuAQki+s/0Z0EEuIPRmtNcV78SbRsgeC988rPGKUy0z51+WE0X/WbbayoGACBsDEQT4EXVF4kUwOaQ05aIwTSe3/E9NM+/5ZKRsJ3WE=; X-YMail-OSG: PiyU5HwVM1nbkFAnh0d4bFxTRiFCN7xByE95ki3sqYHvFNCNluj33iBSeg9jOQw_cLQxjo5mk7GBSaWVD8DwGqulTKD9eC5Ch_l3bTPd58K907Y4Y0Cm7oCu3VddwoHh8IRPbc1wFEI- Received: from [213.54.167.25] by web30314.mail.mud.yahoo.com via HTTP; Tue, 09 Jan 2007 02:22:49 PST Date: Tue, 9 Jan 2007 02:22:49 -0800 (PST) From: "R. B. Riddick" To: Pawel Jakub Dawidek , Ahnjoan Amous In-Reply-To: <20070109101144.GB62430@garage.freebsd.pl> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <713924.74108.qm@web30314.mail.mud.yahoo.com> Cc: freebsd-geom@freebsd.org Subject: Re: GEOM mirror performance - slow X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 10:22:51 -0000 --- Pawel Jakub Dawidek wrote: > On Mon, Jan 08, 2007 at 10:57:14PM -0500, Ahnjoan Amous wrote: > > I'm sorry about the double posting, I have switch e-mail clients and > > hope that the text is now understandable. > > > > While deploying 6.1-RELEASE I'm seeing slower than expected speed > > using geom mirror. > [...] > > So not ~40% slowdown as in your case, but still visible slowdown (~20%). > I have a theory now (when I read it first I was completely puzzled about this): (aa) Since gmirror issues the write requests nearly at the same time, and (bb) since gmirror has to wait for the completion of BOTH requests, and (cc) since the two dd processes are not coupled, (dd) we see here the effects of synchronization and bus/controller contention. In your case (Ahnjoan) this effect is worse (lower DMA mode? older controller?) than in yours (Pawel). Thanks. -Arne __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 10:41:12 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id E2E9716A403 for ; Tue, 9 Jan 2007 10:41:12 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30308.mail.mud.yahoo.com (web30308.mail.mud.yahoo.com [209.191.69.70]) by mx1.freebsd.org (Postfix) with SMTP id 9392B13C478 for ; Tue, 9 Jan 2007 10:41:10 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 51676 invoked by uid 60001); 9 Jan 2007 10:41:10 -0000 Message-ID: <20070109104110.51674.qmail@web30308.mail.mud.yahoo.com> DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=oRUWFzO/JAULU/TjlP0429sNbaBjHxOPEg9zTGWM2knG8OW4U01nAjyP5ZZXe9WUhgWv6QNwVfOQ5+L7bYXg9B4bQDDXBzZ1TvSBOYA+pzelEc7HokVY6dH1D/dUrWgQF1RuoL7AWRCp1oZb9NSIkA6zsF90A6KCmpiyDktzt30=; X-YMail-OSG: hoDkfJsVM1njAW7YsGA9eRVsDD9a9iIeOC9M3NEnFfraeUvWXO67BVuKw60D0kGwOftHLNN15hcp9nCsbrmY3sUuLxTQn80N1gpsHfBaIbLNK1Munt8x2qiQ_X9T94uuvwFQRboeuOY- Received: from [213.54.167.25] by web30308.mail.mud.yahoo.com via HTTP; Tue, 09 Jan 2007 02:41:09 PST Date: Tue, 9 Jan 2007 02:41:09 -0800 (PST) From: "R. B. Riddick" To: Pawel Jakub Dawidek MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Cc: freebsd-geom@freebsd.org Subject: Re: Recommended gmirror solution with swap? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 10:41:13 -0000 For the stability test of a gmirror/graid5 device under regular request load with a sudden disk failure I wrote 2 shell scripts (the one for gmirror crashes the device after some cycles, while the one for graid5 does crash (so quickly)). while [ 1 ] ;do gnop configure -f 0 ad0s1gd.nop echo good gmirror forget fook gmirror insert -h fook ad0s1gd.nop while [ `gmirror status fook | grep -c COMPLETE` -eq 0 ]; do sleep 1 done gnop configure -f 100 ad0s1gd.nop echo fail while [ `gmirror status fook | grep -c COMPLETE` -ne 0 ]; do gmirror status fook sleep 1 done done while [ 1 ] ;do gnop configure -f 0 ad0s1gd.nop echo good graid5 configure -a fook while [ `graid5 status fook | grep -c COMPLETE` -eq 0 ]; do sleep 1 done gnop configure -f 100 ad0s1gd.nop echo fail while [ `graid5 status fook | grep -c COMPLETE` -ne 0 ]; do graid5 status fook sleep 1 done done -Arne __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 12:39:44 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id C941816A416; Tue, 9 Jan 2007 12:39:44 +0000 (UTC) (envelope-from etc@fluffles.net) Received: from auriate.fluffles.net (cust.95.160.adsl.cistron.nl [195.64.95.160]) by mx1.freebsd.org (Postfix) with ESMTP id 7C9D513C46C; Tue, 9 Jan 2007 12:39:44 +0000 (UTC) (envelope-from etc@fluffles.net) Received: from destiny ([10.0.0.21]) by auriate.fluffles.net with esmtpa (Exim 4.63 (FreeBSD)) (envelope-from ) id 1H4GGR-0002lu-7h; Tue, 09 Jan 2007 13:39:39 +0100 Message-ID: <45A38D38.3020407@fluffles.net> Date: Tue, 09 Jan 2007 13:40:24 +0100 From: Fluffles User-Agent: Thunderbird 1.5.0.8 (X11/20061114) MIME-Version: 1.0 To: freebsd-geom@freebsd.org, freebsd-fs@freebsd.org Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: 7bit Cc: Subject: Capturing I/O traces X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 12:39:44 -0000 Hello list, I was wondering if any method is known to "capture" I/O traces. My goal is to be able to simulate I/O access patterns generated by applications such as MySQL or KDE and compare these to other storage systems. This way i can provide more realistic benchmarks (not synthetic) without actually running the application i'm testing. For example, I would like to capture the I/O that occurs when KDE boots, and then be able to reproduce this I/O access on say a gmirror and graid3. This way i can gather more realistic benchmark results. On Windows several commercial applications exist that 'simulate' access patterns used by applications, i was wondering if any BSD/Linux equivalent exists. One thought that comes to mind is the gnop geom class; with verbose mode this provides a text log of all the I/O accesses. But it does not provide the exact time/concurrency etc, only the offset, length, I/O action (read/write) and the serial order of those requests. And even with this information it's not easy to reproduce them; i would have to write an application that reads this log and then be able to reproduce it. I was hoping to find a more elegant solution. If you guys know of any, please share it with me. :) Regards, Veronica From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 13:11:42 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 6DAFB16A403 for ; Tue, 9 Jan 2007 13:11:42 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.freebsd.org (Postfix) with ESMTP id 2971D13C455 for ; Tue, 9 Jan 2007 13:11:41 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1H4GlI-0002V1-E9 for freebsd-geom@freebsd.org; Tue, 09 Jan 2007 14:11:32 +0100 Received: from lara.cc.fer.hr ([161.53.72.113]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Tue, 09 Jan 2007 14:11:32 +0100 Received: from ivoras by lara.cc.fer.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Tue, 09 Jan 2007 14:11:32 +0100 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-geom@freebsd.org From: Ivan Voras Date: Tue, 09 Jan 2007 14:11:22 +0100 Lines: 22 Message-ID: References: <45A38D38.3020407@fluffles.net> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: lara.cc.fer.hr User-Agent: Thunderbird 1.5.0.4 (X11/20060625) In-Reply-To: <45A38D38.3020407@fluffles.net> Sender: news Cc: freebsd-fs@freebsd.org Subject: Re: Capturing I/O traces X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 13:11:42 -0000 Fluffles wrote: > One thought that comes to mind is the gnop geom class; with verbose mode > this provides a text log of all the I/O accesses. But it does not > provide the exact time/concurrency etc, only the offset, length, I/O What do you mean by "time" and "concurrency"? You do realize that requests are serialized on the low level? > action (read/write) and the serial order of those requests. And even You mean when the request was actually completed? Hmmm, it shouldn't be hard to add... > with this information it's not easy to reproduce them; i would have to > write an application that reads this log and then be able to reproduce > it. I was hoping to find a more elegant solution. If you guys know of > any, please share it with me. :) Once upon a time I patched ggatel to generate a log (without the time of completion). Here it is: http://ivoras.sharanet.org/freebsd/ggatel.tgz (but IIRC that was for early 6-stable, don't know if it would work now). From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 13:20:30 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 6501216A412; Tue, 9 Jan 2007 13:20:30 +0000 (UTC) (envelope-from etc@fluffles.net) Received: from auriate.fluffles.net (cust.95.160.adsl.cistron.nl [195.64.95.160]) by mx1.freebsd.org (Postfix) with ESMTP id BAAA213C467; Tue, 9 Jan 2007 13:20:29 +0000 (UTC) (envelope-from etc@fluffles.net) Received: from destiny ([10.0.0.21]) by auriate.fluffles.net with esmtpa (Exim 4.63 (FreeBSD)) (envelope-from ) id 1H4Gts-00052F-Ob; Tue, 09 Jan 2007 14:20:24 +0100 Message-ID: <45A396C5.2000908@fluffles.net> Date: Tue, 09 Jan 2007 14:21:09 +0100 From: Fluffles User-Agent: Thunderbird 1.5.0.8 (X11/20061114) MIME-Version: 1.0 To: Ivan Voras References: <45A38D38.3020407@fluffles.net> In-Reply-To: Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org, freebsd-geom@freebsd.org Subject: Re: Capturing I/O traces X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 13:20:30 -0000 Ivan Voras wrote: > Fluffles wrote: > > >> One thought that comes to mind is the gnop geom class; with verbose mode >> this provides a text log of all the I/O accesses. But it does not >> provide the exact time/concurrency etc, only the offset, length, I/O >> > > What do you mean by "time" and "concurrency"? You do realize that > requests are serialized on the low level? > Sure but simply capturing the serial order of requests might not be sufficient. For example: the application might 'wait' for one request to be finished because it needs that data in order to do another I/O request. I guess this is the hard part. If i would just execute the I/O in a serial way things like accesstime or 'latency' are less important because the overall throughput counts; while this may not be true for real applications but they might wait on one request before they can move on; thus a lower latency might be more important than a higher throughput. I guess it's not easy to really make something like this be reliable and realistic, but i'd like to come as close as possible. For example, the website StorageReview also uses traces to benchmark specific uses, two links: http://www.storagereview.com/articles/200611/ST3750640NS_3.html http://www.storagereview.com/articles/200510/Testbed4_4.html I'd like to use traces of applications on FreeBSD (or GNU/Linux) to benchmark KDE startup, MySQL, Apache and other applications. So i can have benchmark suites like "desktop", "webserver" and "database". That would be very neat. From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 13:24:05 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 6B66116A415 for ; Tue, 9 Jan 2007 13:24:05 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: from nz-out-0506.google.com (nz-out-0506.google.com [64.233.162.239]) by mx1.freebsd.org (Postfix) with ESMTP id 2C8C313C468 for ; Tue, 9 Jan 2007 13:24:05 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: by nz-out-0506.google.com with SMTP id i11so3887872nzh for ; Tue, 09 Jan 2007 05:24:04 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=GijVPiG6dGr2PBe4ZG6UceU2FULXZUYEJTykZXHd5VFTO1WtOG0yQ+rKxgX1uGytgOzfIJJzuJepq24IVji9wQT4/nXbWJrBScN0NY9OVi3musiQS3A/hKAJbjUI2c/02PGvf3Rm+z4aM9YE8IZCXcLsDlHzpX25eRoBK4GOmlc= Received: by 10.35.10.17 with SMTP id n17mr31282254pyi.1168349044713; Tue, 09 Jan 2007 05:24:04 -0800 (PST) Received: by 10.35.16.1 with HTTP; Tue, 9 Jan 2007 05:24:04 -0800 (PST) Message-ID: <520894aa0701090524t217a36ecje1cf7b40d8a2a7e0@mail.gmail.com> Date: Tue, 9 Jan 2007 10:24:04 -0300 From: "Fernan Aguero" To: "Pawel Jakub Dawidek" In-Reply-To: <20070109083846.GA62430@garage.freebsd.pl> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> <20070109001437.GC97624@in-addr.com> <520894aa0701081813x3925b7f1r278785bb01f4232@mail.gmail.com> <20070109083846.GA62430@garage.freebsd.pl> Cc: geom@freebsd.org Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 13:24:05 -0000 On 1/9/07, Pawel Jakub Dawidek wrote: > On Mon, Jan 08, 2007 at 11:13:15PM -0300, Fernan Aguero wrote: > > On 1/8/07, Gary Palmer wrote: > > >On Mon, Jan 08, 2007 at 07:45:06PM -0300, Fernan Aguero wrote: > > > > [snipped] > > > > >> gama# gstripe label -v gs0 /dev/ad4s3 /dev/ad6s3 > > >> Can't store metadata on /dev/ad4s3: Operation not permitted. > > >> > > >> This might be because ad4s3 had been part of a gmirror device before I > > >> reorganized my disks and moved the mirror to the s2 slice. > > > > [snipped] > > > > >Any reason that "gstripe clear" or "gmirror clear" doesn't work? Thats what > > >they're meant to do, as far as I know. > > > > because ad4s3 is no longer part of gm0? > > You get "Operation not permitted." because someone already keep ad4s3 > open for writing. Could you send output of 'sysctl -b kern.geom.confxml' > so we can find out who? http://omega.iib.unsam.edu.ar/kern.geom.confxml The parts that mention ad4s3 are: ad4s3 3 r0w0e0 which refers to this provider: ad4 2 r2w2e3 r0w0e0 ad4s3 96636266496 512 2 96636266496 188742708 75159189504 146795292 165 r1w1e1 ad4s2 75159157248 512 1 75159157248 146795229 8587224576 16771923 165 r1w1e1 ad4s1 8586772992 512 0 8586772992 16771041 32256 63 165 Which to my geom-naive brain seems like the description of how my ad4 disk is set up ... but what does mode r0w0e0 imply ... I couldn't find where these modes are described (nor geom(8) nor geom(4) talk about them) ... does it mean read=0 write=0 execute=0 as my naive brain guesses? If so, maybe I could change it to something that would allow me to write to ad4s3? And also, why does the GEOM config contain information for devices that are not managed by geom? My da0 and swap devices (ad4s1b, ad6s1b) are not geom based ... Thanks for your help, Fernan -- Fernan Aguero From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 14:07:11 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 3B33116A40F for ; Tue, 9 Jan 2007 14:07:11 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (arm132.internetdsl.tpnet.pl [83.17.198.132]) by mx1.freebsd.org (Postfix) with ESMTP id C6DA713C448 for ; Tue, 9 Jan 2007 14:07:08 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id 99DE446DA5; Tue, 9 Jan 2007 15:07:06 +0100 (CET) Received: from localhost (pjd.wheel.pl [10.0.1.1]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id 4EEA9456B1; Tue, 9 Jan 2007 15:06:54 +0100 (CET) Date: Tue, 9 Jan 2007 15:06:25 +0100 From: Pawel Jakub Dawidek To: Fernan Aguero Message-ID: <20070109140625.GD62430@garage.freebsd.pl> References: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> <20070109001437.GC97624@in-addr.com> <520894aa0701081813x3925b7f1r278785bb01f4232@mail.gmail.com> <20070109083846.GA62430@garage.freebsd.pl> <520894aa0701090524t217a36ecje1cf7b40d8a2a7e0@mail.gmail.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="8w3uRX/HFJGApMzv" Content-Disposition: inline In-Reply-To: <520894aa0701090524t217a36ecje1cf7b40d8a2a7e0@mail.gmail.com> X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 7.0-CURRENT i386 User-Agent: mutt-ng/devel-r804 (FreeBSD) X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-5.9 required=3.0 tests=ALL_TRUSTED,BAYES_00 autolearn=ham version=3.0.4 Cc: geom@freebsd.org Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 14:07:11 -0000 --8w3uRX/HFJGApMzv Content-Type: text/plain; charset=iso-8859-2 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Tue, Jan 09, 2007 at 10:24:04AM -0300, Fernan Aguero wrote: > On 1/9/07, Pawel Jakub Dawidek wrote: > >On Mon, Jan 08, 2007 at 11:13:15PM -0300, Fernan Aguero wrote: > >> On 1/8/07, Gary Palmer wrote: > >> >On Mon, Jan 08, 2007 at 07:45:06PM -0300, Fernan Aguero wrote: > >> > >> [snipped] > >> > >> >> gama# gstripe label -v gs0 /dev/ad4s3 /dev/ad6s3 > >> >> Can't store metadata on /dev/ad4s3: Operation not permitted. > >> >> > >> >> This might be because ad4s3 had been part of a gmirror device befor= e I > >> >> reorganized my disks and moved the mirror to the s2 slice. > >> > >> [snipped] > >> > >> >Any reason that "gstripe clear" or "gmirror clear" doesn't work? Tha= ts what > >> >they're meant to do, as far as I know. > >> > >> because ad4s3 is no longer part of gm0? > > > >You get "Operation not permitted." because someone already keep ad4s3 > >open for writing. Could you send output of 'sysctl -b kern.geom.confxml' > >so we can find out who? >=20 > http://omega.iib.unsam.edu.ar/kern.geom.confxml [...] In this output size of ad4 is 160041885696 bytes. In your first post, slices are configured this way: gama# fdisk -s /dev/ad4 /dev/ad4: 310101 cyl 16 hd 63 sec Part Start Size Type Flags 1: 63 16771041 0xa5 0x00 2: 16771923 146795229 0xa5 0x80 3: 146795292 188742708 0xa5 0x00 If ad4s3 starts at 146795292 sectors and is 188742708 sectors big, which bascially means, that ad4s3 end at offset: (146795292+188742708)*512 =3D 171795456000 bytes 160041885696 < 171795456000, which means your slices are misconfigured. Correct that and it should work. > And also, why does the GEOM config contain information for devices that a= re not > managed by geom? My da0 and swap devices (ad4s1b, ad6s1b) are not geom > based ... Every single storage provider in FreeBSD is managed by GEOM. --=20 Pawel Jakub Dawidek http://www.wheel.pl pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --8w3uRX/HFJGApMzv Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (FreeBSD) iD8DBQFFo6FhForvXbEpPzQRAqluAJ9Il3EKI6V2g4aEO8r2K3YA1LQ+mwCfcGEa ZJzEjje04GLrcgAkDfooJe8= =hSuM -----END PGP SIGNATURE----- --8w3uRX/HFJGApMzv-- From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 14:17:32 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id C074316A403 for ; Tue, 9 Jan 2007 14:17:32 +0000 (UTC) (envelope-from bashr@comcast.net) Received: from rwcrmhc13.comcast.net (rwcrmhc13.comcast.net [216.148.227.153]) by mx1.freebsd.org (Postfix) with ESMTP id B04F313C45D for ; Tue, 9 Jan 2007 14:17:32 +0000 (UTC) (envelope-from bashr@comcast.net) Received: from [149.28.227.65] (unknown[149.28.227.65]) by comcast.net (rwcrmhc13) with ESMTP id <20070109140450m1300i24k4e>; Tue, 9 Jan 2007 14:04:50 +0000 Message-ID: <45A3A101.2000203@comcast.net> Date: Tue, 09 Jan 2007 09:04:49 -0500 From: bashr User-Agent: Thunderbird 1.5.0.8 (X11/20061123) MIME-Version: 1.0 To: freebsd-geom@freebsd.org Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: FAILURE - out of memory in start X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: bashr@comcast.net List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 14:17:32 -0000 Messages like the following are regularly logged on this server for each of the four installed hd's: +ad4: FAILURE - out of memory in start They did not occur before implementation of a gmirror of gstripes. Occurrances of failures do not correspond with times of heavy load. Such failures were mentioned on freebsd-geom in Aug 2005, but without a resolution that I could find. Setting vm.kmem_size_scale=2, as suggested elsewhere does not solve the problem. Any advice or suggestions will be much appreciated. Here is some more info: >gmirror status Name Status Components mirror/gm0s1 COMPLETE ad2s1 ad4s1 ad6s1 ad8s1 mirror/gm0s2 COMPLETE stripe/st1s1 stripe/st0s1 > gstripe status Name Status Components stripe/st1s1 UP ad2s3 ad4s3 stripe/st0s1 UP ad6s3 ad8s3 > mount /dev/mirror/gm0s1a on / (ufs, local, soft-updates) devfs on /dev (devfs, local) /dev/mirror/gm0s2a on /var (ufs, local, nosuid, soft-updates) /dev/mirror/gm0s2d on /tmp (ufs, local, nosuid, soft-updates) /dev/mirror/gm0s2e on /usr (ufs, local, soft-updates) /dev/mirror/gm0s2f on /usr/home (ufs, local, nosuid, soft-updates) linprocfs on /usr/compat/linux/proc (linprocfs, local) > uname -a FreeBSD ***.***.*** 6.2-PRERELEASE FreeBSD 6.2-PRERELEASE #0: Tue Dec 12 13:30:20 EST 2006 ***@***.***.***:/usr/obj/usr/src/sys/GENERIC i386 From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 14:43:44 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 6117D16A492 for ; Tue, 9 Jan 2007 14:43:44 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.freebsd.org (Postfix) with ESMTP id E9B0C13C471 for ; Tue, 9 Jan 2007 14:43:43 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1H4ICS-00010j-TV for freebsd-geom@freebsd.org; Tue, 09 Jan 2007 15:43:40 +0100 Received: from lara.cc.fer.hr ([161.53.72.113]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Tue, 09 Jan 2007 15:43:40 +0100 Received: from ivoras by lara.cc.fer.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Tue, 09 Jan 2007 15:43:40 +0100 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-geom@freebsd.org From: Ivan Voras Date: Tue, 09 Jan 2007 15:43:33 +0100 Lines: 45 Message-ID: References: <45A38D38.3020407@fluffles.net> <45A396C5.2000908@fluffles.net> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: lara.cc.fer.hr User-Agent: Thunderbird 1.5.0.4 (X11/20060625) In-Reply-To: <45A396C5.2000908@fluffles.net> Sender: news Cc: freebsd-fs@freebsd.org Subject: Re: Capturing I/O traces X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 14:43:44 -0000 Fluffles wrote: > Ivan Voras wrote: >> Fluffles wrote: >> >> >>> One thought that comes to mind is the gnop geom class; with verbose mode >>> this provides a text log of all the I/O accesses. But it does not >>> provide the exact time/concurrency etc, only the offset, length, I/O >>> >> What do you mean by "time" and "concurrency"? You do realize that >> requests are serialized on the low level? > > Sure but simply capturing the serial order of requests might not be > sufficient. For example: the application might 'wait' for one request to > be finished because it needs that data in order to do another I/O > request. I guess this is the hard part. If i would just execute the I/O If an application has two threads (or there are two processes) making a request at the same time, the lower level WILL get two requests, even if the "first one" hasn't completed. This is nondeterministic - you can't know which application's request will be the "first" and on the GEOM level you don't know what application has made the request. It's all anonymous I/O at that level, completed asynchronously. Is this what you're asking or is it something else? > I guess it's not easy to really make something like this be reliable and > realistic, but i'd like to come as close as possible. For example, the > website StorageReview also uses traces to benchmark specific uses, two > links: > > http://www.storagereview.com/articles/200611/ST3750640NS_3.html > http://www.storagereview.com/articles/200510/Testbed4_4.html > > I'd like to use traces of applications on FreeBSD (or GNU/Linux) to > benchmark KDE startup, MySQL, Apache and other applications. So i can > have benchmark suites like "desktop", "webserver" and "database". That > would be very neat. Nobody is questioning the use of I/O traces for benchmarking - I've seen many utilities that do it. Of course, raw I/O traces are only useful for benchmarking raw I/O - more useful for most workloads would be VFS traces (because it involves CPU, locking, etc...). From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 16:57:28 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id E175416A407 for ; Tue, 9 Jan 2007 16:57:28 +0000 (UTC) (envelope-from victorloureirolima@gmail.com) Received: from an-out-0708.google.com (an-out-0708.google.com [209.85.132.247]) by mx1.freebsd.org (Postfix) with ESMTP id A4FA213C4BD for ; Tue, 9 Jan 2007 16:57:28 +0000 (UTC) (envelope-from victorloureirolima@gmail.com) Received: by an-out-0708.google.com with SMTP id c24so2312856ana for ; Tue, 09 Jan 2007 08:57:28 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=Bddq8iuMsFHztVCwGIj/qkZqREXnp0J2zrObS7EUayUi39wK+qU+MM2R3Yr0PhednBbyMKepuft+qoVIFKfipJB2k6nUkJOWmo4F1TEpeGOxu0jESI1LDt/DnU0dTVZIjstSyvOQJhI6+tnm0ZLDjfoYosTWKIWFw4kmqiXqLWI= Received: by 10.100.190.8 with SMTP id n8mr10832191anf.1168360327458; Tue, 09 Jan 2007 08:32:07 -0800 (PST) Received: by 10.100.109.16 with HTTP; Tue, 9 Jan 2007 08:32:07 -0800 (PST) Message-ID: Date: Tue, 9 Jan 2007 13:32:07 -0300 From: "Victor Loureiro Lima" To: Fluffles In-Reply-To: <45A396C5.2000908@fluffles.net> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <45A38D38.3020407@fluffles.net> <45A396C5.2000908@fluffles.net> Cc: freebsd-fs@freebsd.org, Ivan Voras , freebsd-geom@freebsd.org Subject: Re: Capturing I/O traces X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 16:57:29 -0000 Maybe you could take a look at iostat(8), seems to be able to help you somehow!!! ;) att, victor loureiro lima 2007/1/9, Fluffles : > Ivan Voras wrote: > > Fluffles wrote: > > > > > >> One thought that comes to mind is the gnop geom class; with verbose mode > >> this provides a text log of all the I/O accesses. But it does not > >> provide the exact time/concurrency etc, only the offset, length, I/O > >> > > > > What do you mean by "time" and "concurrency"? You do realize that > > requests are serialized on the low level? > > > > Sure but simply capturing the serial order of requests might not be > sufficient. For example: the application might 'wait' for one request to > be finished because it needs that data in order to do another I/O > request. I guess this is the hard part. If i would just execute the I/O > in a serial way things like accesstime or 'latency' are less important > because the overall throughput counts; while this may not be true for > real applications but they might wait on one request before they can > move on; thus a lower latency might be more important than a higher > throughput. > > I guess it's not easy to really make something like this be reliable and > realistic, but i'd like to come as close as possible. For example, the > website StorageReview also uses traces to benchmark specific uses, two > links: > > http://www.storagereview.com/articles/200611/ST3750640NS_3.html > http://www.storagereview.com/articles/200510/Testbed4_4.html > > I'd like to use traces of applications on FreeBSD (or GNU/Linux) to > benchmark KDE startup, MySQL, Apache and other applications. So i can > have benchmark suites like "desktop", "webserver" and "database". That > would be very neat. > > _______________________________________________ > 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-geom@FreeBSD.ORG Tue Jan 9 18:18:46 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id A51C516A47E for ; Tue, 9 Jan 2007 18:18:46 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.freebsd.org (Postfix) with ESMTP id 5F94A13C4A6 for ; Tue, 9 Jan 2007 18:18:46 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1H4LYW-0004Hb-4q for freebsd-geom@freebsd.org; Tue, 09 Jan 2007 19:18:40 +0100 Received: from 89-172-49-221.adsl.net.t-com.hr ([89.172.49.221]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Tue, 09 Jan 2007 19:18:40 +0100 Received: from ivoras by 89-172-49-221.adsl.net.t-com.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Tue, 09 Jan 2007 19:18:40 +0100 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-geom@freebsd.org From: Ivan Voras Date: Tue, 09 Jan 2007 19:18:17 +0100 Lines: 28 Message-ID: References: <45A38D38.3020407@fluffles.net> <45A396C5.2000908@fluffles.net> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enigC3D231DB3AF85FB2D21A7637" X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: 89-172-49-221.adsl.net.t-com.hr User-Agent: Thunderbird 1.5.0.9 (Windows/20061207) In-Reply-To: X-Enigmail-Version: 0.94.1.2 Sender: news Cc: freebsd-fs@freebsd.org Subject: Re: Capturing I/O traces X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 18:18:46 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enigC3D231DB3AF85FB2D21A7637 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Victor Loureiro Lima wrote: > Maybe you could take a look at iostat(8), seems to be able to help you > somehow!!! ;) iostat reports the total bandwidth, but she needs positions, lengths & timing. --------------enigC3D231DB3AF85FB2D21A7637 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.4 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iD8DBQFFo9xvldnAQVacBcgRAoy0AJsElKhKtIwnf7Ugz+x7FPUGj4Ss4wCdFs4I CNO9hFXhRZSVhVA4itU0vyE= =6fx+ -----END PGP SIGNATURE----- --------------enigC3D231DB3AF85FB2D21A7637-- From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 19:16:46 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 6631D16A407 for ; Tue, 9 Jan 2007 19:16:46 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: from nz-out-0506.google.com (nz-out-0506.google.com [64.233.162.237]) by mx1.freebsd.org (Postfix) with ESMTP id 26F9413C441 for ; Tue, 9 Jan 2007 19:16:44 +0000 (UTC) (envelope-from fernan.aguero@gmail.com) Received: by nz-out-0506.google.com with SMTP id i11so3971270nzh for ; Tue, 09 Jan 2007 11:16:43 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=SeO/TmGD1e10kjVh+VCBXXeATxwW9HWoukqslbeClVyu7AyDQ2M8Uo2EUKsHc8ZIGEn7NpDWNqAZ/okfVtGkj/Ier4cIJODNPOjsOwXatnoOvrOiD4bejpS5crc6HqN7TP/lyARhbrIA8d1//Cz/WMyvxhiAgvmJuc89GJDEtYQ= Received: by 10.35.121.9 with SMTP id y9mr51242770pym.1168370203424; Tue, 09 Jan 2007 11:16:43 -0800 (PST) Received: by 10.35.16.1 with HTTP; Tue, 9 Jan 2007 11:16:43 -0800 (PST) Message-ID: <520894aa0701091116t424ca75coc2167eacea8f1a38@mail.gmail.com> Date: Tue, 9 Jan 2007 16:16:43 -0300 From: "Fernan Aguero" To: "Pawel Jakub Dawidek" In-Reply-To: <20070109140625.GD62430@garage.freebsd.pl> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> <20070109001437.GC97624@in-addr.com> <520894aa0701081813x3925b7f1r278785bb01f4232@mail.gmail.com> <20070109083846.GA62430@garage.freebsd.pl> <520894aa0701090524t217a36ecje1cf7b40d8a2a7e0@mail.gmail.com> <20070109140625.GD62430@garage.freebsd.pl> Cc: geom@freebsd.org Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 19:16:46 -0000 On 1/9/07, Pawel Jakub Dawidek wrote: > On Tue, Jan 09, 2007 at 10:24:04AM -0300, Fernan Aguero wrote: > > On 1/9/07, Pawel Jakub Dawidek wrote: > > >On Mon, Jan 08, 2007 at 11:13:15PM -0300, Fernan Aguero wrote: > > >> On 1/8/07, Gary Palmer wrote: > > >> >On Mon, Jan 08, 2007 at 07:45:06PM -0300, Fernan Aguero wrote: > > >> > > >> [snipped] > > >> > > >> >> gama# gstripe label -v gs0 /dev/ad4s3 /dev/ad6s3 > > >> >> Can't store metadata on /dev/ad4s3: Operation not permitted. > > >> >> > > >> >> This might be because ad4s3 had been part of a gmirror device before I > > >> >> reorganized my disks and moved the mirror to the s2 slice. > > >> > > >> [snipped] > > >> > > >> >Any reason that "gstripe clear" or "gmirror clear" doesn't work? Thats what > > >> >they're meant to do, as far as I know. > > >> > > >> because ad4s3 is no longer part of gm0? > > > > > >You get "Operation not permitted." because someone already keep ad4s3 > > >open for writing. Could you send output of 'sysctl -b kern.geom.confxml' > > >so we can find out who? > > > > http://omega.iib.unsam.edu.ar/kern.geom.confxml > [...] > > In this output size of ad4 is 160041885696 bytes. > > In your first post, slices are configured this way: > > gama# fdisk -s /dev/ad4 > /dev/ad4: 310101 cyl 16 hd 63 sec > Part Start Size Type Flags > 1: 63 16771041 0xa5 0x00 > 2: 16771923 146795229 0xa5 0x80 > 3: 146795292 188742708 0xa5 0x00 > > If ad4s3 starts at 146795292 sectors and is 188742708 sectors big, which > bascially means, that ad4s3 end at offset: > > (146795292+188742708)*512 = 171795456000 bytes > > 160041885696 < 171795456000, which means your slices are misconfigured. > Correct that and it should work. OK, so perhaps the problem is that I used 160Gb in my calculations for the media size, expecting that fdisk will 'round down' the size of the last slice to match available space. I recalculated all the start/length values for my slices and changed the fdisk.config I used with fdisk -f and now everything is fine. Thanks! but why was I ever allowed to go farther from the end of the media size? why didn't fdisk say anything? why didn't geom -- now I know that every single storage provider is managed by geom :) -- say anything? Wouldn't it be good if one could tell fdisk to create a slice to start at a given sector and use '*' as the length (much as bsdlabel allows) so that the slice would occupy all remaining space?, like in p 3 165 146800795 * Again, thanks! fernan -- Fernan Aguero From owner-freebsd-geom@FreeBSD.ORG Tue Jan 9 20:32:07 2007 Return-Path: X-Original-To: geom@freebsd.org Delivered-To: freebsd-geom@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id B558616A416 for ; Tue, 9 Jan 2007 20:32:07 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (arm132.internetdsl.tpnet.pl [83.17.198.132]) by mx1.freebsd.org (Postfix) with ESMTP id A331B13C441 for ; Tue, 9 Jan 2007 20:32:06 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id C5A37487F5; Tue, 9 Jan 2007 21:32:03 +0100 (CET) Received: from localhost (154.81.datacomsa.pl [195.34.81.154]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id 10E1D45CDA; Tue, 9 Jan 2007 21:31:44 +0100 (CET) Date: Tue, 9 Jan 2007 21:31:15 +0100 From: Pawel Jakub Dawidek To: Fernan Aguero Message-ID: <20070109203115.GA65839@garage.freebsd.pl> References: <520894aa0701081445i43d76098m418ce695d2133e53@mail.gmail.com> <20070109001437.GC97624@in-addr.com> <520894aa0701081813x3925b7f1r278785bb01f4232@mail.gmail.com> <20070109083846.GA62430@garage.freebsd.pl> <520894aa0701090524t217a36ecje1cf7b40d8a2a7e0@mail.gmail.com> <20070109140625.GD62430@garage.freebsd.pl> <520894aa0701091116t424ca75coc2167eacea8f1a38@mail.gmail.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="gBBFr7Ir9EOA20Yy" Content-Disposition: inline In-Reply-To: <520894aa0701091116t424ca75coc2167eacea8f1a38@mail.gmail.com> X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 7.0-CURRENT i386 User-Agent: mutt-ng/devel-r804 (FreeBSD) X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-2.6 required=3.0 tests=BAYES_00 autolearn=ham version=3.0.4 Cc: geom@freebsd.org Subject: Re: clear metadata using dd? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jan 2007 20:32:07 -0000 --gBBFr7Ir9EOA20Yy Content-Type: text/plain; charset=iso-8859-2 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Tue, Jan 09, 2007 at 04:16:43PM -0300, Fernan Aguero wrote: > On 1/9/07, Pawel Jakub Dawidek wrote: > >On Tue, Jan 09, 2007 at 10:24:04AM -0300, Fernan Aguero wrote: > >> On 1/9/07, Pawel Jakub Dawidek wrote: > >> >On Mon, Jan 08, 2007 at 11:13:15PM -0300, Fernan Aguero wrote: > >> >> On 1/8/07, Gary Palmer wrote: > >> >> >On Mon, Jan 08, 2007 at 07:45:06PM -0300, Fernan Aguero wrote: > >> >> > >> >> [snipped] > >> >> > >> >> >> gama# gstripe label -v gs0 /dev/ad4s3 /dev/ad6s3 > >> >> >> Can't store metadata on /dev/ad4s3: Operation not permitted. > >> >> >> > >> >> >> This might be because ad4s3 had been part of a gmirror device be= fore I > >> >> >> reorganized my disks and moved the mirror to the s2 slice. > >> >> > >> >> [snipped] > >> >> > >> >> >Any reason that "gstripe clear" or "gmirror clear" doesn't work? = Thats what > >> >> >they're meant to do, as far as I know. > >> >> > >> >> because ad4s3 is no longer part of gm0? > >> > > >> >You get "Operation not permitted." because someone already keep ad4s3 > >> >open for writing. Could you send output of 'sysctl -b kern.geom.confx= ml' > >> >so we can find out who? > >> > >> http://omega.iib.unsam.edu.ar/kern.geom.confxml > >[...] > > > >In this output size of ad4 is 160041885696 bytes. > > > >In your first post, slices are configured this way: > > > >gama# fdisk -s /dev/ad4 > >/dev/ad4: 310101 cyl 16 hd 63 sec > >Part Start Size Type Flags > > 1: 63 16771041 0xa5 0x00 > > 2: 16771923 146795229 0xa5 0x80 > > 3: 146795292 188742708 0xa5 0x00 > > > >If ad4s3 starts at 146795292 sectors and is 188742708 sectors big, which > >bascially means, that ad4s3 end at offset: > > > > (146795292+188742708)*512 =3D 171795456000 bytes > > > >160041885696 < 171795456000, which means your slices are misconfigured. > >Correct that and it should work. >=20 > OK, so perhaps the problem is that I used 160Gb in my calculations > for the media size, expecting that fdisk will 'round down' the size of > the last slice to match available space. >=20 > I recalculated all the start/length values for my slices and changed > the fdisk.config I used with fdisk -f and now everything is fine. >=20 > Thanks! >=20 > > but why was I ever allowed to go farther from the end of the media size? > why didn't fdisk say anything? > why didn't geom -- now I know that every single storage provider > is managed by geom :) -- say anything? >=20 > Wouldn't it be good if one could tell fdisk to create a slice to start at= a > given sector and use '*' as the length (much as bsdlabel allows) so that = the > slice would occupy all remaining space?, like in > p 3 165 146800795 * > fdisk(8) isn't too user friendly, that's for sure. Marcel Moolenaar is doing some work in this area, so he can come up with something better in the future. --=20 Pawel Jakub Dawidek http://www.wheel.pl pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --gBBFr7Ir9EOA20Yy Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (FreeBSD) iD8DBQFFo/uTForvXbEpPzQRAp1qAJ9FJXQDkV19eI18aWIf8EobiBxP1QCg3NnG BMBCGSS5tT64A7OAz406MHc= =Rni4 -----END PGP SIGNATURE----- --gBBFr7Ir9EOA20Yy-- From owner-freebsd-geom@FreeBSD.ORG Wed Jan 10 04:12:14 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 2BD1316A40F; Wed, 10 Jan 2007 04:12:14 +0000 (UTC) (envelope-from unixtools@hotmail.com) Received: from bay0-omc2-s23.bay0.hotmail.com (bay0-omc2-s23.bay0.hotmail.com [65.54.246.159]) by mx1.freebsd.org (Postfix) with ESMTP id 14D7213C45A; Wed, 10 Jan 2007 04:12:14 +0000 (UTC) (envelope-from unixtools@hotmail.com) Received: from hotmail.com ([65.54.161.81]) by bay0-omc2-s23.bay0.hotmail.com with Microsoft SMTPSVC(6.0.3790.2668); Tue, 9 Jan 2007 20:00:14 -0800 Received: from mail pickup service by hotmail.com with Microsoft SMTPSVC; Tue, 9 Jan 2007 20:00:13 -0800 Message-ID: Received: from 203.199.109.165 by BAY106-DAV9.phx.gbl with DAV; Wed, 10 Jan 2007 04:00:09 +0000 X-Originating-IP: [203.199.109.165] X-Originating-Email: [unixtools@hotmail.com] X-Sender: unixtools@hotmail.com From: To: "Fluffles" , , References: <45A38D38.3020407@fluffles.net> Date: Wed, 10 Jan 2007 09:59:51 +0530 MIME-Version: 1.0 Content-Type: text/plain; charset="ISO-8859-15" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1437 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1441 X-OriginalArrivalTime: 10 Jan 2007 04:00:13.0749 (UTC) FILETIME=[D4AB4E50:01C7346B] Cc: Subject: Re: Capturing I/O traces X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 10 Jan 2007 04:12:14 -0000 Hi, To capture appication IO, the best option on freebsd is ktrace. I have no idea how to trace all the io calls triggered by the kernel. Sunil Sunder Raj http://daemon.in ----- Original Message ----- From: "Fluffles" To: ; Sent: Tuesday, January 09, 2007 6:10 PM Subject: Capturing I/O traces > Hello list, > > I was wondering if any method is known to "capture" I/O traces. My goal > is to be able to simulate I/O access patterns generated by applications > such as MySQL or KDE and compare these to other storage systems. This > way i can provide more realistic benchmarks (not synthetic) without > actually running the application i'm testing. For example, I would like > to capture the I/O that occurs when KDE boots, and then be able to > reproduce this I/O access on say a gmirror and graid3. This way i can > gather more realistic benchmark results. On Windows several commercial > applications exist that 'simulate' access patterns used by applications, > i was wondering if any BSD/Linux equivalent exists. > > One thought that comes to mind is the gnop geom class; with verbose mode > this provides a text log of all the I/O accesses. But it does not > provide the exact time/concurrency etc, only the offset, length, I/O > action (read/write) and the serial order of those requests. And even > with this information it's not easy to reproduce them; i would have to > write an application that reads this log and then be able to reproduce > it. I was hoping to find a more elegant solution. If you guys know of > any, please share it with me. :) > > Regards, > > Veronica > _______________________________________________ > 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-geom@FreeBSD.ORG Wed Jan 10 07:08:18 2007 Return-Path: X-Original-To: freebsd-geom@FreeBSD.org Delivered-To: freebsd-geom@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id C8C7616A412; Wed, 10 Jan 2007 07:08:18 +0000 (UTC) (envelope-from vd@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [69.147.83.40]) by mx1.freebsd.org (Postfix) with ESMTP id B43D113C44C; Wed, 10 Jan 2007 07:08:18 +0000 (UTC) (envelope-from vd@FreeBSD.org) Received: from freefall.freebsd.org (vd@localhost [127.0.0.1]) by freefall.freebsd.org (8.13.4/8.13.4) with ESMTP id l0A78Iu4033296; Wed, 10 Jan 2007 07:08:18 GMT (envelope-from vd@freefall.freebsd.org) Received: (from vd@localhost) by freefall.freebsd.org (8.13.4/8.13.4/Submit) id l0A78HOR033295; Wed, 10 Jan 2007 07:08:17 GMT (envelope-from vd) Date: Wed, 10 Jan 2007 07:08:17 +0000 From: Vasil Dimov To: "R. B. Riddick" Message-ID: <20070110070817.GA33206@freefall.freebsd.org> References: <45965441.6010002@fer.hr> <36644.58831.qm@web30303.mail.mud.yahoo.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <36644.58831.qm@web30303.mail.mud.yahoo.com> Cc: Ivan Voras , freebsd-geom@FreeBSD.org Subject: Re: graid3 device gives "Invalid argument" when requested to read>=128kb X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: vd@FreeBSD.org List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 10 Jan 2007 07:08:18 -0000 On Sat, Dec 30, 2006 at 04:39:39AM -0800, R. B. Riddick wrote: > --- Ivan Voras wrote: > > No, probably not. The whole thing was my very first attempt at doing > > anything with GEOM (ggcomp - it still exists somewhere), which wasn't > > very usable :) "Normal" file system operations worked, though I think > > there were problems even here with 16 KB sectors. > > > Sector size seems to be not the reason (at least with gnop and dd on R6.1): > > neo# gnop create -S 16384 md0 > neo# dd if=/dev/md0.nop of=/dev/null > dd: /dev/md0.nop: Invalid argument > 0+0 records in > 0+0 records out > 0 bytes transferred in 0.000155 secs (0 bytes/sec) This is because default dd's read block size is 512b > neo# dd if=/dev/md0.nop of=/dev/null bs=16k > 1024+0 records in > 1024+0 records out > 16777216 bytes transferred in 0.398660 secs (42084027 bytes/sec) > > Just UFS seems to have a problem: > > neo# newfs /dev/md0.nop > /dev/md0.nop: 16.0MB (32768 sectors) block size 16384, fragment size 16384 > using 4 cylinder groups of 4.02MB, 257 blks, 128 inodes. > newfs: can't read old UFS1 superblock: read error from block device: Invalid > argument Look at newfs's -S switch, this is the same issue as with dd above. -- Vasil Dimov gro.DSBeerF@dv From owner-freebsd-geom@FreeBSD.ORG Wed Jan 10 08:58:52 2007 Return-Path: X-Original-To: freebsd-geom@FreeBSD.org Delivered-To: freebsd-geom@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 1F11016A47C for ; Wed, 10 Jan 2007 08:58:52 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30312.mail.mud.yahoo.com (web30312.mail.mud.yahoo.com [209.191.69.74]) by mx1.freebsd.org (Postfix) with SMTP id BF32113C458 for ; Wed, 10 Jan 2007 08:58:51 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 90823 invoked by uid 60001); 10 Jan 2007 08:58:51 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=d35stNRehJ16u46grE5kDBvLgOnhk2KhaJ5VVUzrxCtf2gh95+NLFGQPBZkbcaWSENe3DxarrBvcq4Iatdl2ML3CCM3kO2QV7uFWT/4mlBb6Zw/XMelsVGes+tOgVL0NkZ7lS0B7OJgp/bZbkY0/O8XVPklAesS/7e9EQgE/ouc=; X-YMail-OSG: i9VPCQEVM1lw3oZJK0rBSsEAiE0Lo9aoczoureVtMYpXKCF.ESD4M6KMkD4H1PleRg-- Received: from [85.212.20.209] by web30312.mail.mud.yahoo.com via HTTP; Wed, 10 Jan 2007 00:58:51 PST Date: Wed, 10 Jan 2007 00:58:51 -0800 (PST) From: "R. B. Riddick" To: vd@FreeBSD.org In-Reply-To: <20070110070817.GA33206@freefall.freebsd.org> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <67643.90686.qm@web30312.mail.mud.yahoo.com> Cc: freebsd-geom@FreeBSD.org Subject: Re: graid3 device gives "Invalid argument" when requested to read>=128kb X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 10 Jan 2007 08:58:52 -0000 --- Vasil Dimov wrote: > On Sat, Dec 30, 2006 at 04:39:39AM -0800, R. B. Riddick wrote: > > neo# gnop create -S 16384 md0 > > neo# dd if=/dev/md0.nop of=/dev/null > > dd: /dev/md0.nop: Invalid argument > > 0+0 records in > > 0+0 records out > > 0 bytes transferred in 0.000155 secs (0 bytes/sec) > > This is because default dd's read block size is 512b > Yup... Its the default... > > Just UFS seems to have a problem: > > > > neo# newfs /dev/md0.nop > > /dev/md0.nop: 16.0MB (32768 sectors) block size 16384, fragment size 16384 > > using 4 cylinder groups of 4.02MB, 257 blks, 128 inodes. > > newfs: can't read old UFS1 superblock: read error from block device: > > Invalid argument > > Look at newfs's -S switch, this is the same issue as with dd above. > I tried, but no success... newfs should be able to find out the sector size... But -S does not help, too... Tried it urself? -Arne __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com From owner-freebsd-geom@FreeBSD.ORG Wed Jan 10 09:21:21 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id DC9CD16A412; Wed, 10 Jan 2007 09:21:21 +0000 (UTC) (envelope-from etc@fluffles.net) Received: from auriate.fluffles.net (cust.95.160.adsl.cistron.nl [195.64.95.160]) by mx1.freebsd.org (Postfix) with ESMTP id 628E913C47E; Wed, 10 Jan 2007 09:21:21 +0000 (UTC) (envelope-from etc@fluffles.net) Received: from destiny ([10.0.0.21]) by auriate.fluffles.net with esmtpa (Exim 4.63 (FreeBSD)) (envelope-from ) id 1H4Ze0-000Mhh-Ci; Wed, 10 Jan 2007 10:21:16 +0100 Message-ID: <45A4B03A.5030806@fluffles.net> Date: Wed, 10 Jan 2007 10:22:02 +0100 From: Fluffles User-Agent: Thunderbird 1.5.0.8 (X11/20061114) MIME-Version: 1.0 To: unixtools@hotmail.com References: <45A38D38.3020407@fluffles.net> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org, freebsd-geom@freebsd.org Subject: Re: Capturing I/O traces X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 10 Jan 2007 09:21:22 -0000 Hello list, Thanks for all your input. After some thought about I/O tracing, I guess ktrace won't work properly. I do not see the offset/length of the requests and it does include the actual contents; so it's not what i need. I think the geom_nop approach might be the best or most simple. Arne Woerner provided me a modified gnop which logs the I/O requests at debuglevel 0. But i would need some form of binary logging, to file. So that with a specially modified gnop it would dump all I/O into a file, like: /mnt/memorydisk/ad4.nop.log. It would have to log all accesses binary. I think i will drop the time between requests, so i will just need the serial order of requests and the following information: - read or write - offset - length It should be binary, like: R<32-bit offset><32-bit length>W<32-bit offset><32-bit length>.... The R means Read (so takes 1 byte) and W ofcourse write. This way it will take 9 bytes per I/O request to log. I could log to memory (md malloc) to minimize performance penalty. The logging should be able to turn off/on via sysctl switch or so, so i can prepare the benchmark setup and turn on tracing just before i launch the application i wish to trace. When this modified gnop module is done, i need a C-like program that can read the log and perform the I/O on a given device. Such as calling the following command: ./tracereproduce ./tracereproduce /mnt/memorydisk/ad4.nop.log /dev/raid5/test Then it would execute all I/O requests logged in the .log file at the fastest speed possible, serially. It should record the start time and end time and calculate the microtime it has used to finish all requests. Say this is 14.9 seconds for 20.000 I/O requests, then it would produce 1342 I/O per second as the end result. Then i can reproduce the test on say a gmirror device and i would get another score, being able to compare between classes. What do you guys think? Any flaws in my idea? I know this is at geom level and not VFS-level, but as Arne Woerner pointed out to me; caching/buffering that happens at the VFS-level will never reach the geom-layer anyway; so i do not need it. All benchmarking will be done on one machine so the only thing different is the geom classes; for example a 4-disk gstripe versus 4-disk graid5, etc. There might be better ways to do tracing; but since i'm a simple webdeveloper i do not have the skills to write a sophisticated applications. The geom-tracing approach outlined above might be my best option and might come very close to realistic performance-gains. Feedback is appreciated. :) - Veronica From owner-freebsd-geom@FreeBSD.ORG Wed Jan 10 09:33:54 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 89D0616A403 for ; Wed, 10 Jan 2007 09:33:54 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30309.mail.mud.yahoo.com (web30309.mail.mud.yahoo.com [209.191.69.71]) by mx1.freebsd.org (Postfix) with SMTP id 395DE13C441 for ; Wed, 10 Jan 2007 09:33:54 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 25744 invoked by uid 60001); 10 Jan 2007 09:33:53 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=5h64Is8tVbU6TFlCJgayTd87OxhivvAE3g6jUd0Bs3J5Q2yklChSP7ul4BbocqTb4YoLtRsRKOE5gglLgQ3NGJ/SE00JJyonbML5KWnYQGHxfRKlOsLPcpdXD1Wl08jaLQLFaUmybPtx5K5n1TUs18c0u5YiEM6WkBhid9SHu04=; X-YMail-OSG: jAzsILIVM1n9n7sQGOUaP8hRYWDZBSq.wulzPTHbdMBST4_MGW2KtWUAoEOte4diOg-- Received: from [85.212.20.209] by web30309.mail.mud.yahoo.com via HTTP; Wed, 10 Jan 2007 01:33:53 PST Date: Wed, 10 Jan 2007 01:33:53 -0800 (PST) From: "R. B. Riddick" To: Fluffles In-Reply-To: <45A4B03A.5030806@fluffles.net> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <478499.24007.qm@web30309.mail.mud.yahoo.com> Cc: freebsd-fs@freebsd.org, freebsd-geom@freebsd.org Subject: Re: Capturing I/O traces X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 10 Jan 2007 09:33:54 -0000 --- Fluffles wrote: > It should be binary, like: > R<32-bit offset><32-bit length>W<32-bit offset><32-bit length>.... > What is so bad about syslog? Problems with parsing...? :-) When u dont know start times and end times, you will not be able to identify concurrent/simultaneous requests, which might be bad for performance (I think, UFS can use 9 simultaneous requests). -Arne ____________________________________________________________________________________ Yahoo! Music Unlimited Access over 1 million songs. http://music.yahoo.com/unlimited From owner-freebsd-geom@FreeBSD.ORG Wed Jan 10 10:04:05 2007 Return-Path: X-Original-To: freebsd-geom@FreeBSD.org Delivered-To: freebsd-geom@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 0B21416A40F; Wed, 10 Jan 2007 10:04:05 +0000 (UTC) (envelope-from vd@datamax.bg) Received: from jengal.datamax.bg (jengal.datamax.bg [82.103.104.21]) by mx1.freebsd.org (Postfix) with ESMTP id B8BC113C428; Wed, 10 Jan 2007 10:04:04 +0000 (UTC) (envelope-from vd@datamax.bg) Received: from qlovarnika.bg.datamax (qlovarnika.bg.datamax [192.168.10.2]) by jengal.datamax.bg (Postfix) with SMTP id A3A7DB848; Wed, 10 Jan 2007 12:04:03 +0200 (EET) Received: (nullmailer pid 85312 invoked by uid 1002); Wed, 10 Jan 2007 10:04:03 -0000 Date: Wed, 10 Jan 2007 12:04:03 +0200 From: Vasil Dimov To: "R\. B\. Riddick" Message-ID: <20070110100403.GA85205@qlovarnika.bg.datamax> References: <20070110070817.GA33206@freefall.freebsd.org> <67643.90686.qm@web30312.mail.mud.yahoo.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="SUOF0GtieIMvvwua" Content-Disposition: inline In-Reply-To: <67643.90686.qm@web30312.mail.mud.yahoo.com> Cc: freebsd-geom@FreeBSD.org Subject: Re: graid3 device gives "Invalid argument" when requested to read>=128kb X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: vd@FreeBSD.org List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 10 Jan 2007 10:04:05 -0000 --SUOF0GtieIMvvwua Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Jan 10, 2007 at 00:58:51 -0800, R. B. Riddick wrote: > --- Vasil Dimov wrote: > > On Sat, Dec 30, 2006 at 04:39:39AM -0800, R. B. Riddick wrote: > > > neo# gnop create -S 16384 md0 > > > neo# dd if=3D/dev/md0.nop of=3D/dev/null=20 > > > dd: /dev/md0.nop: Invalid argument > > > 0+0 records in > > > 0+0 records out > > > 0 bytes transferred in 0.000155 secs (0 bytes/sec) > >=20 > > This is because default dd's read block size is 512b > > > Yup... Its the default... >=20 > > > Just UFS seems to have a problem: > > >=20 > > > neo# newfs /dev/md0.nop > > > /dev/md0.nop: 16.0MB (32768 sectors) block size 16384, fragment size = 16384 > > > using 4 cylinder groups of 4.02MB, 257 blks, 128 inodes. > > > newfs: can't read old UFS1 superblock: read error from block device: > > > Invalid argument > >=20 > > Look at newfs's -S switch, this is the same issue as with dd above. > >=20 > I tried, but no success... newfs should be able to find out the sector si= ze... > But -S does not help, too... Tried it urself? # mdconfig -a -t malloc -s 32m -S 16384 -o reserve md0 # dd if=3D/dev/md0 of=3D/dev/null dd: /dev/md0: Invalid argument 0+0 records in 0+0 records out 0 bytes transferred in 0.000080 secs (0 bytes/sec) # dd if=3D/dev/md0 of=3D/dev/null bs=3D16k 2048+0 records in 2048+0 records out 33554432 bytes transferred in 0.052907 secs (634215478 bytes/sec) # newfs /dev/md0 /dev/md0: 32.0MB (65536 sectors) block size 16384, fragment size 16384 using 4 cylinder groups of 8.02MB, 513 blks, 192 inodes. newfs: can't read old UFS1 superblock: read error from block device: Invali= d argument # newfs -S 16384 /dev/md0 /dev/md0: 32.0MB (65536 sectors) block size 16384, fragment size 16384 using 4 cylinder groups of 8.02MB, 513 blks, 192 inodes. newfs: can't read old UFS1 superblock: read error from block device: Invali= d argument If I use mdconfig -S 8192, newfs succeeds with or without -S 8192: # newfs /dev/md0 /dev/md0: 32.0MB (65536 sectors) block size 16384, fragment size 8192 using 4 cylinder groups of 8.02MB, 513 blks, 320 inodes. super-block backups (for fsck -b #) at: 160, 16576, 32992, 49408 just to make it identical with the case when mdconfig -S 16384 is used: # newfs -f 16384 /dev/md0 /dev/md0: 32.0MB (65536 sectors) block size 16384, fragment size 16384 using 4 cylinder groups of 8.02MB, 513 blks, 192 inodes. super-block backups (for fsck -b #) at: 160, 16576, 32992, 49408 --=20 Vasil Dimov gro.DSBeerF@dv % Only a fool has no doubts. --SUOF0GtieIMvvwua Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- iD8DBQFFpLoTFw6SP/bBpCARAi0hAKCvROooHqkpVW9XRbcvDuqNEo1SbwCdEbUT lsSsu7aP2oOGNciD4NrOiXk= =rB/A -----END PGP SIGNATURE----- --SUOF0GtieIMvvwua-- From owner-freebsd-geom@FreeBSD.ORG Wed Jan 10 15:36:11 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 4D75C16A407 for ; Wed, 10 Jan 2007 15:36:11 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.freebsd.org (Postfix) with ESMTP id 0F51E13C441 for ; Wed, 10 Jan 2007 15:36:11 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1H4fUg-0007Ab-5K for freebsd-geom@freebsd.org; Wed, 10 Jan 2007 16:36:02 +0100 Received: from lara.cc.fer.hr ([161.53.72.113]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 10 Jan 2007 16:36:02 +0100 Received: from ivoras by lara.cc.fer.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 10 Jan 2007 16:36:02 +0100 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-geom@freebsd.org From: Ivan Voras Date: Wed, 10 Jan 2007 16:35:51 +0100 Lines: 10 Message-ID: References: <45A38D38.3020407@fluffles.net> <45A4B03A.5030806@fluffles.net> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: lara.cc.fer.hr User-Agent: Thunderbird 1.5.0.4 (X11/20060625) In-Reply-To: <45A4B03A.5030806@fluffles.net> Sender: news Cc: freebsd-fs@freebsd.org Subject: Re: Capturing I/O traces X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 10 Jan 2007 15:36:11 -0000 Fluffles wrote: > - read or write > - offset > - length > > It should be binary, like: > R<32-bit offset><32-bit length>W<32-bit offset><32-bit length>.... So see my patched ggatel. I can modify it to include timestamps as well. From owner-freebsd-geom@FreeBSD.ORG Thu Jan 11 14:09:58 2007 Return-Path: X-Original-To: freebsd-geom@hub.freebsd.org Delivered-To: freebsd-geom@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 44EFD16A407; Thu, 11 Jan 2007 14:09:58 +0000 (UTC) (envelope-from linimon@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [69.147.83.40]) by mx1.freebsd.org (Postfix) with ESMTP id 1E45013C43E; Thu, 11 Jan 2007 14:09:58 +0000 (UTC) (envelope-from linimon@FreeBSD.org) Received: from freefall.freebsd.org (linimon@localhost [127.0.0.1]) by freefall.freebsd.org (8.13.4/8.13.4) with ESMTP id l0BE9v9B093033; Thu, 11 Jan 2007 14:09:57 GMT (envelope-from linimon@freefall.freebsd.org) Received: (from linimon@localhost) by freefall.freebsd.org (8.13.4/8.13.4/Submit) id l0BE9vDx093029; Thu, 11 Jan 2007 14:09:57 GMT (envelope-from linimon) Date: Thu, 11 Jan 2007 14:09:57 GMT From: Mark Linimon Message-Id: <200701111409.l0BE9vDx093029@freefall.freebsd.org> To: linimon@FreeBSD.org, freebsd-bugs@FreeBSD.org, freebsd-geom@FreeBSD.org Cc: Subject: Re: kern/107707: [geom] [patch] add new class geom_xbox360 to slice up xbox360 media X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Jan 2007 14:09:58 -0000 Synopsis: [geom] [patch] add new class geom_xbox360 to slice up xbox360 media Responsible-Changed-From-To: freebsd-bugs->freebsd-geom Responsible-Changed-By: linimon Responsible-Changed-When: Thu Jan 11 14:09:51 UTC 2007 Responsible-Changed-Why: Over to maintainer(s). http://www.freebsd.org/cgi/query-pr.cgi?pr=107707 From owner-freebsd-geom@FreeBSD.ORG Thu Jan 11 17:11:06 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 3BFE216A494 for ; Thu, 11 Jan 2007 17:11:06 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.freebsd.org (Postfix) with ESMTP id BEB9513C4AB for ; Thu, 11 Jan 2007 17:11:05 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1H53S0-0002lj-MW for freebsd-geom@freebsd.org; Thu, 11 Jan 2007 18:10:52 +0100 Received: from p3ee213e5.dip0.t-ipconnect.de ([62.226.19.229]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Thu, 11 Jan 2007 18:10:52 +0100 Received: from christian.baer by p3ee213e5.dip0.t-ipconnect.de with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Thu, 11 Jan 2007 18:10:52 +0100 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-geom@freebsd.org From: Christian Baer Date: Thu, 11 Jan 2007 18:05:47 +0100 (CET) Organization: Convenimus Projekt Lines: 54 Message-ID: X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: p3ee213e5.dip0.t-ipconnect.de User-Agent: slrn/0.9.8.1 (FreeBSD) Sender: news Subject: How to mirror a geli partition? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Jan 2007 17:11:06 -0000 Hello Folks! At the moment I am setting up a new machine. This has two identical drives (Seagate Cheetah) installed. I will hold some very important data an some very unimportant :-) data. What I want to do is to create mirrors of those *partitions* containing the important stuff[1]. Since the data is sensitive I also wish to encrypt it with geli. I've done both things before, just not in combination. And I've never created a mirror with gmirror before. Currently I'm not even sure if I should rather use vinum oder geom. I went for geom, because it is there anyway because of geli. Comments about this are very welcome! These are my main questions: 1st The mirrored partitions will contain the same date (naturally) but the drives however will not. It this a problem? Meaning that the mirrored partitions on drive0 and drive1 will probably habe different positions on their drives. 2nd The gmirror manpage only uses full drives as providers in its examples. I am guessing that I could also use a partition as a provider like /dev/ad0s1d. Did I guess that right? 3rd What happens if the partitions aren't exactly the same size? This could happen if the partitions have different positions on the drive and I specify the size in MB or GB. I don't care if I lose a bit of room (meaning that the size of the smaller partition is the one that counts). I'm just a little worried that a rounding error that makes partition0 a few blocks larger than partition1 could cause problems. 4th This is actually the biggest problem I am facing. In what order do I do this? I was thinking along this way: 1 - Create partions and try to get them the same size. :-) 2 - Fill one (or both?) with random data. 3 - Make a geli provider out of one of them, newfs it. 4 - Do something like 'gmirror label -v -b load secret 1.eli' and 'gmirror insert 2.eli' I am not sure if I should reverse the order of 3 and 4. Or have I gotten the whole idea wrong? Can someone point me in the right direction? Regards, Chris [1] Backups will also be made but probably not always be up to date as the data on these drives will change very frequently. From owner-freebsd-geom@FreeBSD.ORG Thu Jan 11 17:28:03 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 8624516A5BD for ; Thu, 11 Jan 2007 17:28:03 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30302.mail.mud.yahoo.com (web30302.mail.mud.yahoo.com [209.191.69.64]) by mx1.freebsd.org (Postfix) with SMTP id 4F5F213C465 for ; Thu, 11 Jan 2007 17:28:03 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 6086 invoked by uid 60001); 11 Jan 2007 17:28:02 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=C9GRG2y03a4jmuX5sKpdFSd6RVMJnbuBG1lTeR6aAIErv9O204PFtAbvnqbgtUDAT9RRbGSVAQKEcOwXR/rr75YhFNWh0XxiIse71bPCcfRjRnLc1DyiGbKdAk7Hmr8nTdsgRWnGxqd02VnF9hvGVJaGShoSDK3auyOrnEOfAS0=; X-YMail-OSG: kDrdgCYVM1nIAvV2_NdlPKVAbYRYHsYjRK8dMCcR Received: from [85.212.26.193] by web30302.mail.mud.yahoo.com via HTTP; Thu, 11 Jan 2007 09:28:02 PST Date: Thu, 11 Jan 2007 09:28:02 -0800 (PST) From: "R. B. Riddick" To: Christian Baer , freebsd-geom@freebsd.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <373585.5107.qm@web30302.mail.mud.yahoo.com> Cc: Subject: Re: How to mirror a geli partition? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Jan 2007 17:28:03 -0000 --- Christian Baer wrote: > 1st > The mirrored partitions will contain the same date (naturally) but the > drives however will not. It this a problem? Meaning that the mirrored > partitions > on drive0 and drive1 will probably habe different positions on their > drives. > Nope. Since GEOM providers can be consumers, and since partitions, slices and disks are GEOM providers, too, there will be no such prob... > 2nd > The gmirror manpage only uses full drives as providers in its examples. > I am guessing that I could also use a partition as a provider like > /dev/ad0s1d. Did I guess that right? > See above... Slices, partitions can be used like disks regarding GEOM-consumer-able-lish-ness... :-) > 3rd > What happens if the partitions aren't exactly the same size? This could > happen if the partitions have different positions on the drive and I > specify the size in MB or GB. I don't care if I lose a bit of room > (meaning that the size of the smaller partition is the one that counts). > I'm just a little worried that a rounding error that makes partition0 a > few blocks larger than partition1 could cause problems. > gmirror will build the minimum, if I recall the code correctly... At least in verbose mode gmirror will tell u how much u r wasting, IIRC... > 4th > This is actually the biggest problem I am facing. In what order do I do > this? I was thinking along this way: > 1 - Create partions and try to get them the same size. :-) > 2 - Fill one (or both?) with random data. > 3 - Make a geli provider out of one of them, newfs it. > 4 - Do something like 'gmirror label -v -b load secret 1.eli' > and 'gmirror insert 2.eli' > I am not sure if I should reverse the order of 3 and 4. Or have I gotten > the whole idea wrong? > I would do the gmirror first and then the geli on top of the gmirror, as if the gmirror was a normal disk/partition/slice or whatever u r used to... > Can someone point me in the right direction? > Hope I did... -Arne ____________________________________________________________________________________ Do you Yahoo!? Everyone is raving about the all-new Yahoo! Mail beta. http://new.mail.yahoo.com From owner-freebsd-geom@FreeBSD.ORG Thu Jan 11 18:36:52 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 8100116A407 for ; Thu, 11 Jan 2007 18:36:52 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (arm132.internetdsl.tpnet.pl [83.17.198.132]) by mx1.freebsd.org (Postfix) with ESMTP id 3AD4613C45E for ; Thu, 11 Jan 2007 18:36:50 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id 681A5487F0; Thu, 11 Jan 2007 19:36:45 +0100 (CET) Received: from localhost (154.81.datacomsa.pl [195.34.81.154]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id DF17845B26; Thu, 11 Jan 2007 19:36:29 +0100 (CET) Date: Thu, 11 Jan 2007 19:35:53 +0100 From: Pawel Jakub Dawidek To: bashr Message-ID: <20070111183553.GA85073@garage.freebsd.pl> References: <45A3A101.2000203@comcast.net> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="BXVAT5kNtrzKuDFl" Content-Disposition: inline In-Reply-To: <45A3A101.2000203@comcast.net> X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 7.0-CURRENT i386 User-Agent: mutt-ng/devel-r804 (FreeBSD) X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-2.6 required=3.0 tests=BAYES_00 autolearn=ham version=3.0.4 Cc: freebsd-geom@freebsd.org Subject: Re: FAILURE - out of memory in start X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Jan 2007 18:36:52 -0000 --BXVAT5kNtrzKuDFl Content-Type: text/plain; charset=iso-8859-2 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Tue, Jan 09, 2007 at 09:04:49AM -0500, bashr wrote: > Messages like the following are regularly logged on this server for each = of the four installed hd's: > +ad4: FAILURE - out of memory in start > They did not occur before implementation of a gmirror of gstripes. Occurr= ances of failures do not correspond with times of heavy load. Such failures= were mentioned on=20 > freebsd-geom in Aug 2005, but without a resolution that I could find. Set= ting vm.kmem_size_scale=3D2, as suggested elsewhere does not solve the prob= lem. I see it too from time to time, but GEOM knows how to handle ENOMEM errors and I think those are harmless. --=20 Pawel Jakub Dawidek http://www.wheel.pl pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --BXVAT5kNtrzKuDFl Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (FreeBSD) iD8DBQFFpoOJForvXbEpPzQRArCkAJ4zgyQM2qKi1mT6SssgRZmZHxsaYACcDprl erfB3r8eupxg6Wgf6mYoRP0= =UUHA -----END PGP SIGNATURE----- --BXVAT5kNtrzKuDFl-- From owner-freebsd-geom@FreeBSD.ORG Fri Jan 12 00:41:40 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 1E77D16A40F for ; Fri, 12 Jan 2007 00:41:40 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.freebsd.org (Postfix) with ESMTP id A3C3D13C459 for ; Fri, 12 Jan 2007 00:41:39 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1H5AUB-0001PF-Q2 for freebsd-geom@freebsd.org; Fri, 12 Jan 2007 01:41:35 +0100 Received: from 83-131-104-224.adsl.net.t-com.hr ([83.131.104.224]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 12 Jan 2007 01:41:35 +0100 Received: from ivoras by 83-131-104-224.adsl.net.t-com.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 12 Jan 2007 01:41:35 +0100 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-geom@freebsd.org From: Ivan Voras Date: Fri, 12 Jan 2007 01:41:19 +0100 Lines: 43 Message-ID: References: Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig78FEF9148CFAA187314D1EF0" X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: 83-131-104-224.adsl.net.t-com.hr User-Agent: Thunderbird 1.5.0.9 (Windows/20061207) In-Reply-To: X-Enigmail-Version: 0.94.1.2 Sender: news Subject: Re: How to mirror a geli partition? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Jan 2007 00:41:40 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig78FEF9148CFAA187314D1EF0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Christian Baer wrote: > This is actually the biggest problem I am facing. In what order do I do= > this? I was thinking along this way: > 1 - Create partions and try to get them the same size. :-) > 2 - Fill one (or both?) with random data. > 3 - Make a geli provider out of one of them, newfs it. > 4 - Do something like 'gmirror label -v -b load secret 1.eli' > and 'gmirror insert 2.eli' > I am not sure if I should reverse the order of 3 and 4. Or have I gotte= n > the whole idea wrong? >=20 > Can someone point me in the right direction? First mirror the partitions and then create geli drive on top of it. If you do it the other way (encrypt each of the partition separately), you will be asked for password twice and each drive will (AFAIK) get its own internal key even if you use the same password (I'm not sure about that one, though). --------------enig78FEF9148CFAA187314D1EF0 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.4 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iD8DBQFFptk1ldnAQVacBcgRAnlsAKDYcIq04n1VEnaL+MGBqxBFYVKHJQCgnIaW rvune1F5JgNnCqCDu7/vJ60= =/b3y -----END PGP SIGNATURE----- --------------enig78FEF9148CFAA187314D1EF0-- From owner-freebsd-geom@FreeBSD.ORG Fri Jan 12 04:37:45 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id B795216A412 for ; Fri, 12 Jan 2007 04:37:45 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (arm132.internetdsl.tpnet.pl [83.17.198.132]) by mx1.freebsd.org (Postfix) with ESMTP id 47EAB13C45B for ; Fri, 12 Jan 2007 04:37:45 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id F3E3148800; Fri, 12 Jan 2007 05:37:42 +0100 (CET) Received: from localhost (154.81.datacomsa.pl [195.34.81.154]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id 5908645CDA; Fri, 12 Jan 2007 05:37:36 +0100 (CET) Date: Fri, 12 Jan 2007 05:37:03 +0100 From: Pawel Jakub Dawidek To: Ivan Voras Message-ID: <20070112043703.GA87362@garage.freebsd.pl> References: MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="G4iJoqBmSsgzjUCe" Content-Disposition: inline In-Reply-To: X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 7.0-CURRENT i386 User-Agent: mutt-ng/devel-r804 (FreeBSD) X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-2.6 required=3.0 tests=BAYES_00 autolearn=ham version=3.0.4 Cc: freebsd-geom@freebsd.org Subject: Re: How to mirror a geli partition? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Jan 2007 04:37:45 -0000 --G4iJoqBmSsgzjUCe Content-Type: text/plain; charset=iso-8859-2 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, Jan 12, 2007 at 01:41:19AM +0100, Ivan Voras wrote: > Christian Baer wrote: >=20 > > This is actually the biggest problem I am facing. In what order do I do > > this? I was thinking along this way: > > 1 - Create partions and try to get them the same size. :-) > > 2 - Fill one (or both?) with random data. > > 3 - Make a geli provider out of one of them, newfs it. > > 4 - Do something like 'gmirror label -v -b load secret 1.eli' > > and 'gmirror insert 2.eli' > > I am not sure if I should reverse the order of 3 and 4. Or have I gotten > > the whole idea wrong? > >=20 > > Can someone point me in the right direction? >=20 > First mirror the partitions and then create geli drive on top of it. If > you do it the other way (encrypt each of the partition separately), you > will be asked for password twice and each drive will (AFAIK) get its own > internal key even if you use the same password (I'm not sure about that > one, though). Yes, you're correct. Doing mirror on top of two geli-encrypted providers would also consume twice as much CPU for crypto operations. I definiately recommend encrypting a mirror. --=20 Pawel Jakub Dawidek http://www.wheel.pl pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --G4iJoqBmSsgzjUCe Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (FreeBSD) iD8DBQFFpxBvForvXbEpPzQRAq8XAKCZSE7o9KKmOATm0iMmlBDfJM3p7wCfaL1i 0Agb6W7QHBScRPTFg5/f00g= =Btm5 -----END PGP SIGNATURE----- --G4iJoqBmSsgzjUCe-- From owner-freebsd-geom@FreeBSD.ORG Fri Jan 12 18:49:24 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 7197716A407 for ; Fri, 12 Jan 2007 18:49:24 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30309.mail.mud.yahoo.com (web30309.mail.mud.yahoo.com [209.191.69.71]) by mx1.freebsd.org (Postfix) with SMTP id 3B58413C465 for ; Fri, 12 Jan 2007 18:49:24 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 64831 invoked by uid 60001); 12 Jan 2007 18:49:23 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=GYtddDq8yQzRdqK0iqpmS1X1qWQEUONjAlZtQu1tZbeDLigA341ndcV4yp/dYuDcj+f/eho+msG52VqxP1ytjkFomalkktUIF6+XCbOAijc6BmKc4q8hxy9pFuz4FA4nOXxFdviQ+CDBhSub3D6pPJg58/8ITInyNQbrKDR1j90=; X-YMail-OSG: peelR1AVM1lB0D3BmD25oXQUiJv5.IMCzGik5rEvcKP1L_vYsUU5hoOZJOwe2lWgdTJ1zrWz79at1yTlb9BFZWCCq9s3XcMGyi3hTWdCBETwbrTi9J.llX2Qh7IMd96s8l3YkQurwNwjpDffXituX5S_AFxwt39Pg0J.ImrVBjvqo8ZX1A9EmqonEu_c Received: from [85.212.6.114] by web30309.mail.mud.yahoo.com via HTTP; Fri, 12 Jan 2007 10:49:23 PST Date: Fri, 12 Jan 2007 10:49:23 -0800 (PST) From: "R. B. Riddick" To: CyberLeo Kitsana In-Reply-To: <45A7D338.1090402@cyberleo.net> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <666664.62691.qm@web30309.mail.mud.yahoo.com> Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Jan 2007 18:49:24 -0000 --- CyberLeo Kitsana wrote: > I've been making use of the geom_raid5 class for FreeBSD 6.2-PRERELEASE. > I've noticed an odd behavior lately, with the latest sources provided > (as of 2006-01-10) in which, with 'safeop' enabled, the raid5 will stop > responding. > Ohoh... > All works beautifully, until several dozen gigabytes are transferred to > or from the filesystem with safeop enabled, at which point the > filesystem will grow quickly less responsive, and eventually cease > responding entirely (processes stuck in diskwait) CPU usage is at 0%, > and all four members of the raid5 are being read at around 160kB/sec > (16kB/t, 10tps) constantly. It does not naturally recover within 72 > hours. The mirror is unaffected by this behavior. > Strange... :-) SAFEOP means, that a failed disk leads to an IO error for every request, and that every read request reads all corresponding disk areas (if possible) and checks parity. SAFEOP mode is surely useful, if u want to be sure, that neither ur disks nor ur operating system provide bogus data... SAFEOP mode causes a lot of disk activity (e. g. in case of sequential read, it reads n-1 times (where n is the disk count of the RAID5) the whole stripe (n blocks)...). This special form of a read request is used by the rebuild-procedure, so that it should work fine... What does "graid5 list" say in those times? Are there any special messages logged via syslog in those times? > When this occurs, the moment safeop is disabled on the raid5, all the > problems cease, the filesystem begins responding and the programs resume. > So the kernel does not panic or so...? :-) > Is this intentional, an artifact of the hardware or layout I'm using, or > could this be indicative of an obscure bug somewhere? Can I provide any > additional information which would assist in tracking this down? > I would guess: An obscure bug in graid5... You could try to put gcache between the disks and graid5... And the syslog messages (if there r any) would be very interesting (like messages about read error or disk failure or so)... -Arne ____________________________________________________________________________________ Finding fabulous fares is fun. Let Yahoo! FareChase search your favorite travel sites to find flight and hotel bargains. http://farechase.yahoo.com/promo-generic-14795097 From owner-freebsd-geom@FreeBSD.ORG Fri Jan 12 18:55:32 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 4759116A403 for ; Fri, 12 Jan 2007 18:55:32 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: from pizzabox.cyberleo.net (alpha.cyberleo.net [198.145.45.10]) by mx1.freebsd.org (Postfix) with ESMTP id 2BA9F13C45D for ; Fri, 12 Jan 2007 18:55:31 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: (qmail 34465 invoked from network); 12 Jan 2007 18:28:50 -0000 Received: from adsl-69-212-1-127.dsl.chcgil.ameritech.net (HELO ?172.16.44.14?) (cyberleo@cyberleo.net@69.212.1.127) by alpha.cyberleo.net with ESMTPA; 12 Jan 2007 18:28:50 -0000 Message-ID: <45A7D338.1090402@cyberleo.net> Date: Fri, 12 Jan 2007 12:28:08 -0600 From: CyberLeo Kitsana User-Agent: Thunderbird 1.5 (X11/20051201) MIME-Version: 1.0 To: "R. B. Riddick" Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD Geom Subject: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Jan 2007 18:55:32 -0000 Hi. I've been making use of the geom_raid5 class for FreeBSD 6.2-PRERELEASE. I've noticed an odd behavior lately, with the latest sources provided (as of 2006-01-10) in which, with 'safeop' enabled, the raid5 will stop responding. I have an 800MHz Celeron (i815 chipset) with 512MB RAM and 4x 400GB PATA100 disks, two on a Promise PCI ATA controller, running FreeBSD 6.2-PRERELEASE (2006-01-10). The kernel is SMP, with DEVICE_POLLING and HZ=100 set. The disks are configured with a 2GB slice 1 as a 4-disk geom_mirror containing /, and the remainder in slice 2 as a 4-disk geom_raid5 (32768 stripe size). The box is designed to receive daily backups from production servers, so data integrity is preferred over throughput or latency. All works beautifully, until several dozen gigabytes are transferred to or from the filesystem with safeop enabled, at which point the filesystem will grow quickly less responsive, and eventually cease responding entirely (processes stuck in diskwait) CPU usage is at 0%, and all four members of the raid5 are being read at around 160kB/sec (16kB/t, 10tps) constantly. It does not naturally recover within 72 hours. The mirror is unaffected by this behavior. When this occurs, the moment safeop is disabled on the raid5, all the problems cease, the filesystem begins responding and the programs resume. Is this intentional, an artifact of the hardware or layout I'm using, or could this be indicative of an obscure bug somewhere? Can I provide any additional information which would assist in tracking this down? ---- [cyberleo@mikayla ~]$ gmirror list Geom name: root State: COMPLETE Components: 4 Balance: load Slice: 4096 Flags: NONE GenID: 0 SyncID: 2 ID: 89087781 Providers: 1. Name: mirror/root Mediasize: 1610563584 (1.5G) Sectorsize: 512 Mode: r1w1e1 Consumers: 1. Name: ad0s1a Mediasize: 1610564096 (1.5G) Sectorsize: 512 Mode: r1w1e1 State: ACTIVE Priority: 0 Flags: DIRTY GenID: 0 SyncID: 2 ID: 3326083319 2. Name: ad2s1a Mediasize: 1610564096 (1.5G) Sectorsize: 512 Mode: r1w1e1 State: ACTIVE Priority: 0 Flags: DIRTY GenID: 0 SyncID: 2 ID: 1957052293 3. Name: ad4s1a Mediasize: 1610564096 (1.5G) Sectorsize: 512 Mode: r1w1e1 State: ACTIVE Priority: 0 Flags: DIRTY GenID: 0 SyncID: 2 ID: 3131999117 4. Name: ad6s1a Mediasize: 1610564096 (1.5G) Sectorsize: 512 Mode: r1w1e1 State: ACTIVE Priority: 0 Flags: DIRTY GenID: 0 SyncID: 2 ID: 2209607005 [cyberleo@mikayla ~]$ graid5 list Geom name: raid5 State: COMPLETE CALM Status: Total=4, Online=4 Type: AUTOMATIC Pending: (wqp 0 // 0) Stripesize: 32768 MemUse: 3467264 (msl 138) Newest: -1 ID: 3906282509 Providers: 1. Name: raid5/raid5 Mediasize: 1193822846976 (1.1T) Sectorsize: 512 Mode: r1w1e1 Consumers: 1. Name: ad6s2 Mediasize: 397940981760 (371G) Sectorsize: 512 Mode: r2w2e2 DiskNo: 3 Error: No 2. Name: ad4s2 Mediasize: 397940981760 (371G) Sectorsize: 512 Mode: r2w2e2 DiskNo: 2 Error: No 3. Name: ad2s2 Mediasize: 397940981760 (371G) Sectorsize: 512 Mode: r2w2e2 DiskNo: 1 Error: No 4. Name: ad0s2 Mediasize: 397940981760 (371G) Sectorsize: 512 Mode: r2w2e2 DiskNo: 0 Error: No ---- -- Fuzzy love, -CyberLeo Technical Administrator CyberLeo.Net Webhosting http://www.CyberLeo.Net Furry Peace! - http://www.fur.com/peace/ From owner-freebsd-geom@FreeBSD.ORG Fri Jan 12 20:29:18 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id AF72A16A407 for ; Fri, 12 Jan 2007 20:29:18 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: from pizzabox.cyberleo.net (alpha.cyberleo.net [198.145.45.10]) by mx1.freebsd.org (Postfix) with ESMTP id 9306313C455 for ; Fri, 12 Jan 2007 20:29:18 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: (qmail 36556 invoked from network); 12 Jan 2007 20:29:17 -0000 Received: from adsl-69-212-1-127.dsl.chcgil.ameritech.net (HELO ?172.16.44.14?) (cyberleo@cyberleo.net@69.212.1.127) by alpha.cyberleo.net with ESMTPA; 12 Jan 2007 20:29:17 -0000 Message-ID: <45A7EF74.9050204@cyberleo.net> Date: Fri, 12 Jan 2007 14:28:36 -0600 From: CyberLeo Kitsana User-Agent: Thunderbird 1.5 (X11/20051201) MIME-Version: 1.0 To: "R. B. Riddick" References: <666664.62691.qm@web30309.mail.mud.yahoo.com> In-Reply-To: <666664.62691.qm@web30309.mail.mud.yahoo.com> Content-Type: text/plain; charset=iso-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Jan 2007 20:29:18 -0000 R. B. Riddick wrote: > --- CyberLeo Kitsana wrote: >> I've been making use of the geom_raid5 class for FreeBSD 6.2-PRERELEASE. >> I've noticed an odd behavior lately, with the latest sources provided >> (as of 2006-01-10) in which, with 'safeop' enabled, the raid5 will stop >> responding. >> > Ohoh... > >> All works beautifully, until several dozen gigabytes are transferred to >> or from the filesystem with safeop enabled, at which point the >> filesystem will grow quickly less responsive, and eventually cease >> responding entirely (processes stuck in diskwait) CPU usage is at 0%, >> and all four members of the raid5 are being read at around 160kB/sec >> (16kB/t, 10tps) constantly. It does not naturally recover within 72 >> hours. The mirror is unaffected by this behavior. >> > Strange... :-) > SAFEOP means, that a failed disk leads to an IO error for every request, and > that every read request reads all corresponding disk areas (if possible) and > checks parity. SAFEOP mode is surely useful, if u want to be sure, that neither > ur disks nor ur operating system provide bogus data... SAFEOP mode causes a lot > of disk activity (e. g. in case of sequential read, it reads n-1 times (where n > is the disk count of the RAID5) the whole stripe (n blocks)...). > This special form of a read request is used by the rebuild-procedure, so that > it should work fine... > > What does "graid5 list" say in those times? > Are there any special messages logged via syslog in those times? > >> When this occurs, the moment safeop is disabled on the raid5, all the >> problems cease, the filesystem begins responding and the programs resume. >> > So the kernel does not panic or so...? :-) > >> Is this intentional, an artifact of the hardware or layout I'm using, or >> could this be indicative of an obscure bug somewhere? Can I provide any >> additional information which would assist in tracking this down? >> > I would guess: An obscure bug in graid5... > > You could try to put gcache between the disks and graid5... > And the syslog messages (if there r any) would be very interesting (like > messages about read error or disk failure or so)... Hence the testing. I wish to ensure there are as few problems as possible when this is put into production. The kernel does not panic, and everything resumes just fine as soon as safeop is disabled. There are no new messages in the kernel log, nor in syslog, and all disks are operating properly, if slowly (around 40 kilobytes per second each, with dd bs=4096). Also, gcache doesn't seem to exist in the base system. Is this easier to build than gjournal? (patching for that caused a whole ton of kernel and world problems I'd rather not revisit) The attached list was taken during the most recent lockup. ---- [cyberleo@mikayla ~]$ graid5 list Geom name: raid5 State: COMPLETE CALM (safeop) Status: Total=4, Online=4 Type: AUTOMATIC Pending: (wqp 0 // 0) Stripesize: 32768 MemUse: 147456 (msl 7) Newest: -1 ID: 3906282509 Providers: 1. Name: raid5/raid5 Mediasize: 1193822846976 (1.1T) Sectorsize: 512 Mode: r1w1e1 Consumers: 1. Name: ad6s2 Mediasize: 397940981760 (371G) Sectorsize: 512 Mode: r2w2e2 DiskNo: 3 Error: No 2. Name: ad4s2 Mediasize: 397940981760 (371G) Sectorsize: 512 Mode: r2w2e2 DiskNo: 2 Error: No 3. Name: ad2s2 Mediasize: 397940981760 (371G) Sectorsize: 512 Mode: r2w2e2 DiskNo: 1 Error: No 4. Name: ad0s2 Mediasize: 397940981760 (371G) Sectorsize: 512 Mode: r2w2e2 DiskNo: 0 Error: No ---- -- Fuzzy love, -CyberLeo Technical Administrator CyberLeo.Net Webhosting http://www.CyberLeo.Net Furry Peace! - http://www.fur.com/peace/ From owner-freebsd-geom@FreeBSD.ORG Fri Jan 12 20:36:59 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 92DE716A412 for ; Fri, 12 Jan 2007 20:36:59 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30301.mail.mud.yahoo.com (web30301.mail.mud.yahoo.com [209.191.69.63]) by mx1.freebsd.org (Postfix) with SMTP id 5CABD13C465 for ; Fri, 12 Jan 2007 20:36:59 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 4591 invoked by uid 60001); 12 Jan 2007 20:36:58 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=l7HhaIuYH23Z97M/5jMWBDgABkXwdVgMAtjFJ0IauDk8+9lVBcsNrFZTi43E8EIwvMjpwjzH6AJjbrvwpRECysJzwCCR3GRh8FalMq+eHQmSAx+GckUdTQK4BUJ2gvflx1TJ6LFd8N+C5/s1ihkVojvsi/KbcRzQyEytm3mV7NQ=; X-YMail-OSG: ox.6zJIVM1l57GAvEnfyD_obk7LrSg83Fnv0.33MI29ms.v66_IU9ojsT862khCvvJ6Ws4g4lzQJ7ekxSlgP1Tnfk1qILXtiq4dGHqJ1_Mqot9pCGBzE0siageXhpDPoK1Fi8aZJ0iHsHWk- Received: from [85.212.6.114] by web30301.mail.mud.yahoo.com via HTTP; Fri, 12 Jan 2007 12:36:58 PST Date: Fri, 12 Jan 2007 12:36:58 -0800 (PST) From: "R. B. Riddick" To: CyberLeo Kitsana In-Reply-To: <45A7EF74.9050204@cyberleo.net> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <765687.4465.qm@web30301.mail.mud.yahoo.com> Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Jan 2007 20:36:59 -0000 --- CyberLeo Kitsana wrote: > Hence the testing. I wish to ensure there are as few problems as > possible when this is put into production. > OK... I understand that... Testing is important, but the programmer tends to test not so good... ;-) > The kernel does not panic, and everything resumes just fine as soon as > safeop is disabled. There are no new messages in the kernel log, nor in > syslog, and all disks are operating properly, if slowly (around 40 > kilobytes per second each, with dd bs=4096). > Hmm - and at the same time u feel that the processes have to wait much longer than necessary? Or is it possible, that the processes r just idle and read not so often? What does "gstat" say (a screen shot during a suspected live lock would be fine)? CPU usage according to "top"? > Also, gcache doesn't seem to exist in the base system. Is this easier to > build than gjournal? (patching for that caused a whole ton of kernel and > world problems I'd rather not revisit) > Hmm - gcache is possibly only in 7-CURRENT... > The attached list was taken during the most recent lockup. > Looks perfect to me... :-) You could try to activate graid5's debugging by setting the debug level to 2: sysctl kern.geom.raid5.debug=2 Then u should see the requests in /var/log/messages... I would be interested then in those messages during a suspected live lock (just wait for that strange condition and then set the debug level to 2 for some seconds until u feel u have enough data...)... -Arne ____________________________________________________________________________________ Do you Yahoo!? Everyone is raving about the all-new Yahoo! Mail beta. http://new.mail.yahoo.com From owner-freebsd-geom@FreeBSD.ORG Fri Jan 12 21:32:24 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 2B07216A407 for ; Fri, 12 Jan 2007 21:32:24 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: from pizzabox.cyberleo.net (alpha.cyberleo.net [198.145.45.10]) by mx1.freebsd.org (Postfix) with ESMTP id DE77113C44B for ; Fri, 12 Jan 2007 21:32:23 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: (qmail 38116 invoked from network); 12 Jan 2007 21:32:23 -0000 Received: from adsl-69-212-1-127.dsl.chcgil.ameritech.net (HELO ?172.16.44.14?) (cyberleo@cyberleo.net@69.212.1.127) by alpha.cyberleo.net with ESMTPA; 12 Jan 2007 21:32:23 -0000 Message-ID: <45A7FE3F.3040505@cyberleo.net> Date: Fri, 12 Jan 2007 15:31:43 -0600 From: CyberLeo Kitsana User-Agent: Thunderbird 1.5 (X11/20051201) MIME-Version: 1.0 To: "R. B. Riddick" References: <765687.4465.qm@web30301.mail.mud.yahoo.com> In-Reply-To: <765687.4465.qm@web30301.mail.mud.yahoo.com> Content-Type: text/plain; charset=iso-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Jan 2007 21:32:24 -0000 R. B. Riddick wrote: > --- CyberLeo Kitsana wrote: >> ... > You could try to activate graid5's debugging by setting the debug level to 2: > sysctl kern.geom.raid5.debug=2 > Then u should see the requests in /var/log/messages... > I would be interested then in those messages during a suspected live lock (just > wait for that strange condition and then set the debug level to 2 for some > seconds until u feel u have enough data...)... http://home.cyberleo.net/cyberleo/workspace/Zip/graid5-testing.png As shown in top, one rsync and one find process are stuck in biord waiting for data from the filesystem, while the CPU is otherwise mostly quiescent. I can't find evidence anywhere of what could be using the raid5 and mirror providers so much, though. The frozen processes are one locate database update (find) and one rsync process copying data from an old backup machine to the new one. The frozen processes do not respond to attempts to kill them until the filesystem begins responding. Also, tuning the sysctl had no effect prior to, nor during, the livelock. Nothing new appeared in /var/log/messages while set to 1 or 2. Thanks! -- Fuzzy love, -CyberLeo Technical Administrator CyberLeo.Net Webhosting http://www.CyberLeo.Net Furry Peace! - http://www.fur.com/peace/ From owner-freebsd-geom@FreeBSD.ORG Fri Jan 12 21:44:41 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 625A916A509 for ; Fri, 12 Jan 2007 21:44:41 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30304.mail.mud.yahoo.com (web30304.mail.mud.yahoo.com [209.191.69.66]) by mx1.freebsd.org (Postfix) with SMTP id 2B36413C43E for ; Fri, 12 Jan 2007 21:44:40 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 12379 invoked by uid 60001); 12 Jan 2007 21:44:40 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=O6NjE4hFjoqULtCRW5NdQnnX51SquGti9RVu/DoGFAA+dWHbMgrPJDiSk9L2JA0xac+kn9rXvICwbM0GM3mn/vkyrpAni7gchwZmvdE0x2WtgLan7uHDPHHwxxas6xsCbG+dnW/mE4g6W5LrEXQOB8mhsbVf4ZerJQS+10F9JnQ=; X-YMail-OSG: iXYIgTkVM1lkmn1fVWWxeZEeqApE_FwSusmr8taXsbT7iu1vwQc7m856sBaQ2DWwZ1pMkd2WPFDvKwRKsRP0hw0j31.OHtF34kjLtdGFTZJ3KcDeCcxo6VfhWcgPLwWR5IPn2LgoEAJNFHg- Received: from [85.212.6.114] by web30304.mail.mud.yahoo.com via HTTP; Fri, 12 Jan 2007 13:44:40 PST Date: Fri, 12 Jan 2007 13:44:40 -0800 (PST) From: "R. B. Riddick" To: CyberLeo Kitsana In-Reply-To: <45A7FE3F.3040505@cyberleo.net> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <416255.11150.qm@web30304.mail.mud.yahoo.com> Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Jan 2007 21:44:41 -0000 --- CyberLeo Kitsana wrote: > http://home.cyberleo.net/cyberleo/workspace/Zip/graid5-testing.png > Aha... Looks like gmirror is quite busy, too, while idle at the same time... This might mean, that we have a new GEOM problem... > As shown in top, one rsync and one find process are stuck in biord > waiting for data from the filesystem, while the CPU is otherwise mostly > quiescent. I can't find evidence anywhere of what could be using the > raid5 and mirror providers so much, though. > Me, too... > The frozen processes are one locate database update (find) and one rsync > process copying data from an old backup machine to the new one. The > frozen processes do not respond to attempts to kill them until the > filesystem begins responding. > Hmm... Can u try without gmirror? :-) I mean: Just if it is not too complicated for u (I have no hard evidence, that gmirror is the cause of something)... > Also, tuning the sysctl had no effect prior to, nor during, the > livelock. Nothing new appeared in /var/log/messages while set to 1 or 2. > Hmm... That might show, that ur /etc/syslog.conf does not log every message... :-) Can u try the line "*.* /var/log/all" to /etc/syslog.conf (after editing that file, touch the log file ("touch /var/log/all") and then reload the syslogd conf ("/etc/rc.d/syslogd reload" or so))? -Arne ____________________________________________________________________________________ Do you Yahoo!? Everyone is raving about the all-new Yahoo! Mail beta. http://new.mail.yahoo.com From owner-freebsd-geom@FreeBSD.ORG Fri Jan 12 22:48:50 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 30B0916A4AB for ; Fri, 12 Jan 2007 22:48:50 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: from pizzabox.cyberleo.net (alpha.cyberleo.net [198.145.45.10]) by mx1.freebsd.org (Postfix) with ESMTP id CA12E13C4B8 for ; Fri, 12 Jan 2007 22:48:49 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: (qmail 39689 invoked from network); 12 Jan 2007 22:48:48 -0000 Received: from adsl-69-212-1-127.dsl.chcgil.ameritech.net (HELO ?172.16.44.14?) (cyberleo@cyberleo.net@69.212.1.127) by alpha.cyberleo.net with ESMTPA; 12 Jan 2007 22:48:48 -0000 Message-ID: <45A81027.6000503@cyberleo.net> Date: Fri, 12 Jan 2007 16:48:07 -0600 From: CyberLeo Kitsana User-Agent: Thunderbird 1.5 (X11/20051201) MIME-Version: 1.0 To: "R. B. Riddick" References: <416255.11150.qm@web30304.mail.mud.yahoo.com> In-Reply-To: <416255.11150.qm@web30304.mail.mud.yahoo.com> Content-Type: text/plain; charset=iso-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Jan 2007 22:48:50 -0000 R. B. Riddick wrote: > --- CyberLeo Kitsana wrote: >> http://home.cyberleo.net/cyberleo/workspace/Zip/graid5-testing.png >> > Aha... > Looks like gmirror is quite busy, too, while idle at the same time... > This might mean, that we have a new GEOM problem... > >> As shown in top, one rsync and one find process are stuck in biord >> waiting for data from the filesystem, while the CPU is otherwise mostly >> quiescent. I can't find evidence anywhere of what could be using the >> raid5 and mirror providers so much, though. >> > Me, too... > >> The frozen processes are one locate database update (find) and one rsync >> process copying data from an old backup machine to the new one. The >> frozen processes do not respond to attempts to kill them until the >> filesystem begins responding. >> > Hmm... Can u try without gmirror? :-) > I mean: Just if it is not too complicated for u (I have no hard evidence, that > gmirror is the cause of something)... > >> Also, tuning the sysctl had no effect prior to, nor during, the >> livelock. Nothing new appeared in /var/log/messages while set to 1 or 2. >> > Hmm... > That might show, that ur /etc/syslog.conf does not log every message... :-) Can > u try the line "*.* /var/log/all" to /etc/syslog.conf (after editing that file, > touch the log file ("touch /var/log/all") and then reload the syslogd conf > ("/etc/rc.d/syslogd reload" or so))? http://home.cyberleo.net/cyberleo/workspace/Zip/graid5-testing2.png Disabled gmirror and booted from a single member of the array. The lower-right xterm is tailing all.log, enabled as you suggested in syslog, with kern.geom.raid5.debug = 2. It was logging to /var/log/messages, four lines every 10 seconds or so. I was just impatient. ^.^ -- Fuzzy love, -CyberLeo Technical Administrator CyberLeo.Net Webhosting http://www.CyberLeo.Net Furry Peace! - http://www.fur.com/peace/ From owner-freebsd-geom@FreeBSD.ORG Fri Jan 12 23:07:06 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id B0FEE16A412 for ; Fri, 12 Jan 2007 23:07:06 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30312.mail.mud.yahoo.com (web30312.mail.mud.yahoo.com [209.191.69.74]) by mx1.freebsd.org (Postfix) with SMTP id 62D1A13C442 for ; Fri, 12 Jan 2007 23:07:06 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 84174 invoked by uid 60001); 12 Jan 2007 23:07:05 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=mNo1bq2V2Q2dR13hqCphfJ1n7EfosEYzIhf7P9pY+locNmZg5FFiwe7FpDRr87otdwLxtVLUFJU3WvfSdqYdGwWRe4ZwM1zsp5R4lua+ZWbvHzSvPGv9qZX6JI+ucyv869ZZbXHZojQNFXGOoxoZvrVZXGQhVLSz8zRkpayjwsQ=; X-YMail-OSG: ctcJf4cVM1l7.xD4iwt1RFQSaFVIJAlU1CkOqvaZQcze1Qh2qE9DyGmQekw5k_pT04BQhw6.ST9oxXPguQ6IGpsPMmvloeV.gJdgetWgTmJdG4Ts1FBdxpANRzD2v0MoBgW5CodAK9VpfpI- Received: from [85.212.6.114] by web30312.mail.mud.yahoo.com via HTTP; Fri, 12 Jan 2007 15:07:05 PST Date: Fri, 12 Jan 2007 15:07:05 -0800 (PST) From: "R. B. Riddick" To: CyberLeo Kitsana In-Reply-To: <45A81027.6000503@cyberleo.net> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <765642.82951.qm@web30312.mail.mud.yahoo.com> Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Jan 2007 23:07:06 -0000 --- CyberLeo Kitsana wrote: > http://home.cyberleo.net/cyberleo/workspace/Zip/graid5-testing2.png > OK. The changes in the lower right window show, that there is still successful write request processing... > Disabled gmirror and booted from a single member of the array. The > lower-right xterm is tailing all.log, enabled as you suggested in > syslog, with kern.geom.raid5.debug = 2. > OK - gmirror was not the cause... :) But since gmirror had a quite high "ms/r" value, it might be, that graid5 isnt the real cause, too (maybe ur box just cant take so many simultaneous read requests)... Unfortunately I removed some debug code. I inserted it now. It would be nice, if u could upgrade to the newest version of graid5 (some minutes old)... Then debug level 2 should produce more output (each read/write request gets two lines: start and done)... :-) -Arne ____________________________________________________________________________________ Sucker-punch spam with award-winning protection. Try the free Yahoo! Mail Beta. http://advision.webevents.yahoo.com/mailbeta/features_spam.html From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 01:08:11 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 74AC316A417 for ; Sat, 13 Jan 2007 01:08:11 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: from pizzabox.cyberleo.net (alpha.cyberleo.net [198.145.45.10]) by mx1.freebsd.org (Postfix) with ESMTP id 372FC13C441 for ; Sat, 13 Jan 2007 01:08:11 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: (qmail 42863 invoked from network); 13 Jan 2007 01:08:10 -0000 Received: from adsl-69-212-1-127.dsl.chcgil.ameritech.net (HELO ?172.16.44.14?) (cyberleo@cyberleo.net@69.212.1.127) by alpha.cyberleo.net with ESMTPA; 13 Jan 2007 01:08:10 -0000 Message-ID: <45A830CE.2050506@cyberleo.net> Date: Fri, 12 Jan 2007 19:07:26 -0600 From: CyberLeo Kitsana User-Agent: Thunderbird 1.5 (X11/20051201) MIME-Version: 1.0 To: "R. B. Riddick" References: <765642.82951.qm@web30312.mail.mud.yahoo.com> In-Reply-To: <765642.82951.qm@web30312.mail.mud.yahoo.com> Content-Type: text/plain; charset=iso-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 01:08:11 -0000 R. B. Riddick wrote: > --- CyberLeo Kitsana wrote: >> ... > OK - gmirror was not the cause... :) But since gmirror had a quite high "ms/r" > value, it might be, that graid5 isnt the real cause, too (maybe ur box just > cant take so many simultaneous read requests)... > Unfortunately I removed some debug code. I inserted it now. It would be nice, > if u could upgrade to the newest version of graid5 (some minutes old)... Then > debug level 2 should produce more output (each read/write request gets two > lines: start and done)... :-) http://home.cyberleo.net/cyberleo/workspace/Zip/graid5-all.log That log contains two full seconds of requests, under the same circumstances as before (rsync and find processes stuck in wait, along with an 'ls' or two). If you need more, I can produce it. It appears to be completing requests, but always the same requests over and over. Watching the log for about a minute doesn't show any other requests during this time. [start] raid5/raid5[READ(offset=779825545216, length=16384)] [start] raid5/raid5[READ(offset=764410200064, length=16384)] Thanks! -- Fuzzy love, -CyberLeo Technical Administrator CyberLeo.Net Webhosting http://www.CyberLeo.Net Furry Peace! - http://www.fur.com/peace/ From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 01:17:05 2007 Return-Path: X-Original-To: freebsd-geom@FreeBSD.org Delivered-To: freebsd-geom@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 6883116A403 for ; Sat, 13 Jan 2007 01:17:05 +0000 (UTC) (envelope-from tataz@tataz.chchile.org) Received: from postfix2-g20.free.fr (postfix2-g20.free.fr [212.27.60.43]) by mx1.freebsd.org (Postfix) with ESMTP id 2D1E313C43E for ; Sat, 13 Jan 2007 01:17:04 +0000 (UTC) (envelope-from tataz@tataz.chchile.org) Received: from smtp1-g19.free.fr (smtp1-g19.free.fr [212.27.42.27]) by postfix2-g20.free.fr (Postfix) with ESMTP id 6131A8E736D for ; Sat, 13 Jan 2007 00:46:19 +0100 (CET) Received: from tatooine.tataz.chchile.org (tataz.chchile.org [82.233.239.98]) by smtp1-g19.free.fr (Postfix) with ESMTP id 077089B57E for ; Sat, 13 Jan 2007 01:46:10 +0100 (CET) Received: from obiwan.tataz.chchile.org (unknown [192.168.1.25]) by tatooine.tataz.chchile.org (Postfix) with ESMTP id 486F59D3DA for ; Sat, 13 Jan 2007 00:47:28 +0000 (UTC) Received: by obiwan.tataz.chchile.org (Postfix, from userid 1000) id 2F7F8405D; Sat, 13 Jan 2007 01:47:28 +0100 (CET) Date: Sat, 13 Jan 2007 01:47:28 +0100 From: Jeremie Le Hen To: freebsd-geom@FreeBSD.org Message-ID: <20070113004728.GQ2616@obiwan.tataz.chchile.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.13 (2006-08-11) Cc: Subject: What is gstripe ? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 01:17:05 -0000 Hi list, Please forgive me, I know this is a dumb question. I've checked the manpage, Wikipedia [1], Webopedia [2] and a few other documents, but I'm still not sure to fully understand the striping concept. gmirror(8) provides RAID-1 and is very easy to understand. gconcat(8) is easy to grasp as well. However, I'm experiencing some difficulties to understand gstripe(8). I would say it's a kind of smart disk concatenation which stores block X on disk (X % N), where N is the number of disk in the RAID-0. This permits faster read/write. Am I right ? [1] http://en.wikipedia.org/wiki/Data_striping [2] http://www.webopedia.com/TERM/R/RAID.html Thank you. Best regards, -- Jeremie Le Hen < jeremie at le-hen dot org >< ttz at chchile dot org > From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 04:25:42 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 9451E16A40F for ; Sat, 13 Jan 2007 04:25:42 +0000 (UTC) (envelope-from anderson@centtech.com) Received: from mh1.centtech.com (moat3.centtech.com [64.129.166.50]) by mx1.freebsd.org (Postfix) with ESMTP id 6900813C442 for ; Sat, 13 Jan 2007 04:25:42 +0000 (UTC) (envelope-from anderson@centtech.com) Received: from [192.168.42.21] (andersonbox1.centtech.com [192.168.42.21]) by mh1.centtech.com (8.13.8/8.13.8) with ESMTP id l0D4PYAt049234; Fri, 12 Jan 2007 22:25:39 -0600 (CST) (envelope-from anderson@centtech.com) Message-ID: <45A85F40.7050703@centtech.com> Date: Fri, 12 Jan 2007 22:25:36 -0600 From: Eric Anderson User-Agent: Thunderbird 1.5.0.9 (X11/20061223) MIME-Version: 1.0 To: Jeremie Le Hen References: <20070113004728.GQ2616@obiwan.tataz.chchile.org> In-Reply-To: <20070113004728.GQ2616@obiwan.tataz.chchile.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.88.4/2437/Thu Jan 11 17:59:09 2007 on mh1.centtech.com X-Virus-Status: Clean X-Spam-Status: No, score=-2.5 required=8.0 tests=AWL,BAYES_00 autolearn=ham version=3.1.6 X-Spam-Checker-Version: SpamAssassin 3.1.6 (2006-10-03) on mh1.centtech.com Cc: freebsd-geom@freebsd.org Subject: Re: What is gstripe ? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 04:25:42 -0000 On 01/12/07 18:47, Jeremie Le Hen wrote: > Hi list, > > Please forgive me, I know this is a dumb question. I've checked the > manpage, Wikipedia [1], Webopedia [2] and a few other documents, > but I'm still not sure to fully understand the striping concept. > > gmirror(8) provides RAID-1 and is very easy to understand. > gconcat(8) is easy to grasp as well. > > However, I'm experiencing some difficulties to understand gstripe(8). > I would say it's a kind of smart disk concatenation which stores > block X on disk (X % N), where N is the number of disk in the RAID-0. > This permits faster read/write. > > Am I right ? > > [1] http://en.wikipedia.org/wiki/Data_striping > [2] http://www.webopedia.com/TERM/R/RAID.html > > Thank you. > Best regards, Yea, that's pretty close! A stripe (RAID 0 - called that because it really isn't redundant in any way) is just like you described. Write one block to the first disk, then the next block to the next disk, etc. It distributes your read/write activity to increase performance. Sequential read/write performance may not be affected, but random IO should get a nice boost. See this site for some pretty graphics: http://www.raid.com/04_00.html or more specifically: http://www.raid.com/04_01_00.html Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology An undefined problem has an infinite number of solutions. ------------------------------------------------------------------------ From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 08:57:52 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id B47F316A407 for ; Sat, 13 Jan 2007 08:57:52 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30309.mail.mud.yahoo.com (web30309.mail.mud.yahoo.com [209.191.69.71]) by mx1.freebsd.org (Postfix) with SMTP id 7D3D213C46C for ; Sat, 13 Jan 2007 08:57:52 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 32064 invoked by uid 60001); 13 Jan 2007 08:57:51 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=wXasYloajFNu3XSu6eOP/zX7WvdylbFQIQZ0SASODyLxcHAmWyVYA0JeAH9G0nAbSkx7xFo4lX1o1B1aV/Yeqx5c+pp19KtPnOErYF6+wbPV9oLnZaRQTMcRc2YUt5tzmhSs5nHQtWUtb6UPGBhQAumt/uyY+i2CSe8LLO2Nb4g=; X-YMail-OSG: HSF9mvsVM1nknosatE6sT73tt4VnrWEXV8A3R3tLme4yTpFlRmwQETwZnmyGMbfOU3BHX9E05a0l74.m_lsZxIhv9VXcCPKsuhm36b70uNCXPgc.49oVNgM9u8IbLWpNIHKjQqUdcN7CInQ- Received: from [213.54.176.27] by web30309.mail.mud.yahoo.com via HTTP; Sat, 13 Jan 2007 00:57:51 PST Date: Sat, 13 Jan 2007 00:57:51 -0800 (PST) From: "R. B. Riddick" To: CyberLeo Kitsana In-Reply-To: <45A830CE.2050506@cyberleo.net> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <835894.31143.qm@web30309.mail.mud.yahoo.com> Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 08:57:52 -0000 --- CyberLeo Kitsana wrote: > R. B. Riddick wrote: > http://home.cyberleo.net/cyberleo/workspace/Zip/graid5-all.log > > That log contains two full seconds of requests, under the same > circumstances as before (rsync and find processes stuck in wait, along > with an 'ls' or two). If you need more, I can produce it. > > It appears to be completing requests, but always the same requests over > and over. Watching the log for about a minute doesn't show any other > requests during this time. > > [start] raid5/raid5[READ(offset=779825545216, length=16384)] > [start] raid5/raid5[READ(offset=764410200064, length=16384)] > Hmm... Thats strange... Possibly there happens an ENOMEM error, which would explain the repititions... A further debug line (it is again at debug level 2) before the current line 1165 (inside the inbed==children IF but in the end of it): G_RAID5_LOGREQ(bp, "[ready err%d cmp%jd]", obp->bio_error, obp->bio_completed); Or turn on "bootverbose"... For better data safety (e. g. in case of a power loss), I would recommend to reduce kern.geom.raid5.wdt to 0 or 1 (the lower the safer). For less memory consumtion I would use lower values for .maxmem and for .maxwql... -Arne ____________________________________________________________________________________ Now that's room service! Choose from over 150,000 hotels in 45,000 destinations on Yahoo! Travel to find your fit. http://farechase.yahoo.com/promo-generic-14795097 From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 10:40:00 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 375B816A407 for ; Sat, 13 Jan 2007 10:40:00 +0000 (UTC) (envelope-from etc@fluffles.net) Received: from auriate.fluffles.net (cust.95.160.adsl.cistron.nl [195.64.95.160]) by mx1.freebsd.org (Postfix) with ESMTP id 3F22213C448 for ; Sat, 13 Jan 2007 10:39:56 +0000 (UTC) (envelope-from etc@fluffles.net) Received: from destiny ([10.0.0.21]) by auriate.fluffles.net with esmtpa (Exim 4.63 (FreeBSD)) (envelope-from ) id 1H5gIh-000ONL-3b for freebsd-geom@freebsd.org; Sat, 13 Jan 2007 11:39:51 +0100 Message-ID: <45A8B722.7020302@fluffles.net> Date: Sat, 13 Jan 2007 11:40:34 +0100 From: Fluffles User-Agent: Thunderbird 1.5.0.8 (X11/20061114) MIME-Version: 1.0 To: freebsd-geom@freebsd.org References: <20070113004728.GQ2616@obiwan.tataz.chchile.org> <45A85F40.7050703@centtech.com> In-Reply-To: <45A85F40.7050703@centtech.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Subject: Re: What is gstripe ? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 10:40:00 -0000 Eric Anderson wrote: > On 01/12/07 18:47, Jeremie Le Hen wrote: >> Hi list, >> >> Please forgive me, I know this is a dumb question. I've checked the >> manpage, Wikipedia [1], Webopedia [2] and a few other documents, >> but I'm still not sure to fully understand the striping concept. >> >> gmirror(8) provides RAID-1 and is very easy to understand. >> gconcat(8) is easy to grasp as well. >> >> However, I'm experiencing some difficulties to understand gstripe(8). >> I would say it's a kind of smart disk concatenation which stores >> block X on disk (X % N), where N is the number of disk in the RAID-0. >> This permits faster read/write. >> >> Am I right ? >> >> [1] http://en.wikipedia.org/wiki/Data_striping >> [2] http://www.webopedia.com/TERM/R/RAID.html >> >> Thank you. >> Best regards, > > > Yea, that's pretty close! A stripe (RAID 0 - called that because it > really isn't redundant in any way) is just like you described. Write > one block to the first disk, then the next block to the next disk, > etc. It distributes your read/write activity to increase performance. > Sequential read/write performance may not be affected, but random IO > should get a nice boost. Both sequential and random I/O performance will be boosted. In fact, the sequential increase could be lineair; meaning that with twice the number of drives; twice the sequential transfer rate is achieved; if bus speed allows and the raid implementation is clean and efficient. The increase in random I/O is not always pronounced; only with a high concurrency a large performance increase in Random I/O is visible. Some benchmarks to illustrate this: Single drive (ad8) concurrency Performance in I/O's per sec. average 1 106 106 107 106 4 106 106 106 106 16 116 116 116 116 32 127 125 126 126 128 151 151 150 150 256 156 156 157 156 gstripe 4xad - 128KB stripe - FM off concurrency Performance in I/O's per sec. average 1 173 173 173 173 4 270 270 270 270 16 338 338 338 338 32 370 370 370 370 128 444 434 434 437 256 465 465 465 465 This comparison is a bit unfair since it's one disk versus 4, but the effect is clear; the largest performance increase happens with multiple concurrency. It's very important to select a high stripe size though; if you lower the stripesize to say 16KB the parallellisation effect will be almost gone: gstripe 4xad - 16KB stripe - FM off concurrency results (3 times) average 1 129 129 129 129 4 151 150 151 150 16 173 173 172 172 32 188 188 190 188 128 222 222 222 222 256 232 229 229 230 The increase in Sequential Transfer Rate (STR) is clearly visible here: -------Sequential Output-------- ---Sequential Input-- --Random-- -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks--- Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU 4096 104288 90.4 237690 74.4 71008 22.0 87837 91.9 250858 44.6 114.8 0.7 Here it shows 237MB/s write and 250MB/s read speed; which is almost lineair increase (4 x max STR). This, also, is with 4 drives. Compare with single drive: -------Sequential Output-------- ---Sequential Input-- --Random-- -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks--- Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU 4096 59391 50.7 59105 16.9 23664 7.0 62471 65.2 63045 10.0 103.7 0.6 Notice the big difference in rewrite-performance; that's a thing RAID0 is strong in. - Veronica From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 17:43:25 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id CE9EA16A403 for ; Sat, 13 Jan 2007 17:43:25 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: from pizzabox.cyberleo.net (alpha.cyberleo.net [198.145.45.10]) by mx1.freebsd.org (Postfix) with ESMTP id 8C7C813C44B for ; Sat, 13 Jan 2007 17:43:23 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: (qmail 60039 invoked from network); 13 Jan 2007 17:43:22 -0000 Received: from adsl-69-212-1-127.dsl.chcgil.ameritech.net (HELO ?172.16.44.14?) (cyberleo@cyberleo.net@69.212.1.127) by alpha.cyberleo.net with ESMTPA; 13 Jan 2007 17:43:22 -0000 Message-ID: <45A91A0F.8070701@cyberleo.net> Date: Sat, 13 Jan 2007 11:42:39 -0600 From: CyberLeo Kitsana User-Agent: Thunderbird 1.5 (X11/20051201) MIME-Version: 1.0 To: "R. B. Riddick" References: <835894.31143.qm@web30309.mail.mud.yahoo.com> In-Reply-To: <835894.31143.qm@web30309.mail.mud.yahoo.com> Content-Type: text/plain; charset=iso-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 17:43:25 -0000 R. B. Riddick wrote: > --- CyberLeo Kitsana wrote: >> ... > Possibly there happens an ENOMEM error, which would explain the repititions... > > A further debug line (it is again at debug level 2) before the current line > 1165 (inside the inbed==children IF but in the end of it): > G_RAID5_LOGREQ(bp, "[ready err%d cmp%jd]", obp->bio_error, obp->bio_completed); > Or turn on "bootverbose"... > > For better data safety (e. g. in case of a power loss), I would recommend to > reduce kern.geom.raid5.wdt to 0 or 1 (the lower the safer). > > For less memory consumtion I would use lower values for .maxmem and for > .maxwql... Good morning! http://home.cyberleo.net/cyberleo/workspace/Zip/graid5-all2.log http://home.cyberleo.net/cyberleo/workspace/Zip/graid5-all2-2.log I'm not sure what error 5 is, but it looks ominous. The first log shows two seconds of the first test, where only ad2s2 was showing up. The second log is after a restart of everything, and ad0s2, ad2s2, and ad6s2 show up, indicating that this most likely isn't just a drive, bus, or controller failure. The machine is on a UPS, so power loss isn't too much of an issue. What other impacts would reducing kern.geom.raid5.wdt have? -- Fuzzy love, -CyberLeo Technical Administrator CyberLeo.Net Webhosting http://www.CyberLeo.Net Furry Peace! - http://www.fur.com/peace/ From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 17:56:26 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id BA7B816A403 for ; Sat, 13 Jan 2007 17:56:26 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30305.mail.mud.yahoo.com (web30305.mail.mud.yahoo.com [209.191.69.67]) by mx1.freebsd.org (Postfix) with SMTP id 84D5A13C428 for ; Sat, 13 Jan 2007 17:56:26 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 51174 invoked by uid 60001); 13 Jan 2007 17:56:26 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=GerBdZIDbPJeisyIs9bsnGxCYblwxb6Cn0ovBNa8Cm7G2M551p6qwHTEe4mnUp1+MPNsyM02XvljEiP6buWPJXpSle6QISVat2zU9OJM5b8mMe3ckLdi4Bz1MoweQYlV7PwJS3LF4X1b9TJ26u8iaeRStZgnDv6v5r9JPyLcR1I= ; Message-ID: <20070113175625.51172.qmail@web30305.mail.mud.yahoo.com> X-YMail-OSG: PervTLwVM1n.Br3n6kEuMFbHzHjhdJtx_BkJYejXRODcXTGI9yu54EmnC5Bm7wWQLrdF66rd0G3I55ozQrqANkoxVx0z_pDaUb53IgHTTrryPO5ir1DrRHz5uQQBXbWLsBsymmkbW_exz08- Received: from [213.54.176.27] by web30305.mail.mud.yahoo.com via HTTP; Sat, 13 Jan 2007 09:56:25 PST Date: Sat, 13 Jan 2007 09:56:25 -0800 (PST) From: "R. B. Riddick" To: CyberLeo Kitsana In-Reply-To: <45A91A0F.8070701@cyberleo.net> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 17:56:26 -0000 --- CyberLeo Kitsana wrote: > Good morning! > Thx. U2! :-) > I'm not sure what error 5 is, but it looks ominous. > That is EIO... Dont know where it comes from. We would know better, if u change the line around 1292 or so from G_RAID5_LOGREQ(bp, "[done]"); to G_RAID5_LOGREQ(bp, "[done err%d]",bp->bio_error); and after line 1160 (the line with = EIO;) G_RAID5_LOGREQ(bp, "[not-equal]"); Then wait for this suspected live lock again and look for messages and then set debug level to 2... > The first log shows two seconds of the first test, where only ad2s2 was > showing up. The second log is after a restart of everything, and ad0s2, > ad2s2, and ad6s2 show up, indicating that this most likely isn't just a > drive, bus, or controller failure. > Possibly... Maybe U need to run a verify manually (graid5 configure -R )... Are u sure, that a complete verify run took place after label'ing the graid5 device? > The machine is on a UPS, so power loss isn't too much of an issue. What > other impacts would reducing kern.geom.raid5.wdt have? > OK - UPS is nice... is the number of seconds, graid5 waits before it executes a write request... So lower wdt means, lower chances for write optimization in favor to lower chances for data loss... Btw.: A kernel crash could result in such data loss, too (just like a power failure)... -Arne ____________________________________________________________________________________ 8:00? 8:25? 8:40? Find a flick in no time with the Yahoo! Search movie showtime shortcut. http://tools.search.yahoo.com/shortcuts/#news From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 18:48:04 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 354B616A403 for ; Sat, 13 Jan 2007 18:48:04 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: from pizzabox.cyberleo.net (alpha.cyberleo.net [198.145.45.10]) by mx1.freebsd.org (Postfix) with ESMTP id EA82A13C45A for ; Sat, 13 Jan 2007 18:48:03 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: (qmail 61025 invoked from network); 13 Jan 2007 18:48:03 -0000 Received: from adsl-69-212-1-127.dsl.chcgil.ameritech.net (HELO ?172.16.44.14?) (cyberleo@cyberleo.net@69.212.1.127) by alpha.cyberleo.net with ESMTPA; 13 Jan 2007 18:48:03 -0000 Message-ID: <45A9293B.2070607@cyberleo.net> Date: Sat, 13 Jan 2007 12:47:23 -0600 From: CyberLeo Kitsana User-Agent: Thunderbird 1.5 (X11/20051201) MIME-Version: 1.0 To: "R. B. Riddick" References: <20070113175625.51172.qmail@web30305.mail.mud.yahoo.com> In-Reply-To: <20070113175625.51172.qmail@web30305.mail.mud.yahoo.com> Content-Type: text/plain; charset=iso-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 18:48:04 -0000 R. B. Riddick wrote: > and after line 1160 (the line with = EIO;) > G_RAID5_LOGREQ(bp, "[not-equal]"); Does this addition go within the 'if' block or below it? I am certain that the verify ran to completion because, while initially assembling the RAID, I distinctly remember complaining about how long it took to verify 1.2 terabytes. I also emulated a disk failure during later testing, to verify that the array was rebuilt correctly afterwards. It is unlikely the wdt setting will have much effect, as the data gets dumped all at once anyways, and all filesystems are sync'ed immediately afterwards. Thanks for the suggestion, though. -- Fuzzy love, -CyberLeo Technical Administrator CyberLeo.Net Webhosting http://www.CyberLeo.Net Furry Peace! - http://www.fur.com/peace/ From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 19:14:33 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 1BDB316A407 for ; Sat, 13 Jan 2007 19:14:33 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30312.mail.mud.yahoo.com (web30312.mail.mud.yahoo.com [209.191.69.74]) by mx1.freebsd.org (Postfix) with SMTP id C356713C44B for ; Sat, 13 Jan 2007 19:14:32 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 58053 invoked by uid 60001); 13 Jan 2007 19:14:32 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=pUYO7ukm8bbMoIFfSuFPQp3eKc2pZwl7nR87vSQJQPkr2g3b3puT70zPg/SXowBZC22FQg4+2uR6zD1hSbwcfBuEX8XbAIlJntVroA49CicExrdCHk5CYozBvdoWQY+xf0Ta0jpBJJAKcgaatPjbEhnxRAzhrnSkmM/8XwRDpso=; X-YMail-OSG: MDZ4xpIVM1nO3p70LiA4YjmVeOiQ8R8SPlckFzLLFcoTrqcyUB1HhfvsYRxaX7iGS1htCOp4JaloDMNXGYQE7WmkI_0Ivb1.mD._tGq4r5LKArPM77_Bzy3Ww7W7agxqvK.48_33HLLnNYw- Received: from [213.54.176.27] by web30312.mail.mud.yahoo.com via HTTP; Sat, 13 Jan 2007 11:14:31 PST Date: Sat, 13 Jan 2007 11:14:31 -0800 (PST) From: "R. B. Riddick" To: CyberLeo Kitsana In-Reply-To: <45A9293B.2070607@cyberleo.net> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <157957.58037.qm@web30312.mail.mud.yahoo.com> Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 19:14:33 -0000 --- CyberLeo Kitsana wrote: > R. B. Riddick wrote: > > and after line 1160 (the line with = EIO;) > > G_RAID5_LOGREQ(bp, "[not-equal]"); > > Does this addition go within the 'if' block or below it? > Just below the 'if block'... > I am certain that the verify ran to completion because, while initially > assembling the RAID, I distinctly remember complaining about how long it > took to verify 1.2 terabytes. I also emulated a disk failure during > later testing, to verify that the array was rebuilt correctly afterwards. > Hmm... And after that "emulated disk failure"? :-) Did u run the verify again? > It is unlikely the wdt setting will have much effect, as the data gets > dumped all at once anyways, and all filesystems are sync'ed immediately > afterwards. Thanks for the suggestion, though. > OK... -Arne ____________________________________________________________________________________ Want to start your own business? Learn how on Yahoo! Small Business. http://smallbusiness.yahoo.com/r-index From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 20:10:51 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 2792E16A412 for ; Sat, 13 Jan 2007 20:10:51 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.freebsd.org (Postfix) with ESMTP id DD4AF13C465 for ; Sat, 13 Jan 2007 20:10:50 +0000 (UTC) (envelope-from gcubfg-freebsd-geom@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1H5pDC-0005Eo-9s for freebsd-geom@freebsd.org; Sat, 13 Jan 2007 21:10:46 +0100 Received: from p3ee2281c.dip0.t-ipconnect.de ([62.226.40.28]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Sat, 13 Jan 2007 21:10:46 +0100 Received: from christian.baer by p3ee2281c.dip0.t-ipconnect.de with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Sat, 13 Jan 2007 21:10:46 +0100 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-geom@freebsd.org From: Christian Baer Date: Sat, 13 Jan 2007 21:01:05 +0100 (CET) Organization: Convenimus Projekt Lines: 17 Message-ID: X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: p3ee2281c.dip0.t-ipconnect.de User-Agent: slrn/0.9.8.1 (FreeBSD) Sender: news Subject: What does geli attach -a do? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 20:10:51 -0000 Good evening, folks! Ok, I know what that does. I can read manpages. :-) Is the effekt of this somehow documented by numbers though? Basicly meaning: Does this function 'only' tell me if the data on the provider is currupt? Or does it help to isolate it or can even restore broken data (to a point). If one of the latter ist the case, what are the numbers on this? How much data (in per cent) may be broken, before no more isolation and/or restoration is possible? Does it make sense to use this in combination with a mirror? Regards Chris From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 20:21:03 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 3A7E816A403 for ; Sat, 13 Jan 2007 20:21:03 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (arm132.internetdsl.tpnet.pl [83.17.198.132]) by mx1.freebsd.org (Postfix) with ESMTP id C4FB713C45B for ; Sat, 13 Jan 2007 20:21:01 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id C537D487FF; Sat, 13 Jan 2007 21:20:59 +0100 (CET) Received: from localhost (154.81.datacomsa.pl [195.34.81.154]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id BB852487F2; Sat, 13 Jan 2007 21:20:54 +0100 (CET) Date: Sat, 13 Jan 2007 21:20:18 +0100 From: Pawel Jakub Dawidek To: Christian Baer Message-ID: <20070113202018.GK90718@garage.freebsd.pl> References: MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="M0YLxmUXciMpOLPE" Content-Disposition: inline In-Reply-To: X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 7.0-CURRENT i386 User-Agent: mutt-ng/devel-r804 (FreeBSD) X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-2.6 required=3.0 tests=BAYES_00 autolearn=ham version=3.0.4 Cc: freebsd-geom@freebsd.org Subject: Re: What does geli attach -a do? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 20:21:03 -0000 --M0YLxmUXciMpOLPE Content-Type: text/plain; charset=iso-8859-2 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sat, Jan 13, 2007 at 09:01:05PM +0100, Christian Baer wrote: > Good evening, folks! >=20 > Ok, I know what that does. I can read manpages. :-) >=20 > Is the effekt of this somehow documented by numbers though? Basicly > meaning: Does this function 'only' tell me if the data on the provider > is currupt? Or does it help to isolate it or can even restore broken > data (to a point). It'll tell you exact offset and size where corrupted data were detected. It won't help you bring you data back, it's a security feature, not a reliability feature, but can be used also to detect silent data corruptions. > If one of the latter ist the case, what are the numbers on this? How > much data (in per cent) may be broken, before no more isolation and/or > restoration is possible? >=20 > Does it make sense to use this in combination with a mirror? If you're afraid of silent data corruptions, then yes. When one half of the mirror will be corrupted and geli will detect it, gmirror will read the data from the other half. Unfortunately authentication-only mode is not supported in geli at the moment, so you have encryption/decription overhead. If you don't care about this overhead, and don't care about security, this is how you can create such configuration: # geli init -a HMAC/MD5 -s 4096 -P -K /dev/null /dev/da0 # geli init -a HMAC/MD5 -s 4096 -P -K /dev/null /dev/da1 # geli attach -p -k /dev/null /dev/da0 # geli attach -p -k /dev/null /dev/da1 # gmirror label foo /dev/da? --=20 Pawel Jakub Dawidek http://www.wheel.pl pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --M0YLxmUXciMpOLPE Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (FreeBSD) iD8DBQFFqT8CForvXbEpPzQRAu+CAKCwG3WuCERNXll3LAd31ApwdcNDqwCdEV8f JsT6U1JPsHTJt3QVjc/7e8E= =3pv4 -----END PGP SIGNATURE----- --M0YLxmUXciMpOLPE-- From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 23:02:15 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id A7CB216A412 for ; Sat, 13 Jan 2007 23:02:15 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: from pizzabox.cyberleo.net (alpha.cyberleo.net [198.145.45.10]) by mx1.freebsd.org (Postfix) with ESMTP id 6D45813C448 for ; Sat, 13 Jan 2007 23:02:15 +0000 (UTC) (envelope-from cyberleo@cyberleo.net) Received: (qmail 65956 invoked from network); 13 Jan 2007 23:02:14 -0000 Received: from adsl-69-212-1-127.dsl.chcgil.ameritech.net (HELO ?172.16.44.14?) (cyberleo@cyberleo.net@69.212.1.127) by alpha.cyberleo.net with ESMTPA; 13 Jan 2007 23:02:14 -0000 Message-ID: <45A964CA.5090408@cyberleo.net> Date: Sat, 13 Jan 2007 17:01:30 -0600 From: CyberLeo Kitsana User-Agent: Thunderbird 1.5 (X11/20051201) MIME-Version: 1.0 To: "R. B. Riddick" References: <157957.58037.qm@web30312.mail.mud.yahoo.com> In-Reply-To: <157957.58037.qm@web30312.mail.mud.yahoo.com> Content-Type: text/plain; charset=iso-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 23:02:15 -0000 R. B. Riddick wrote: > --- CyberLeo Kitsana wrote: >> ... > Hmm... And after that "emulated disk failure"? :-) Did u run the verify again? Yeah. Rebuilt the whole thing, then verified the parity, as well as all the data on the filesystem. Is there a way to unload the geom_raid5 module? Every time I try using kldunload or graid5 unload, it tells me it's busy. graid5 stop does stop the array (after unmounting) but it's started up again immediately after. Thanks! -- Fuzzy love, -CyberLeo Technical Administrator CyberLeo.Net Webhosting http://www.CyberLeo.Net Furry Peace! - http://www.fur.com/peace/ From owner-freebsd-geom@FreeBSD.ORG Sat Jan 13 23:21:30 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 5796316A403 for ; Sat, 13 Jan 2007 23:21:30 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30301.mail.mud.yahoo.com (web30301.mail.mud.yahoo.com [209.191.69.63]) by mx1.freebsd.org (Postfix) with SMTP id 0760A13C442 for ; Sat, 13 Jan 2007 23:21:29 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 20263 invoked by uid 60001); 13 Jan 2007 23:21:29 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=ftba2ytrbTQaIXaGp5eX5+YFF2g9b1y7BsGfteZ5Jr4KSC1MUNAHbBTCXeZrHFPqORaMrmZnf+RvCVXn00twOf8PlJj9wsvX0gWVnIETjEF7wg5RIx9VKtWCPLtnLMfK/BL2Nnkrim1Im33RSusuYEXlE1nzLLhlOSHEfc2TbB0=; X-YMail-OSG: KXg1BZcVM1mrBd0HjQzKORTrdNr5n8iTSTWbQqn4FKSgBX.76xDgwxrwd_szfStIU72n1gnWWvzC6ghd.Bpm6SrdKHpHegoZirkUyfa2PkGoF1ql_f9MPc0INjlbhAGgj3qr3Uh_lDL.UhQ- Received: from [213.54.176.27] by web30301.mail.mud.yahoo.com via HTTP; Sat, 13 Jan 2007 15:21:29 PST Date: Sat, 13 Jan 2007 15:21:29 -0800 (PST) From: "R. B. Riddick" To: CyberLeo Kitsana In-Reply-To: <45A964CA.5090408@cyberleo.net> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <376348.20105.qm@web30301.mail.mud.yahoo.com> Cc: FreeBSD Geom Subject: Re: geom_raid5 livelock? X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Jan 2007 23:21:30 -0000 --- CyberLeo Kitsana wrote: > Is there a way to unload the geom_raid5 module? Every time I try using > kldunload or graid5 unload, it tells me it's busy. graid5 stop does stop > the array (after unmounting) but it's started up again immediately after. > Hmm - not really... If u r really fast possibly... ;-) Try "repeat 100 sh -c 'kldunload geom_raid5.ko &'" (on ur OWN risk)... ;-) What happened to our little debug message project (lets call it "Preparation D")? I mean: The debug message in case of a parity mismatch during a verify read... -Arne ____________________________________________________________________________________ 8:00? 8:25? 8:40? Find a flick in no time with the Yahoo! Search movie showtime shortcut. http://tools.search.yahoo.com/shortcuts/#news