From owner-freebsd-questions@FreeBSD.ORG Fri Jan 28 09:29:00 2005 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id EF39C16A4CE for ; Fri, 28 Jan 2005 09:29:00 +0000 (GMT) Received: from chello084114137224.1.15.vie.surfer.at (chello084114137224.1.15.vie.surfer.at [84.114.137.224]) by mx1.FreeBSD.org (Postfix) with SMTP id 759E343D46 for ; Fri, 28 Jan 2005 09:28:57 +0000 (GMT) (envelope-from 4711@chello.at) Received: (qmail 71385 invoked from network); 28 Jan 2005 09:28:56 -0000 Received: from matrix010.matrix.net (HELO localhost) (192.168.123.10) by ns.matrix.net with SMTP; 28 Jan 2005 09:28:56 -0000 From: Christian Hiris <4711@chello.at> To: freebsd-questions@freebsd.org, Chad Morland Date: Fri, 28 Jan 2005 10:28:37 +0100 User-Agent: KMail/1.7.2 References: <8ca9329050127121428870c21@mail.gmail.com> <200501272257.13719.4711@chello.at> <8ca932905012714123989b0d6@mail.gmail.com> In-Reply-To: <8ca932905012714123989b0d6@mail.gmail.com> MIME-Version: 1.0 Content-Type: multipart/signed; boundary="nextPart1302693.ax1jV1fY2j"; protocol="application/pgp-signature"; micalg=pgp-sha1 Content-Transfer-Encoding: 7bit Message-Id: <200501281028.55885.4711@chello.at> Subject: Re: RAID1, a failed disk and performance X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 28 Jan 2005 09:29:01 -0000 --nextPart1302693.ax1jV1fY2j Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline On Thursday 27 January 2005 23:12:23, Chad Morland wrote: > > http://members.chello.at/freebsd-5.3/bonnie-gmirror/summary > > http://members.chello.at/freebsd-5.3/bonnie-gmirror/detail > > I expect to see data transfer rate increase when you break the mirror. > RAID1 has the higest disk overhead of all RAID configurations and is > very inefficient in that regard. It would be interesting to see > performance results with the bad disk still attached to the mirror. > Unfortunately I am not able to break disks on a whim so I can't test > it out. :P I also run the bechmarks with the gnop class invoked. It seems that the 'gn= op=20 =2Df nnn' option doesn't work, so that I couldn't observe any significant=20 performance differences. I own several really nice broken IBM SCSI disks, b= ut=20 they are broken in such a way, that the mirrors break immediately after=20 hitting the damaged areas. Maybe it's the better solution to run smartd fro= m=20 ports/smartctl and replace flaky disks asap. =20 =2D-=20 Christian Hiris <4711@chello.at> | OpenPGP KeyID 0x3BCA53BE=20 OpenPGP-Key at hkp://wwwkeys.eu.pgp.net and http://pgp.mit.edu --nextPart1302693.ax1jV1fY2j Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.0 (FreeBSD) iD8DBQBB+gXX09WjGjvKU74RAsaZAKCDBM6JirKa+g2hJk5AHXosj7K/OwCeMqEK cXfg2vDF6kX8LJSIIWGKXis= =E65/ -----END PGP SIGNATURE----- --nextPart1302693.ax1jV1fY2j--