From owner-freebsd-hackers Fri Jul 28 17:43: 6 2000 Delivered-To: freebsd-hackers@freebsd.org Received: from wantadilla.lemis.com (wantadilla.lemis.com [192.109.197.80]) by hub.freebsd.org (Postfix) with ESMTP id D6BAC37B5C3 for ; Fri, 28 Jul 2000 17:42:55 -0700 (PDT) (envelope-from grog@wantadilla.lemis.com) Received: (from grog@localhost) by wantadilla.lemis.com (8.9.3/8.9.3) id KAA14319; Sat, 29 Jul 2000 10:12:40 +0930 (CST) (envelope-from grog) Date: Sat, 29 Jul 2000 10:12:40 +0930 From: Greg Lehey To: Maxim Konovalov Cc: freebsd-hackers@FreeBSD.ORG Subject: Re: vinum striping quiestion Message-ID: <20000729101239.B92724@wantadilla.lemis.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.4i In-Reply-To: ; from koma@rbc.ru on Fri, Jul 28, 2000 at 07:21:10PM +0400 Organization: LEMIS, PO Box 460, Echunga SA 5153, Australia Phone: +61-8-8388-8286 Fax: +61-8-8388-8725 Mobile: +61-418-838-708 WWW-Home-Page: http://www.lemis.com/~grog X-PGP-Fingerprint: 6B 7B C3 8C 61 CD 54 AF 13 24 52 F8 6D A4 95 EF Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Friday, 28 July 2000 at 19:21:10 +0400, Maxim Konovalov wrote: > > Hello, > > I've got a question about vinum. There are two scsi disks with vinum > stripe. Here is a vinum config: > > drive a device /dev/da2s1e > drive b device /dev/da3s1e > volume vinum0 > plex name vinum0.p0 org striped 1024s vol vinum0 > sd name vinum0.p0.s0 drive a plex vinum0.p0 > len 34791424s driveoffset 265s plexoffset 0s > sd name vinum0.p0.s1 drive b plex vinum0.p0 > len 34791424s driveoffset 265s plexoffset 1024s Please show the output of 'vinum list'. > # uname -sr > FreeBSD 4.1-STABLE > > There are not any other fs on these disks. The problem is - when I run > iozone (iozone 4096 /logs/io0.tmp) I get a very strange result: > > # iostat -d da1 da3 10 > da1 da3 > KB/t tps MB/s KB/t tps MB/s > 0.00 0 0.00 0.00 0 0.00 > 4.50 107 0.47 0.00 0 0.00 > 4.51 98 0.43 0.00 0 0.00 > 4.50 116 0.51 0.00 0 0.00 > 4.49 117 0.52 0.00 0 0.00 > 4.50 111 0.49 0.00 0 0.00 > .... > > You see, there is not activity on da3. Are there any explanations? I think this says more about iozone than it does about Vinum. Try running rawio instead and see what happens. Note also that a stripe size which is a power of two is not a good idea. It can give rise to the kind of behaviour you report: since cylinder groups are usually 32 MB in size, this arrangement will put all the super blocks on the same subdisk. Use an odd number, say 283 kB, instead. Greg -- Finger grog@lemis.com for PGP public key See complete headers for address and phone numbers To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message