Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 24 Feb 2004 18:28:12 +1030
From:      Greg 'groggy' Lehey <grog@FreeBSD.org>
To:        Danny Carroll <danny@dannysplace.net>
Cc:        freebsd-questions@freebsd.org
Subject:   Re: Help with Vinum disk crash...
Message-ID:  <20040224075812.GI87020@wantadilla.lemis.com>
In-Reply-To: <1077607815.7l8mfcl97gso@mailsrv.dannysplace.net>
References:  <1077093269.15aypd5fp76s@mailsrv.dannysplace.net> <20040218111653.GB289@marvin.home.local> <1077106518.yyrhxqeampw@mailsrv.dannysplace.net> <20040218140429.GG289@marvin.home.local> <1077180395.4prky8v4skqo@mailsrv.dannysplace.net> <20040219222221.GA88317@marvin.home.local> <20040223043113.GV87020@wantadilla.lemis.com> <1077536659.61xvlite2kso@mailsrv.dannysplace.net> <20040224001635.GM87020@wantadilla.lemis.com> <1077607815.7l8mfcl97gso@mailsrv.dannysplace.net>

next in thread | previous in thread | raw e-mail | index | archive | help

--jp3593ZFbct1pBYM
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline

On Tuesday, 24 February 2004 at  8:30:15 +0100, Danny Carroll wrote:
>>> vinum and ide on my system results is very poor disk performance, I
>>> see a 10-fold increase in read/write actions.  I'll be interested in
>>> revisiting vinum with some SCSI disks sometime soon.
>>
>> How did you test it?
>
> I have 4 ata133 ide disks, all identical.  They run off a promise ata133 io
> card.
>
> With vinum, all 4 disks are accessed at pretty much the same time, no matter
> what you do.

No, that's not correct.  It does happen if you choose too small a
stripe size, but that's the best reason for choosing larger stripes.
That's described in much detail in the man page.

>  Without, you only access the disk that you are writing to.  It goes
> a lot faster but I have to manage my data usage more.
>
> I dont blame vinum, I blame my ide subsystem.

No, it's not your IDE subsystem.  That usually works better than you
think.  But performance is an issue.  You need to test with access
patterns which relate to what you're really doing: sequential access
testing can often prove irrelevant.

Greg
--
When replying to this message, please copy the original recipients.
If you don't, I may ignore the reply or reply to the original recipients.
For more information, see http://www.lemis.com/questions.html
Note: I discard all HTML mail unseen.
Finger grog@FreeBSD.org for PGP public key.
See complete headers for address and phone numbers.

--jp3593ZFbct1pBYM
Content-Type: application/pgp-signature
Content-Disposition: inline

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.0 (FreeBSD)

iD8DBQFAOwQUIubykFB6QiMRAvLuAKCbLF6cDE1VtnK9LUb+Ov5UB4g2VQCfaIFx
pwp2VlhTyyZRRW+uBRl/zfA=
=oCok
-----END PGP SIGNATURE-----

--jp3593ZFbct1pBYM--



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20040224075812.GI87020>