Date: Fri, 4 May 2007 19:38:03 +1000 From: Peter Jeremy <peterjeremy@optushome.com.au> To: Ian Smith <smithi@nimnet.asn.au> Cc: stable@freebsd.org Subject: Re: acd and iostat [was Re: FreeBSD vs Region Code DVDs] Message-ID: <20070504093803.GD818@turion.vk2pj.dyndns.org> In-Reply-To: <Pine.BSF.3.96.1070504164043.16876D-100000@gaia.nimnet.asn.au> References: <463AD28B.9070709@samsco.org> <Pine.BSF.3.96.1070504164043.16876D-100000@gaia.nimnet.asn.au>
next in thread | previous in thread | raw e-mail | index | archive | help
--g7w8+K/95kPelPD2 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On 2007-May-04 16:51:05 +1000, Ian Smith <smithi@nimnet.asn.au> wrote: >Thanks. The only other reason I can see for removing acdX from these >stats would be to save on some admittedly precious screen real estate. Having cd0, acd0 and pass0 as three separate entries does strike me as excessive. I think that, in general, what is wanted is an indication of the I/O load on a device, not the I/O load on the different I/O paths to that device. Not reporting acd0 at all is not a fix. Ideally, either the kernel or vmstat would combine these statistics into a single set (though I'm not sure how to work out that cd0, acd0 and pass0 reference the same device). --=20 Peter Jeremy --g7w8+K/95kPelPD2 Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (FreeBSD) iD8DBQFGOv77/opHv/APuIcRAksYAKCKA0UTCCB19VYyGfc/OKVddnYGpACdHXvi nJOUVprrXGhQcSbEo5jO9Qg= =77Ia -----END PGP SIGNATURE----- --g7w8+K/95kPelPD2--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070504093803.GD818>