Date: Mon, 14 Sep 1998 21:55:36 +0000 (GMT) From: Terry Lambert <tlambert@primenet.com> To: dg@root.com Cc: dan@math.berkeley.edu, freebsd-current@FreeBSD.ORG Subject: Re: Download of FreeBSD 3.0-SNAP Message-ID: <199809142155.OAA00546@usr05.primenet.com> In-Reply-To: <199809141722.KAA16867@implode.root.com> from "David Greenman" at Sep 14, 98 10:22:02 am
next in thread | previous in thread | raw e-mail | index | archive | help
> >> >FreeBSD no longer does elevator sorts on data pending output, > >> >relying instead on the disk hardware to be smarter about this, > >> >especially given the likelihood that the drive is lying about > >> >its pysical geometry, making it unlikely that any sort you > >> >could do would result in an optimization. > > > >Even so, the driver should sort the I/O requests whenever the > >system's buffer queue for the drive exceeds the capacity of > >the system/host-adapter/drive for concurrently active commands. > >Since actual drive "geometry" is usually messy these days, > >a simple minded sort by block number would be appropriate. > > For the record, the quote that you sited above was Terry's, not mine, and > in any case doesn't match reality. As I already stated in a followup; I was mistaken about the code having been diked out in all cases; it was only diked out in some; which ones, I can't tell you right now. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199809142155.OAA00546>