Subject: Re: comparing raid-like filesystems
To: Martin J. Laubach <email@example.com>
From: Jason R Thorpe <firstname.lastname@example.org>
Date: 02/02/2003 09:06:10
On Sun, Feb 02, 2003 at 01:31:25PM +0000, Martin J. Laubach wrote:
> (b) no MAXPHYS at all and let the low level driver deal with
> segmenting large requests if necessary
This is clearly what we prefer.
> Remind me again why MAXPHYS is needed at all, is it just for histerical
> reasons and no one ever bothered to remove that limitation?
Yes, but those reasons are now well-entrenched. E.g. we still map pages
into KVA in order to do I/O, even if that is not actually necessary.
-- Jason R. Thorpe <email@example.com>