On 4 Jun 2002 eeh@netbsd.org wrote:

> | As I understand what Chuck did, all i/os have to be in terms of underlying
> | disk sectors. So you won't get two writes to sub-sector parts because you
> | can't write less than a sector.
>
> Actually, I thought it was the other way around.  All IOPs are done in terms
> of DEV_BSIZE.  If they were all done in terms of the device's block size we
> wouldn't be having any of this conversation and 2KB devices would just work.

As I understand it, all IOPs are expressed in units of DEV_BSIZE, but they
have to map to an integer number of real sectors.

So for instance on a 1k device when DEV_BSIZE is 512, all i/o has to be in
an even number of DEV_BSIZE sectors, and start on even DEV_BSIZE sector
boundries.

> I suppose I need to re-read large parts of the kernel post-UBC to see what's
> really going on now.

I'm not sure if that'll help for this. The work is in progress, and so you
mightn't find the code in a consistent state. :-|

Take care,

Bill