From: David Wood (jbevren_at_starbase.globalpc.net)
Date: 2007-12-14 23:02:57
I realize this would be slow, but relative to the speed of the IEC protocol,
why not swap bufferspace into and out of a couple reserved harddisk sectors?
That may cause premature flash failure on flash devices taht arent smart
enough to do proper wear leveling, but on a regular magnetic disk I dont see
a problem.
Impact would be minimal as well, only causing delays while writing data.
-jbev
On Fri, 14 Dec 2007, Jim Brain wrote:
> ruud.baltissen@abp.nl wrote:
> > I only have one remark: it will be very difficult to use the 512 bytes
> > sectors as they are. For example: using the well known Track/Sector
> > linking won't work as the Sector byte is used to tell the system how
> > many bytes are used on the last track. And a byte cannot store numbers
> > greater than 255 :(
> > And I already mentioned it on my site: splitting the 512 bytes sector in
> > two 256 bytes Commodore sectors is no problem. But it needs extra work
> > to save one C= sector and IMHO extra RAM.
> >
> I see no other option short of mapping each IDE sector into 2 CBM
> sectors. But, it does require at least 1 more 256 byte buffer.
> > These remarks are not for putting the design down but just to remind
> > people of some facts. I only hope that maybe one of us comes with an
> > enginious idea to cope with these challenges.
> >
> It is my hope that the HW design will allow more people to work with it,
> reducing the problem to a small issue.
>
>
> Jim
>
> Message was sent through the cbm-hackers mailing list
>
Message was sent through the cbm-hackers mailing list
Archive generated by hypermail pre-2.1.8.