pretty big deal as the linux implementations I have worked with all turn
on the DAT bit.
Linux is pretty sophisticated about address space handling as compared
to say CMS.
XC  - extended configuration - mode was more or less invented as a way
for a DAT off
o/s (CMS) to get at dataspaces. Data spaces in the truest z/series
context are DAT on implementations.

However in the weeds seems to me that a true DAT on dataspace
implementation would be awesome.

David Kreuter

Adam Thornton wrote:

This is wandering off into the weeds a bit:

How hard would it be to teach Linux about XC mode?

I mean, a most-console-stuff shared filesystem, before any big apps go
on it, is close to 500M.  I can see wanting well over a gig there.  The
problem, of course, is that (virtual machine size) + (filesystem DCSS
size) must be < 2G.

Now, if I could put my filesystems in a dataspace, I could have a whole
bunch of 2G filesystems, and I could LVM them together if I wanted
(obviously, I don't want to do much of this, since I have a limited
amount of real memory, but I can see wanting, say, a 3G shared Linux
filesystem for my guests on a 24G real storage box).

Of course, for this to happen, Linux would have to learn about XC mode.
I don't know enough to know whether this is "no big deal", "ooh,
tricky", or "hey, while you're wishing, how about throwing in the pony
too" in terms of implementation complexity.

Anyone?

Adam



Reply via email to