On 3/23/09 11:46 PM, "Shane Ginnane" <sginn...@isi.com.au> wrote:
>> Interesting, but requires Xen or KVM to work in current form, and relies > on >> being able to just pass through instructions to the base hardware for > things >> that don't require privileged ops. > > I don't see that as an intrinsic problem. > Remove z/VM from the equation and ... ? Let's just say its an enourmous amount of effort to do right, and in this case, good enough isn't good enough. > No doubt Mark is correct re the usability of the z KVM at present, but one > would imagine that has to improve. I doubt it. There is a reliable low-cost solution already available, and one that does a far better job of providing resource management knobs. I know I wouldn't pay anyone to bother with zKVM. It's not designed to scale in the way we need it to work on Z, and I really don't much care for the way the KVM developers operate wrt NIH patches. ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to lists...@vm.marist.edu with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390