|
|
|
|
|
|
|
|
|
|
xen-devel
[Xen-devel] Re: Linux patch "translate Xen-provided PIRQs"
On 8/9/08 12:17, "Jan Beulich" <jbeulich@xxxxxxxxxx> wrote:
>> I'm not personally bothered enough about this patch to fix it myself (I know
>> that Jeremy has other approaches in pv_ops, which has to be what we move to
>> during 3.4 development), so this is FYI if you want to fix it up for the
>> 2.6.18 tree.
>
> So you really think this will not only be available, but also stable and at
> feature parity with the current tree within about half a year? I've got
> other significant changes to event channel handling pending that I would
> only bother to make apply to 2.6.18 if there's really going to be any use
> (and testing) for them in that tree. They mostly have to do with the
> scalability issue of currently binding per-CPU IPIs and VIRQs to one
> (kernel) IRQ for each CPU, whereas they should really use a single per-CPU
> IRQ to bind all event channels resulting from the same IPI/VIRQ (Jeremy
> indicated he had something similar in mind for pv-ops).
I believe we will be testing and running a xenbits pv_ops-based tree within
6 months, yes. Obviously we will have branches containing patches not yet
in, or perhaps suitable for, upstream. Actually I hope we can move
decisively towards this in the next couple of months, once Jeremy has the
basic dom0 stuff working well enough.
-- Keir
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
|
|
|
|