This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
Home Products Support Community News


[Xen-devel] Re: Linux patch "translate Xen-provided PIRQs"

To: Jan Beulich <jbeulich@xxxxxxxxxx>
Subject: [Xen-devel] Re: Linux patch "translate Xen-provided PIRQs"
From: Keir Fraser <keir.fraser@xxxxxxxxxxxxx>
Date: Mon, 08 Sep 2008 13:12:04 +0100
Cc: xen-devel@xxxxxxxxxxxxxxxxxxx
Delivery-date: Mon, 08 Sep 2008 05:12:33 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
In-reply-to: <48C52603.76E4.0078.0@xxxxxxxxxx>
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
Thread-index: AckRrBrkWbkmmH2fEd2nVwAX8io7RQ==
Thread-topic: Linux patch "translate Xen-provided PIRQs"
User-agent: Microsoft-Entourage/
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

<Prev in Thread] Current Thread [Next in Thread>