[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] Event channel performance optimize

To: Pasi Kärkkäinen <pasik@xxxxxx>
From: Keir Fraser <keir.fraser@xxxxxxxxxxxxx>
Date: Tue, 27 Apr 2010 06:47:59 +0100
Cc: qiushanggao <qsg0720@xxxxxxx>, "xen-devel@xxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxx>
Delivery-date: Mon, 26 Apr 2010 22:49:03 -0700
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
Thread-index: AcrliCjF3TmmCOyCRQWwMe+IlarbIQARQhvM
Thread-topic: [Xen-devel] Event channel performance optimize

On 26/04/2010 22:33, "Pasi Kärkkäinen" <pasik@xxxxxx> wrote:

>> It's not true. An event can be delivered to any dom0 vcpu. They are
>> presented as a type of irq to the dom0 kernel, and hence normal Linux
>> load-balancing strategies such as irqbalanced will apply.
>> 
> 
> I think he meant domUs and dom0.. does the same apply to domUs?

The limitation to vcpu0 applies only to HVM domUs.

 -- Keir



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel

References:
- Re: [Xen-devel] Event channel performance optimize
  - From: Pasi Kärkkäinen

Prev by Date: Re: [Xen-devel] [PATCH 6 of 6] PV on HVM suspend\resume
Next by Date: Re: [Xen-devel] event_lock not initialized in the idle domain (permitted actions in a tasklet?)
Previous by thread: Re: [Xen-devel] Event channel performance optimize
Next by thread: [Xen-devel] Xen on vmware
Index(es):
- Date
- Thread

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.