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

Re: [Xen-devel] [PATCH] [RESEND] remove redundent call tohvm_do_resume


  • To: "Li, Xin B" <xin.b.li@xxxxxxxxx>, <xen-devel@xxxxxxxxxxxxxxxxxxx>
  • From: Keir Fraser <Keir.Fraser@xxxxxxxxxxxx>
  • Date: Wed, 08 Nov 2006 09:31:38 +0000
  • Delivery-date: Wed, 08 Nov 2006 01:32:00 -0800
  • List-id: Xen developer discussion <xen-devel.lists.xensource.com>
  • Thread-index: Acb0CVpf06Hxya4XT6uW1ULXYRyKAQCGO58QABu3EN4AAPpr0ABl5NXwAATVQ8sCtQ65IAABH6Jm
  • Thread-topic: [Xen-devel] [PATCH] [RESEND] remove redundent call tohvm_do_resume



On 8/11/06 09:04, "Li, Xin B" <xin.b.li@xxxxxxxxx> wrote:

> since this is done :-), I think hvm_do_resume can be clean up more since
> HVM vcpu can't be waked up by interrupts now.
> And you mentioned that we can batch interrupts notification hypercalls,
> so is it OK to batch IO events done notification hypercalls too?

Yes. The biggest win in qemu I suspect will be to remember the current state
of each 'interrupt wire' and only do a hypercall when the state changes.
Feel free to generate patches to maintain that shaodw state, and to do
batched multicalls.

 -- Keir



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


 


Rackspace

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