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

RE: [Xen-ia64-devel] Some things to be considered for ptc.ga emulation


  • To: "Xu, Anthony" <anthony.xu@xxxxxxxxx>, <xen-ia64-devel@xxxxxxxxxxxxxxxxxxx>
  • From: "Tian, Kevin" <kevin.tian@xxxxxxxxx>
  • Date: Wed, 5 Apr 2006 14:08:58 +0800
  • Delivery-date: Tue, 04 Apr 2006 23:09:21 -0700
  • List-id: Discussion of the ia64 port of Xen <xen-ia64-devel.lists.xensource.com>
  • Thread-index: AcZYbs3SKr7CnMI0RCCIEHq4K7nbfAAA7LHgAAEmaTA=
  • Thread-topic: [Xen-ia64-devel] Some things to be considered for ptc.ga emulation

>From: Xu, Anthony
>Sent: 2006年4月5日 13:56
>
>
>Considering VTIdomain, I have below concerns,
>If a vcpu receives a IPI, just before do_block( waiting device model
>on dom0 to handle IO request), do_block will schedule out this vcpu,
>and the schedule in vcpu may use the old tlb mapping.
>And the wait maybe long.

Yes, we need more thinking on this specific case...

>
>
>Moreover, if this IO request is sent to the vcpu of domain0, which runs
>On the same vcpu that send out IPI, because this vcpu is waiting other
>Vcpus' response of IPI handling, it can't be scheduled to vcpu of
>domain0,
>Then dead loop happens.
>
>The vcpu that sends IPI should not wait by tight polling, this vcpu should
>yield
>LP and poll.
>

Yes, 'wait' shouldn't be polling, which is instead yield. :-)

Thanks,
Kevin

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel


 


Rackspace

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