Re: [PATCH RFC] x86/ioreq server: Optimize p2m cleaning up code in p2m_finish_type_change().

[Yu Zhang <yu.c.zhang@linux.intel.com>]

On 4/5/2017 11:11 PM, George Dunlap wrote:
> On 05/04/17 16:10, George Dunlap wrote:
>> On 05/04/17 09:59, Yu Zhang wrote:
>>> Previously, p2m_finish_type_change() is triggered to iterate and
>>> clean up the p2m table when an ioreq server unmaps from memory type
>>> HVMMEM_ioreq_server. And the current iteration number is set to 256
>>> And after these iterations, hypercall pre-emption is checked.
>>>
>>> But it is likely that no p2m change is performed for the just finished
>>> iterations, which means p2m_finish_type_change() will return quite
>>> soon. So in such scenario, we can allow the p2m iteration to continue,
>>> without checking the hypercall pre-emption.
>> Suppose you have a guest with 128TiB of RAM, and the ioreq_server p2m
>> entries are at the very end of RAM.  Won't this run for several minutes
>> before even allowing preemption?
> Sorry, this should be GiB.  But I think you get my point. :-)

Yep. I got it.
I'd better reconsider it - my head is quite dizzy now. Maybe together 
with your generic p2m change solution in 4.10. :-)

Thanks
Yu
>
>   -George
>
>


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel