qemu-devel
[Top][All Lists]
Advanced

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

Re: [PATCH 4/9] vfio/migration: Skip pre-copy if dirty page tracking is


From: Joao Martins
Subject: Re: [PATCH 4/9] vfio/migration: Skip pre-copy if dirty page tracking is not supported
Date: Mon, 23 May 2022 10:45:15 +0100

On 5/23/22 07:11, Avihai Horon wrote:
> On 5/20/2022 1:58 PM, Joao Martins wrote:
>>> +        migrate_get_current()->skip_precopy = true;
>>> +    }
>>> +
>> Perhaps it might be easier to reuse the existing knob to disable pre-copy
>> per device that Kirti added some time ago, rather than changing migration 
>> core just
>> yet (e.g. you might wanna bail of the migration preemptively because the CPU 
>> is dirtying
>> too many pages for example?):
>>
>> if (!container->dirty_pages_supported) {
>>      warn_report_once(...)
>>      pre_copy_dirty_page_tracking = ON_OFF_AUTO_OFF;
>> }
> 
> But this doesn't prevent the VFIO device from dirtying RAM pages during 
> pre-copy phase.
> The VFIO device can dirty RAM pages during pre-copy and it won't have a 
> way to report the dirtied pages to QEMU and migration will be faulty.
> 

You're quite right, sorry for the noise. I was a little too obsessed in reusing 
the
existing field that forgot that letting the iterate stage go the PCI device 
could
also be driven into dirtying RAM too.



reply via email to

[Prev in Thread] Current Thread [Next in Thread]