Re: [Qemu-devel] Re: [PATCH 19/19] migration: add a parser to accept FT migration incoming mode.

[Yoshiaki Tamura]

2011/1/28 Paolo Bonzini <address@hidden>:
> On 01/28/2011 02:53 PM, Yoshiaki Tamura wrote:
>>>
>>> >  1) I am not sure what would happen with -incoming exec;
>>
>> Nothing happens if used with other protocols, but I assume you're
>> mentioning that it's not clear from the code, which makes sense.
>
> I assume nothing just because the code for other protocols isn't using
> ft_mode.  However, for -incoming exec the parsing code as it is now would
> trigger if the executed file ended with "ft_mode".

Hmm.  Haven't thought about it.

> So now I think it should be at the beginning of the scheme for forward
> compatibility with everything.  Is it possible to detect a migration scheme
> that does not support Kemari, and give an error in that case?

Having a scheme like "kemari:tcp:host:port" looks quite
challenging to me.  We can of course add some quick hacks for it,
but adding a nice layered architecture should be more
appropriate.  Similar to protocols and formats in block layer?
At the same time, I want to avoid anything over engineered.

Thanks,

Yoshi

>
> Paolo
>
>