Re: about network live connection during migration

[tgh <wwwwww4187@sina.com.cn>]

Thank you
and you say ,"The unsolicited ARP is generated by the network frontend 
whenever it is brought up, as would be the case upon resume."
that is , the guestos should be aware of its suspend-and-resume ,but xen 
maybe support the transparent migration for the guestos, that is ,the 
guestos does not know itself has been suspended ,is it?

but may be some action did the same thing  in the net backend, is it ?
and fake_arp() has not been found, it is helpful ,even though ,i have 
not found the code

could you or someone help me
i am still interested in the  code  for  sending  The unsolicited ARP 
after migration

Thanks


 

Daniel Stodden 写道:
> On Sun, 2008-03-09 at 10:50 +0800, tgh wrote:
>   
>> hi
>>   I try to understand to the mechanism of live migration, and I read the 
>> code ,and have some confusion about the network live connection during 
>> the migration,could you help me, i read the paper about the live 
>> migration,it explaine that in a single switched LAN,host sends 
>> unsolicited ARP,and in router case, broadcastARP will not be accecpted 
>> ,and migratedOS need to sends to the interfaces in the ARPcache,while in 
>> a switched net,migrated OS holds the same MAC address,and network switch 
>> could detect the change of location,   i am confused about where the 
>> code for all of these , could you give me some more detailed explanation 
>> or tell me where the code for these
>>     
>
> The unsolicited ARP is generated by the network frontend whenever it is
> brought up, as would be the case upon resume. look out for something i
> believe is called fake_arp (?) in netfront. This is a very simple
> operation, btw.
>
> Unicasting to peers listed in the ARP cache is, to my knowledge, not
> performed. I believe the paper just outlines what the alternatives would
> look like.
>
> regards,
> daniel
>
>