Re: [PATCH] multifd: Set a higher "backlog" default value for listen()

[Wang, Lei]

On 5/19/2023 10:44, Wang, Wei W wrote:
> On Friday, May 19, 2023 9:31 AM, Wang, Lei4 wrote:
>> On 5/18/2023 17:16, Juan Quintela wrote:
>>> Lei Wang <lei4.wang@intel.com> wrote:
>>>> When destination VM is launched, the "backlog" parameter for listen()
>>>> is set to 1 as default in socket_start_incoming_migration_internal(),
>>>> which will lead to socket connection error (the queue of pending
>>>> connections is full) when "multifd" and "multifd-channels" are set
>>>> later on and a high number of channels are used. Set it to a
>>>> hard-coded higher default value 512 to fix this issue.
>>>>
>>>> Reported-by: Wei Wang <wei.w.wang@intel.com>
>>>> Signed-off-by: Lei Wang <lei4.wang@intel.com>
>>>
>>> [cc'd daiel who is the maintainer of qio]
>>>
>>> My understanding of that value is that 230 or something like that
>>> would be more than enough.  The maxiimum number of multifd channels is
>> 256.
>>
>> You are right, the "multifd-channels" expects uint8_t, so 256 is enough.
>>
> 
> We can change it to uint16_t or uint32_t, but need to see if listening on a 
> larger
> value is OK to everyone.

Is there any use case to use >256 migration channels? If not, then I suppose
it's no need to increase it.

> 
> Man page of listen mentions that the  maximum length of the queue for
> incomplete sockets can be set using /proc/sys/net/ipv4/tcp_max_syn_backlog,
> and it is 4096 by default on my machine