Re: [net-next RFC PATCH 5/5] virtio-net: flow director support

[Sridhar Samudrala <sri@us.ibm.com>]

On 12/7/2011 3:02 AM, Jason Wang wrote:
> On 12/06/2011 11:42 PM, Sridhar Samudrala wrote:
>> On 12/6/2011 5:15 AM, Stefan Hajnoczi wrote:
>>> On Tue, Dec 6, 2011 at 10:21 AM, Jason Wang<jasowang@redhat.com>  
>>> wrote:
>>>> On 12/06/2011 05:18 PM, Stefan Hajnoczi wrote:
>>>>> On Tue, Dec 6, 2011 at 6:33 AM, Jason Wang<jasowang@redhat.com>    
>>>>> wrote:
>>>>>> On 12/05/2011 06:55 PM, Stefan Hajnoczi wrote:
>>>>>>> On Mon, Dec 5, 2011 at 8:59 AM, Jason Wang<jasowang@redhat.com>
>>>>>>>   wrote:
>>>>> The vcpus are just threads and may not be bound to physical CPUs, so
>>>>> what is the big picture here?  Is the guest even in the position to
>>>>> set the best queue mappings today?
>>>>
>>>> Not sure it could publish the best mapping but the idea is to make 
>>>> sure the
>>>> packets of a flow were handled by the same guest vcpu and may be 
>>>> the same
>>>> vhost thread in order to eliminate the packet reordering and lock
>>>> contention. But this assumption does not take the bouncing of vhost 
>>>> or vcpu
>>>> threads which would also affect the result.
>>> Okay, this is why I'd like to know what the big picture here is.  What
>>> solution are you proposing?  How are we going to have everything from
>>> guest application, guest kernel, host threads, and host NIC driver
>>> play along so we get the right steering up the entire stack.  I think
>>> there needs to be an answer to that before changing virtio-net to add
>>> any steering mechanism.
>>>
>>>
>> Yes. Also the current model of  a vhost thread per VM's interface 
>> doesn't help with packet steering
>> all the way from the guest to the host physical NIC.
>>
>> I think we need to have vhost thread(s) per-CPU that can handle 
>> packets to/from physical NIC's
>> TX/RX queues. Currently we have a single vhost thread for a VM's i/f 
>> that handles all the packets from
>> various flows coming from a multi-queue physical NIC.
>
> Even if we have per-cpu workthread, only one socket is used to queue 
> the packet then, so a multiple queue(sockets) tap/macvtap is still 
> needed.
I think so.  We need per-cpu tap/macvtap sockets along with per-cpu 
vhost threads.
This will parallelize all the way from physical NIC to vhost.

Thanks
Sridhar