Re: [dpdk-dev] [PATCH] vhost: add support to large linear mbufs

[Ilya Maximets <i.maximets@ovn.org>]

On 02.10.2019 20:15, Flavio Leitner wrote:
> On Wed, 2 Oct 2019 17:50:41 +0000
> Shahaf Shuler <shahafs@mellanox.com> wrote:
> 
>> Wednesday, October 2, 2019 3:59 PM, Flavio Leitner:
>>> Obrembski MichalX <michalx.obrembski@intel.com>; Stokes Ian
>>> <ian.stokes@intel.com>
>>> Subject: Re: [dpdk-dev] [PATCH] vhost: add support to large linear
>>> mbufs
>>>
>>>
>>> Hi Shahaf,
>>>
>>> Thanks for looking into this, see my inline comments.
>>>
>>> On Wed, 2 Oct 2019 09:00:11 +0000
>>> Shahaf Shuler <shahafs@mellanox.com> wrote:
>>>    
>>>> Wednesday, October 2, 2019 11:05 AM, David Marchand:
>>>>> Subject: Re: [dpdk-dev] [PATCH] vhost: add support to large
>>>>> linear mbufs
>>>>>
>>>>> Hello Shahaf,
>>>>>
>>>>> On Wed, Oct 2, 2019 at 6:46 AM Shahaf Shuler
>>>>> <shahafs@mellanox.com> wrote:
>>>>>>   
>>
>> [...]
>>
>>>>>
>>>>> I am missing some piece here.
>>>>> Which pool would the PMD take those external buffers from?
>>>>
>>>> The mbuf is always taken from the single mempool associated w/ the
>>>> rxq. The buffer for the mbuf may be allocated (in case virtio
>>>> payload is bigger than current mbuf size) from DPDK hugepages or
>>>> any other system memory and be attached to the mbuf.
>>>>
>>>> You can see example implementation of it in mlx5 PMD (checkout
>>>> rte_pktmbuf_attach_extbuf call)
>>>
>>> Thanks, I wasn't aware of external buffers.
>>>
>>> I see that attaching external buffers of the correct size would be
>>> more efficient in terms of saving memory/avoiding sparsing.
>>>
>>> However, we still need to be prepared to the worse case scenario
>>> (all packets 64K), so that doesn't help with the total memory
>>> required.
>>
>> Am not sure why.
>> The allocation can be per demand. That is - only when you encounter a
>> large buffer.
>>
>> Having buffer allocated in advance will benefit only from removing
>> the cost of the rte_*malloc. However on such big buffers, and further
>> more w/ device offloads like TSO, am not sure that is an issue.
> 
> Now I see what you're saying. I was thinking we had to reserve the
> memory before, like mempool does, then get the buffers as needed.
> 
> OK, I can give a try with rte_*malloc and see how it goes.

This way we actually could have a nice API.  For example, by
introducing some new flag RTE_VHOST_USER_NO_CHAINED_MBUFS (there
might be better name) which could be passed to driver_register().
On receive, depending on this flag, function will create chained
mbufs or allocate new contiguous memory chunk and attach it as
an external buffer if the data could not be stored in a single
mbuf from the registered memory pool.

Supporting external memory in mbufs will require some additional
work from the OVS side (e.g. better work with ol_flags), but
we'll have to do it anyway for upgrade to DPDK 19.11.

Best regards, Ilya Maximets.

> 
>>> The current patch pushes the decision to the application which
>>> knows better the workload. If more memory is available, it can
>>> optionally use large buffers, otherwise just don't pass that. Or
>>> even decide whether to share the same 64K mempool between multiple
>>> vhost ports or use one mempool per port.
>>>
>>> Perhaps I missed something, but managing memory with mempool still
>>> require us to have buffers of 64K regardless if the data consumes
>>> less space. Otherwise the application or the PMD will have to
>>> manage memory itself.
>>>
>>> If we let the PMD manages the memory, what happens if a port/queue
>>> is closed and one or more buffers are still in use (switching)? I
>>> don't see how to solve this cleanly.
>>
>> Closing of the dev should return EBUSY till all buffers are free.
>> What is the use case of closing a port while still having packet
>> pending on other port of the switch? And why we cannot wait for them
>> to complete transmission?
> 
> The vswitch gets the request from outside and the assumption is that
> the command will succeed. AFAIK, there is no retry mechanism.
> 
> Thanks Shahaf!
> fbl