On 8/26/22 14:14, David Marchand wrote:
> Hi Ilya,
> 
> On Thu, Jun 30, 2022 at 3:06 PM Ilya Maximets <[email protected]> wrote:
>>
>> On 3/18/22 16:33, David Marchand wrote:
>>> DPDK based dp-packets points to data buffers that can't be expanded
>>> dynamically.
>>> Their layout is as follows:
>>> - a 128 bytes headroom chosen at DPDK build time (RTE_PKTMBUF_HEADROOM),
>>> - a maximum size chosen at mempool creation,
>>>
>>> In some usecases though (like encapsulating with multiple tunnels),
>>> a 128 bytes headroom is too short.
>>>
>>> Dynamically allocate buffers in DPDK memory and make use of DPDK
>>> external buffers API (previously used for userspace TSO).
>>>
>>> Signed-off-by: David Marchand <[email protected]>
>>> ---
>>
>> Hi, David.  This is a nice change!  I didn't test much, but
>> the code looks correct in general.
>>
>> If you can create a system test for this issue, that would be great.
> 
> The issue is netdev-dpdk / dpdk related, so I intend to add such a
> test in system-dpdk.at.
> Do you have any objection/better location?

Yeah, we do not really have any other place to run dpdk-specific
tests at the moment, even if they are not really system tests.

We can probably create some actual unit-tests with ovstest though.
But I'm not sure how much work that will require.

For this particular problem though, we will need a real system test
anyway.

Best regards, Ilya Maximets.
_______________________________________________
dev mailing list
[email protected]
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Reply via email to