Re: [dpdk-dev] [PATCH v3] net/mlx5: add 200G link speed

[Ferruh Yigit <ferruh.yigit@intel.com>]

On 5/6/2020 3:19 PM, Thomas Monjalon wrote:
> 06/05/2020 16:01, Ferruh Yigit:
>> On 5/6/2020 2:17 PM, Thomas Monjalon wrote:
>>> 06/05/2020 14:59, Ferruh Yigit:
>>>> On 5/6/2020 1:22 PM, Asaf Penso wrote:
>>>>> There is no way to report back a link speed of 200Gbps.
>>>>>
>>>>> Adding 200G link speed.
>>>>>
>>>>> Signed-off-by: Asaf Penso <asafp@mellanox.com>
>>>>> ---
>>>>> v2 - reword commit log and remove 400G
>>>>>
>>>>> v3 - rebase and fix checkpatch warning
>>>>> ---
>>>>>  app/test-pmd/cmdline.c                      | 12 +++++++-----
>>>>>  doc/guides/rel_notes/release_20_05.rst      |  2 ++
>>>>>  doc/guides/testpmd_app_ug/testpmd_funcs.rst |  2 +-
>>>>>  drivers/net/mlx5/mlx5_ethdev.c              | 22 +++++++++++++++++++++-
>>>>>  lib/librte_ethdev/rte_ethdev.c              |  2 ++
>>>>>  lib/librte_ethdev/rte_ethdev.h              |  2 ++
>>>>>  6 files changed, 35 insertions(+), 7 deletions(-)
>>>>
>>>> Hi Asaf,
>>>>
>>>> Patch looks good, but it updates ethdev & testpmd to have 200G defines and mlx5
>>>> to use it, so net/mlx5 prefix not really fits to the patch, can you separate
>>>> mlx5 changes into another patch?
>>>
>>> I think I was the one advising to squash all.
>>> The reason is that the changes in testpmd and ethdev are
>>> simple and mechanical.
>>> The real change is in mlx5 in my opinion, but I'm fine with splitting as well.
>>>
>>
>> Agree the real change is in the PMD and rest is mechanical, my concern was if we
>> need to refer the ethdev or testpmd change later, we will need to use commit
>> "net/mlx5: ..." which may be confusing.
>>
>> I think ethdev, testpmd & doc can be combined into one "ethdev: ..." and PMD
>> implementation into other patch.
>>
>> Does it make sense?
> 
> Yes I understand your concern about future reference.
> I am OK with what you propose:
> 	1/ ethdev: add 200G link speed
> 	2/ net/mlx5: support 200G link speed
> 

OK I will split while merging.