Re: [dpdk-dev] [PATCH v8 10/10] app/testpmd:test VxLAN Tx checksum offload

[Olivier MATZ <olivier.matz@6wind.com>]

Hi Konstantin,

On 11/12/2014 03:39 PM, Ananyev, Konstantin wrote:
>> I'm not sure having get_ipv4_udptcp_checksum() in librte_net would
>> help. The value we have to set in the TCP checksum field depends on the
>> PMD (altought only ixgbe is supported now). So, it would require
>> another parameter <portid> and a new PMD eth_ops... which looks very
>> similar to dev_prep_tx() (except that dev_prep_tx() can be bulked).
>> I think a stack will not be able to call get_udptcp_checksum(m ,port)
>> because it does not know the physical port at the time the packet is
>> built. Moreover, calling a function through a pointer is more efficient
>> when bulked. So I think the dev_prep_tx() you initially describe is
>> a better answer to the problem.
>
> Yes I understand that it might not be applicable for non-Intel NICs.
> Though I thought it is ok as a temporary measure as right now we
> support these offloads for Intel NICs only.
> Basically my thought was what you proposed as option 3 below.
> Why common function in librte_net?
> So people don't need to write their own each time.
> Plus as I remember all 3 Intel NIC types (ixgbe/igb/i40e) we support have similar
> requirements for what need to be set/calculated for these TX offloads.
> So my thought was that having a common function might help to avoid code duplication in future,
> If/when will implement dev_prep_tx().

OK, now I understand better what you suggest. I'll try to implement
the option 3 (below) with a common checksum function in librte_net
in the next version of the TSO patchset.

Regards,
Olivier


>
>>
>> I don't know what is the exact timeframe for 1.8, maybe Thomas can help
>> on this? Depending on it, we have several options:
>>
>> - implement dev_prep_tx() for 1.8 in the TSO series: this implies that
>>     the community agrees on this new API. We need to check that it will
>>     be faster in a pipeline model (I think this is obvious) but also that
>>     it does not penalize the run-to-completion model: introducing another
>>     function dev_prep_tx() can result in duplicated tests in the driver
>>     (ex: test the offload flag values).
>>
>> - postpone dev_prep_tx() or similar to next version and push the current
>>     TSO patchset (including the comments done on the list). It does not
>>     modify the current offload API, it provides the TSO feature on ixgbe
>>     based on a similar API concept (set the TCP phdr cksum). The drawback
>>     is a potential performance loss when using a pipeline model.
>>
>> - another option that you may prefer is to bind the API behavior to
>>     ixgbe (for 1.8): we can ask the application to set the pseudo-header
>>     checksum without the IP len when doing TSO, as required by the ixgbe
>>     driver. Then, for next release, we can think about dev_prep_tx(). The
>>     drawback of this solution is that we may go back on this choice if the
>>     dev_prep_tx() approach is not validated by the community.