[dpdk-dev] [PATCH v3 1/6] ethdev: fix max Rx packet length

Ferruh Yigit ferruh.yigit at intel.com
Tue Oct 5 18:46:48 CEST 2021


On 10/1/2021 4:07 PM, Stephen Hemminger wrote:
> On Fri,  1 Oct 2021 15:36:18 +0100
> Ferruh Yigit <ferruh.yigit at intel.com> wrote:
> 
>> Other issues causing confusion is:
>> * maximum transmission unit (MTU) is payload of the Ethernet frame. And
>>    'max_rx_pkt_len' is the size of the Ethernet frame. Difference is
>>    Ethernet frame overhead, and this overhead may be different from
>>    device to device based on what device supports, like VLAN and QinQ.
>> * 'max_rx_pkt_len' is only valid when application requested jumbo frame,
>>    which adds additional confusion and some APIs and PMDs already
>>    discards this documented behavior.
>> * For the jumbo frame enabled case, 'max_rx_pkt_len' is an mandatory
>>    field, this adds configuration complexity for application.
> 
> One other issue which DPDK inherits from Linux and BSD is that
> MTU (Maximum Transmission Unit) is overloaded to mean MRU (Maximum Receive Unit).
> 
> On Linux, network devices are allowed to receive packets of any size they
> want. MTU is used as a hint about "you need to accept at least MTU size
> packets on receive". So MRU >= MTU.
> 
> In practice, and documentation, MRU and MTU are used synonymously.
> 

Yes MTU is used to refer both MTU & MRU, same config value (MTU) is used
to configure both.

I don't know if there is a need to configure them separately, if there is we
can address it in another patch.


More information about the dev mailing list