[dpdk-dev] [PATCH] net/bonding: add rte flow support

Doherty, Declan declan.doherty at intel.com
Tue Apr 24 14:54:44 CEST 2018


Firstly, apologies on the very large delay on reviewing this. This looks 
good to me and I've verified that flow configuration propagates as 
expected to bonded slaves using IXGBE PMDs for testing.

I had to do some minor rebasing to get the patch to apply cleanly to 
next-net, so I'll leave it up to Ferruh on whether he wants a rebased 
revision of the patch or if he is happy to apply as is and handle the 
rebasing himself.

I will do a v6 of the tunnel encap/decap patchset rebased to this 
patchset to handle the changes to the rte_flow_query API as I need to 
send a new revision of that to fix some whitespace issue I added in the 
last revision of it.

Regards
Declan

On 28/03/2018 12:16 PM, Matan Azrad wrote:
> Ethernet devices which are grouped by bonding PMD, aka slaves, are
> sharing the same queues and RSS configurations and their Rx burst
> functions must be managed by the bonding PMD according to the bonding
> architectuer.
   ^^
typo
> 
> So, it makes sense to configure the same flow rules for all the bond
> slaves to allow consistency in packet flow management.
> 
> Add rte flow support to the bonding PMD to manage all flow
> configuration to the bonded slaves.
> 
> Signed-off-by: Matan Azrad <matan at mellanox.com>
> ---
....
> 

Acked-by: Declan Doherty <declan.doherty at intel.com>


More information about the dev mailing list