[ovs-dev] [PATCH] Documentation: add notes for TSO & i40e

[David Marchand]

On Mon, Jan 13, 2020 at 4:49 PM Ciara Loftus <ciara.loftus at intel.com> wrote:
>
> When using TSO in OVS-DPDK with an i40e device, the following
> commit is required for DPDK, which fixes an issue on the TSO path:
> http://git.dpdk.org/next/dpdk-next-net/commit/?id=b2a4dc260139409c539fb8e7f1b9d0a5182cfd2b

Please avoid referencing dpdk-next-net sha1's, as this tree is rebased
on dpdk master quite frequently.
This commit will reach the master branch in a few days hopefully
(20.02-rc1 is expected this week).

In URLs, prefer https://.


> Document this as a limitation until a DPDK release with the fix
> included is supported by OVS.
>
> Also, document best known methods for performance tuning when
> testing TSO with the tool iperf.
>
> Signed-off-by: Ciara Loftus <ciara.loftus at intel.com>
> ---
>  Documentation/topics/dpdk/tso.rst | 27 +++++++++++++++++++++++++++
>  1 file changed, 27 insertions(+)
>
> diff --git a/Documentation/topics/dpdk/tso.rst b/Documentation/topics/dpdk/tso.rst
> index 189c86480..5c56c458c 100644
> --- a/Documentation/topics/dpdk/tso.rst
> +++ b/Documentation/topics/dpdk/tso.rst
> @@ -94,3 +94,30 @@ datapath must support TSO or packets using that feature will be dropped
>  on ports without TSO support.  That also means guests using vhost-user
>  in client mode will receive TSO packet regardless of TSO being enabled
>  or disabled within the guest.
> +
> +When the NIC performing the segmentation is using the i40e DPDK PMD, a fix
> +must be included in the DPDK build, otherwise TSO will not work. The fix can
> +be found on `the dpdk.org net-next tree`__.
> +
> +__ http://git.dpdk.org/next/dpdk-next-net/commit/?id=e975e3720ba16278c6b43f8938b75710573bbd6a

Ditto.


> +
> +This fix is expected to be included in the 19.11.1 release. When OVS migrates
> +to this DPDK release, this limitation can be removed.
> +
> +~~~~~~~~~~~~~~~~~~
> +Performance Tuning
> +~~~~~~~~~~~~~~~~~~
> +
> +iperf is often used to test TSO performance. Care needs to be taken when
> +configuring the environment in which the iperf server process is being run.
> +Since the iperf server uses the NIC's kernel driver, IRQs will be generated.
> +By default with some NICs eg. i40e, the IRQs will land on the same core as that
> +which is being used by the server process, provided the number of NIC queues is
> +greater or equal to that lcoreid. This causes contention between the iperf
> +server process and the IRQs. For optimal performance, it is suggested to pin
> +the IRQs to their own core. To change the affinity associated with a given IRQ
> +number, you can 'echo' the desired coremask to the file
> +/proc/irq/<number>/smp_affinity
> +For more on SMP affinity, refer to the `Linux kernel documentation`__.
> +
> +__ https://www.kernel.org/doc/Documentation/IRQ-affinity.txt
> --
> 2.17.1
>
> _______________________________________________
> dev mailing list
> dev at openvswitch.org
> https://mail.openvswitch.org/mailman/listinfo/ovs-dev
>


-- 
David Marchand