Begin forwarded message:
Date: Wed, 9 Mar 2022 18:20:00 +0800
From: Carl Lei <m...@xecycle.info>
To: "Benoit Ganne (bganne)" <bga...@cisco.com>
Subject: Re: [vpp-dev] Question on checksum offload in veth+AF_XDP
Sorry, forgot to CC list.

Hi Benoit,

On Wed, 9 Mar 2022 09:45:58 +0000
"Benoit Ganne (bganne)" <bga...@cisco.com> wrote:

> Hi Carl,
> 
> Indeed, there is no way in AF_XDP to detect whether the checksum is
> offloaded or not. We could always add a flag but I am not sure it
> would worth it. Can you try host-interface (AF_PACKET) and see if it
> solves your issue:
> https://s3-docs.fd.io/vpp/22.06/cli-reference/clis/clicmd_src_vnet_devices_af_packet.html
> With veth, AF_XDP and AF_PACKET should have similar performance
> anyway.  

Yes, AF_PACKET works fine, but performance is...  iperf3 says 2Mbps for
AF_PACKET, 7Gbps for AF_XDP.

Setup is
host veth - VPP veth - L2 bridge - VPP veth - container veth,
by AF_PACKET I mean both VPP veths are connected by AF_PACKET, same for
AF_XDP.

This 7Gbps is different from my 10Gbps result yesterday, which is
host veth - VPP veth - L2 bridge - VPP tap - container.





-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20989): https://lists.fd.io/g/vpp-dev/message/20989
Mute This Topic: https://lists.fd.io/mt/89659077/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Reply via email to