Hello All, I am setting up next call in this series to discuss further on approaches to enable full hardware acceleration in OVS-DPDK.
Agenda for this meeting is to discuss further on two proposals (one from Intel and another from Napatech) for enabling full hardware acceleration in OVS-DPDK. The Previous meeting minutes can be found at following google doc https://docs.google.com/document/d/1KeQB5NIUph721uuk1f1wMy4QXwSWxlzDaumd_bWX6YI/edit?usp=sharing I would encourage everyone to have look at the following two patch series before the call, so that we can have a productive discussion. The Napatech hardware acceleration approach in OVS-DPDK can be found below, >>>>>> Hi All, As agreed in last meeting, I have created an OVS branch of our OVS fork (from late January - v2.9), and added the Partial hw offload proposal, followed by our full offload extension - 3 additional commits. It should compile against DPDK 17.11, and for that to be possible an existing RTE_FLOW_ACTION_TYPE_VF is (mis-)used to send port-id to PMD. Furthermore, tcp_flags update from NIC is commented out due to lack of that field in the RTE FLOW query structure. Please see this as a PoC. It is not yet ready for an actual proposal, though it is fully functioning in our lab. https://github.com/napatech/ovs/tree/hw-full-offload-v1 Further notes: As mentioned at the last meeting, this proposal is based on vPorts on NIC (being VF, virtio or other vPort), completely handled outside OVS. The vPorts are then connected and configured in OVS as "normal" type=dpdk ports. I know this is not in-line with Intels proposal, however, we think it might be a good idea. It makes it simpler in OVS, since we only need either capabilities, or trial & error to do transparent full hw-offload. Anyway, this is our current proposal for the next discussion meeting. Thanks, Finn >>>>>> The intel hardware acceleration proposal can be found at >>>>>>>>>>>>>>>> Hello All, As discussed in the last meeting, I have created a OVS 2.7 fork with our hardware acceleration implementation as below. https://github.com/sugchand/ovs.git (branch - dpdk-hw-accel-intel<https://github.com/sugchand/ovs/tree/dpdk-hw-accel-intel>) Few points on the implementation. 1) This implementation is just for reference to show the proposal. 2) The code is still 2.7 based. We will merge to latest branch once we have finalized on the approach. 3) Some of the hardware acceleration functionalities still missing in this implementation, such as flow offload thread , flow stat and tcp-flag handling. We are working on it to add those support. 4) This implementation uses some of hardware specific APIs that are not yet available in the DPDK main tree. So the code may not build properly. Please review the implementation (in the last 12 commits), Will setup a follow up call to discuss further on this. Thank you! Regards _Sugesh >>>>>>>>>>>>>>>>> ......................................................................................................................................... --> Join Skype Meeting<https://meet.intel.com/sugesh.chandran/LW26GQKW> Trouble Joining? Try Skype Web App<https://meet.intel.com/sugesh.chandran/LW26GQKW?sl=1> Join by phone +1(916)356-2663 (or your local bridge access #) Choose bridge 5.<tel:+1(916)356-2663%20(or%20your%20local%20bridge%20access%20#)%20Choose%20bridge%205.> (Global) English (United States) Find a local number<https://dial.intel.com> Conference ID: 9273892307 Forgot your dial-in PIN?<https://dial.intel.com> |Help<https://o15.officeredir.microsoft.com/r/rlidLync15?clid=1033&p1=5&p2=2009> [!OC([1033])!] ......................................................................................................................................... _______________________________________________ dev mailing list [email protected] https://mail.openvswitch.org/mailman/listinfo/ovs-dev
