Re: [ovs-dev] [PATCH 00/25] netdev datapath vxlan offload

2020-07-15 Thread William Tu
Hi Eli, I'm having another question, thanks in advance! On Mon, Jan 20, 2020 at 7:09 AM Eli Britstein wrote: > > In the netdev datapath, packets arriving over a tunnel are processed by > more than one flow. For example a packet that should be decapsulated and > forwarded to another port is

Re: [ovs-dev] [PATCH 00/25] netdev datapath vxlan offload

2020-07-08 Thread William Tu
On Thu, Mar 5, 2020 at 11:12 AM Pravin Shelar wrote: > > On Sun, Mar 1, 2020 at 8:25 PM Sriharsha Basavapatna via dev > wrote: > > > > On Tue, Feb 18, 2020 at 3:30 PM Eli Britstein wrote: > > > > > > > > > On 2/10/2020 11:16 PM, Hemal Shah wrote: > > > > Eli, > > > > > > > > There are some

Re: [ovs-dev] [PATCH 00/25] netdev datapath vxlan offload

2020-03-05 Thread Pravin Shelar
On Sun, Mar 1, 2020 at 8:25 PM Sriharsha Basavapatna via dev wrote: > > On Tue, Feb 18, 2020 at 3:30 PM Eli Britstein wrote: > > > > > > On 2/10/2020 11:16 PM, Hemal Shah wrote: > > > Eli, > > > > > > There are some fundamental architecture issues (multi HW tables vs. > > > single HW table, use

Re: [ovs-dev] [PATCH 00/25] netdev datapath vxlan offload

2020-03-01 Thread Sriharsha Basavapatna via dev
On Tue, Feb 18, 2020 at 3:30 PM Eli Britstein wrote: > > > On 2/10/2020 11:16 PM, Hemal Shah wrote: > > Eli, > > > > There are some fundamental architecture issues (multi HW tables vs. > > single HW table, use of rte_flow JUMP action for mapping ovs sw > > tnl_pop action, etc.) that we need to

Re: [ovs-dev] [PATCH 00/25] netdev datapath vxlan offload

2020-02-18 Thread Eli Britstein
On 2/10/2020 11:16 PM, Hemal Shah wrote: Eli, There are some fundamental architecture issues (multi HW tables vs. single HW table, use of rte_flow JUMP action for mapping ovs sw tnl_pop action, etc.) that we need to discuss before we can get into the details of the patchset. I'm inlining

Re: [ovs-dev] [PATCH 00/25] netdev datapath vxlan offload

2020-02-10 Thread Hemal Shah via dev
Eli, There are some fundamental architecture issues (multi HW tables vs. single HW table, use of rte_flow JUMP action for mapping ovs sw tnl_pop action, etc.) that we need to discuss before we can get into the details of the patchset. I'm inlining my comments on the discussion between you and

Re: [ovs-dev] [PATCH 00/25] netdev datapath vxlan offload

2020-02-05 Thread Eli Britstein
On 2/3/2020 7:05 PM, Sriharsha Basavapatna wrote: Hi Eli, Thanks for sending this patchset. I have some questions about the design, please see my comments below. Thanks, -Harsha On Mon, Jan 20, 2020 at 8:39 PM Eli Britstein wrote: In the netdev datapath, packets arriving over a tunnel are

Re: [ovs-dev] [PATCH 00/25] netdev datapath vxlan offload

2020-02-03 Thread Sriharsha Basavapatna via dev
Hi Eli, Thanks for sending this patchset. I have some questions about the design, please see my comments below. Thanks, -Harsha On Mon, Jan 20, 2020 at 8:39 PM Eli Britstein wrote: > > In the netdev datapath, packets arriving over a tunnel are processed by > more than one flow. For example a

Re: [ovs-dev] [PATCH 00/25] netdev datapath vxlan offload

2020-02-03 Thread Eli Britstein
ping On 1/20/2020 5:08 PM, Eli Britstein wrote: In the netdev datapath, packets arriving over a tunnel are processed by more than one flow. For example a packet that should be decapsulated and forwarded to another port is processed by two flows: 1. in_port=, outer-header matches, dst-port=4789

[ovs-dev] [PATCH 00/25] netdev datapath vxlan offload

2020-01-20 Thread Eli Britstein
In the netdev datapath, packets arriving over a tunnel are processed by more than one flow. For example a packet that should be decapsulated and forwarded to another port is processed by two flows: 1. in_port=, outer-header matches, dst-port=4789 (VXLAN), actions:tnl_pop(vxlan_sys_4789). 2.