>>What is your use case(s) ? >>My usecase might be setup a VBRAS VNF with OVS-DPDK as an NFV normal >>case, and it requires a good performance, however, OVS-DPDK seems still >not >>reach its needs compared with hardware offloading, we are evaluating VPP >as >>well, >As you mentioned VPP here, It's worth looking at the benchmarks that were >carried comparing >OvS and VPP for L3-VPN use case by Intel, Ericsson and was presented in OvS >Fall conference. >The slides can be found @ >http://openvswitch.org/support/ovscon2016/8/1400-gray.pdf. >In above pdf page 12, why does classifier showed a constant throughput with >increasing concurrent L4 flows? shouldn't the performance get degradation >with more subtable look up as you mentioned.
You raised a good point. The reason being the 'sorted subtable ranking' implementation in 2.7 release. With this we will have the subtable vector sorted by frequency of hits and this reduces the number of subtable lookups. That is the reason why I asked for the ' avg. subtable lookups per hit:' number. I recommend watching the video of the presentation here https://www.youtube.com/watch?v=cxRcfn2x4eE , as the bottlenecks you are referring in this thread are more or less similar to ones discussed at the conference. - Bhanuprakash. _______________________________________________ discuss mailing list disc...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-discuss
