Hi VSPERF'ers Dev updates come first, but I think it would help to collect insights on what we see here.
- CI Results Discussion Martin's plotting wiki page: https://wiki.opnfv.org/display/vsperf/VSPERF+CI+Results presents an excellent basis for discussion. Back2Back on all scenarios and the SR-IOV results make for some interesting comparisons. - Multi-Stream N-tuple field access affects results Sridhar's Summaries in Appendix E: https://wiki.opnfv.org/display/vsperf/Traffic+Generator+Testing#TrafficGeneratorTesting-AppendixE:HardwareandBaremetalTrafficGenerators-Summarized appear to show that varying different fields in the N-tuple (because different generators have different abilities to select and vary the field values) has an effect on throughput. What exact fields were varied to create 4K flows in each of the T-gens? And what method was used to vary the values (linear, random)? thanks and regards, Al _______________________________________________ opnfv-tech-discuss mailing list opnfv-tech-discuss@lists.opnfv.org https://lists.opnfv.org/mailman/listinfo/opnfv-tech-discuss