Is your feature request related to a problem? Please describe.
k8s-netperf doesn't support configuring a parallelism higher than 1 in pod 2 service scenarios. Having this feature can be interesting since it will allow a user to saturate the network link using this traffic pattern. With just one thread/process is not possible to get close to the maximum theoretical network bandwidth .
Describe the solution you'd like
Among the several possible approaches to code this feature, I think that running N netperf/iperf/netperf servers pointed by the same service, with the pods being exposed in different service ports. And N clients connecting to these ports
Is your feature request related to a problem? Please describe.
k8s-netperf doesn't support configuring a parallelism higher than 1 in pod 2 service scenarios. Having this feature can be interesting since it will allow a user to saturate the network link using this traffic pattern. With just one thread/process is not possible to get close to the maximum theoretical network bandwidth .
Describe the solution you'd like
Among the several possible approaches to code this feature, I think that running N netperf/iperf/netperf servers pointed by the same service, with the pods being exposed in different service ports. And N clients connecting to these ports