Sorry to keep following up with this; the other thing it gives you is things like sysctl parameters, kernel, tcp window scaling (pre and post test) and a bunch of per stream and aggregated metadata relating to the entire suite. In a nice self contained gzip that can produce lovely graphs using matplotlib.
Basically a repeatable standardized test with all the things you might be interested in captured for distribution/reference. flent-gui provides a nice interactive graphical interface (but you can just as easily using the cli) for interacting with the datasets. -Joel On 30 January 2018 at 10:52, Joel Wirāmu Pauling <j...@aenertia.net> wrote: > In terms of what you need on the target netserver/netperf from ipkg is > tiny and is all you need. > > On 30 January 2018 at 10:51, Joel Wirāmu Pauling <j...@aenertia.net> wrote: >> FLENT + RRUL testing is 4 up 4 down TCP streams with 4 different QoS >> Markings, and then 4 different QoS Marked UDP probes and ICMP. >> >> It gives you a measure of how much the CPU and Network path can cope >> with load conditions, which are more realistic for everyday use. >> >> iperf3 isn't going to give you any measure of that. >> >> On 30 January 2018 at 10:48, Karl Palsson <ka...@tweak.net.au> wrote: >>> >>> Joel Wirāmu Pauling <j...@aenertia.net> wrote: >>>> Any chance I can convince you to use netperf + FLENT for doing >>>> your tests rather than iperf(3)? >>>> >>>> flent.org >>>> >>> >>> For those playing at home, could you elaborate on _why_? What do >>> you expect to change? By what sort of percentage? >>> >>> Sincerely, >>> Karl Palsson _______________________________________________ Lede-dev mailing list Lede-dev@lists.infradead.org http://lists.infradead.org/mailman/listinfo/lede-dev
