<div dir="ltr"><div dir="ltr"><div dir="ltr">On Fri, Apr 5, 2019 at 11:51 AM Dave Taht <<a href="mailto:dave.taht@gmail.com">dave.taht@gmail.com</a>> wrote:<br></div><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br>
Was GRO/GSO enabled on the router? host? server?<br></blockquote><div><br></div><div>In this particular invocation of this particular test, the sender, receiver, and router functionality were all running on the same machine, using network namespaces and veth devices; TSO and GRO were enabled.</div><div> <br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
><br>
>><br>
>> 5) What was the result with fq_codel instead?<br>
><br>
><br>
> With fq_codel and the same ECN marking threshold (fq_codel ce_threshold 242us), we see slightly smoother fairness properties (not surprising) but with slightly higher latency.<br>
><br>
> The basic summary:<br>
><br>
> retransmits: 0<br>
> flow throughput: [46.77 .. 51.48]<br>
> RTT samples at various percentiles:<br>
> % | RTT (ms)<br>
> ------+---------<br>
> 0 1.009<br>
> 50 1.334<br>
> 60 1.416<br>
> 70 1.493<br>
> 80 1.569<br>
> 90 1.655<br>
> 95 1.725<br>
> 99 1.902<br>
> 99.9 2.328<br>
> 100 6.414<br>
<br>
This is lovely. Is there an open source tool you are using to generate<br>
this from the packet capture? From wireshark? Or is this from sampling<br>
the TCP_INFO parameter of netperf?</blockquote><div><br></div><div>Thanks. The results and bandwidth graphs are from an internal test orchestration/evaluation/visualization tool written a few years ago by our BBR team member, Soheil Hassas Yeganeh, and further enhanced by others on our team over the years. We are trying to find the time to open-source it, but haven't yet. It can generate the graphs either from pcap files or "ss" output. This one was from "ss" output.</div><div><br></div><div>neal</div><div><br></div></div></div></div>