[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAA93jw5pMqz3qm35jpkdQQQOX1pUSStR8yF+Eger=+17Eur8Dw@mail.gmail.com>
Date: Mon, 16 Oct 2023 12:56:24 -0700
From: Dave Taht <dave.taht@...il.com>
To: rjmcmahon <rjmcmahon@...cmahon.com>
Cc: netdev@...r.kernel.org
Subject: Re: Suggest use -e or --enhanced with iperf 2
Bob has put in a lot of work over the past few years on improving
iperf2's capabilities. The new bounceback tests and histograms are
great! I hope more folk here upgrade to the newer versions, and pour
through the man pages for the new options.
There is more to good networking than just throughput tests.
On Mon, Oct 16, 2023 at 12:20 PM rjmcmahon <rjmcmahon@...cmahon.com> wrote:
>
> Hi All,
>
> I suggest the use of enhanced reports w/iperf 2, for those using iperf 2
> version that's actively maintained (not 2.0.5.) This will provide a bit
> more information to the user including CWND & RTT samples.
>
> If the clocks are synced, then also use the --trip-times option on the
> client which will enable latency related stats. There are also
> histograms.
>
> Man page is here: https://iperf2.sourceforge.io/iperf-manpage.html
>
> Finally, there is some python code in the flows directory - though it
> may be a bit brittle.
>
> Source code is here:
> https://sourceforge.net/p/iperf2/code/ci/master/tree/
>
> Bob
>
--
Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html
Dave Täht CSO, LibreQos
Powered by blists - more mailing lists