Date: Wed, 7 Oct 2015 09:14:06 +1100 From: grenville armitage <garmitage@swin.edu.au> To: freebsd-arm@freebsd.org Subject: Re: dwc on banana pi pro and poor network performance Message-ID: <561447AE.3090509@swin.edu.au> In-Reply-To: <obbelm.nvmqh8.1hge18i-qmf@smtp.gmail.com> References: <560ED8DF.4080709@gmx.de> <560F2706.9@toomeek.waw.pl> <F69250DB-0096-41D4-85C1-244122357C45@netgate.com> <obbelm.nvmqh8.1hge18i-qmf@smtp.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 10/03/2015 15:41, jau789@gmail.com wrote: > Since iperf uses tcp by default, the congestion control methods > used on the test systems may affect the test results quite seriously. > Most of the cc methods known to freebsd were not designed with > short high capasity links in mind. Many of those cc methods were > in fact intended for long distances and high bandwidth. In this case > the RTT is very short while many of the CC methods expext much > higher RTTs. I'm curious which of FreeBSD's cc_* algorithms you consider to _expect_ "much higher RTTs". This seems like something we should fix. cheers, gja > For the best results on short distances and high > bandwidth enable ECN bits and use dctcp. The dctcp method was > from day one intended to behave gracefully also when RTT is very > short and the bandwidth is large. > > --jau [...]
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?561447AE.3090509>