Re: [Cake] lan keyword affects host fairness

2017-11-24 Thread Pete Heist
> On Nov 24, 2017, at 9:32 PM, Jonathan Morton wrote: > Mmm, that's a lot of drops. So you're not using ECN? > Not using ecn. I did one ecn run but didn’t see much change. I did more runs at 950mbit- 20ms, 50ms 100ms and added a chart at the bottom of rtt vs fairness

Re: [Cake] lan keyword affects host fairness

2017-11-24 Thread Pete Heist
> On Nov 24, 2017, at 8:48 PM, Jonathan Morton wrote: > Can I just point out that the four hardware queues will themselves be > interfering with the backpressure on short timescales when Cake is in > unlimited mode, and can easily explain the poorer host-fairness

Re: [Cake] lan keyword affects host fairness

2017-11-24 Thread Dave Taht
I support removing metro and below as keywords. Note: I am more interested in throughput (w/ecn) at the lower rtt settings than flow fairness (is the aqm scaling?). If we can have shorter queues overall while not taking a throughput hit, in the datacenter, that's a win. I have a hope, however,

Re: [Cake] lan keyword affects host fairness

2017-11-24 Thread Marcelo Ricardo Leitner
On Fri, Nov 24, 2017 at 01:06:12PM +0100, Sebastian Moeller wrote: > > > On Nov 24, 2017, at 12:21, Toke Høiland-Jørgensen wrote: > > > > Dave Taht writes: > > > >> Pete Heist writes: > >> > >>>On Nov 23, 2017, at 10:44 AM, Jonathan

Re: [Cake] lan keyword affects host fairness

2017-11-23 Thread Dave Taht
Pete Heist writes: > On Nov 23, 2017, at 10:44 AM, Jonathan Morton > wrote: > > This is most likely an interaction of the AQM with Linux' scheduling > latency. > > At the 'lan' setting, the time comstants are similar in magnitude

Re: [Cake] lan keyword affects host fairness

2017-11-23 Thread Pete Heist
> On Nov 23, 2017, at 10:44 AM, Jonathan Morton wrote: > This is most likely an interaction of the AQM with Linux' scheduling latency. > > At the 'lan' setting, the time comstants are similar in magnitude to the > delays induced by Linux itself, so congestion might be

Re: [Cake] lan keyword affects host fairness

2017-11-23 Thread Jonathan Morton
This is most likely an interaction of the AQM with Linux' scheduling latency. At the 'lan' setting, the time comstants are similar in magnitude to the delays induced by Linux itself, so congestion might be signalled prematurely. The flows will then become sparse and total throughput reduced,

[Cake] lan keyword affects host fairness

2017-11-23 Thread Pete Heist
It seems that the ‘lan’ keyword (and probably other lower rtt settings in general) may adversely impact host fairness in some cases. Is this to be expected? I set up a fairness test with rrul_be_nflows where one client has 2/2 TCP flows and the other has 8/8 TCP flows, then ran five tests: