Re: [Cake] Cubic issues?

[Alan Jenkins <alan.christopher.jenkins@gmail.com>]

On 29/09/2015, Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk> wrote:
> This is interesting
> http://www.theregister.co.uk/2015/09/29/google_cubists_fix_congestion_control_for_faster_tcp/

heh, I would recommend reading their source because they seemed to
omit the point

http://bitsup.blogspot.co.uk/2015/09/thanks-google-tcp-team-for-open-source.html

[Patrick McManus] The problem can be roughly summarized as the
controller mistakenly characterizing the lack of congestion reports
*over a quiescent period*  as positive evidence that the network is
not congested

[thereg] the bug was simple: TCP CUBIC interprets a lack of congestion
reports as an opportunity to send data at a faster rate.

[thereg] That condition could, however, arise merely because the
system hasn't been getting any congestion reports.

i.e. someone choked on the word quiescent and forgot to re-word it,
leaving a tautology.

Alan