[e2e] TCP ex Machina
mail at detlef-bosau.de
Sun Sep 22 14:59:20 PDT 2013
Am 21.09.2013 11:59, schrieb Martin Geddes:
> The converse, however, is true under some circumstances: nodes in the
> network can accurately predict what the self-contention effects of
> already-sent traffic will be, given knowledge of the static properties
> of the onward path. If I pump packets back-to-back down a gigabit link
> to a known megabit bottleneck, I can with certainty say they will
> contend. That opens up the possibility for much smarter ways of
> trading contention and spacing traffic. However, receiving the
> consequent benefits requires letting go of some cherished beliefs
> about how data networks ought to operate.
I'm still to understand "static properties" here.
More information about the end2end-interest