My comments basically mirror jims in: http://www.ietf.org/mail-archive/web/aqm/current/msg01117.html
which i see gathered no discussion here. Those interested in evaluating aqms in the real world might want to try their favorite aqms against the new dslreports speedtest (which includes bufferbloat measurements). The methods they are using have been extensively discussed on the bloat list over the past few weeks. http://www.dslreports.com/speedtest They do not have enough servers in europe, but the more distant eu results would be nice, particularly of their higher end tests (say cable or fiber), against slower dsl lines, as they use progressively more streams per "faster" technology, which have a ramp up period based on RTT. For the ecn fans, the dslreports servers are ecn enabled, you can try turning it on for your clients and aqms and see what happens. -- Dave Täht Open Networking needs **Open Source Hardware** https://plus.google.com/u/0/+EricRaymond/posts/JqxCe2pFr67 _______________________________________________ aqm mailing list [email protected] https://www.ietf.org/mailman/listinfo/aqm
