Previous instalments:
For tonight’s edition I have increased the number of small packet sizes in the experiment and dropped the larger sizes. For each of the following data sizes (iperf -l) there are five seconds of traffic: 0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150, 160, 170, 180, 190, 200, 210, 220, 230, 240, 250, 260, 270, 280, 290 and 300 bytes.
Packets per second observed at the destination
For data sizes of up to 90 bytes the packet per second value is pretty much constant. Alex Burr offered a theory on the Bufferbloat list that I may be hitting a packet rate limitation. If I understand properly, the above chart seems to support this.
Bitrate observed at the destination
From the bitrate perspective, the curve flattens around 90 bytes of data as well.