...
Linux 2.4 and later versions implemented a sender-side autotuning mechanism, so that setting the optimal buffer size on the sender is not needed (see here). This assumes you have set large buffers on the receive side, as the sending buffer will not grow beyond the size of the receive buffer.
| Wiki Markup |
|---|
There is an interesting \[discussion on the effects of buffering on [RTTs|http://gettys.wordpress.com/2010/12/03/introducing-the-criminal-mastermind-bufferbloat/]. |
The poor reachability of UETTAXILA makes the problem harder to diagnose.
...
On the other hand looking at the smokeping plot above there is an obvious reduction in minimum RTT on or about November 10th. Prior to that date it is about 60ms, after that date it drops to about 35ms.
Further Analysis: Jan 14 to Jan 27, 2011
Analysis for Jan 14 to Jan 27 didn't reveal any patterns apart from heavy network utilization from midnight to 4am (Pakistan Daylight Time) in the morning. Possible reason could be data transfer between NCP and UETTAXILA. This is part of their research collaboration. Below is the strip graph from Jan 14 to Jan 27. Spreadsheet attached here.
