[Bloat] Progress with latency-under-load tool

[Jonathan Morton]

On 18 Mar, 2011, at 1:38 am, grenville armitage wrote:

> So, this is probably tangential to what the latency-under-load tool is
> aiming to achieve, but we have a tool that can be used to measure
> RTT between two points (e.g. either side of an 802.11 link) using
> tcpdump on consumer-grade PCs and no active probing (ala ping).

The average actual consumer isn't going to be able to set that up.  Sounds great for research though.

After much headbutting of walls, my tool finally seems to work.  The biggest challenge turned out to be getting both ends to shut down gracefully (and more-or-less simultaneously) after each phase of the test.

With that solved, I'm now running a full test run between two of my less powerful machines on a wired LAN.  I can immediately see that even a 1996-vintage PC can saturate a 100Mbps link hard enough to exhibit bloat-related problems.  Once again, anyone claiming this to be a "new problem" is grossly misinformed.

More details when I have them.

 - Jonathan