[Bloat] new members, welcome!

[Dave Täht]

We hit a milestone sometime early this morning. There are now 100
people on this mailing list!

New members, welcome! I'd love it if we/you'd could circle back to some
earlier threads in conversation[1], in particular I'd like to see the
glossary of agreed upon terms expanded. [2]

I'd like the "dark buffers" concept expanded [3] to include retransmits
or a new term invented.

If any of the 28 that have signed up for the wiki do not have editing
privs, please contact me off list. 

Also we had much discussion, since fizzled out, on a good introductory
analogy to how the internet actually works. [4]

I confess that I'm a little buried right now in trying to assemble
additional hardware resources worldwide, while working at layers 8 & 9 of
the stack on the background bufferbloat detector idea. [5]. I just got a
large data set to play with.

Nathaniel's iwl patches look promising (only minor quibbles on the
Linux-wireless list[6] - 

I am editing down a recorded conversation with Felix Fietkau (one of the
main openwrt & wireless developers and author of the minstrel rate
control algorithm) that started as a discussion of my
latency-smashing-yet-horrifying-to-him ath9k patch[7].

It later turned into a marvelous indepth discussion of how 802.11n
wireless actually works and some possible solutions[8], down to a low
level. I think it is well worth understanding for people more familiar
with wires or higher levels of the stack [9]. I like the concept of
"Bufferbloat Public Radio" in that sometimes it's just nice to get away
from the computer and listen to something while doing something else,
but that's me. Do others like this idea? We had a LOT of downloads
(probably over a 1000 by now) of jg's mp3.

Thanks everybody for your concern and interest in fixing bufferbloat.


1: https://lists.bufferbloat.net/pipermail/bloat/2011-February/thread.html
2: http://www.bufferbloat.net/projects/bloat/wiki/Glossary
3: http://www.bufferbloat.net/projects/bloat/wiki/Dark_buffers
4: https://lists.bufferbloat.net/pipermail/bloat/2011-February/000050.html
5: https://github.com/dtaht/Cosmic-Background-Bufferbloat-Detector
   I also ran into data representation issues - perhaps postgres isn't
   the right thing.
6: http://thread.gmane.org/gmane.linux.kernel.wireless.general/64733
7: https://github.com/dtaht/Cruft/blob/master/bloat/558-ath9k_bufferbloat.patch
8:
https://lists.bufferbloat.net/pipermail/bloat-devel/2011-February/thread.html

9: Would people mind if it was more of a 1HR podcast than 30 minute
exposition? We diverged off the bufferbloat/wireless topic several
times, in interesting ways, and editing it down will take more time than
I would like. 

-- 
Dave Taht
http://nex-6.taht.net