General list for discussing Bufferbloat
 help / color / mirror / Atom feed
From: Dave Taht <dave.taht@gmail.com>
To: bloat <bloat@lists.bufferbloat.net>,
	Jacopo Cesareo <jcesareo@cs.princeton.edu>
Subject: [Bloat] Testing wireless broadcast/multicast within cerowrt
Date: Wed, 3 Aug 2011 09:39:18 -0600	[thread overview]
Message-ID: <CAA93jw7gcZwB-sWtvr9ZTPknRjd__5LntdW7neAwn853Mvp9wg@mail.gmail.com> (raw)

[-- Attachment #1: Type: text/plain, Size: 2661 bytes --]

Given how devastatingly effective my call to the list for help was, on:

http://www.bufferbloat.net/issues/216
http://www.bufferbloat.net/issues/195

(195 is NAILED right now, 216 is making serious progress - see the bug
reports for more details)

I figure that perhaps leveraging y'all expertise to take a harder look at
multicast - which we've discussed extensively here, would be good.

I picked uftp out of thin air as a possibly useful tool for analyzing
multicast behavior on wired and multiple radios simultaneously. It's one of
the few multicast tools that is widely used.

One really excellent suggestion that has gone by was to break with the
802.11 standard and multicast at the highest rate all the stations are known
to accept, but it would be good to have some tool - not necessarily uftp -
to tweak at it.

I have no idea as to the overall state of multicast support in Linux. Most
multicast research died ages ago, but 'turning up the volume' in this way
may lend some insight into the problems we are having with the more common
'ANT' multicast packets like ARP, etc.

I've been working with a grad student over at princeton (cc'd) on getting
uftp to work right, but we're running into issues that I don't have the
spare cycles to resolve right now. Maybe I missed something in the kernel
build? Maybe there's something weird about jacobo's laptop or the router
itself? (I've already asked dennis for insight)

http://www.bufferbloat.net/issues/206

My dream, in trying to use uftp for this, is to have a knob I can turn up or
down for bandwidth for almost isosyncronous and simultaneous! multicast
streams running across gigE, various forms of 802.11abgn, on multiple
radios, all at the same time - to analyze, and get more insight as to what's
going on - not just with basic multicast - but as I've been seeing broadcast
like arp and dhcp failing everywhere I've encountered a 'n' network, of
late, to be able to take a hard look at all of it.

I've thrown out the codebase that cerowrt RC4 was based on and development
builds are currently taking place here:

http://huchra.bufferbloat.net/~andrewm/cerowrt/

My problem at the moment could be something basic - a missing config in the
build? - but it would be nice to know if uftp works right on more
conventional systems before working harder at it.

Complete configuration info on how to use it, and it's performance, etc,
would be useful.

And suggestions on other multicast/broadcast tools generating data worth
analyzing is highly desired.


-- 
Dave Täht
SKYPE: davetaht
US Tel: 1-239-829-5608
http://the-edge.blogspot.com

[-- Attachment #2: Type: text/html, Size: 3160 bytes --]

             reply	other threads:[~2011-08-03 14:52 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-08-03 15:39 Dave Taht [this message]
2011-08-03 19:18 ` Dave Hart
2011-08-03 19:23   ` Dave Taht

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://lists.bufferbloat.net/postorius/lists/bloat.lists.bufferbloat.net/

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAA93jw7gcZwB-sWtvr9ZTPknRjd__5LntdW7neAwn853Mvp9wg@mail.gmail.com \
    --to=dave.taht@gmail.com \
    --cc=bloat@lists.bufferbloat.net \
    --cc=jcesareo@cs.princeton.edu \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox