On Wed, 1 Jun 2016, Wesley Eddy wrote:
- Are the current couple of algorithms all that's needed for the Internet, or
are there other algorithms building on these, learning from experience with
them, or making other improvements which we should work on? (e.g. we have
the DualQ draft, and recently the GSP draft has been updated)
People are always working on better ideas :-)
right now, there is work being done on 'cake' [email protected]
(started off as 'convert sqm scripts to C code for speed' that is working on
being able to handle rate limiting and enhance from fq_codel)
This has been ongoing and is available in some OpenWRT builds. Unfortunantly it
keeps growing new special-case features, so it may never settle down.
also on that list there was the suggestion to look at combining BLUE and Codel
(working name COBALT) letting each cover the weak points of the other, and
simplifying the code in the process (by eliminating a lot of special case code
by letting the other algorithm handle it)
This is a recent suggestion and the first cut of the code is in the process of
being nailed down, so there isn't any real-world experience with it yet.
Info on both of these can be found in the list archives
https://lists.bufferbloat.net/listinfo/codel
David Lang
_______________________________________________
aqm mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/aqm
