Post by d***@reed.comVery good. So the idea, rather than Comcast implementing codel or
something proper in the DOCSIS 3.0 systems they have in the field, is to
emulate power boost to "impedance match" the add-on router-based codel
approach to some kind of knowledge of what the DOCSIS CMTS buffering state
looks like....
http://tools.ietf.org/html/draft-white-aqm-docsis-pie-00
is mandated in DOCSIS 3.1 modems.
The ECO has gone out for DOCSIS 3.0 as well.
Pie is tightly intertwined with the powerboost capable scheduler.
The powerboost feature is viewed
Post by d***@reed.comAnd of course nothing can be done about "downstream" bufferbloat in the
Comcast DOCSIS deployment.
I have seen promising noises from Arris at least, on the CMTS side, and
had posted some of their thinking from the last meeting of the society
of cable engineers on one of our mailing lists fairly recently, which
induced no comment.
http://www.ietf.org/mail-archive/web/aqm/current/msg00538.html
They had come up with a variant of red, called "LRED", and a nifty enhancement
to SFQ, but hadn't got as far as grokking that queue length and packet
scheduling
together were a better answer.
I would certainly like the overall level of overbuffering in CMTSes to be
reduced which is something the cable providers could do today, and that
certainly bugs me.
Post by d***@reed.comSo instead of fixing Comcast's stuff "correctly", we end up with a literal "half measure".
The cable ISP industry as a whole is slave to their equipment makers.
cablelabs only has dominion over the cable modem side.
What the world needs is better long distance media types not designed
by former telecoms, and designed for packet data.
If you thought cable was complex and had bad ideas
in it, see gpon, also. Or moca, or various powerline standards.
What my hope has been has been that the increasingly common
hybrid cable modem/wireless gateways would gain fq_codel support and manage
both the up and downstreams themselves, thus bypassing the
slow to update million dollar head end portion of the industry
entirely.
I'd like something as powerful and as loved as the revolution V6 box
to appear.
I'm not holding my breath.
Apple could do it right.
Post by d***@reed.comWho does Comcast buy its CMTS gear from, and if it has a Heartbleed bug,
maybe some benevolent hacker should just fix it for them?
There are only 3 makers of CMTS gear - cisco, arris, and a third company
from china whose name I forget.
Post by d***@reed.comIt's now been 2 years since Comcast said they were deploying a fix. Was
that just them hoping the critics would dissipate their time and effort?
Competition is needed. I'm rooting for gfiber to provide some.
Post by d***@reed.comAnd is Comcast still using its Sandvine DPI gear?
No idea. I certainly see an aweful lot of packets remarked CS1.
Post by d***@reed.comI'm afraid that monopolists really don't care. Even friendly-sounding ones.
Especially when they can use their technical non-deployments to get paid
more by Netflix.
Well, grump, I am fair minded. Netflix's business model has always been
to colocate their servers within the ISP itself with things like the
open-connect
appliance.
http://www.networkworld.com/community/blog/netflix-goes-edge-internet
It makes a rediculous amount of sense to do so, and is a cost savings
to both ISP and netflix on external bandwidth, but somebody still has to
cover the rack space, hardware, and electricity no matter where located.
Post by d***@reed.comPost by Dave TahtThe features of the PowerBoost feature are well documented at this
point. A proper
emulation of them is in the ns2 code. It has been a persistent feature
request, to
add support to some Linux rate shaper to properly emulate PowerBoost,
but no funding
ever arrived.
Basically you get 10 extra megabytes above the base rate at whatever
rate the line
can sustain before it settles back to the base rate.
You can also see that as presently implemented, at least on a short
RTT path, the feature
does not prevent bufferbloat.
http://snapon.lab.bufferbloat.net/~cero2/jimreisert/results.html
I'd like a faster, less cpu intense rate shaper than sch_htb in
general, and powerboost emulation would be nice.
Post by Aaron Woodhttp://snapon.lab.bufferbloat.net/~cero2/jimreisert/results.html
And talking off-list with Jim, I think that the "PowerBoost" is above the
quoted rate, as the 24/4 service hits >36Mbps TCP data rate. I'm
definitely
Post by Aaron Woodsad that using SQM in the router instead of the modem loses features like
that. But I'll just be happy to have upload over 1Mbps again.
I do know that the FCC was cracking down on advertised vs. actual rates, and
http://www.fcc.gov/measuring-broadband-america
-Aaron
As a non-Comcast-customer, I am curious too. I had thought their
"boost"
Post by Aaron Woodfeature allowed temporary rates *larger* than the quoted "up to" rates.
(but I remember the old TV-diagonal games and disk capacity games, where
any
Post by Aaron Woodway to get a larger number was used in the advertising, since the FTC
didn't
Post by Aaron Woodhave a definition that could be applied).
I wonder if some enterprising lawyer might bring the necessary consumer
fraud class-action before the FTC to get clear definitions of the
numbers?
Post by Aaron WoodIt's probably too much to ask for Comcast to go on the record with a
precise
Post by Aaron Wooddefinition.
On Saturday, April 19, 2014 8:55am, "Aaron Wood"
I'm setting up new service in the US, and I'm currently assuming that
all
Post by Aaron Woodof Comcast's rates are "boosted" rates, not the "provisioned" rates.
So if they quote 50/10Mbps, I assume that's not what will need to be set
in SQM with CeroWRT.
Does anyone have good info on the "provisioned" rates that go with each
of
Post by Aaron Woodthe Comcast tiers?
Basically, I'm trying to get to an apples-to-apples comparison with
Sonic.net DSL (I'll be close enough to the CO to run in Annex M "upload
priority" mode and get ~18/2 service).
Thanks,
Aaron
_______________________________________________
Cerowrt-devel mailing list
https://lists.bufferbloat.net/listinfo/cerowrt-devel
--
Dave Täht
https://w2.eff.org/Censorship/Internet_censorship_bills/russell_0296_indecent.article
--
Dave Täht
NSFW: https://w2.eff.org/Censorship/Internet_censorship_bills/russell_0296_indecent.article