* Re: [Cerowrt-devel] Anything but "AQM"
2013-12-20 21:22 ` dpreed
@ 2013-12-20 21:29 ` Rich Brown
2013-12-20 21:36 ` Sebastian Moeller
2013-12-20 21:58 ` Dave Taht
2 siblings, 0 replies; 8+ messages in thread
From: Rich Brown @ 2013-12-20 21:29 UTC (permalink / raw)
To: dpreed; +Cc: cerowrt-devel
[-- Attachment #1: Type: text/plain, Size: 419 bytes --]
On Dec 20, 2013, at 4:22 PM, dpreed@reed.com wrote:
> They are based on a completely false premise - that queues should be allowed to build at all, and that local information can solve highly transient global problems.
>
> "Dumb Queue Management" is going to be far superior. Keep the queue at zero length, and try to be fair.
Maybe we should go for ATHQM - “Attila (the Hun) Queue Management”. :-)
Rich
[-- Attachment #2: Type: text/html, Size: 1844 bytes --]
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [Cerowrt-devel] Anything but "AQM"
2013-12-20 21:22 ` dpreed
2013-12-20 21:29 ` Rich Brown
@ 2013-12-20 21:36 ` Sebastian Moeller
2013-12-21 0:47 ` Rich Brown
2013-12-20 21:58 ` Dave Taht
2 siblings, 1 reply; 8+ messages in thread
From: Sebastian Moeller @ 2013-12-20 21:36 UTC (permalink / raw)
To: dpreed; +Cc: cerowrt-devel
Hi David,
On Dec 20, 2013, at 22:22 , dpreed@reed.com wrote:
> Given that there is no likelihood of making localized queue management "intelligent" because it has no global information whatsoever, I strongly suggest that "smart" "intelligent" and even "active" are hugely misleading.
>
> They are based on a completely false premise - that queues should be allowed to build at all, and that local information can solve highly transient global problems.
>
> "Dumb Queue Management" is going to be far superior. Keep the queue at zero length, and try to be fair.
Well, this thread is about the "marketing" of the concept, we assume that the solution Dave created by combining a number of great components works much better than what is out there. Now we want other people to want and get the fruits of Dave's work in their home router. So I for one assume a catchy name is going to help to make it popular. DQM will need another expansion than dumb QM to be a keeper...
>
> There's a simple way to do the latter - use a filter (similar to a Bloom filter) that captures recent/frequent users of the queue, and when the queue on an outbound link grows more than about 2-3 packets (double buffering is all you need to keep the link full) discard the most recent and frequent packets (or send information that tells them to slow down).
For the bloom filter have a look at the BLUE aqm, but the way I understood the cam codel paper is that it basically does that keep the standing queue short while allowing some burstiness in the input...
>
> There's been a lot of wasted time and effort trying to build queues long enough so that you can be "intelligent", but by then you have already lost the battle. You've gotten into a positive feedback loop where you have encouraged the endpoints to send more packets than you can ever drain out of the queue.
>
> I truly, truly do not understand why people don't look at realistic network loads and structures.
>
>
>
> On Friday, December 20, 2013 3:52pm, "Rich Brown" <richb.hanover@gmail.com> said:
>
> > Dave,
> >
> > You wrote:
> >
> > > What's in a name? AQM has been pretty thoroughly defined to equal
> > > active queue *length* management and not packet scheduling.
> > > Overloading "AQM" what cerowrt does is apt to cause even more
> > > confusion in the field than it already does. We discussed using LBO as
> > > a word but that appears hopelessly overloaded with leveraged buy out.
> > >
> > > I go back to one I liked a while back:
> > >
> > > Smart Queue Management. (SQM)
> > >
> > > This got dissed on the aqm list too, but so far a viable alternative
> > > TLA has not appeared. It's sufficiently different to hang a different
> > > definition off of ("Smart queue management is an intelligent
> > > combination of better packet scheduling (flow queuing) techniques
> > > along with with active queue length management (aqm)”)
> >
> > and
> >
> > > Any ideas for a name for packet scheduling, prioritization, and active
> > > queue management better than just "AQM", or "QoS"?
> > >
> > > SQM "Smarter Queue Management"
> > > CeroShaper
> > > LBO Latency and Bandwidth Optimisation
> >
> > I was prepared to agree with “SQM”, and had written a long note
> > (below) when my brain uttered “Intelligent Queue Management”.
> > I’m not convinced that one is better than the other…
> >
> > Rich
> >
> > ===== The benefits of SQM ======
> >
> > Wikipedia sez… SQM may refer to:
> >
> > - Sociedad Química y Minera de Chile - a Chilean mining and chemical
> > enterprise
> > - Software quality management
> > - Spectrum quality management
> > - Supplier Quality Management
> > - Sensors Quality Management Inc. - provides unbiased evaluations of a company's
> > operations relating to issues of quality, service, cleanliness and value
> > - Sky Quality Meter, a device for measuring light pollution
> >
> > and also : São Miguel do Araguaia airport IATA code
> >
> > sqm may refer to :
> >
> > - square metre
> > - Windows Live Messenger log file extension
> >
> > So it doesn’t appear that there are any seriously conflicting uses of that
> > TLA…
> >
> > And I prefer “Smart Queue Management” to “Smarter Queue
> > Management”. We’ll leave to someone else to go out on the weak branch
> > and espouse “Smarter queue management” and “Smartest queue
> > management”. (What comes after that? “Smart and a half”,
> > Smart**2"?)
> >
> > Rich
> > _______________________________________________
> > Cerowrt-devel mailing list
> > Cerowrt-devel@lists.bufferbloat.net
> > https://lists.bufferbloat.net/listinfo/cerowrt-devel
> >
> _______________________________________________
> Cerowrt-devel mailing list
> Cerowrt-devel@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cerowrt-devel
^ permalink raw reply [flat|nested] 8+ messages in thread* Re: [Cerowrt-devel] Anything but "AQM"
2013-12-20 21:36 ` Sebastian Moeller
@ 2013-12-21 0:47 ` Rich Brown
2013-12-21 2:55 ` Dave Taht
0 siblings, 1 reply; 8+ messages in thread
From: Rich Brown @ 2013-12-21 0:47 UTC (permalink / raw)
Cc: cerowrt-devel
Folks,
I just remembered that about a year ago, Bill McGonigle offered a “marketing name” for CeroWrt - BroadbandEQ. He wrote:
> From: Bill McGonigle <bill@bfccomputing.com>
> Subject: Re: Dang, I forgot...
> Date: December 10, 2012 11:13:55 PM EST
> To: Richard Brown
>
> Rationale: Not a precise technical name, but in the vein of "WiFi" it's
> something that people can make a prior association with. Hi-Fi's and equalizers, right?
> To backcronym it, "Broadband Enhanced Queueing" which ain't such a bad description.
> I know that "broadband" is technically wrong on many topologies, but it seems to
> have achieved popular usage for "high speed Internet". I realize that Co-Del will be
> also useful on non-last-mile links and such, but the intent is to have something on a
> label on a SOHO router box at the warehouse club for people to recognize, right?
> Getting it in use is more important than being technically pedantic anyway, and a catchy
> marketing name seems to have worked for WiFi, err, I mean "802.11[b,g,a,n] wireless
> ethernet and associated standards."
>
> It would be fairly simple to create a logo involving the word and slider knobs
> or something. If there's interest I could whip up a Rev. A. logo. And, besides,
> it looks like it's not in use: https://www.google.com/search?q=“broadbandeq"
The name continues to grow on me…
Rich
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [Cerowrt-devel] Anything but "AQM"
2013-12-21 0:47 ` Rich Brown
@ 2013-12-21 2:55 ` Dave Taht
0 siblings, 0 replies; 8+ messages in thread
From: Dave Taht @ 2013-12-21 2:55 UTC (permalink / raw)
To: Rich Brown; +Cc: cerowrt-devel
Given that StreamBoost(tm) consists of fq_codel + bigfoots packet
classification technology and service which gives prioritization to
gamer packets + some kind of automatic rate finder (better than
gargoyle's ACC I'm told). I am increasingly irked by how the roles
these technologies' interplay are being sold by the people selling it.
(the prioritization bit is thoroughly oversold, fq_codel is never
mentioned)
I AM happy it's being sold, winning things like best in show at SCTE
for example. there is clearly demand for debloating technologies!
I liked the idea of BroadBandEQ(tm) last year. Still do. Being that at
the time I was nominally working for the cable industry I wasn't in a
position to go around trademarking things. Now I'm not. I can't
remember if Bill followed up on the trademark or not.
I'm not sure if what I have in mind for this code is "competitive"
with StreamBoost or Pie, I think I was trying merely to go for a term
(like SQM) that covered more stuff than "AQM", rather than a "brand",
like BroadBandEQ.
I do like things like the Dolby brand to ensure quality for the final
product (and make a little money). CeroWrt doesn't exactly roll off
the tongue.
There are billions of devices that need fixing, and perhaps creating a
trusted brand, and trusted tests, would help? I've long thought about
setting up a 501c6 for bufferbloat.net, maybe that would work?
Aside from the name and branding discussion here:
Next years effort is going to be "make-wifi-fast", which will apply a
lot of things we've discussed here to some new hardware. It's a lot
easier to talk to people about the goal of making wifi fast, than it
is to describe bufferbloat, or ipv6.
On Fri, Dec 20, 2013 at 4:47 PM, Rich Brown <richb.hanover@gmail.com> wrote:
> Folks,
>
> I just remembered that about a year ago, Bill McGonigle offered a “marketing name” for CeroWrt - BroadbandEQ. He wrote:
>
>> From: Bill McGonigle <bill@bfccomputing.com>
>> Subject: Re: Dang, I forgot...
>> Date: December 10, 2012 11:13:55 PM EST
>> To: Richard Brown
>>
>> Rationale: Not a precise technical name, but in the vein of "WiFi" it's
>> something that people can make a prior association with. Hi-Fi's and equalizers, right?
>> To backcronym it, "Broadband Enhanced Queueing" which ain't such a bad description.
>> I know that "broadband" is technically wrong on many topologies, but it seems to
>> have achieved popular usage for "high speed Internet". I realize that Co-Del will be
>> also useful on non-last-mile links and such, but the intent is to have something on a
>> label on a SOHO router box at the warehouse club for people to recognize, right?
>> Getting it in use is more important than being technically pedantic anyway, and a catchy
>> marketing name seems to have worked for WiFi, err, I mean "802.11[b,g,a,n] wireless
>> ethernet and associated standards."
>>
>> It would be fairly simple to create a logo involving the word and slider knobs
>> or something. If there's interest I could whip up a Rev. A. logo. And, besides,
>> it looks like it's not in use: https://www.google.com/search?q=“broadbandeq"
>
> The name continues to grow on me…
>
> Rich
> _______________________________________________
> Cerowrt-devel mailing list
> Cerowrt-devel@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cerowrt-devel
--
Dave Täht
Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subscribe.html
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [Cerowrt-devel] Anything but "AQM"
2013-12-20 21:22 ` dpreed
2013-12-20 21:29 ` Rich Brown
2013-12-20 21:36 ` Sebastian Moeller
@ 2013-12-20 21:58 ` Dave Taht
2 siblings, 0 replies; 8+ messages in thread
From: Dave Taht @ 2013-12-20 21:58 UTC (permalink / raw)
To: David Reed; +Cc: cerowrt-devel
On Fri, Dec 20, 2013 at 1:22 PM, <dpreed@reed.com> wrote:
> Given that there is no likelihood of making localized queue management
> "intelligent" because it has no global information whatsoever, I strongly
> suggest that "smart" "intelligent" and even "active" are hugely misleading.
>
>
>
> They are based on a completely false premise - that queues should be allowed
> to build at all, and that local information can solve highly transient
> global problems.
>
David, I think we should have this discussion offline. I thought you were paying
attention on the bloat list.
> "Dumb Queue Management" is going to be far superior. Keep the queue at zero
> length, and try to be fair.
Heh.
> There's a simple way to do the latter - use a filter (similar to a Bloom
> filter) that captures recent/frequent users of the queue, and when the queue
Tried SFB. It didn't work.
> on an outbound link grows more than about 2-3 packets (double buffering is
> all you need to keep the link full) discard the most recent and frequent
> packets (or send information that tells them to slow down).
Nope, due to the bursty nature of tcp and of things like wifi packet
aggregation you need be able to absorbe a burst of an RTT's worth of
queue around, what kathy and van call "good queue".
I have a lot of hope that now that we are seeing "paced" tcp
schedulers that we'll see much less structure at the bottlenecks from
isochronous sources, but the batchy ones like gpon, wifi, and cable,
will induce more, and structure does seem to arrive from navigating
bottlenecks also, as per slide 30 in this:
http://www.pollere.net/Pdfdocs/QrantJul06.pdf
>
>
>
> There's been a lot of wasted time and effort trying to build queues long
> enough so that you can be "intelligent", but by then you have already lost
> the battle. You've gotten into a positive feedback loop where you have
> encouraged the endpoints to send more packets than you can ever drain out of
> the queue.
The goal here is 100% utilization at 0 latency. We are getting
preciously close to it with fq_codel and derivatives.
> I truly, truly do not understand why people don't look at realistic network
> loads and structures.
I like to think I do.
>
>
>
>
>
> On Friday, December 20, 2013 3:52pm, "Rich Brown" <richb.hanover@gmail.com>
> said:
>
>> Dave,
>>
>> You wrote:
>>
>> > What's in a name? AQM has been pretty thoroughly defined to equal
>> > active queue *length* management and not packet scheduling.
>> > Overloading "AQM" what cerowrt does is apt to cause even more
>> > confusion in the field than it already does. We discussed using LBO as
>> > a word but that appears hopelessly overloaded with leveraged buy out.
>> >
>> > I go back to one I liked a while back:
>> >
>> > Smart Queue Management. (SQM)
>> >
>> > This got dissed on the aqm list too, but so far a viable alternative
>> > TLA has not appeared. It's sufficiently different to hang a different
>> > definition off of ("Smart queue management is an intelligent
>> > combination of better packet scheduling (flow queuing) techniques
>> > along with with active queue length management (aqm)”)
>>
>> and
>>
>> > Any ideas for a name for packet scheduling, prioritization, and active
>> > queue management better than just "AQM", or "QoS"?
>> >
>> > SQM "Smarter Queue Management"
>> > CeroShaper
>> > LBO Latency and Bandwidth Optimisation
>>
>> I was prepared to agree with “SQM”, and had written a long note
>> (below) when my brain uttered “Intelligent Queue Management”.
>> I’m not convinced that one is better than the other…
>>
>> Rich
>>
>> ===== The benefits of SQM ======
>>
>> Wikipedia sez… SQM may refer to:
>>
>> - Sociedad Química y Minera de Chile - a Chilean mining and chemical
>> enterprise
>> - Software quality management
>> - Spectrum quality management
>> - Supplier Quality Management
>> - Sensors Quality Management Inc. - provides unbiased evaluations of a
>> company's
>> operations relating to issues of quality, service, cleanliness and value
>> - Sky Quality Meter, a device for measuring light pollution
>>
>> and also : São Miguel do Araguaia airport IATA code
>>
>> sqm may refer to :
>>
>> - square metre
>> - Windows Live Messenger log file extension
>>
>> So it doesn’t appear that there are any seriously conflicting uses of that
>> TLA…
>>
>> And I prefer “Smart Queue Management” to “Smarter Queue
>> Management”. We’ll leave to someone else to go out on the weak branch
>> and espouse “Smarter queue management” and “Smartest queue
>> management”. (What comes after that? “Smart and a half”,
>> Smart**2"?)
>>
>> Rich
>> _______________________________________________
>> Cerowrt-devel mailing list
>> Cerowrt-devel@lists.bufferbloat.net
>> https://lists.bufferbloat.net/listinfo/cerowrt-devel
>>
--
Dave Täht
Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subscribe.html
^ permalink raw reply [flat|nested] 8+ messages in thread