[Bloat] Terminology for Laypeople
Simon Barber
simon at superduper.net
Mon May 17 01:18:55 EDT 2021
Bufferbloat -
At every router there are buffers that hold packets about to go out on a link, incase the packets coming into the router arrive faster than they can go out. If the packets keep arriving too fast the buffers fill up and eventually arriving packets have nowhere to go and are dropped. TCP is a protocol that underlies most data transferred on the internet - every time you load a webpage for example, you are using TCP. The way TCP works is by gradually sending data faster and faster until a packet is dropped, then slowing down a bit before trying to ramp speed up again, and again, and again for ever. This means that TCP is trying to keep the buffers in the router that feeds the slowest link in your connection full (Ramping up it’s speed until a packet is dropped - i.e. the buffers are full). Unfortunately these days routers have way more buffers than necessary and every data packets that goes into a buffer must wait for all the other packets ahead of it in the buffer to be sent first. This can add seconds of delay to your connection in some cases.
How’s that?
Simon
> On May 16, 2021, at 11:48 AM, john <email at matrix8.org> wrote:
>
> Hello,
> I have been on this mailing list since March this year. I am one of the
> laypeople who is very interested in bufferbloat and have been trying to
> understand what the bufferbloat actually is by reading your email
> exchanges.
>
> I was very happy when the subject: [Bloat] Questions for Bufferbloat
> Wikipedia article, came up. I thought someone could finally explain it
> with very easy word which I could understand. But the more discussion
> goes on the more I got confused and I thought this mailing list is for
> aliens exchanging idea not for me human.
> :-)
>
> I also watched Dave's
> Making Wifi Fast + Slides - BattleMeshV8 - YouTube
> https://www.youtube.com/watch?v=Rb-UnHDw02o&t=1657s
> But I still could not really understand exactly what Dave was trying to
> explain in it.
>
> Then, another subject: [Bloat] Terminology for Laypeople, came up. I
> thought I could finally understand what the bufferbloat is. But so far I
> am not even close to the understanding. Now it seems to me that this
> mailing list is only for Albert Einstein class scientists to discuss
> something super difficult to understand. This is because no one seems to
> be able to explain in a manner laypeople can understand. Or probably my
> effort to understand it is not really enough yet. But I think I have
> been really doing my best trying to understand what all of you are
> trying to explain about.
>
> I thought I could not be qualified to even drop a line to this mailing
> list because I can not write nor explain in the manner others on this
> mailinglist do. I have been hesitating to ask a question. But please
> allow me to share with you what image came up in my mind after reading
> all the Emails exchanged here since March.
>
> As of now, I am wondering if the bufferbloat could be explained with
> something like a sushi belt-conveyor, the one you may find at the sushi
> restaurant equipped with automated belt-conveyor to bring plates with
> sushi to customer's seat.
>
> In my mind, I am seeing the plate as a packet and the conveyor as
> network. For Europeans and Americans, it may be easier to picture the
> KrispyKreme's donuts belt conveyor in mind instead of sushi one. Donuts
> are the packets and they go around the network on conveyor in my mind.
>
> After watching Dave's YouTube video, it seems to me, the congestion of
> the packets which Dave was explaining is equivalent to sushi plats on
> conveyor stuck on the route and colliding each other on the conveyor
> since the conveyor keeps bringing more packets one after another to the
> collision point, then plats overflow from the conveyor and dropped on
> the floor.
>
> So now, my question is the picture I described above is close to what
> bufferbloat is? Or I am still very far from understanding? If I am still
> far from understanding, will you be able to explain it to me, the
> laypeople, using the sushi or donuts conveyor? Is the problem the speed
> adjustment of the conveyor? Or too many plates or donuts are placed on
> the conveyor? If so, why the rate or speed of each factors can not be
> adjusted? I even wonder if you could explain it using the door to door
> package delivery service since you are talking about delivering packets.
>
> By the way, thank you very much for your effort to make the explanation
> of bufferbloat to laypeople!
>
> john
>
>
>
>
> --------- Original Message ----------
> Subject: Re: [Bloat] Terminology for Laypeople
> From: Dave Collier-Brown <davecb.42 at gmail.com>
> To: bloat at lists.bufferbloat.net
> Cc:
> Date: Wed, 12 May 2021 17:51:16 -0400
>
> "lag" is often understood by non-technical folks, as in "the lag between
> the time you step on the gas and the time the car actually speeds up".
> Some folks who've been exposed to video enough will know about "lag and
> jitter" (;-))
>
> --dave
> On 2021-05-12 11:50 a.m., Ingemar Johansson S via Bloat wrote:
>> Hi
>
> Yes. "Idle latency" and "Working latency" make sense.
>
> Note however that if you think of idle latency as sparse ping, then
> these sparse ping can give unreasonably high values over cellular access
> (4G/5G). The reason is here mainly DRX which is a battery saving
> function in mobile devices. More frequent pings like every 20ms over the
> course of 100ms or so can give more correct values.
>
> /Ingemar
>
>
> Message: 1
> Date: Tue, 11 May 2021 21:26:21 +0000
> From: Greg White <g.white at CableLabs.com>
> To: Jonathan Foulkes <jf at jonathanfoulkes.com> , "Livingood, Jason"
> <Jason_Livingood at comcast.com>
> Cc: bloat <bloat at lists.bufferbloat.net>
> Subject: Re: [Bloat] Terminology for Laypeople
> Message-ID: <0A5DF790-7A71-4B84-A20B-559A5E0CE65F at cablelabs.com>
> Content-Type: text/plain; charset="utf-8"
>
> I recently heard Stuart Cheshire (sort of tongue-in-cheek) refer to "
> idle
> latency" as "the latency that users experience when they are not using
> their
> internet connection" (or something along those lines).
>
> I think terminology that reinforces that the baseline (unloaded) latency
> is not
> always what users experience, and that latency under load is not
> referring to
> some unusual corner-case situation, is good. So, I like "idle latency"
> and
> "working latency".
>
> -Greg
>
>
>
>
>> _______________________________________________
> Bloat mailing list
> Bloat at lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/bloat
> --
> David Collier-Brown, | Always do right. This will gratify
> System Programmer and Author | some people and astonish the rest
> dave.collier-brown at indexexchange.com | -- Mark Twain
> -------------------------------text/plain-------------------------------
>
> _______________________________________________
> Bloat mailing list
> Bloat at lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/bloat
>
> _______________________________________________
> Bloat mailing list
> Bloat at lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/bloat
More information about the Bloat
mailing list