[Bloat] Overview modifications

[Jim Gettys]

On 02/06/2011 03:20 PM, Eric Raymond wrote:
> Jim Gettys<jg at freedesktop.org>:
>>> Change in progress -- append to the "Hating" paragraph the following
>>> sentence: "Lossy networks such as wireless actually show less chaotic
>>> behavior under load than clean ones."  Is this correct and adequate?
>>
>> It's not chaotic behaviour.  In fact, it is much more worrying: it
>> is periodic (oscillatory) behaviour.  Chaos is good, in this case.
>
> Dave also says my take is wrong and is promising to suggest a correction.
> I have enough other stuff to do that I'll wait on that.
>
>> My nightmare, is that as traffic shifts over more and more to
>> saturated links as XP retires, we end up with self synchronising
>> behaviour on a local, regional or global scale, and havoc ensues,
>> and parts/all of the Internet stop working. Whether these fears are
>> justified, I do not know.
>>
>> Think: we may be a column of soldiers in cadence approaching a bridge...
>
> New graphs at the end of "From Highway to Network":
>
>      We also have some worries about the future.  For various reasons
>      (including the gradual retirement of Windows XP) more and more
>      Internet traffic is now running over saturated links.  In this new
>      environment, we think there is a possibility that bufferbloat cascades
>      and defects in management strategies might produce self-synchronising
>      behaviour in network traffic - packet floods and network resonance on
>      a local, regional or global scale that could be a greater threat to
>      the Internet than the congestion-driven near-collapse of the NSF
>      backbone in 1986.

It's not just bufferbloat: a number of network technologies are bunching 
up packets and injecting them into the Internet with periodic bursts. 
Unfortunately, I don't have good references to this; I gather this is 
true of both wireless and wired technologies.

>
>      This is a classic "black swan" situation in Nassim Taleb's sense; in
>      today's Internet-dependent economy there is a potential for nearly
>      inacalculable havoc in the worst case, but we don't even know in
>      principle how to estimate the overall risk.  Bufferbloat mitigation
>      might keep us out of some very serious trouble, and is worth pursuing
>      on those grounds alone.

It's actually a general fear of any periodic behaviour; I'm just spooked 
to see it in such long period TCP traffic.

Van warned me about time based congestion phenomena in general.