Re: Internet diameter?

[Ignacio de castro]

It is indeed hard to say how useful is to know hop counts when a large
fraction of IXP member are remote and plenty of content is cached, but that
question was bugging me too and I have been looking into it. From what we
could see, pretty stable around 5 hops.

https://arxiv.org/abs/1810.10963

Disclaimer this is  an ongoing work. Feedback welcome!

On Thu, Nov 22, 2018 at 7:33 PM Keith Medcalf  wrote:

> >> I'd argue that's just content (though admittedly a lot of it).
>
> "just static content" would be more accurate ...
>
> >I would further argue that you can't cache active Web content, like
> >bank account statements, utility billing, help desk request/responses,
> >equipment status, and other things that change constantly.
>
> There were many attempts at this by Johhny-cum-lately ISPs back in the
> 90's -- particularly Telco and Cableco's -- with their "transparent
> poxies".  Eventually they discovered that it was more cost efficient to
> actually provide the customer with what the customer had purchased.
>
> ---
> The fact that there's a Highway to Hell but only a Stairway to Heaven says
> a lot about anticipated traffic volume.
>
>
> >-Original Message-
> >From: NANOG [mailto:nanog-boun...@nanog.org] On Behalf Of Stephen
> >Satchell
> >Sent: Wednesday, 21 November, 2018 20:45
> >To: nanog@nanog.org
> >Subject: Re: Internet diameter?
> >
> >On 11/21/2018 07:32 PM, Ross Tajvar wrote:
>
>
>
>

Re: Internet diameter?

[Lars Prehn]

Hi,


Does anybody have more or less recent data on the average, median and maximum 
diameter (ip hop count) of the Internet?


First, to give some hints regarding the initial question: A year ago I 
did some analysis based on Caida's routed /24 topology data set 
(https://www.caida.org/data/active/ipv4_routed_24_topology_dataset.xml) 
for data at the beginning of Jan. 2015. Its not using all available data 
but rather only traceroutes that reached the destination. The attached 
figure shows violin plots for each day - vertically, they show the 
distribution of Hopcounts (looks a little weird due to Hopcounts only 
beeing Integers).


However, please keep in mind:

i.) the data set is collected from only few physical locations but has 
traceroutes towards every routed /24 prefix.

ii.) only a subset of the entire data set is shown.
iii.) its from 2015.
iv.) there is a good chance that it is not representative for the 
"entire" Internet.




Secondly, regarding the ongoing discussion:

+1 for Tim's answer. IMHO, neither AS paths nor IP paths, in general, 
are reliable proxies for e.g. latency or physical distance. In addition, 
keep in mind that we are only able to observe a certain part of the 
Internet and thus it's hard to make claims about the "entire" Internet.


best regards,
Lars

Am 22.11.18 um 10:55 schrieb t...@pelican.org:


On Thursday, 22 November, 2018 05:30, "William Herrin" 
 said:


> Good question! It matters because a little over two decades ago we had
> some angst as equipment configured to emit a TTL of 32 stopped being
> able to reach everybody. Today we have a lot of equipment configured
> to emit a TTL of 64. It's the default in Linux, for example. Are we
> getting close to the limit where that will cause problems? How close?

If it's hop-count that's interesting, I think that raises a question 
on the potential for a sudden large change in the answer, potentially 
with unforeseen consequences if we do have a lot of devices with TTL=64.


Imagine a "tier-1" carrying some non-trivial fraction of Internet 
traffic who is label-switching global table, with no TTL-propagation 
into MPLS, and so looks like a single layer-3 hop today.  In response 
to traceroute-whingeing, they turn on TTL-propagation, and suddenly 
look like 10 layer-3 hops.


Having been in the show/hide MPLS hops internal debate at more than 
one employer, I'd expect flipping the switch to "show" to generate a 
certain support load from people complaining that they are now "more 
hops" away from something they care about (although RTT, packet-loss, 
throughput remain exactly the same).  I wouldn't have expected to 
break connectivity for a whole class of devices.


Regards,

Tim.

Re: Internet diameter?

[Bajpai, Vaibhav]

Hello,

> Does anybody have more or less recent data on the average, median and
> maximum diameter (ip hop count) of the Internet? My google fu is
> failing me: I've only found stuff from the ‘90s.

In the past 2 years of running `traceroute` towards YouTube from 
home networks, the maximum IP path length we have seen is around 22 IP hops. 

details, see:
https://vaibhavbajpai.com/documents/papers/proceedings/youtube-traceroutes-commag-2018.pdf

> Thanks,
> Bill Herrin

PS: This (path lengths) is only towards YouTube destinations.

-- Vaibhav

--
Vaibhav Bajpai
www.vaibhavbajpai.com

Postdoctoral Fellow
Technische Universität München
--

Re: Internet diameter?

[Bradley Huffaker]

Hi William,

We don’t have the number sitting around, but you can get a pretty good feel by 
clicking
through a few of the ark monitors 
(http://www.caida.org/projects/ark/locations). Click on “data”
to the right of each monitor.

Bradley 

On Nov 22, 2018, at 7:55 AM, William Herrin  wrote:
> 
> 
> Hi folks,
> 
> Does anybody have more or less recent data on the average, median and
> maximum diameter (ip hop count) of the Internet? My google fu is
> failing me: I've only found stuff from the '90s.
> 
> Thanks,
> Bill Herrin
> 
> -- 
> William Herrin  her...@dirtside.com  b...@herrin.us
> Dirtside Systems . Web: 
> 

Re: Internet diameter?

[Casey Russell]

It's not exactly a measurement of "user to content" but CAIDA has swarms of
Raspberry Pi nodes all over the world, that constantly measure... well, a
lot of things, but they continually also monitor traceroute paths to each
other.  If you're looking for a "average length from any one node to any
other node on the Internet" you'd likely find some good data points here.

https://www.caida.org/projects/ark/statistics/

Sincerely,
Casey Russell
Network Engineer
[image: KanREN] 
[image: phone]785-856-9809
2029 Becker Drive, Suite 282
Lawrence, Kansas 66047
[image: linkedin]

[image:
twitter]  [image: twitter]
 need support? 



On Sun, Nov 25, 2018 at 11:10 AM Christopher Morrow 
wrote:

>
>
> On Sat, Nov 24, 2018 at 8:48 PM Hal Murray <
> hgm+na...@ip-64-139-1-69.sjc.megapath.net> wrote:
>
>>
>> Keith Medcalf  said:
>> > "just static content" would be more accurate ...
>>
>>   and using http rather than https
>>
>> > There were many attempts at this by Johhny-cum-lately ISPs back in the
>> 90's
>> > -- particularly Telco and Cableco's -- with their "transparent poxies".
>> > Eventually they discovered that it was more cost efficient to actually
>> > provide the customer with what the customer had purchased.
>>
>> One of the complications in this area is an extra layer of logging which
>> could
>> turn into privacy invasion.
>>
>> I'm pretty sure it was Comcast, but a quick search didn't find a good
>> reference.  Many years ago, there were a lot of complaints when customers
>>
>
> did you mean the 'sandvine experiment' that happened ~10 yrs back?
> or did you mean the plan verizon had to proxy all http/https traffic from
> consumer (fios/dsl) links through their gear so they could replace ad
> content and such?
> or did you mean the various (barefruit/nominim/paxfire) dns fake-answer
> companies that dropped your customer on their "search platform" for
> monetization?
>
> fairly much all of those are a wreck for consumer privacy :(
>
>
>> discovered that their transparent proxy web site traffic was getting
>> logged.
>> Comcast said they weren't using it for anything beyond normal operations
>> work,
>> but nobody believed them.  Shortly after that, they gave up on proxying.
>>
>> I'm sure the general reputation of modern Telcos and Cablecos for privacy
>> invasion didn't help.
>>
>>
> it's a rough business to be in, they say... but invading privacy of their
> users makes things seem a heck of a lot worse.
>
>
>>
>> --
>> These are my opinions.  I hate spam.
>>
>>
>>
>>

Re: Internet diameter?

[Christopher Morrow]

On Sat, Nov 24, 2018 at 8:48 PM Hal Murray <
hgm+na...@ip-64-139-1-69.sjc.megapath.net> wrote:

>
> Keith Medcalf  said:
> > "just static content" would be more accurate ...
>
>   and using http rather than https
>
> > There were many attempts at this by Johhny-cum-lately ISPs back in the
> 90's
> > -- particularly Telco and Cableco's -- with their "transparent poxies".
> > Eventually they discovered that it was more cost efficient to actually
> > provide the customer with what the customer had purchased.
>
> One of the complications in this area is an extra layer of logging which
> could
> turn into privacy invasion.
>
> I'm pretty sure it was Comcast, but a quick search didn't find a good
> reference.  Many years ago, there were a lot of complaints when customers
>

did you mean the 'sandvine experiment' that happened ~10 yrs back?
or did you mean the plan verizon had to proxy all http/https traffic from
consumer (fios/dsl) links through their gear so they could replace ad
content and such?
or did you mean the various (barefruit/nominim/paxfire) dns fake-answer
companies that dropped your customer on their "search platform" for
monetization?

fairly much all of those are a wreck for consumer privacy :(


> discovered that their transparent proxy web site traffic was getting
> logged.
> Comcast said they weren't using it for anything beyond normal operations
> work,
> but nobody believed them.  Shortly after that, they gave up on proxying.
>
> I'm sure the general reputation of modern Telcos and Cablecos for privacy
> invasion didn't help.
>
>
it's a rough business to be in, they say... but invading privacy of their
users makes things seem a heck of a lot worse.


>
> --
> These are my opinions.  I hate spam.
>
>
>
>

RE: Internet diameter?

[Hal Murray]

Keith Medcalf  said:
> "just static content" would be more accurate ...

  and using http rather than https

> There were many attempts at this by Johhny-cum-lately ISPs back in the 90's
> -- particularly Telco and Cableco's -- with their "transparent poxies".
> Eventually they discovered that it was more cost efficient to actually
> provide the customer with what the customer had purchased. 

One of the complications in this area is an extra layer of logging which could 
turn into privacy invasion.

I'm pretty sure it was Comcast, but a quick search didn't find a good 
reference.  Many years ago, there were a lot of complaints when customers 
discovered that their transparent proxy web site traffic was getting logged.  
Comcast said they weren't using it for anything beyond normal operations work, 
but nobody believed them.  Shortly after that, they gave up on proxying.

I'm sure the general reputation of modern Telcos and Cablecos for privacy 
invasion didn't help.


-- 
These are my opinions.  I hate spam.

Re: Internet diameter?

[Christopher Morrow]

On Thu, Nov 22, 2018 at 12:30 AM William Herrin  wrote:

> On Wed, Nov 21, 2018 at 7:58 PM Christopher Morrow
>  wrote:
> > now, why does it matter?
>
> Good question! It matters because a little over two decades ago we had
> some angst as equipment configured to emit a TTL of 32 stopped being
> able to reach everybody. Today we have a lot of equipment configured
> to emit a TTL of 64. It's the default in Linux, for example. Are we
> getting close to the limit where that will cause problems? How close?
>
>
ah-ha! :) good, much easier to see the point with the goal in mind :)
So... you COULD spin up some set of traceroute measurements from
ripe-atlas, right? pick 5 probes per city and traceroute to common targets?

I think there are a few things to consider:
  1) not ever network exposes their hops all the time (mpls where the paths
no-decrement-ttl, for instance).
  2) the common user traffic pattern is likely not to fall into the 'too
many hops' problem because of cdn and/or other trickery to shorten the path
between end-user && content (to increase effective bw to the customer AND
lower latency,etc)
  3) I would think it rare for consumers (the largest pool of internet
users by role) to need to send packets to the far side of the internet
  Or put another way: "How would you pick what's important to measure
to?"

RE: Internet diameter?

[Keith Medcalf]

To get back to the original question regarding the "diameter" of the Internet, 
it would appear to me that we are easily looking at about 30 to 40 hops just 
within North America -- and easily double that to reach the rest of the 
Internet outside of North America.  Of course, the "Top 5 Channels" are 
probably only a few hops away due to CDNs, but this is for the most part 
irrelevant (unless one only wants to watch the Top 5 channels) ...

---
The fact that there's a Highway to Hell but only a Stairway to Heaven says a 
lot about anticipated traffic volume.

Re: Internet diameter?

[Mike Hammett]

" Eventually they discovered that it was more cost efficient to actually 
provide the customer with what the customer had purchased." 


Sometimes yes, sometimes no. Big content has been making this more complicated. 




- 
Mike Hammett 
Intelligent Computing Solutions 
http://www.ics-il.com 

Midwest-IX 
http://www.midwest-ix.com 

- Original Message -

From: "Keith Medcalf"  
To: nanog@nanog.org 
Sent: Thursday, November 22, 2018 1:31:24 PM 
Subject: RE: Internet diameter? 

>> I'd argue that's just content (though admittedly a lot of it). 

"just static content" would be more accurate ... 

>I would further argue that you can't cache active Web content, like 
>bank account statements, utility billing, help desk request/responses, 
>equipment status, and other things that change constantly. 

There were many attempts at this by Johhny-cum-lately ISPs back in the 90's -- 
particularly Telco and Cableco's -- with their "transparent poxies". Eventually 
they discovered that it was more cost efficient to actually provide the 
customer with what the customer had purchased. 

--- 
The fact that there's a Highway to Hell but only a Stairway to Heaven says a 
lot about anticipated traffic volume. 


>-Original Message- 
>From: NANOG [mailto:nanog-boun...@nanog.org] On Behalf Of Stephen 
>Satchell 
>Sent: Wednesday, 21 November, 2018 20:45 
>To: nanog@nanog.org 
>Subject: Re: Internet diameter? 
> 
>On 11/21/2018 07:32 PM, Ross Tajvar wrote: 

RE: Internet diameter?

[Keith Medcalf]

>> I'd argue that's just content (though admittedly a lot of it).

"just static content" would be more accurate ...

>I would further argue that you can't cache active Web content, like
>bank account statements, utility billing, help desk request/responses,
>equipment status, and other things that change constantly.

There were many attempts at this by Johhny-cum-lately ISPs back in the 90's -- 
particularly Telco and Cableco's -- with their "transparent poxies".  
Eventually they discovered that it was more cost efficient to actually provide 
the customer with what the customer had purchased.

---
The fact that there's a Highway to Hell but only a Stairway to Heaven says a 
lot about anticipated traffic volume.


>-Original Message-
>From: NANOG [mailto:nanog-boun...@nanog.org] On Behalf Of Stephen
>Satchell
>Sent: Wednesday, 21 November, 2018 20:45
>To: nanog@nanog.org
>Subject: Re: Internet diameter?
>
>On 11/21/2018 07:32 PM, Ross Tajvar wrote:

Re: Internet diameter?

[t...@pelican.org]

On Thursday, 22 November, 2018 05:30, "William Herrin"  said:
 

> Good question! It matters because a little over two decades ago we had
> some angst as equipment configured to emit a TTL of 32 stopped being
> able to reach everybody. Today we have a lot of equipment configured
> to emit a TTL of 64. It's the default in Linux, for example. Are we
> getting close to the limit where that will cause problems? How close?


If it's hop-count that's interesting, I think that raises a question on the 
potential for a sudden large change in the answer, potentially with unforeseen 
consequences if we do have a lot of devices with TTL=64.
 
Imagine a "tier-1" carrying some non-trivial fraction of Internet traffic who 
is label-switching global table, with no TTL-propagation into MPLS, and so 
looks like a single layer-3 hop today.  In response to traceroute-whingeing, 
they turn on TTL-propagation, and suddenly look like 10 layer-3 hops.
 
Having been in the show/hide MPLS hops internal debate at more than one 
employer, I'd expect flipping the switch to "show" to generate a certain 
support load from people complaining that they are now "more hops" away from 
something they care about (although RTT, packet-loss, throughput remain exactly 
the same).  I wouldn't have expected to break connectivity for a whole class of 
devices. 
 
Regards,
Tim.
 

Re: Internet diameter?

[Oliver O'Boyle]

^
This

On Thu, Nov 22, 2018, 00:32 William Herrin  On Wed, Nov 21, 2018 at 7:58 PM Christopher Morrow
>  wrote:
> > now, why does it matter?
>
> Good question! It matters because a little over two decades ago we had
> some angst as equipment configured to emit a TTL of 32 stopped being
> able to reach everybody. Today we have a lot of equipment configured
> to emit a TTL of 64. It's the default in Linux, for example. Are we
> getting close to the limit where that will cause problems? How close?
>
> Regards,
> Bill Herrin
>
>
>
> --
> William Herrin  her...@dirtside.com  b...@herrin.us
> Dirtside Systems . Web: 
>

Re: Internet diameter?

[William Herrin]

On Wed, Nov 21, 2018 at 7:58 PM Christopher Morrow
 wrote:
> now, why does it matter?

Good question! It matters because a little over two decades ago we had
some angst as equipment configured to emit a TTL of 32 stopped being
able to reach everybody. Today we have a lot of equipment configured
to emit a TTL of 64. It's the default in Linux, for example. Are we
getting close to the limit where that will cause problems? How close?

Regards,
Bill Herrin



-- 
William Herrin  her...@dirtside.com  b...@herrin.us
Dirtside Systems . Web: 

Re: Internet diameter?

[Ross Tajvar]

> I’m not sure on what use this data, if collected, would be. Latency is
the most important.
It's not operationally useful in any way that I can think of, but it is
interesting (at least to me). It's possible that Bill has something in
mind, though.

> [...] which is more meaningful a metric, AS-path or hop count?
Good point. Before we can decide which is more useful, we have to decide
what they would be useful for.
But, I think it's not really feasible to analyze hop count, because you
would have to collect that data with a huge number of traceroutes.
Average/median AS-path length can be estimated by static analysis of BGP
tables from various routers.

> Many networks have a large number of routers but the packets don’t stay
in them very long.
It wouldn't be a very good router if the packets hung around for a long
time before leaving :)

On Wed, Nov 21, 2018 at 11:26 PM Ben Cannon  wrote:

> This begs the question, which is more meaningful a metric, AS-path or hop
> count?  Many networks have a large number of routers but the packets don’t
> stay in them very long.
>
> -Ben.
>
>
> On Nov 21, 2018, at 8:10 PM, Bryce Wilson 
> wrote:
>
> I don’t have any hard statistics but I notice that on a majority of ASs on
> bgp.he.net, the average AS path length is between 4 and 5. As for the
> average number of hops, it clearly depends on what type of traffic and many
> ASNs have more than one router. Going on my own experience I would say
> between 8 and 10 hops would be the average of non-cached content. If you
> included cached content such as cdns and caches then the actual average
> might be closer to 5 to 7. This is only an estimate from my own network and
> those of my clients so the actual value may be completely different.
>
> As with what others have said, I’m not sure on what use this data, if
> collected, would be. Latency is the most important.
>
>
> Thanks ~ Bryce Wilson, AS202313, EVIX, AS137933
>
>
>

Re: Internet diameter?

[Ben Cannon]

This begs the question, which is more meaningful a metric, AS-path or hop 
count?  Many networks have a large number of routers but the packets don’t stay 
in them very long.

-Ben.


> On Nov 21, 2018, at 8:10 PM, Bryce Wilson  wrote:
> 
> I don’t have any hard statistics but I notice that on a majority of ASs on 
> bgp.he.net , the average AS path length is between 4 and 
> 5. As for the average number of hops, it clearly depends on what type of 
> traffic and many ASNs have more than one router. Going on my own experience I 
> would say between 8 and 10 hops would be the average of non-cached content. 
> If you included cached content such as cdns and caches then the actual 
> average might be closer to 5 to 7. This is only an estimate from my own 
> network and those of my clients so the actual value may be completely 
> different.
> 
> As with what others have said, I’m not sure on what use this data, if 
> collected, would be. Latency is the most important.
> 
> 
> Thanks ~ Bryce Wilson, AS202313, EVIX, AS137933
> 

Re: Internet diameter?

[Andy Ringsmuth]

> On Nov 21, 2018, at 9:32 PM, Ross Tajvar  wrote:
> 
> I'd argue that's just content (though admittedly a lot of it). You can't 
> cache, e.g., a SIP trunk, and offices which need to connect to each other 
> can't cache one another in a CDN either.
> 
> On Wed, Nov 21, 2018, 10:29 PM Aaron1  Considering 40% of the “internet” is sitting in my backyard in cdn caching, 
> I’d say the perceived diameter for that content is 3 or 4 hops.  ;)
> 
> ...but something tells me that isn’t they response you were seeking... 
> 
> ... but seriously it is interesting that with local caching that much of the 
> Internet is now sitting local in the subscriber’s ISP.
> 
> Aaron
> 
>> On Nov 21, 2018, at 4:55 PM, William Herrin  wrote:
>> 
>> Hi folks,
>> 
>> Does anybody have more or less recent data on the average, median and
>> maximum diameter (ip hop count) of the Internet? My google fu is
>> failing me: I've only found stuff from the '90s.
>> 
>> Thanks,
>> Bill Herrin
>> 

Obligatory XKCD:

https://xkcd.com/908/


-Andy

Re: Internet diameter?

[Bryce Wilson]

I don’t have any hard statistics but I notice that on a majority of ASs on 
bgp.he.net , the average AS path length is between 4 and 5. 
As for the average number of hops, it clearly depends on what type of traffic 
and many ASNs have more than one router. Going on my own experience I would say 
between 8 and 10 hops would be the average of non-cached content. If you 
included cached content such as cdns and caches then the actual average might 
be closer to 5 to 7. This is only an estimate from my own network and those of 
my clients so the actual value may be completely different.

As with what others have said, I’m not sure on what use this data, if 
collected, would be. Latency is the most important.


Thanks ~ Bryce Wilson, AS202313, EVIX, AS137933

Re: Internet diameter?

[Christopher Morrow]

42

now, why does it matter?

On Wed, Nov 21, 2018 at 10:49 PM Aaron1  wrote:

> Yes I agree Ross/Stephen.  I didn’t mean to overstate the CDN fact.
>
> I wonder what the answer is to Bill’s question is. “average, median and
>
> maximum diameter (ip hop count) of the Internet? “
>
>
> Aaron
>
> On Nov 21, 2018, at 9:44 PM, Stephen Satchell  wrote:
>
> On 11/21/2018 07:32 PM, Ross Tajvar wrote:
>
> I'd argue that's just content (though admittedly a lot of it). You can't
>
> cache, e.g., a SIP trunk, and offices which need to connect to each other
>
> can't cache one another in a CDN either.
>
>
>
> I would further argue that you can't cache active Web content, like bank
> account statements, utility billing, help desk request/responses,
> equipment status, and other things that change constantly.
>
>

Re: Internet diameter?

[Aaron1]

Yes I agree Ross/Stephen.  I didn’t mean to overstate the CDN fact.

I wonder what the answer is to Bill’s question is. “average, median and
> maximum diameter (ip hop count) of the Internet? “

Aaron

> On Nov 21, 2018, at 9:44 PM, Stephen Satchell  wrote:
> 
>> On 11/21/2018 07:32 PM, Ross Tajvar wrote:
>> I'd argue that's just content (though admittedly a lot of it). You can't
>> cache, e.g., a SIP trunk, and offices which need to connect to each other
>> can't cache one another in a CDN either.
> 
> 
> I would further argue that you can't cache active Web content, like bank
> account statements, utility billing, help desk request/responses,
> equipment status, and other things that change constantly.

Re: Internet diameter?

[Stephen Satchell]

On 11/21/2018 07:32 PM, Ross Tajvar wrote:
> I'd argue that's just content (though admittedly a lot of it). You can't
> cache, e.g., a SIP trunk, and offices which need to connect to each other
> can't cache one another in a CDN either.


I would further argue that you can't cache active Web content, like bank
account statements, utility billing, help desk request/responses,
equipment status, and other things that change constantly.

Re: Internet diameter?

[Ross Tajvar]

I'd argue that's just content (though admittedly a lot of it). You can't
cache, e.g., a SIP trunk, and offices which need to connect to each other
can't cache one another in a CDN either.

On Wed, Nov 21, 2018, 10:29 PM Aaron1  Considering 40% of the “internet” is sitting in my backyard in cdn
> caching, I’d say the perceived diameter for that content is 3 or 4
> hops.  ;)
>
> ...but something tells me that isn’t they response you were seeking...
>
> ... but seriously it is interesting that with local caching that much of
> the Internet is now sitting local in the subscriber’s ISP.
>
> Aaron
>
> > On Nov 21, 2018, at 4:55 PM, William Herrin  wrote:
> >
> > Hi folks,
> >
> > Does anybody have more or less recent data on the average, median and
> > maximum diameter (ip hop count) of the Internet? My google fu is
> > failing me: I've only found stuff from the '90s.
> >
> > Thanks,
> > Bill Herrin
> >
> > --
> > William Herrin  her...@dirtside.com  b...@herrin.us
> > Dirtside Systems . Web: 
>
>

Re: Internet diameter?

[Aaron1]

Considering 40% of the “internet” is sitting in my backyard in cdn caching, I’d 
say the perceived diameter for that content is 3 or 4 hops.  ;)

...but something tells me that isn’t they response you were seeking... 

... but seriously it is interesting that with local caching that much of the 
Internet is now sitting local in the subscriber’s ISP.

Aaron

> On Nov 21, 2018, at 4:55 PM, William Herrin  wrote:
> 
> Hi folks,
> 
> Does anybody have more or less recent data on the average, median and
> maximum diameter (ip hop count) of the Internet? My google fu is
> failing me: I've only found stuff from the '90s.
> 
> Thanks,
> Bill Herrin
> 
> -- 
> William Herrin  her...@dirtside.com  b...@herrin.us
> Dirtside Systems . Web: 

Internet diameter?

[William Herrin]

Hi folks,

Does anybody have more or less recent data on the average, median and
maximum diameter (ip hop count) of the Internet? My google fu is
failing me: I've only found stuff from the '90s.

Thanks,
Bill Herrin

-- 
William Herrin  her...@dirtside.com  b...@herrin.us
Dirtside Systems . Web: