The scale of streaming video on the Internet.

Fri Dec 3 16:39:32 UTC 2010

On Fri, Dec 3, 2010 at 11:18 AM, Leo Bicknell <bicknell at ufp.org> wrote:
> In a message written on Fri, Dec 03, 2010 at 11:08:21AM -0500, Christopher Morrow wrote:
>> the above is essentially what Akamai (and likely other CDN products)
>> built/build... from what I understand (purely from the threads here)
>> Akamai lost out on the traffic-sales for NetFlix to L3's CDN. Comcast
>> (for this example) lost the localized in-network caching when that
>> happened.
>
> Playing devils advocate here....
>
> I think the issue here is that the Akamai model saves the end user
> providers like Comcast a boatload of money.  By putting a cluster
> in Fargo to serve those local users Comcast doesn't have to build
> a network to say, Chicago Equinix to get the traffic from peers.

right.

> However, the convential wisdom is that the Akamai's of the world
> pay Comcast for this privledge; Comcast charges them for space,
> power, and port fees in Fargo.
>
> The irony here is that Comcast's insistance to charge Akamai customer
> rates for these ports in Fargo make Akamai's price to Netflix too
> high, and drove them to Level 3 who wants to drop off the traffic
> in places like Equinix Chicago.  Now they get to build backbone to
> those locations to support it.  In many ways I feel they are reaping
> what they sowed.

right.

> I think the OP was actually thinking that /Comcast/ should run the
> caching boxes in each local market, exporting the 50-100 /32 routes

sure... which was what I was addressing. If comcast runs these boxes,
how does flix aim their customer 'through' them? how does flix assure
their SLA with their customer is being met? how do they then avoid
(and assure the traffic is properly handled) these boxes when problems
arise?

I get that the network operator (comcast here) has the best idea of
their internal painpoints and costs, I just don't see that them
running a set of boxes is going to actually happen/help. Also, do they
charge the content owners (or their customers?) for data that passes
through these boxes? how do they do cost-recovery operations for this
new infra that they must maintain?

> to "content peers" at Equinix's and the like, but NOT the end user
> blocks.  This becomes more symbiotic though as the content providers
> then need to know how to direct the end users to the Comcast caching
> boxes, so it's not so simple.

right, that was the point(s) I was trying to make... sadly I didn't
make them I guess.

-chris

> --
>       Leo Bicknell - bicknell at ufp.org - CCIE 3440
>        PGP keys at http://www.ufp.org/~bicknell/
>