dsp

Disabling tso alone would not be enough. You also need to disable gso if you go that route.

Yes.

https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.gi...

CDNs, at least, are announcing /48s for traffic engineering. Some even depend on the specific for routing to work if they don’t have a backbone.

Buy credit-default swaps on said debt. The swaps can even be found bundled conveniently in ETFs. Not recommended; good luck.

The numbers are right. If you want to compare to your own data you need to filter for users from the big four US mobile providers like mentioned in the post.

Are you aware of the client location (%lo) support introduced in 1.04? Since it works at a per-record level---instead of per-zone---I find it more useful than the typical split view support.

http://cr.yp.to/djbdns/tinydns-data.html

"company statistics suggest they route roughly five percent of global web requests"

What is CloudFlare's request rate, and how did they arrive at the five percent estimate?

DNS compression is actually described in section 4.1.4 of IETF RFC 1035:

  In order to reduce the size of messages, the domain system utilizes a
  compression scheme which eliminates the repetition of domain names in a
  message.  In this scheme, an entire domain name or a list of labels at
  the end of a domain name is replaced with a pointer to a prior occurance
  of the same name.

Advertising http/1.1 via npn enables tls false start.

http://www.imperialviolet.org/2012/04/11/falsestart.html

I can't find any public reports topping ~100 Gbps. For example, here's a recent article that interviewed an Arbor employee and mentions a ~100 Gbps plateau:

http://www.techweekeurope.co.uk/news/ddos-attacks-power2012-...

Do you have a source for the 1 Tbps attack? I'd like to read about it, but my search came up empty-handed.

His assertions are not confidence inspiring:

http://paul-m-jones.com/?p=413#comment-410123