Re: [tlug] Is Japan closer to U.S. or ...?

["Stephen J. Turnbull" <turnbull@example.com>]

Curt Sampson writes:

To get the easy stuff out of the way first:

 > Well, financial markets are a weird thing, because they are actually
 > influenced by the things people write about them.

All markets are.  Those of us who are homeowners have had a very big
increase in the number of contacts from real estate agents who want to
know our intent to sell or not.  That's because they want to close by
March 31 to avoid the sales tax increase.  But that turned out to be a
hot air balloon. :-)  (Or :-(, if you care about Japan's future.)

 > But you're correct that attempting market predictions in general is
 > nonsense. The basic issue, as I see it, is that the markets are already
 > predicting various economic realities, and when you're trying to predict
 > the market, you're trying to predict what prediction it's going to make,
 > which strikes me as just silly.

It's not silly, it's a fundamental feature of all equilibrium analysis
under uncertainty.  (Black-Scholes is a pure no-arbitrage condition,
there's no actual interaction in their model, so it doesn't apply to
Black-Scholes.)

Back to measuring "close" on networks:

 > While this is true within computers, when it comes to services delivered
 > over wide-area networks, 97% of the the time the biggest bottleneck
 > is the latency.

OK.

 > Beyond that there's a lot more to almost any application than just TCP;
 > And then we come to UDP

In other words, to judge you really need to know the application....

I think you should have just rested on the original claim that "it's
the latency, stupid". :-)
 
 > On 2014-12-26 01:09 +0900 (Fri), Stephen J. Turnbull wrote:
 > 
 > > The point was that I don't feel qualified to talk about the ins
 > > and outs of TCP/IP performance tuning, but I was very bothered by
 > > the form of the original request (which is closer, for arbitrary
 > > metrics on a delay-prone network in the sphere).
 > 
 > As a network engineer, I found the original request pretty
 > reasonable.

Well, that's because you already had 32:1 odds that you were giving
the right answer.  If he had *specifically* asked for "in terms of
bandwidth", you would have ignored him and said

 > but given that both the U.S. and Singapore links from Japan have
 > gobs of bandwidth,

"it's the latency, stupid". :-)  I don't have the background to do
that.

What I'm interested in is "how to ask good questions."  I do know that
most of the time asking the wrong question will get you a wrong
answer.  Figuring out whether to locate his servers in Singapore or
the U.S. won't solve all his problems, you know. :-)

Steve