Tunnel overhead [On killing IPv6 transition mechanisms]
tedm at ipinc.net
Wed Mar 17 21:27:02 CET 2010
Kurt Jaeger wrote:
>> "...Network latency is without question on that list....additional
>> client-server latency due to IPv6 being used will quickly add
>> up to seconds in terms of overall page load time for a complex web site..."
>> That is factually incorrect. TCP/IP uses sliding windows.
> describes the problem: Websites do not provide one large tcp stream,
> but many small ones, many of them with multiple tcp connection setups
> and teardowns. Those are eating up the latency budget for a snappy
OK, I see, however from a users perspective I actually like this,
because it discourages content providers from sticking in a bunch of
extra advertisements and such that crap up their site.
I still maintain, though, that for 90% of the machines out there, the
browser rendering engine is a far larger contributor to "unsnappy"
websites. Based on our customer feedback most people have older systems
or newer systems that are crapped-up with adware.
The google toolbar alone ads an extra 2-3 seconds for most systems, and
I've had people call in with yahoo, google, aol, avg, bing, and msn
toolbars loaded in. It's a wonder there was any room to display the
page at all.
Years ago I worked for a software developer and what your illustrating
is "developer myopia"
Website developers and software developers always get the very fastest
and latest PCs handed to them by their companies for free - so they
develop these pigs of websites and software then think they are "snappy"
for everyone on the Internet, because they can't see how they work
If they wanna blame IPv6 then let them - you cannot educate people who
have rose-colored glasses on and think everyone on the Internet has a
4Ghz CPU system with 8GB of ram and a $200 video card, on a 10Mbt cable
line to do their surfing.
The users with the fastest systems on the Internet typically buy them
for watching video, and that IS "one large tcp stream", or they buy
them for gaming and that's a whole different issue.
> There's a cute tool which allowes one to test it:
> "A graphical tool that enables Web content providers to rapidly and
> accurately measure client side performance of Web pages."
Cute too, I wonder how many content providers actually read the
advice in the help to put their sites on a diet.
More information about the ipv6-ops