On Sat, 11 Nov 2006, David Barrett wrote:
Just to make sure I understand the implications of this, are you saying that
bandwidth *improvements* have been increasing with the square of latency
*improvements* since 1980? (I assume this must be what you mean, as
bandwidth has gotten faster while latency has gone down.)
yup. sorry if i was unclear.
Also, do you mean that this standard rule applies to all data transfer
mediums (internet, LAN, wireless, CPU bus, etc) about equally? A sort of
Moore's law for the relationship between latency and bandwidth improvements?
yes. he looked at cpu, memory, disk, and network. for simplicity, he just
looked at ethernet, but i suspect the same conclusion applies to internet
backbone providers, wireless, and last mile connectivity.
specifically, he concludes: "In the time that bandwidth doubles, latency
improves only by factors of 1.2 to 1.4."
What would you say are the consequences of such a trend? With TCP on my
...
But in a broader sense, what does this mean for the future? Greater use of
decentralized caching over central serving? Or is this observation true but
it's only a partial solution, but we probably will see more caching.
coderman makes a great point about implicit feedback, which i'm also a big fan
of. we might begin to see more of that driving things like prefetching - for
example, browser accelerators prefetch the links on each page you visit.
i'll be the first to admit that i don't know what the trend means, or what to
do about it. i just think it's important, and probably underappreciated.
-Ryan
--
http://snarfed.org/
_______________________________________________
p2p-hackers mailing list
[email protected]
http://lists.zooko.com/mailman/listinfo/p2p-hackers
