Slashdot Mirror
NETI@Home to Examine Net's Strengths
UnresolvedExternal writes "Wired is reporting about Georgia Tech researchers who want thousands of computer users to install their program to help them monitor traffic patterns on the Internet. They plan to use the data to strengthen the Net and unblock bottlenecks."
1. pr0n
2. uninformed babbling by consipracy freaks
3. iditiotic blogs noobody cares about
"Indicate the presence of a large DDoSing group known as 'Slashdot'. We will be looking further into this matter"
That CSS file that blocks ads
Gee, sounds like gator got into academics.
meh
Well taking spam is put at between 30-50% of email usage how about getting rid of that for a start? Of course easier said than done
Rus
Cheap UK and US VPS
and the financial resources to unblock those bottlenecks are raised with the money they make from selling those 'traffic patterns' to anyone who bids...
Arggh Its every geeks worst scheduling nightmare! Do I want the aliens or the faster pr0n. Dang what a scheduling conflict.
Researchers at Georgia Tech are concluding their two-year distributed analysis of network usage, concluding that most bottlenecks were, in fact, caused by NETI@Home traffic.
Internet traffic composition:
49.7% 0
49.7% 1
00.6% Other
They want to figure out how to make the Internet faster and more reliable, but to do that they need to gather data from tens of thousands of personal computers around the world.
So, they want to make it faster by having people send out and receive more data.
just looked at their THIS AIN'T SPYWARE, RILLY! page. Well, what else is it but that? Of course it is, just for their claim to be a benevolent purpose, it's "whitehat" spying to be totally fair about it. But, we don't know if any "blackhats" will get the information over to the university, or--well, if any foreign states might have an interest in it and some of the juicer info gets transferred to some other places that might have a different idea on what to do with the information. Could be, anyone who's seen the demographics at most unis would have to agree, and tech has a lot of students that might have loyalties other than what is publically presented here. Just a note, but it's valid.
The high security setting is the one I predicteth gets used the most by people who run it, for obvious reasons.
hmm, probable bottlenecks. Whenever the latest mega worm hits you'll see which routers choke easiest. Massive constant traffic from owned and zombiefied end users home machines, that should be fairly random and even. Pockets/areas where file sharing is still big. And places with a derth of fat pipes obviously.
Interesting project, but I will have to think on it some if I want to run it. Also, maybe I am not seeing it, but it doesn't seem to have any info on how much of your machine it uses, I see the operating system requirements,installation, etc, but not the resources required. Anyone see that? My apologies if I missed it.
One of the defining characteristics of the Net seems to have been its ability to defy planning and design.
Even simply "increasing capacity" without addressing specific bottlenecks is often a waste of time. Look at the heavy investment in fibre-optics, most of which lies unused as new technology squeezes more and more out of existing cables.
Call me a cynic, but such projects sound more like fun for research grants than useful for real life.
My humble opinion of the Net is that it is a largely a self-steering phenomena that feeds on change and technology cycles. Since you can't predict change, and you can't prevent the technology cycles that cause it, it's meaningless to hope to plan this.
Ceci n'est pas une signature
Different people value things differently.
... you can start a heavily computational algorithm now, and waste your time, or wait a few years for computers to be many times faster, and then do the parts of the calculation that you put off in a fraction of the time. Or wait a little longer ...
For example, a concerted effort to improve the quality of the net infrastructure could lead to more efficient distributed computing platforms, which means that eventually someone would write an improved folding program.
It's akin to an old computer science problem
So, some people do the work now, and others work to improve the systems we use to do work. Seems worthwhile to me.
Personally, I run chessbrain.
Well, since it's looking at the 'Net, it's clearly yet another futile search for evidence of terrestrial intelligence.