Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Towards an Internet-Scale Operating System

michael posted more than 12 years ago | from the worldwide-reboot dept.

The Internet 305

gschoder writes: "Two Berkeley computer scientists (including David P. Anderson of SETI@home) envision an Internet-scale operating system to harness the processing power, networking efficiency, and storage capacity of everyone's computers. Scientific American has their proposal."

cancel ×

305 comments

Sorry! There are no comments related to the filter you selected.

fp (-1, Offtopic)

real_b0fh (557599) | more than 12 years ago | (#2994840)

hell yeah!

Goddamn it! That's what I get for reading replies! (0, Funny)

YourMissionForToday (556292) | more than 12 years ago | (#2994846)

Just pretend this is FP... This FP reads as follows: Look around you, folks. How many of you have sigs that refer to "karma", "ACs," getting "modded up" and the like? Has Slashdot become your hermetically sealed environment? Is it the filter through which you perceive reality? Has Slashdot become an empty game where you regurgitate earlier posts to get 'karma'?

Some of you might be surprised to learn that this "karma" has no value whatsoever!!! When Slashdot goes under (and don't worry, it will) you won't be able to exchange that "karma" for Denny's coupons, anime DVDs, or anything worth a shit!!!

And don't think there's any spiritual value either! Slashdot "karma" won't help you break the cycle of reincarnation, it won't get you "high", and it won't even win you friends at Magic: The Gathering tournaments!

Fellow Slashdotter, you have been deceived!!! You will not achieve immortality by posting "Imagine a Beowulf cluster of this!" or "Linux is really good for the desktop!" The only way you'll ever be remembered when this decrepit weblog tumbles into nothingness is to post something really FUCKED UP!!! I can't stress this enough!!!

Don't waste your time chasing the "karma" cap! Don't whine about your stories not being published when you know that the news on this site is randomly chosen by monkeys!!! The only way you'll be remembered long after CmdrTaco returns to his old position as shift leader at Pizza Hut is by posting ABSOLUTE FREAKING MADNESS!!! Do it now!!! Do it often!!! And karma be damned!!!

fuck off (-1, Offtopic)

Anonymous Coward | more than 12 years ago | (#2994863)

looser.

Re:fuck off (-1, Offtopic)

Anonymous Coward | more than 12 years ago | (#2994889)

Couldn't you have put the loser in the subject too so I don't have to click on your post.

looser (-1, Offtopic)

Anonymous Coward | more than 12 years ago | (#2994918)

fuck you.

Re:fuck off (-1, Offtopic)

YourMissionForToday (556292) | more than 12 years ago | (#2994922)

than your asshole? Now that goatse is gone, I don't think that's possible.

Rim-ram my jimmity jim jam AC fucktwat.

counting down towards first post (-1, Offtopic)

Anonymous Coward | more than 12 years ago | (#2994847)

....FP!!!!

Re:counting down towards first post (-1)

real_b0fh (557599) | more than 12 years ago | (#2994860)

in your dreams, AC

hehe ther goes more karma...

FIRST POST (-1, Flamebait)

Anonymous Coward | more than 12 years ago | (#2994851)

slashdot is really damn stupid and you're a bunch of freakin morons who should jump off a cliff@!

3rd Post (-1)

DonkeyHote (521235) | more than 12 years ago | (#2994854)

Another Glorious Victory for the Retards!

RWD 2002!

Nothing (-1)

Guns n' Roses Troll (207208) | more than 12 years ago | (#2994865)

I have nothing useful to add here, so I'll just drone on and on and on and on and on and on and on and on

Wow. Imagine a beowolf clus... (-1, Offtopic)

Unknown Poltroon (31628) | more than 12 years ago | (#2994868)

Someone had to say it. ;)

Now go ahead and waste your points modding me down you humorless moron!

Re:Wow. Imagine a beowolf clus... (2)

jonr (1130) | more than 12 years ago | (#2994898)

hehe... finally an article that fits :)
And ist Bjólfur, not Beowulf... *ACK*

Re:Wow. Imagine a beowolf clus... (-1, Offtopic)

sysrequest (325177) | more than 12 years ago | (#2994900)

only that your silly beowulf cluster is most likely going to pale in comparison.

Why not use OpenMOSIX? (0)

Anonymous Coward | more than 12 years ago | (#2994872)

looks good to me.

Hrmmm.... (1)

T3kno (51315) | more than 12 years ago | (#2994874)

Imagine being able to download the actual scene files for a movie like Shrek and being able to render and watch them in real time. I wonder how the movie studios would feel about that?

That's right. (2, Insightful)

forged (206127) | more than 12 years ago | (#2994895)

And you will of course let other people freely benefit from your bandwidth / CPU power / etc., will you ? No, I didn't think so either.

Re:Hrmmm.... (1)

dnoyeb (547705) | more than 12 years ago | (#2994947)

Yea, they are getting a little ambitious. I am donating my time for a worthy cause. Not so someone can marvel at the fact they run MS Word on a cluster of a million computers...

As for white history month? White history was 4 years in highschool. And all thorough geography and math, and science, etc.

Not sure how many schools in America actualy have a single solitary Black History class.

If you think Black history is unnecessary, I would tend to agree. Just show Blacks in their proper light...In American History. Last time I picked up such a history book, it contained NO Blacks and I am talking about books even in predominantly Black highschools.

Re:Hrmmm.... (-1)

real_b0fh (557599) | more than 12 years ago | (#2994964)

black highschools?

wtf?

are you from south africa?

Re:Hrmmm.... (0)

Anonymous Coward | more than 12 years ago | (#2995015)

Perhaps the US would benefit from dumping "American History" as a subject and instead adopt the more general "History" - i.e. learn about the history of the world, significant world events (which would include a subset of the american history!). :}

Re:Hrmmm.... (0, Offtopic)

Squareball (523165) | more than 12 years ago | (#2995054)

Really? You didn't learn about George Washington Carver? MLK jr.? Jesse Jackson? Colon Powell? Weird. I did. How about a WHITE college fund? Oh wait THAT would be racist wouldn't it? ermm.. right.. let's just keep breaking every thing down to the group identity of black and white and male and female.. and let's just ignore the individual.

How about desk-sized? (4, Insightful)

pacc (163090) | more than 12 years ago | (#2994875)

There are still no simple ways to use a pair
of computers on the same desk efficiently, why not start there?

Who gets root access? (2, Funny)

jparp (316662) | more than 12 years ago | (#2994878)

...

Internet-Scale OS'es (-1)

DonkeyHote (521235) | more than 12 years ago | (#2994881)

Just Imagine... A beowulf.... Ah nevermind,
MAC's Sucks, Windows Sucks, BeOS Sucks, Linux is the one true path, you can MOD ME UP NOW!

RWD 2002

Why buy a computer? (1, Interesting)

JohnBE (411964) | more than 12 years ago | (#2994885)

Won't people just use the minimum specification of machine and leach processing power from the rest of the network?

Re:Why buy a computer? (1)

ichimunki (194887) | more than 12 years ago | (#2994934)

If everyone did that, there would be no processing power left on the rest of the network to use, it would be consumed in full locally.

Re:Why buy a computer? (1)

The Smith (305645) | more than 12 years ago | (#2994980)

No, because you pay for what you use and get paid for what you supply. `Leeches' would have to pay for the difference in dollars. Theoretically though, if all processor time was utilizable, the cost per second of processing would be vanishingly small.

Seti At Home (2, Insightful)

JohnHegarty (453016) | more than 12 years ago | (#2994890)

This is basically SetiAtHome on a massive scale. I wounder home many work units this cluster could do an hour ;-)

Scary... (3, Insightful)

Em Emalb (452530) | more than 12 years ago | (#2994896)

"When Mary gets home from work and goes to her PC to check e-mail, the PC isn't just sitting there. It's working for a biotech company, matching gene sequences to a library of protein molecules. Its DSL connection is busy downloading a block of radio telescope data to be analyzed later. Its disk contains, in addition to Mary's own files, encrypted fragments of thousands of other files. Occasionally one of these fragments is read and transmitted; it's part of a movie that someone is watching in Helsinki. Then Mary moves the mouse, and this activity abruptly stops. Now the PC and its network connection are all hers."

Nope. Cause some l33t h4x0r will have own3d her already.

This is scary as hell. I hope it doesn't get implemented. This is far different from Seti...

Worse yet (2)

Pac (9516) | more than 12 years ago | (#2995007)

"I am sorry Mary, but 15% of this file's backup were lost due to last week "You are really an idiot if you click this attachment" Outlook 2010 virus, 20% are unavailable at this moment due to orbital problems with the Earth-Moon Internet backbone and other 5% were in computers seized by the government in the on-going war on spammers. Should I guess the missing 40% from the available 60%?"

The first thing I will do.... (3, Funny)

SamBeckett (96685) | more than 12 years ago | (#2994905)

cat > test.c

int main() {

while(1) fork();

return(0);

}

Two things. (-1, Offtopic)

GoatTroll (556420) | more than 12 years ago | (#2994965)

1) Why hasn't this post been modded down as offtopic?
2) You forgot to hit Ctrl-D to quit writing to cat.

Re:Two things. (0)

Anonymous Coward | more than 12 years ago | (#2994997)

this is on topic.

unbounded CPU is a problem for such an "Internet Computer"

Re:Two things. (0)

Anonymous Coward | more than 12 years ago | (#2995021)

oh.. and in your desperation.. you for got to inform the poster to uh compile and run their program!? geesh man.... get a grip with your trolling...

Re:Two things. (-1)

GoatTroll (556420) | more than 12 years ago | (#2995099)

... and get a grip with your identity and login, you loser AC.

Re:The first thing I will do.... (1, Informative)

Anonymous Coward | more than 12 years ago | (#2995009)

Sure you will, and as soon as your isos-karma runs out your fork will fail .... read the article and think about it.

You wouldn't do this just like you don't

int main() {

while(1){
walk down street giving $1 to each person you meet
}

return(0);

}

Re:The first thing I will do.... (2)

oddjob (58114) | more than 12 years ago | (#2995023)

Since the proposed system charges $$ for resouce usage, the joke will be on you when the bill arrives.

i don't know.. (4, Insightful)

lowtekneq (469145) | more than 12 years ago | (#2994906)

I'm not so sure how i feel about something i own being used for something i don't. I use seti, but i downloaded it myself and agree with its purpose. But whose to say what my computer will be used for, whose to say what files will fill up my hd, ect. Luckly we still have a choice of the OS we want to run.

Nice picture (1)

motox (312416) | more than 12 years ago | (#2994907)

Looks like Mary has been infected by code-red :>
Seriously, provided that computing resources, storage and bandwidth becomes free that's the future. But until then i'm not letting any pharmaceutical company to use my connection, cpu, or storage, and im not storing "encrypted fragments" of anything else that my own stuff, i will go on doing my backups on cd-roms.

Lawsuits could prevent "Internet Computer" (0)

Anonymous Coward | more than 12 years ago | (#2994908)

Remember the sys admin who was recently charged (and let off with probation) when he ran SETI on the school's computers?

Why should I want my computer doing others' work? (2, Interesting)

Navius Eurisko (322438) | more than 12 years ago | (#2994909)

In Scientific American, the writer gives the example of Mary's computer being ultilized by a Biotech company while it's idle. Another example is a movie that is stored on several hundred people's computers. Why should I let my computer be ultilized for someone else's for-profit work or entertainment when they can do it for themselves?

It's another thing when a person volunteers to participate (I run SETI@athome) but this proposal sounds like a forced standard upon a consumer.

Simple answer - you get paid (1)

SuperKendall (25149) | more than 12 years ago | (#2994971)

I imagine if you provided all these people with processing power that you'd probably be paid for it somehow - perhaps the computer itself was free to you (along with bandwith). If you could get a free computer and internet connection as long as others could use the spare processing power on your machine, wouldn't you go for it?

$$$ (3)

jxqvg (472961) | more than 12 years ago | (#2994996)

You would want your computer doing other peoples' work in this article's description because you would be paid for it.

These guys seem to envision this happening through some sort of micropayment system, though, which is still an overall iffy proposition considering the current cost of performing a transaction.

There are several other significant issues with using presumably anonymous internet connected machines, and their use of the term "microkernel" only clues you in that it's a NotSoBrandNew concept, but it's a fun read to get PHBs and Venture Capitalists interested.

Whats in it for me? (1, Insightful)

Anonymous Coward | more than 12 years ago | (#2994910)

So how am I compensated for my contribution of electricity, computing resources, and maintainence?

Once the geek value wears off, this is just turning my office into a community resource.

Re:Whats in it for me? (2, Interesting)

CmdrPinkTaco (63423) | more than 12 years ago | (#2995024)

I was thinking of an idea similar to this a while ago and thinking how to get people to get people on a system and how a company could profit from a system such as this. The idea that I came up with is as follows (and granted, this is very much a rough outline):

Sell computers at or just above cost to consumers in a package that provides all the necessary hardware / software. The end user will be forced to sign an agreement that will provide for them the DSL / cable line at a reduced cost and the computer for the end user. They must also agree (stated within the terms of service, that their computer should always remain on (when reasonable) and when not being used is subject to being used by my company (we'll call it MyCo).

Now, to offset the costs of the reduced price of computers and the reduced cost of cable / dsl - MyCo then can sell a client to a larger corporation who is interested in large scale computing without having to purchase one. For those of you who are familiar with the supercomputer environment, it isn't uncommon to lease out cycles on a larger scale computer to other entities to help offset the cost of some of the larger super computers. By leasing out the number crunching abilities of the distributed network of computers, this would be able to cover the costs of selling consumer hardware / packages and would allow for large-ish companies to harness the power of a distributed number crunching system.

Like I said, this is all very preliminary and more of just a thought than anything, but I think that something like this might attract more than just the "geek novelty" users. It would allow consumers to benefit, and would allow other companies to piggy-back on the system without having to make the large investment into a "supercomputer."

well and good, but... (4, Insightful)

Bandito (134369) | more than 12 years ago | (#2994916)

This is all great, but let's face it. People don't leave their computers on all of the time. In fact, here in California, they run ads on television telling you to turn _off_ your computer when you're "out of the room."

Liquid cooling for PC's is still out of the reach of many, so noise is a factor. And I can only assume that this work will require your computer to be awake, so power management goes out the window.

Even if these were overcome, there's still the obstacle of just getting people to go along with this. It doesn't sound to me like these "pennies trickling into a virtual bank account" are going to pay for that broadband connection or the increased electricity bill.

Like most other things, it sounds great on paper...

Re:well and good, but... (2, Insightful)

Bozar (458678) | more than 12 years ago | (#2994961)

Not entirely true. You don't have to have things like your monitor and speakers on, and i believe that they take up much more energy than a dinky processor running at 1.5 V. And you should be able to save power by turning off things like the video card, sound card, a significant portion of the ram, all but one hard disk, the cd rom, lower the power consumption by the processor and slow it down so your fan can turn off, etc. The core of a computer (CPU, ram, and HD) doesn't take up much power. Otherwise how could you have things like those 10 gb mp3 players that run for hours and hours on batteries? It is the human interface part of a computer that takes up all the juice, and you can turn that off if there is no human to interface with :D

Looking for a Good Time? (-1)

DonkeyHote (521235) | more than 12 years ago | (#2994988)

Are you just sitting around with nothing to do?
Do you want to talk with an interesting intelligent
woman from nevada, call 800-618-8255 from 8:00 p.m.
to 12:00 p.m. and ask for Arte Belle!

High latency? (4, Interesting)

Telastyn (206146) | more than 12 years ago | (#2994927)

The only thing I could immagine these things being used for is very high storage, very very parrellized problems. Factoring, travelling salesman (otherwise known as airport scheduling), SETI@home and the such.

The OS will never be fully "functional" as OSes are considered today, because people will lie and cheat and steal. IMO (read: opinion removed from ass) the only practical use of this would be the equivalent of making a kernel patch that could have a slice of disk, a slice of memory usage, and a slice of bandwidth, and then it would run SETI@home, or whatever code it was instructed to run from the "master".

If it was not run on public machines I could immagine something akin to Beowulf from the ground up. An OS designed for premeditated clustering. That's not Internet sized though...

P2P makes the inroad more acceptable (3, Interesting)

2Flower (216318) | more than 12 years ago | (#2994930)

Five years ago, I'd have said no way, this is unfeasible, people would not contribute their storage space and CPU cycles to someone else.

But now, with server-obfuscated peer to peer systems like AudioGalaxy, it could be possible. Imagine selling people on the idea of a 'universal public hard drive', where all you do is search for a file, then copy it over locally without actually knowing where/who it came from. I doubt there'd be any objections, given how convenient and 'anonymous' it would be. Sacrificing a share of your own hard drive space for cacheing files you might not be interested in would be a small price to pay for that. That's one resource down; do the same thing for CPU cycles (provided we have a killer app reason for people to need more cycles, given high speed processors of today) and other computing resources and the rest will fall in place.

I doubt it'll go as far as this proposal, at leastnot for a LONG time, but the unthinkable is already becoming the thinkable in some areas.

Sounds like Freenet II (5, Insightful)

Sanity (1431) | more than 12 years ago | (#2994931)

In the 1999 paper [freenetproject.org] "A Distributed Decentralized Information Storage and Retrieval System" which formed the basis for the Freenet [freenetproject.org] project, the following future direction is suggested:
Generalisation of Adaptive Network for data processing
A longer term and more ambitious goal would be to determine whether a distributed decentralised data processing system could be constructed using the information distribution Adaptive Network [Freenet] as a starting point. Such a development would allow the creation of a complete distributed decentralised computer

Guess there is nothing new under the sun.

When Donkey's Attack II (-1)

DonkeyHote (521235) | more than 12 years ago | (#2994948)

Are you just sitting around with nothign to do?
Do you want to talk with an interesting intelligent
woman from nevada, call 800-618-8255 from 8:00 p.m.
to 12:00 p.m. and ask for Arte Belle!

ridiculous (0)

IAgreeWithThisPost (550896) | more than 12 years ago | (#2994936)

that's all I can say. This is just plain stupid.

Guest Accounts (1)

Robert Frazier (17363) | more than 12 years ago | (#2994939)

It used to be the case that one had a guest account, which people could use for whatever. However, this depended on a level of trust which no longer exists. This might be a good idea, but it runs ahead of the real security concerns that people have.

"Trustworthy" computing has to be sorted before, I, for one, would allow others access to my box.

Why, O' why, is security always a second ran?

Best wishes,
Bob

Stealing from the poor and giving to the rich (5, Insightful)

b.foster (543648) | more than 12 years ago | (#2994942)

Let me preface this by saying that work related to SETI@home, the Human Genome Project, and politically motiviated cypher cracking is a Good Thing(tm) and should be preserved.

However, the proposed ISOS is big, powerful, and likely to be sought after by the most powerful corporations and institutions on the planet. How much lobbying would a large drug company need to do to get more than its share of distributed processing power? How much money would the U.S. Government need to give to them to use the system for cracking "terrorist" messages from the "evil ones" like Kevin Mitnick and Bernie G? How much money would the Government need to give to them to use the system for spying on individual users? Remember, this is the same government who pays Hollywood to put anti-drug themes in their sit-coms, so what would they not be willing to try?

The end result of this, then, is that ordinary computer users will be forced to subsidize (through the use of CPU cycles, electricity, wear and tear on hardware, and memory use) the efforts of large companies and governments who are working against their best interests. So, tell me again... what would we gain from this?

Bill

Pay for use goes both ways (4, Insightful)

Blue23 (197186) | more than 12 years ago | (#2994943)

The article mentions:

"As her PC works, pennies trickle into her virtual bank account."

However, it doesn't mention the other side, that as her files are backed up elsewhere, pennies trickle out. In addition, assuming an equal amount of "work", the outflow needs to be greater then in inflow. Take for example, the pay-per-view movie. It has a set cost to purchase. Everyone storing the movie gets a bite. But a single copy of it won't work - a single system off (or back under control of the user) means that part of the real-time delivery of the movie is delayed. So the movie has to be stored in such a way that dozens of systems can be inaccessable and yet still play in real time. As such, you need to have a large numebr of copies.

Now think about this for data backup. Is Mary gets paid "X" to hold some data, she can't be the sole recipient of it. Say she's one of 3 people with a copy of it (a rather low number). So the total cost is 3X. Now, she's going hand having her data backed up, which is the same size. She's paying out 3X to back up the same amount of storage she's only getting paid X to provide - it's much more economical to back it up herself, say a copy on her laptop and her home coputer, or work and home so the never share geographical space.

Same goes for processing power - you can't assume that a unit will finish the task given it, so that you need to run it multiple times if it is time sensitive, leading to the same inflation on what you pay out over what you are paid for your unused resources.

=Blue(23)

Internet-Scale Operating System... (0)

Anonymous Coward | more than 12 years ago | (#2994946)

...found it. [slashcode.com]

It's been done, and no one uses it (4, Informative)

Frank Sullivan (2391) | more than 12 years ago | (#2994952)

Massively distributed operating systems have been around for years... check out Tannenbaum's work on Amoeba. Does anyone use Amoeba? No.

This is two days in a row now that Slashdot has posted articles on the great new idea of distributed operating systems that CS theorists solved and have largely ignored for the last ten years. Besides Amoeba, there was the Connection Machine, VMS clusters, and others.

The fact is, massive distribution is of VERY limited use, and doesn't require OS-level hooks - Napster and distributed.net are both prime examples of useful massive distribution without involving the OS at all.

Re:It's been done, and no one uses it (4, Insightful)

Salamander (33735) | more than 12 years ago | (#2995075)

This is two days in a row now that Slashdot has posted articles on the great new idea of distributed operating systems that CS theorists solved and have largely ignored for the last ten years. Besides Amoeba, there was the Connection Machine, VMS clusters, and others.

...none of which were designed to tolerate the high latencies and frequent failures that a truly Internet-scale OS would face. Legion [virginia.edu] and similar projects are much nearer the mark, but this is still nowhere near being the sort of "solved problem" you claim it is.

Need more coffe (1)

felipeal (177452) | more than 12 years ago | (#2994954)

Damn, I swear I read "Torvalds and Internet-Scale Operating System".

I thought it would be a new venture for the Linu[x|s] saga...

Fire Down Below (0)

Anonymous Coward | more than 12 years ago | (#2994959)

Vinge's book had a civilization killing computer
virus. A global OS is one step closer to enabling
such a virus.

Data security? (4, Insightful)

gillbates (106458) | more than 12 years ago | (#2994963)

Given the fact that most companies don't want the possibility of anyone outside the company viewing their information, I don't think this will take off. I don't think that many businesses will be able to offload their processing, even if from a purely legal standpoint. What happens if Jim's payroll data is accidentally disclosed to Mary by a core dump? The legal implications of this alone would keep most businesses from using it. Consider also the following things:
  • Yes, it could render the special effects for the next LOTR movie in record time, but the MPAA would never endorse this, for fear of 'piracy concerns'
  • Biotech could make revolutionary advances, except that they run the risk of divulging a proprietary secret gene before it can be patented. A distributed network like this is practically begging for industrial espionage.
  • It's not likely that banks will use it, as an accidental disclosure, or worse, alteration of the data could result in the corruption of account information and costly litigation.
Yes, scientists could very well use a general-purpose, distributed network. But with all the concern about privacy and IP rights, I doubt that any largely profitable business would be able to utilize such a system.

Re:Data security? (1)

jhines0042 (184217) | more than 12 years ago | (#2995020)

The data would be split up and divided amongst hundreds of computers. In order to effectively change the balance of your bank account for example you would not just have to go to one location you would have to hack into 100s of computers simultaneously and find the right bits and then change them. If you didn't get a majority of the data (which BTW, is probably also stored at the Bank) then your corrupted data would get fixed when the computers put their heads together to find out what your balance was.

This can actually be more secure than current systems.

Hopefully OS developers are not that naive (2)

Pac (9516) | more than 12 years ago | (#2995071)

Besides cryptography (or do you expect files to be exchanged as plaintext?), no computer will have more than a tiny portion of any given dataset. Even a large farm of eavesdropping servers would represent no more than a small drop in this processing and storage ocean.

Very Large Governments, of course, would probably have the power to successfully mine information, but even they would be given a good run for their money. And then again, Very Large Governments already have access to almost anything they care to want.

werd (-1, Offtopic)

karmalien (129660) | more than 12 years ago | (#2994967)

of course the key word here is envsion....

The Collective (1)

sherms (15634) | more than 12 years ago | (#2994969)

Its sounds closer to being apart of the collective :)

anyone still use (-1, Offtopic)

Anonymous Coward | more than 12 years ago | (#2994970)

mojo nation? tell me about it please.

Key problem: no viable business model (4, Insightful)

LinuxParanoid (64467) | more than 12 years ago | (#2994973)

For technical computing jobs, this makes great sense.

For commercial computing jobs, as a business with economic incentives for participation, a distributed operating system unfortunately makes little or no sense due to the types of applications that are currently server-limited.

Commercial computing jobs which need "big servers" are typically very database-dependent. You can't distribute the application very well unless you can distribute the database. (And hopefully you aren't crunching terabyte data warehouses, right? That takes a while to send down the pipes...) Besides the inherent difficulty of distributing your database across many nodes, you have the the typical basket of problems the IOS must overcome with a very high degree of assurance: security of your highly-proprietary information, reliability, backup, etc.

Most of the P2P plays a year or two ago discovered this the hard way. The most promising sales approaches ended up being things like distributed caching for search engine companies, which is a niche, not a mainstream business.

--LP

nothing will get done... (1)

.pentai. (37595) | more than 12 years ago | (#2994976)

I see a small problem with this...
My computer is idle...it works on someone elses stuff...the second I do anything it stops that. That means that distributed task will take FOREVER to get back to the owner...because lets face it my computer doesn't stay idle that long. In the long run it could take LONGER for a computer to shell out tasks than to just do it itself.

And more importantly...I'm paying for my hardware, I'm paying for my electricity...if someone else needs more processing power let them do it themselves. It sounds rather prick-ish but oh well. My computer is for MY use and not for thousands of random people around the world to mess with.

And how long before someone cracks the encrypted data that's distributed...guess what, someone's reading all your email, and your work, and your accountants payroll information, etc. Distributed information on a large-scale like this (hopefully) won't catch on.

Do you really think the government would go for this? It's bad enough Intel has us doing bio-chemical research (they claim it's trying to find a cure for anthrax, but how do I know?) for them for next to no cost.

Formal CS (-1, Offtopic)

Anonymous Coward | more than 12 years ago | (#2994978)

I am always suspicious of formal mathematics applied to software. I agree
with Richard Feynman: "Computer Science" is a misnomer. Our field isn't
about science; it's about engineering. A better term for the entire field is
"Software Engineering".

Electrical engineering is a field with much more excuse for heavy
mathematics (I would know--my masters is in EE), and they don't call the
branches that use it "Electrical Science".

As far as I can tell, ALL of the formalistic areas of computer "science" are
bogus. I would like to see just one example where these ideas pay off,
starting with the theory of computation. Just why do we care about the
halting problem? And precisely why is the heavy formalism necessary to build
simple pattern matching tools? (I would know about this one: I've
designed/implemented my own matcher/parser from the ground up--and I didn't
need any fancy formalisms to do it).

Yes, my training is in EE, not CS, so maybe I just don't "get it". But I
think it's more likely that poor CS students are going to absorb whatever
their professor tells them, and not be able to tell that it's junk. After
years of solving homework problems that depend on these formalisms, they
take it for granted that they're useful (after all, they ARE useful--for
solving homework problems).

I have an opinion as to why these formalistic approaches are in CS. The
field was founded by a bunch of mathematicians. They were the type who
worshiped the form and not the purpose of mathematics--to them mathematics
was an end in itself. They regarded the computer not as a device whose
construction is guided by the purpose of filling engineering needs, but as a
brute fact of nature, to be mathematically analyzed for what it is, with the
only end being a mathematical "understanding" (which to them means only: a
mathematical catalog and description).

The form worshippers are in essence no different than any of a number of
people who attempt to combine mysticism with science. E.g., we have
"Scientology", and the various Christian groups who put the word "Science"
in their titles. Why do they do this? To ride on the coattails of science's
reputation for objectivity and truth. These groups are for people who are
honest enough to recognize that science does discover the truth, that
science's methods of reason are superior to mysticism's methods of faith,
but who are not honest enough to reject the ritualistic, faith-based
approaches they had previously accepted.

I.e., they want to have their cake and eat it too.

Why are the form worshippers like mystics? They think of mathematics as some
kind of magical system, where you manipulate symbols from another dimension
and then, magically, you get answers that work in this world. They don't
understand the reason why mathematics works, or that the symbols are merely
symbols, so they're in an awed stupor, just as a witch doctor would be in
awe over airplanes (see Richard Feynman on this--I'm borrowing his line of
thinking here). So they get their PhD's in mathematics to become witch
doctors of mathematics--experts at symbology, but nothing else.

Since mathematics is their God, they see him as Universal. EVERYTHING is
mathematical. And so is CS.

Shayne Wissler

perhaps it should be based on this (0)

Anonymous Coward | more than 12 years ago | (#2994982)

Distributed Resource Aggregation (2)

Jordy (440) | more than 12 years ago | (#2994984)

Obviously, distributed resource aggregation isn't a new concept and has been discussed many times before. There have been a couple attempts at a generalized resource aggregation system, but they all seem to have two major problems: no one wants to donate their resources to commercial entities without getting something back in return and the number of problems that can be distributed over high latency, low speed connections is limited.

SETI@home works well because the problem-space can split up and the amount of time it takes for a client to process it far exceeds the time it takes to transfer the data. There are also a good number of users out there who just like the idea of searching for ET.

Distributed.net works well for the same reasons as SETI@home, but instead of users wanting to look for ET... users adopted it originally for chance at cash and later for the ego boost.

If you build a generalized infrastructure to handle arbitrary requests for resources, the end-users loses touch with what they are working with eliminating any type of ego boost. Plus, I can't imagine many people are going to want to donate their space cycles to a pharmacutical company who will then go and patent a drug developed from information you give them, sell it at highly inflated prices in the name of R&D costs while you get nothing in return except a higher power bill and constant noise coming from your computer.

That's not to say there aren't good causes that people would be willing to donate resources to still out there, but these causes are attractive because they give the users a direct connection to them.

Of course, that's just my opinion, I could be wrong.

Too Utopian (1)

BCGlorfindel (256775) | more than 12 years ago | (#2994985)

The problem is of course going to be people who lie, cheat, and steal other people's resources. Not to mention the issues people may have with some company profitting from their personal electricity and bandwidth usage.

IMHO or WAG(wild assed guess), whichever... I see the future of massive internet distributed computing as having too much potential to be ignored. But I honestly see something less revolutionary than the paper suggests. More likely the next generation of programs like Seti@home will start becoming more widespread and efficient. Unless users can pick and choose what kind of work their distributed usage goes towards(if they want any at all) the idea just doesn't fly.

I want one (1)

jhines0042 (184217) | more than 12 years ago | (#2994989)

I think that this will be great, where can I sign up?

Heck, I would get additional computers that I never "used" directly and sign them up into the ISOS, make some money. Then when I wanted to do something compute intensive I would pay myself and have an instant home super computer. This home super computer would of course be available to everyone else when I wasn't doing anything.

Sign me up!

Joe H.

erf (0)

Anonymous Coward | more than 12 years ago | (#2994990)

We advocate two basic principles in our ISOS design: a minimal core operating system and control by central servers.
What's with this constant control by central servers fetish everyone's so preoccupied by?
Since RSA, if you're the Original source, you can join the network anywhere and propagate your changes, because no one else can sign your updates, etc.
True, without a central server any "protocol" could in theory segment into disjoint networks, but this doesn't really matter, since supernodes would probably know about each other since there aren't that many of them. Further, I don't see why it's absolutely necessary for the graph to be joined. If you have two, then, okay, a person on one can't chat with a person on the other, but other than that, are there any problems?

Seemed like a good idea at the time (1)

boltar (263391) | more than 12 years ago | (#2994991)

At least I reckon thats the category that this idea will eventually end up in. Why do some people
always assume that everyone wants to be online the whole time? WHy do they assume that everywhere
is like america and no one has to pay for local calls to ISPs? And how will effectively turning
my computer into a vast distributed system benefit me? Great idea if you want to run a
distributed equivalent of an SIMD parallel machine but pretty useless if you simply want to
do word processing. Who's going to want to wait
5 minutes while their WP downloads their document
from 101 different locations byte by byte over
a their 56K modem instead of loading it in a few
seconds off the disk?
I really feel some academics need to get out of their research labs and take a stroll in the real
world sometimes.

Half-true assertion (2)

Ed Avis (5917) | more than 12 years ago | (#2994992)

It's been done. See MULTICS.

hmmm (4, Interesting)

ekephart (256467) | more than 12 years ago | (#2995003)

Don't get me wrong the marvels of distributed computing are endless, but why don't we make ourselves more efficient on a smaller scale first. Besides there are some questions to work out.

"Consider Mary's movie, being uploaded in fragments from perhaps 200 hosts. Each host may be a PC connected to the Internet by an antiquated 56k modem--far too slow to show a high-quality video--but combined they could deliver 10 megabits a second, better than a cable modem."

Ok, thats nice, how do they propose Mary receive 10Mbps? Get 12 DSL lines? What about the people on dial-up? While people gain access to the internet around the world, those of us with the uber-connections will just leech on them? Now, they talk about the "digital divide" but that is just plain vicious. I'd rather be stickin it to The Man then Uncle Sven in Stockholm. So then what, everyone gets a fast connection -> backbone upgrade -> ATT, MCI, Earthlink, Sprint, etc. spend the money that Amgen would save.

Also: How would individuals choose who can use their computers resources given their ethical or moral convictions. While I would surely donate my CPU and disks to cancer research or finding larger prime numbers, I don't want the DoD using it to think up new ways to kill people.

Re: BeoWulf Cluster (0)

Anonymous Coward | more than 12 years ago | (#2995005)

Nope, I actually see this using something similiar to QNX's Qnet. Most of the infrastructure work would already be handled by that. Just need an encrypted FS and some extra security features and you're ready to go. Currently runs across CPU-architectures, provided the endianess is the same.

Of course, I've never used a BeoWulf cluster. It's kinda like distributed RPC, isn't it?

Better pay... (2)

nahtanoj (96808) | more than 12 years ago | (#2995012)

...for my processor time. It's one thing to be able to do SETI@HOME. But if some biotech company wants some remote computer to use my PC for DNA analysis, it had better pay me well for my generosity.

Damn I'm antisocial.

nahtanoj

Acceptance (2)

asv108 (141455) | more than 12 years ago | (#2995013)

I could really see technical minded people eating this stuff up, but the real problem lies with non-techies. Yes, the seti@home screensaver for windows looks cool so non-techies seem to have no problem installing that but will Mary really be willing to have a distributed back up system on her computer? What about gamers, who need every available bit of bandwidth? These technologies are really promising but they need widespread adoption to become a success. That's what made napster so successful, it wasn't bleeding edge technology but it had widespread acceptance.

Needs to pay for the Juice/Power impact (2)

Zergwyn (514693) | more than 12 years ago | (#2995014)

Idle CPU time, especially if the computer is just left on at night without any other use, is not free. The computer requires electricity, and in some cases internet connection bills. Any system needs to be able to pay owners at least enough to make up for these costs, or they will be losing money. In addition, if users can make money leaving their computers on 24/7, how will it affect our nations power systems? Many grids are already pushed to the limit, and if every person with a computer began to have it on all the time it might push things over the edge in some places. That might cause obsticles to the systems deployment.

Really... (1)

DickPhallus (472621) | more than 12 years ago | (#2995016)

"networking efficiency"

Uhh, is this what the internet is? Hmmmm... where can I get some of this networking efficiency?

We already have it (0)

Anonymous Coward | more than 12 years ago | (#2995036)

It's called jini [sun.com] .
dumb assess....

Half a picture (4, Informative)

Salamander (33735) | more than 12 years ago | (#2995038)

As happens too often, this proposal concentrates entirely too much on distributed computation, and pretty much ignores the problem of distributed storage. They're quite different problems, each requiring its own solution, even though it's intuitively obvious that any true "Internet Scale Operating System" would have to deal with both.

If you're interested in this "other half of the problem" here are some links:

  • Farsite [microsoft.com] (Microsoft; focus on many nodes, not long distances, but still relevant)
  • OceanStore [berkeley.edu] (UC Berkeley)
  • CFS [mit.edu] (MIT)
  • Publius [nyu.edu] (ATT/NYU)
  • Intermezzo [inter-mezzo.org]

There are many more. The bibliographies for the above will mention many earlier systems, while a quick Google search for these project names will show more recent ones.

How does this benefit me? (2)

fleener (140714) | more than 12 years ago | (#2995040)

Hmm, we can harness the unrealized potential of millions of desktop PCs. Ummm, why would we - the users and owners of the computers - want to do that?

How does it benefit me as a user, aside from #1 increasing my energy bill by encouraging me to leave my PC on, #2 increasing wear and tear on my PC as my hard drive is accessed repeatedly, and #3 increasing my vulnerability to hackers? Oh, and #4 - sucking up the bandwidth of my ISP because of all of these always-on computers, thus trashing any hope of decent pings for my first-person shooters.

Gee, where do I sign up?

What Happens When A Computer Goes Down? (1)

Grassferry49 (458582) | more than 12 years ago | (#2995047)

Ok so say I'm Bob and my friend Joe Blow just happens to have a portion of my data backed up on his computer (which of course the computer to back up on is completely picked at random, but for the sake of my question it's going to be my friend Joe Blow). So Joe's data is then backed up on Mary's computer. Say Joe's computer goes down (and needs to be reformatted) but Mary and my computer stay running. Joe can retrieve all his crucial backup data because it is on Mary's computer (perfect right?), but while Joe's computer is down mine goes down too. Now since Joe (or my backup) is gone, what computer do I turn to get my backup that I'm supposed to have from? I understand that Joe here may only have 1% of my total data stored on his hard drive, but what if that 1% is crucial to me? So in reality are we going to have to backup our data multiple times? If everyone's hard drives were spread just twice a cross the Internet onto other people's hard drives I do believe this would present a massive storage problem.

I've seen this before in an Apple commercial... (2, Funny)

josquint (193951) | more than 12 years ago | (#2995048)

... which aired January 1984...

.

Just wait.... (3, Interesting)

st0rmshad0w (412661) | more than 12 years ago | (#2995056)

Until your system and damn near everyone elses is siezed for evidence in some computer crime or some move in the war on terrorism.

Read, update, mangle, forget... (1)

SpringRevolt (1046) | more than 12 years ago | (#2995057)

Sounds a bit like Thomas Bushnell's Hurd design paper [gnu.org] with the technicalities stripped out and made buzword compliant.

ILOVEYOU (3, Funny)

sporty (27564) | more than 12 years ago | (#2995060)

Doesn't the "I Love You"/SirCam/Nimbda virus already do this? :)

DOS (1)

switcha (551514) | more than 12 years ago | (#2995078)

So...you could launch a DOS attack from your system against your system...uh...it'd be your...but not your box...but...

my head hurts.

Communist, Schmommunist... (2, Interesting)

RumGunner (457733) | more than 12 years ago | (#2995082)

This won't work for the same reason that communism doesn't work. There are too many people who are greedy, manipulative jerks, and more often than not they will take advantage of the rest of us.

Perhaps if you set up your computer service like a secret society this would work. Then you'd have to know all the users, and would be able to track everything. It would be like the Masons, only with computers.

Regulation (0)

Anonymous Coward | more than 12 years ago | (#2995085)

The government would then have the right to do what they wanted with it then wouldn't they? That could be not such a good thing, especially with p2p networks the way they are right now :-) Trade files for bogomips and bandwidth and you have an OS that is independant.

Yay

I'll have mine without the government added "flavor" thank-you. DARPA snuck thru btw........

Someone's must have mentioned this.... (1)

SGDarkKnight (253157) | more than 12 years ago | (#2995088)

but what about someone creating a virus designed to take down all the system running this new os? what type of system down time are we looking at if this were to occur. espically if some of the major backbones decided to go along with this universal internet os, we could be talking about major internet breakdown in communication... or did i just misread something here...

and harness the copying, sharing and communicating (1)

RodeoBoy (535456) | more than 12 years ago | (#2995090)

but who shall operate this system and who hires the admins?

distributed backup is the killer app (4, Interesting)

emin (149044) | more than 12 years ago | (#2995092)

The article mentions distributed backup as a possible application, but in my mind distributed backup is the killer application.

Consider a distributed backup program which works roughly as follows.

  • You install the program and give it a certain amount of space on your hard drive.
  • You tell the agent which files or directories you want backed up (e.g. /home).
  • The distributed backup program periodically contacts other computers and swaps encrypted versions of your data for their data.
  • If your machine crashes or you lose data or your city gets nuked, you can easily recover your data from the computers you shared with.

This type of application would provide at least 3 important benefits for backup. First, its relatively cheap. If you want to backup more data, just buy more local disk space and trade files with more computers. This seems much easier (at least for a home user) than setting up a tape backup system, making sure the tapes get replaced, making sure the tapes get put someplace safe, etc. Second, its much safer than pretty much any backup system you could buy today commericially since your data is literally spread all over the world. Finally, the backup system isn't controlled by any large corporation.

Obviously there are still some details left to be worked out such as how to let computers who want to trade files find each other (both centralized and distributed options exist analagous to napster and gnutella), how to prevent cheating (having your computer periodically ask its partners for hashes of the data they are backing up should work), how to control redundancy most efficiently (error correcting codes like Reed-Solomon codes or Tornado codes would probably be smarter than just repeating data).

If you're looking for a great distributed open source project that will make the world a better place, I encourage you to develop prototypes for distributed backup. I plan to develop my own prototype one day, but currently I'm pretty busy with graduate school.

-Emin

do i really want this? (2)

digidave (259925) | more than 12 years ago | (#2995093)

*sniff* *sniff* what's that I smell? A bigger security threat than Windows? It can't be!

worst Idea (0)

Anonymous Coward | more than 12 years ago | (#2995101)

this is quite possibly the worst idea in the long sad history of bad ideas.
1)you hack your computer and screw up the biotech company protien folding. Millions wasted
2)everybody with a fragment that you need shuts off their computers.
3)you leave your computer on all day sucking up electricity
4)your naughty pictures of yourself get copied to somebody else's compuer
5)everybody uses the same OS
6)I dont want to pay people to crunch large numbers. People that need this capacity have the money to rent supercomputers
7)I can go on

Number 100 (1)

cjc84 (543977) | more than 12 years ago | (#2995104)

98...99...100, yay! This is interesting, cant wait for it to come out. better be free. and secure.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>