Slashdot Mirror
How Heavy Is a Petabyte?
Jon Morgan writes "Whilst heaving around numerous data storage systems to sell (they weigh A LOT!), we got to wondering: How heavy is a Petabyte of data storage? Our best guess is 365KG, which is 6 million times lighter than in 1980! But is there a lighter way to store a Petabyte?"
How heavy is a Library of Congress?
What doesn't kill you only delays the inevitable
What are these Petabytes of which you speak? America measures data in units of Libraries of Congress.
...weighs something like 300mg/card. That's 48GB/gram, or a bit over 20g/TB, or 20Kg/PB.
What's the storage capacity of a human brain? We know how much THAT weighs, on average.
End of lesson. You may press the button.
A PB now fits in one rack also.
Help stamp out iliturcy.
I think that a 2.5 inch drive weighs less than half the weight of a 3.5 inch drive, so using twice as many of the 2.5" drives (available up to 1TB today) will reduce the weight.
The real "Libtards" are the Libertarians!
A lighter way? Of course there is!
LINE 10 PRINT "byte"
LINE 20 goto 10 REPEAT 8.881784197E-16
Then you wait for long time.....
I judt got a nre Kinesis keybiartf so please excusr ant egregiou typos.
Then you could always farm out a petabyte into multiple units that would add up to it and then weight wouldn't be an issue (though dealing with multiple units would be)
"This is the value of a summer spent and a winter earned"
Honestly, it is.
It will take me a while but committing all that data to my memory won't add any measurable weight to me at all.
Just stick the petabyte on the cloud! Clouds are as light as air!
(why yes, I am from Marketing, why do you ask?)
Since data storage is just one case of transmission channel (just sending it through time, not space) you can store the 6 Petabytes in a transmission. All you need to do is place one sender here, and one eh, let's say at the end of the Universe. As long as the data is being transmitted, it doesn't really weight anything. Yes silly question will get a silly answer :)
I've seen stats that all the books ever written by mankind add up to 50 PB of data storage. Presumable unZipped :)
http://www.object-matrix.com/
RS
Shoes for Industry. Shoes for the Dead.
Whatever gave you that idea?
Warning: this article may contain humor, sarcasm, parody, and perhaps even irony. Read at your own risk.
Nobody knows exactly how much data the average human brain can hold, but one estimate is 500 to 1000 TB. If the average adult human brain weighs about 1.3 or 1.4 Kilos, then "about 2 Kilos" would hold 1 Petabyte.
I don't know. How long have you been petting it?
"Speaking the Truth in times of universal deceit is a revolutionary act." -- George Orwell
... if you transmit it into space encoded in waves of light. Of course, you have to travel faster than light to get ahead of the signal and read it again ...
And after you compress that, you get 42.
Sure. Store it in a WOM chip. They only weigh a few grams, hold literally unlimited data, and are really fast.
Warning: this article may contain humor, sarcasm, parody, and perhaps even irony. Read at your own risk.
And after you decompress it, you get 48 and a buttload of fragmented chains.
"Eve of Destruction", it's not just for old hippies anymore...
We use a modulated light beam that travels to a geo sync satellite and back. The data has darn little mass, or weight. Now the sat, (which amplifies and redrives the signal to the ground station), and the ground stations weighs a bit, but the data weighs nothing.
Thinking about the decrease in mass of a petabyte got me thinking about Information Theory and the minimum energy required to store a bit. Or rather, to irreversibly manipulate one bit of information, which I think describes the act of writing to any kind of RAM (disk or otherwise). If I extrapolate that to also mean a mass whose rest energy is sufficient to manipulate a bit, that could give the theoretical minimum mass for a bit of storage. I don't actually know enough information theory to know that value, or even if the comparison from energy of information manipulation to mass of storage is valid, but it struck me as interesting and maybe somebody knows? What's the minimum mass of a petabyte?
The enemies of Democracy are
Seriously, before I get flamed for this, think of it: how many inner-scohol kids would fall for this on an IQ-ish test? Oh, and BTW, when a person dies does the body weigh a tiny amount less after the sole leaves?
Are you storing mostly 1s or mostly 0s? Everybody knows they don't weigh the same.
As of 10/06/03, I hate COBOL developers.
and a lot bulkier than...
a few strands of DNA.
Good judgement comes from experience, and experience comes from bad judgement.
- W. Wriston, former Citibank CEO
Oh, and BTW, when a person dies does the body weigh a tiny amount less after the sole leaves?
Depends on the shoe they are wearing. On a boot, no, its a large amount, on sneakers, yes it might be a tiny amount.
Taxation is legalized theft, no more, no less.
Is that a petabyte of lead, or a petabyte of feathers?
"Speaking the Truth in times of universal deceit is a revolutionary act." -- George Orwell
What about TB tapes? I assume those would still weigh less than their Hard drive equivalents. For that matter, what about high density optical media? Does a 2TB Hard drive still weigh less than 40 Blu-Rays? I have no idea, but I'm guessing tap at least might still weigh less.
May the Maths Be with you!
Assuming you're not already compressing your data, this would be a good method to make it "lighter." A quick Google search has a test which shows gzip compressing things down to between 25% to 40% of their original size. This pretty much makes the data useless for mining or quick lookups, but it would drop the weight of storage media required, regardless of what you're using to store it. If it's just data that needs to be stored as a backup then it shouldn't be too much of a problem.
Some other poster did it in 20Kg using MicroSD cards. Use the cards and compression and you've maybe dropped it down to 5Kg with an excellent compression ratio.
A common misconception, and just saying it on Slashdot doesn't make it true. Clouds weigh more than elephants - much more. In fact, you can learn the weight of clouds in elephant units here.
Not only that, but clouds are usually darker than the air around them.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
This subject has already been discussed.
I don't think there is a storage media with higher density available commercially right now - and probably not until the 64GB microsd cards becomes available.
You can buy a 16GB microSDHC which weighs 0.05oz (1.4g). You would need 62,500 of them to make a petabyte. That comes to a total of just 87.5kg. Of course this does not include the interface needed to access them.
Since when was a Kilogram a unit of weight?
For such a small article, that was a fascinating read. Thanks for the link.
---
ECHELON is a government program to find words like bomb, jihad, plutonium, assassinate, and anarchy.
I'm guessing that we are measuring this earth standard units because we could just store it in space. Or just put it underwater...
Air also weights more than elephants.
In fact, every square meter of the world has 2 elephants of air on top of them.
So "missconception" my ass.
HI O WISE PRINCE. WHT TOOK U SO DAM LONG?
Is there a better way to waste your time?
And if you took all the air in the world and weighted it you would get...?
being light is not the same as weight.
I've been doing my daily backups to /dev/null for years. Really good compression. My colleagues keep pestering me to test the restore part, but management is on my side due to the low cost.
Yeah, but that's called "voiding their bladder" or the even more unpleasant related process.
What's funny is, back in "the day" people would do experiments like this. I don't recall any about souls, specifically, but according to a Nova episode I just watched, heat used to be considered a substance that flowed into and out of objects; in attempting to discover the weight of heat, they found out that it wasn't material at all, but rather motion. Seems obvious now, but someone had to figure it out at some point.
what you call it when you pet your pet and they byte you.
Being pedantic is the wrong place to fail , like you did.
You failed to take the weight of air into account. Why, when you do that they are, in fact, lighter then air.
Otherwise they would fall down, and we call that 'rain'
The Kruger Dunning explains most post on
where you sit around dealing with heavy petting all day? And don't you just think that a lighter version of it would just be annoying? Maybe even leading to the infamous BBOD? Or maybe I am just reading this wrong ...
Doesn't that depend on the temparature?
Stephan
http://stephan.sugarmotor.org
That's probably something to do with the relaxation of certain muscles. I plan on wearing adult-size pullups if I anticipate my imminent death.
Admit it. You post strawman arguments as AC so you get modded Insightful for refuting them, rather than Troll
Thanks for nothing Peggy LeMone. Saying that a "typical cumulus cloud" weighs as much as 100 elephants is a meaningless statement without giving us a hint as to what the hell is the size of a "typical cumulus cloud". I bet we are talking about a hell of a lot greater volume than 100 elephants.
Here is an equally interesting piece of news for you: a pile of feathers is heavier than a tank! Of course it all depends on the size of the pile but who can bother with those little details.
Negative moral value of force outweighs the positive value of good intentions.
I've seen stats that all the books ever written by mankind add up to 50 PB of data storage. Presumable unZipped :)
You've seen ESTIMATES.
These posts express my own personal views, not those of my employer
A European Petabyte, or an African Petabyte...
Suppose you were an idiot and suppose you were a member of Congress
My /dev/null is light and very fast to write to. Just remember though, when you want to find that data, you'll find it have magically been moved to /dev/urandom. Be wary though, since /dev/urandom actually encrypts the data for you, it is just THAT cool! To decrypt, it's really simple, you just read a chunk X from /dev/urandom, and the same chunk Y from the original data, and do X XOR X XOR Y, and wee, you've just stored infinite amounts of data in under one gram!
That should always begin with "What do you mean,"
It seems the new unit is the 1980's, judging from the few last posts.
And then you say, "oh fsck!". I hate it when that happens!
So which Petabyte are we talking about? The functional petabyte (i.e. 1,125,899,906,842,624 bytes), or the hard drive manufacturer's version( i.e. 1,000,000,000,000,000 bytes)?
Actually, a quick wikipedia search tells me that 10^15 is indeed the petabyte, while 1024^5 is the pebibyte. But according to Wikipedia I've been using the wrong terms this whole time anyway. kibibytes, mebibytes, gibibytes, tebibytes. etc... Somehow it all feels wrong now, and I want to blame Western Digital, or maybe Maxtor.
"Operating systems suck: you're better off using only the BIOS" --trainsaw.com
What are the units that measure "lighterness"? Put another way, if it were 1 time lighter than in 1980, how heavy would it be?
Problem is those methods of dropping the weight, also increase the cost (TFA assesses both). In the case of 3.5" SATA HDDs, that weight/cost should include a storage system that renders all the data available at the same time. 140 Lbs for 48 Hard drives is reasonable.
Off the wall idea but how to store a petabyte for near very few kilos and it scales up. Place mirrors in space, from a satellite fire a laser for 10 light seconds of 1 PB of data into space at the mirror. When it comes back send it out again. While 1 PB goes out, the other PB comes back. Create as many steams you want. Near infinite storage. Only hitch is if the relay loop is broke, there goes the data as your not likely to catch up to it. Next issue is random access is 0 to 20 seconds. That is, use light in outer space.
You can store data on a rock, or on a optic crystal. Trying to 'weigh' it is just stupid, as its all about context.
---- Booth was a patriot ----
A common misconception. Weight is not mass.
Air also has mass, not much different from the mass of cloud (which is mostly air).
I guess that explains why an elephant can fly, too. Huh. I always wondered about the science of that movie! Well now I know.
GE holographic storage disks are the size and weight of a DVD and hold 500 GB. A stack of 50 DVDs weighs about 1 KG (a bit less without the spindle and cover, but let's go with it). A stack of 50 holographic disks would hold 25 TB. 40 stacks of 50 would hold 1 PB and weigh 40 KG. Not in production, but in working prototype.
Vapor/patentware but interesting: http://colossalstorage.net/3d_holo.htm
40,000 terabits (5 petabytes) per cubic centimeter of a ferroelectric optical perovskite, specific gravity 4 give or take a fraction. 1 PB would be around a gram.
"I may be synthetic, but I'm not stupid." -- Bishop 341-B
Just store it in orbit, and regardless of the media it'll be weightless!
The link says 1Million (pinky to mouth) mainframe drives in 1980.
Did they even *HAVE* 1GB drives on mainframes in 1980?
Fascism starts when the efficiency of the government becomes more important than the rights of the people.
Approximately 82 kg if you use 32GB SDHC cards, assuming 2.5g per card.
is there a reason we couldnt simply 'wire' them altogether and actually have a petabyte drive? on that note what is the volume of that many micro SD cards? im sure you can take a good percentage off of the final volume due to having more plastic and interface pins than if they were all merged together.
51.2 LoC's
Assuming LoC is still = 20TB
"The problem with socialism is eventually you run out of other people's money" - Thatcher.
Perfect! We'll use my encryption method, CLOUDZIP, to get out the data:
CLOUDZIP DECRYPTION METHOD:
IF EXISTS($CLOUD) THEN OUTPUT($PETABYTE_OF_ORIGINAL DATA)
Admittedly, it is a very big decryption program. If I only had somewhere to store it...
a Petabyte of data is not a material thing, the object that contains the data is what weighs in as far as heavy goes.
A Petabyte of data has no weight, it is a pattern of electrons etc stored on a device, the electrons and device are not part of the data but contain the data.
One day we assume there will be a Petabyte storage device, until then we will keep stacking up storage devices and weighing them until they add up to a Petabyte.
Remember, Slashdot does not have a -1 disagree moderation, and no, troll, flamebait, and overrated are not substitutes.
Sure, it's mostly useless. But it does exercise all the bits on your disk drives, so you'll know if you've got checksum problems, bad blocks, etc. and can recover from faults before you lose lots more data.
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
LTO-4 tape cartridges are about half a gram of mass per gigabyte uncompressed, including the shell, so on the order of 250kg for a petabyte, but if you didn't have to store the cartridge shell it could be much less.
-fb Everything not expressly forbidden is now mandatory.
For offline storage, that's pretty lightweight. But if you need online storage, you need to put the MicroSD flakes into readers that weigh more than the storage does, and string a bunch of those things together, which probably requires active computers with lots of ports on them. Still not that heavy, but it's a lot bigger than just a bunch of flakes with sequence numbers written on them in Sharpie pen or punched into Columns 73-80...
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
Store it in the cloud.... clouds are light, fluffy and they float, right?
I say don't drink and drive, you might spill your drink. Before you get behind the wheel just stop and think.
One AT/TA pair for 0, CG/GC for 1.
Chop into suitably sized chains with primers indicating directory structure.
Advantages - Can be easily read and replicated and stored either in vitro (cryo) on in vivo via inserts.
Disadvantages - Time consuming to run searches, writing new data involves multiple single-point mutations.
The memory capacity of an isolinear optical chip is 2.15 kiloquads, which is about 2.15 exabytes. I don't know how much they weigh, but they're about the size of a stick of gum... I'd guess they weigh about the same... say... 20g... so that'd be about .002g/petabyte.
The Admin and the Engineer
From the first hit on Google for "first 1gb drive":
... kilogram-to-gigabyte ratio from 121 kilograms per gigabyte... link.
.72kg or .00048Kg/GB which is EXACTLY the predicted value (250Kg * (1/2)^19) so it would appear so!
World's first 1GB disk drive (IBM 3380) introduced 1980, was the size of a refrigerator, weighed about 250 kg and cost $40,000 link
Then there was this tidbit:
in 1982, Hitachi shipped the first drive with more than 1GB of storage. The 1.2GB H-8598, seen here, consisted of 10 14-inch platters and two read-write heads.
Assuming it was ~18 months later do we have another close analog to Moore's law? A 1.5TB HDD weighs only
There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
Yes, you can get 1 Petabyte server with only 20 storage servers now. These are available now.
Here is the spec. You would need only 20 units for 1 Petabyte. Thanks for reading!
Qty Description
1 KING STAR 4U SYSTEM SERVON XS413
1 MB SM XEON X7DBE Motherboard
Integrated ESB2 6-port SATAII Controller, RAID 0, 1, 5, 10 support
Integrated Intel 82563EB Dual-Port Gigabit Ethernet Controller
Integrated ATI ES1000 16MB Graphics"
2 CPU XEON QUAD CORE 2.66 12M 1333 E5430
2 FAN SM 2U XEON SNK-P0018..DEMPSEY LGA771 PASSIVE
2 MEM DDRII 667 4GB FB-DIMM
1 CO SM AOC-SIMLP-B+
1 LSI Logic MegaRAID SAS 84016E 16-port 3Gb/s PCI-Express SAS/SATA RAID Adapter
24 HD SATAII 2TB WD WD20EADS
2 HD SATAII 2TB WD WD20EADS
1 CASE SUPERMICRO SC846E1-R900B
Ray Liu
King Star Computer
1259 Reamwood Ave
Sunnyvale, CA 94089
Tel: 408-736-8590 x108
Fax: 408-736-4151
www.kingstarusa.com
ray at kingstarusa.com
Rackmount Server Specialist
What are the units that measure "lighterness"? Put another way, if it were 1 time lighter than in 1980, how heavy would it be?
I believe author means current storage weighs 1/6000000th of the equivalent in 1980. Ergo, 1980's tech weighs 6 million times heavier/more, what have you. Since the invert of heavier/more is lighter/less you can't blame them for saying 6 million times lighter. It makes sense to me.
Did a quick google, apparently "times less" is 12 times less common than "times more".
"There are no facts, only interpretations." --Friedrich Nietzsche.
You are welcome. People here seldom say thanks. As for the article, I'd read that one, or a similar one, several years ago and thought it was great too. It just stuck with me to where I saw the original poster's comment. Now if we could only have an A.I. search engine that could parse postings and automatically create these links.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Tell that to my doctor the next time I stand on his scales.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
According to this website
http://www.consumer.philips.com/consumer/en/ph/consumer/cc/_productid_FM32FD05B_97_PH_CONSUMER/USB-Flash-Drive+FM32FD05B-97
1PB = 822.8 kg
or this site
http://www.compusa.com/applications/SearchTools/item-details.asp?EdpNo=4484940&CatId=2413
1 PB = 81.92 kg
3 parsecs
It's one thing to take your chances and ignore failures when you're storing a gig or two. But once you've got 1024 or 512 disk drives spinning away, one of them is going to fail and you don't know which one it will be.
So maybe to store a petabyte, you've really got to store two copies of a petabyte. That doubles the weight.
every square meter of the world has 2 elephants of air on top of them.
And if we assume an elephant covers about a square meter (probably a conservative estimate), then, because of all that air on top of it weighing it down, an elephant must weigh--at a minimum--at least as much as three elephants. :)
I can see the future now:
"Nobody will ever need more than 640kg of RAM!"
A single particle of Autographa californica nuclear polyhedrosis virus has a mass of about 1.5 femtograms, and its genome is 128 kilobases. If my calucaltions are right, you could store 1PB in 100 milligrams of virus particles. This was the only virus I've managed to find both figures for, so this result can probably be improved. For what I know, viruses can survive pretty harsh conditions, and this is a DNA virus, and DNA has two strands, so you're basically getting a RAID1. And it's the most popular data storage format on this planet.
If streaming access is okay, then tape is king. Cheaper than spinning rust or solid state, much lighter than HDDs. An HP LTO 4 Ultrium cartridge holds 1.6TB and weighs a few ounces. At say 6 ounces per tape, a PB clocks in at around 100KG.
Remember that the whole E=mc^2 thing only applies when you are actually converting mass to energy, as in a nuclear reaction. There mass is being destroyed and becoming energy. In a chemical reaction, that's not happening. You have the same mass on both sides of the reaction. You are just converting energy form one form (potential energy in the atomic bonds) to another (thermal energy). The bonds are not objects with mass, just energy potential among the atoms.
So there is no difference, not even a trivial one, in mass since batteries are a purely chemical reaction.
You can store a petabyte using no mass at all. Pulses of light would function as the bits. Of course, reading the data would be tricky, as it tends to move a great deal quicker than you do.
How fast are we moving?
and all of this sits upon a tortoise? Amazing!
Perhaps if you don't care about your data. Who would use 2TB desktop class drives to store 1PB? Biggest drives you could use would be 1TB SATA or 600GB SAS.
Is that petabyte full or empty?
But there is 2 elephants worth of air pressure pushing you from below, so it evens out. Plus you don't occupy a whole square meter when you stand up, but when you lie down flat, you get closer to it. But as the elephants worth of air weights accumulate on top, so do the ones pushing up from the bottom.
I've been considering the problem of data storage increase, and I've come to some conclusions.
1. We are on a collision course with limited resources in data-as-matter representation.
2. There are several solutions but they are:
a. Computationally intensive, and np complete (or very likely np complete)
b. Impossible due to entropy (the universe only flows in one direction)
Quite frankly, I think we are hitting the bounds of continuous time. We need to hand round the cake, and cut it after.
If it where 1 time lighter than in 1980, it would be 5,840,000,000KG. The unit measuring lighterness isn't a unit, its a ratio, which would work in any unit...
2 mirrors 3 meters apart. Bounce light between them, and a year is 3 meters wide. Your statement may sound clever and insightful, but it does not stand well. I would rather go with a funny mod.
Take your raid arrays and storage racks and blast them into space. Problem solved. (Good for overheating issues, too!)
What are the units that measure "lighterness"?
Inverse kilograms.
is a petabyte?
Neither the MDS600 nor the X4540 is offered with 2TB SATA disks, so we're both off of spec.
Help stamp out iliturcy.
Since it's nomen. will be Pb why not shorten the term to a Lead. ;)
The S2A 9900, 1200 1TB drives in two racks.
Over 9000!?
Here's the one that'll really get you:
A pound of feathers weighs more than a pound of gold.
>>You failed to take the weight of air into account. Why, when you do that they are, in fact, lighter then air.
Talking of being pedantic, I think the word you are looking for is density, not weight.
1m^3 of air weighs about 1200g.
1 teaspoon of water weighs about 5g (based on volume of a teaspoon being about 5 ml).
If you drop one teaspoon of water into a one cubic metre box that's full of air, the water is going to fall straight to the bottom of the box. If you heat the same weight of water (somehow without heating the air as well!) above the boiling point it will increase in density and float to the top of the box. Neither weight has changed, only the density has.
I like my coffee the way I like my women - roasted and ground up into little tiny pieces.
Of course not, photons have no mass...
According to the math on this QDB, the average ejaculation is 7.49400542 petabytes. So I would say less than an ounce.
Assuming you represent 1s and 0s as the presence/absence of an atom of aluminum on a sheet one atom thick, then it weighs (at the most, if you store all 1s) about 0.807 micrograms. This all fits onto a sheet of aluminum 1 atom (250 picometers) thick and about 3.35 by 1.67 centimeters in size. Though that would be some impressive hardware that could manipulate that.
Every computer I've ever seen has one actually. Most are made by the NuLLite company, so the *nix device is /dev/null. The interface is quite simple also. Redirect your data in to the device and it will be stored there forever.
A DVD weight is normally 0.034 lbs and a blue ray disc can hold 50GB. 1 petabyte = 1,048,576 GB / 50GB = 20,972 blue ray discs, which weighs approximately 713 lbs. Its not at all unwieldy, really!
1 3.5" floppy = 30 gram
1 floppy = 1.44 MB
1 petabyte = 1,073,741,824 MB
1 petabyte (stored in floppy format) weighs: 745,654,044.44 grams (745.65404444 metric tons)
Not if you use troy (or standard) ounces for both.
-bugg
Hard disk capacity grows in spurts though. In 2001 we had 100GB drives max or so, by 2003 that was 300GB and by 2005 it was 500GB.
But from 2005 to today, we've only gone from 500GB to 1.5TB
http://www.mattscomputertrends.com/harddrives.html
This sort of backs up my observations there... things have kind of petered out since 2005.. with a steady but slow growth compared to before.
I've had enough abrasive sigs. Kittens are cute and fuzzy.
not much detail given as to what kind of memory (access abilities, etc) is specified...
1cc of brain probably has more than a PB of DNA and other memory...
how about a PB of WOM (write-only memory)... can make that *real* small and light...
I have a Windows XP machine. And I've learnt this. The more I install, the slower it becomes. How else could you explain this phonemenom ?
So don't tell me that memory has no weight, cos it does !!!
Machines gets heavy yeah? Them fat disks spinnin ever more sloow.
Easiest way to solve. Make a compression scheme designed specifically for the petabyte of data. Store "1" on something that weights practically nothing. I'm not going to talk about the weight of the compression scheme :)
I thought about asking the question - "What is the total weight of all womens boobs in the world?", but then I realised I was on slashdot. Not something many people would know anything about here.
Infinite loop of elephant math?
Well if you use these very light discs that will eventually be able to hole 6 Tera each,
then a petabyte may weigh a lot less.
http://en.wikipedia.org/wiki/Holographic_Versatile_Disc
google "32 trillion offshore needs IRS attention"
But is there a lighter way to store a petabyte?
Use the surface of a black hole as a hologram by encoding your information on there ( best one can do according to http://en.wikipedia.org/wiki/Holographic_principle )...
_____________
[begin tangent to actually calculate the bounds on black hole information storage...]
Entropy of black hole:
[E:black hole entropy (bits)] = [black hole surface area]/4 * constant(k*)
* = [Boltzmann's constant] / [Planck length^2
( http://en.wikipedia.org/wiki/Black_hole_thermodynamics )
Surface area of sphere:
[surface area] = 4 * pi * [radius]^2
Schwarzchild radius:
[radius] = 2 * [G:grav. constant] * [m:mass] / [c:speed of light]^2
( I think r (in radially-symmetric general relativity settings) is defined such that the sphere-radius thing works )
________________
Solve system of equations. The result is:
E = 4 pi (G / c^2)^2 * k * m^2
[mass required] = sqrt([desired bits] * [conversion factor: thermo info] * 2.7mil joules/degree)
[ Google: 4 pi ((gravitational constant) / (speed of light)^2)^2 * (boltzmann's constant)/(hbar * (gravitational constant) / (speed of light)^3) ]
Some things are probably very wrong here; if a modern physics professional would like to step in please do so. The units work out... but the result is really weird: If one desires to write X bits of info, one only needs mass proportional to sqrt(X)?! Something seems fishy.
[end tangent]
I once saw an article on theoretical limits of computation discussing black holes, which I could not dig up.
Tell that to my doctor the next time I stand on his scales.
When you step on the scales, your own weight is added to the 2 elephants of air already on that scale, and the scale just shows the wieght difference...
That is, of course, due to the fact that a Troy pound (used for gold) measures a lower weight than an avoirdupois pound.
Not a sentence!
Back in the 1940's one petabyte would have weigh a whole lot more. Those Delay line memories consisting of tubes filled with mercury seems a bit...bulky.
http://echochamber.me/viewtopic.php?f=36&t=15611
http://www.youtube.com/watch?v=kignGE77l_I
Google calculator gives me 1petabyte in kilograms:
((1e15 * (Boltzmann constant * 293 K * ln(2))) / c) / c = 3.11986188 x 10-23 kilograms ... not so much... :-)
Maybe in the basement is is colder than 20C, then it would be even less
No, not just one. It's tortoises all the way down, young man.
8 of 13 people found this answer helpful. Did you?
Clever boffins are beavering away at understanding the interlinks between super-conductors and gravity. When they finally work it out, look for a data storage system that can store data at the atomic level by reducing gravity on selected atoms. Sheets of atoms don't weigh much - even less when approximately half of them are gravity reduced.
Nah. The volume of water in a cloud weighing the same as 100 elephants is pretty much identical to the volume of the same 100 elephants.
This follows because elephants and water have similar density (both around 1000kg/m^3)
I found a lighter storage method. My shift + del keys together have a mass of 10 grams.
helium...
There was an article a couple years back where some Indian engineering student claimed some 2.7GB/in^2, or 4.1TB/m^2, in some 'rainbow format'. With standard office paper at 80g/m^2, that puts a petabyte at 250 sheets and 20kg.
People are ignorant. Really, sole? Try spelling correctly people. It's "soul." I commend you for pointing out this heinousness.
Added to my units.dat.
What a depressingly stupid machine.
A common misconception
What did you expect from marketing?
Actually, today we have 2TB drives. http://www.wdc.com/en/products/products.asp?DriveID=576
140 Lbs. for 48 hard drives is not reasonable, when you have to lug two of them to a datacenter and rack them.
Ow, my splagnic ganglia.
http://forgetomori.com/2008/science/enlarge-your-penis-data-bandwidth/
The "H-Word" has died for me.
Resonant anisotropic venal beams can store 1 Petabyte in 2mg - but the magnetic containment field has a volume of just over 6 parsecs. This is not a problem in deep space, but bandwidth overlapping can cause problems inside star systems containing magnetic stars.
I'm British, and my pound didn't buy me much gold at all, you insensitive clod!
Finally had enough. Come see us over at https://soylentnews.org/
Considering the other thread that gave us energetic equivalent of 1 LoC = 14,770 gigajoules, at 20TB, we get 12 bits per joule.
45 5F E1 04 22 CA 29 C4 93 3F 95 05 2B 79 2A B2
http://uncyclopedia.wikia.com/wiki/Kilobyte
I would say approximatly 15ng (nanogram). If you store each bit in a seperate hydrogen atom in some magic way.
If you instead use carbon atoms, and each bit has one other atom as a link to some magic intrastructure, the weight will be 360ng.
And for silicon, two atoms per bit: 840ng
Lets say a storage device of 100g is acceptable, then it can contain an 113ZiB of above silicon storage (ZiB = zettabyte with base 1024... called zibibyte?)
Note: this is just hypothetical...
You talk that silly talk about your butt and some chains, did not need that visual.... O_O
What do you mean ? An African elephant and/or an Europ^W Asian elephant ?
I used to ask "what does a bit weigh" as a rhetorical question. Two years ago, reading up on black holes I discovered that a bit does not have mass but it does have area.
This relates to the size of a black hole, conservation of entropy/information, and the surface area of the event horizon. As it turns out, a bit requires one Planck area (see http://en.wikipedia.org/wiki/Planck_units), or about (1.6E-35)^2 meters,.
It's easier to be a result of the past, but more fun to be a cause of the future! http://www.spacefinancegroup.com/
Exactly. Once you find out, the cat dies.
"Speaking the Truth in times of universal deceit is a revolutionary act." -- George Orwell
I put all my data on to an ecrypted laser beam and launch it into space.
If I ever want it again I just have to get into my FTL spaceship and get in front of the data.
But then none of my data is really heavy.
Someone should let this guy know!
Roughly 12 parsecs.
Read what I mean, not what I wrote.
That's about 16gm per disc, 50GB each, so you need 20,000 discs... but they total weight is only 320KG, beating the HDDs on weight if not necessarily volume. That's gonna run around $270,000, based on the best "cakebox" price I could quickly find online...goes to $380,000 if you need REs... the HDDs still win here. Going to BD-R 20s, you're going to about double the weight to 640KG with the 40,000 discs needed, but the price would drop to $112,000, also based on per unit prices of today's 50-disc cakeboxes at an online retailer. Obviously, you could get a better deal in this volume... but same goes for the WD drives.
-Dave Haynie
Just store it in "the cloud..."
That Guy
If you subtract the storage medium?
Send the data stream in a low-attenuation beam to reflect around a black hole. Then in 10000 years pick it up.
Then I suppose the weight of the data would depend on what is stored. If the info stored is regarded as Brillouin's negentropy with an entropy rate of 1.0 and Szilard is right, then presumably it could potentially be expanded into energy and that converted, courtesy of Einstein and the creator, into mass.
However, that calculation would have to be done by someone who knew what they were doing and had not simply pulled all of this out of his arse / Wikipedia like me :)
Nullius in verba
For a while I was thinking: "Heck, that guy must be writing mighty long lines when he is coding!"...
Technically if a PETA idiot bite another, the only mass will be the saliva that they left behind...
Or it may of infinite mass due to amount of drool produced...
If you use me and a torch as the storage the size of the petabyte could be my weight + weight of the torch(155 pounds). For every set bit, I would point the light towards a particular direction and for every bit that was not set, I would point the light towards a different direction. Of course if you decide to use me as the storage, read and write operations would be very slow, well I guess that is something we are not interested in! I am also guessing we are not interested in the amount of power consumed to perform the operation( in my case, the number of batteries necessary for the torch and the amount of food you would have to feed me to read/write data)!
When a thief sees a saint, all he sees are his pockets!
A full drive is going to weigh a bit more from all the dust that gets sucked in while filling it up. A running drive in a perfect clean room would weigh a little bit less because the air inside would warm up and have a lower density. The frame dragging effect of the rotating disk platters might affect the apparent weight a bit, too.
How much does all that weigh?
And another thing...In the often-convenient description of "n things laid end-to-end in a straight line would go so far" the maximum possible value of n is around 10^62.
I'm a Programmer. That's one level above Software Engineer and one level below Engineer.
That's odd. I have a very clear memory of crashing a Bryant 2GB disk drive in 1970. And it was a lot bigger than a refrigerator.
I'm a Programmer. That's one level above Software Engineer and one level below Engineer.
I must be depraved. The first thing I thought of was "Heavy Petting" bytes.
Wot a sad life I lead.
With approx. 8250 128GB flash drives, you would have 1PB storage, and it would only weigh 160KG.
See here.
Double Helix DNA, which is really tiny and only a fraction of a single cell, stores 0.35 gb of data. Weight is in the medium and not the data itself.
I am wondering if you need to register with the state for having a file with one petabyte of data.
After all it would be considered a petafile, correct?
Is that a metric buttload or an imperial buttload?