Slashdot Log In
Storing Data For the Next 1,000 Years
Posted by
kdawson
on Tue Apr 22, 2008 11:37 PM
from the long-now dept.
from the long-now dept.
An anonymous reader writes "This may be an interesting take on creating long-term storage technologies. A team of researchers at UCSC claims to have come up with a power-efficient, scalable way to reliably store data for a theoretical 1,400 years with regular hard drives. TG Daily has an article describing this technology and it sounds intriguing as it uses self-contained but networked storage units. It looks like a complicated solution, but the approach is manageable and may be an effective solution to preserve your data for decades and possibly centuries." Nice to see research on this using the kinds of real-world figures for disk lifetimes that recent studies have been turning up.
Related Stories
[+]
Everything You Know About Disks Is Wrong 330 comments
modapi writes "Google's wasn't the best storage paper at FAST '07. Another, more provocative paper looking at real-world results from 100,000 disk drives got the 'Best Paper' award. Bianca Schroeder, of CMU's Parallel Data Lab, submitted Disk failures in the real world: What does an MTTF of 1,000,000 hours mean to you? The paper crushes a number of (what we now know to be) myths about disks such as vendor MTBF validity, 'consumer' vs. 'enterprise' drive reliability (spoiler: no difference), and RAID 5 assumptions. StorageMojo has a good summary of the paper's key points."
Submission: Storing data for the next 1000 years by Anonymous Coward
This discussion has been archived.
No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
Full
Abbreviated
Hidden
Loading... please wait.
Only half the problem (Score:5, Informative)
I tend to think systems such as the one described in the article aren't good long-term solutions. If their math works on the failure rates, that's fantastic- but just try to hook up a 2028 computer to one of these things to pull the data off.*
(Ever tried to get data off an obsolete tape backup?)
I think the most reliable archival system is going to be an active one, where data is saved on modern storage hardware and always copied to more modern tech as it arrives.
The other side of this is, for anything more advanced than text-- given that you can get at the data, what do you open it with? File types die over time and it's basically impossible to find programs to open certain files nowadays, much less such programs that will run on a modern OS. I think the answer to this has to be virtualization. Store the data *and* programs that can open the filetypes you need opened inside a portable virtual machine (e.g., a Windows vmware image). Over time, you may have to layer virtual machines inside virtual machines as OSes grow obsolete. But that's okay- virtualization is only going to become more elegant, and the end result is that you'd have your data in its original environment, completely accessible by native programs.
*Some elements of this problem could be solved by having backup servers use wireless and filesharing protocols that might stand the test of time- e.g., 802.11n and SAMBA. No need to just pick one 'most likely to be future-proof' combination, either: run bluetooth and serial access, webdav and a http fileserver, etc. Still, *not* storing data on modern hardware is always going to be a risky kludge.
There's probably room for a lucrative business based around this-- figuring out the most elegant way to archive and retain meaningful access to data under various computing/disaster scenarios. Hey, I do consulting.
Re:Only half the problem (Score:5, Informative)
I think the most reliable archival system is going to be an active one, where data is saved on modern storage hardware and always copied to more modern tech as it arrives.
Maybe old data was meant to die.
Parent
Re: (Score:3, Informative)
Only in the MS Windows world. For the rest of us if it predates ASCII we can use "dd" to convert from EBCDIC if we have to. The tapes from 1982 I recently read in however were transcribed to new media for me first in case the media had become damaged over time and because I'm not familiar with 9 track drives. It was a direct copy so the data format was retained even if it was on new media (IBM3490 format but done
Re: (Score:3, Interesting)
Maybe proprietary formats were meant to die.
I still have documents in plain ASCII that I can open from over ten years ago. I've got a few .wri's that I can still open, thanks to reverse engineering efforts by the open source community. Older proprietary formats are now defacto open standards. The thing that can kill this off? Patents, for one. Trade secrets in the form of overly complicated proprietary formats for another.
And yes, I realize I'm not talking about GB's of
Re: (Score:3, Informative)
It's not enough to know what's on the thing; you also need the hardware to read the gadget, and that hardware is often unavailable due to its failure to succeed, or
Re:Only half the problem (Score:5, Funny)
Find a chisel. [wikipedia.org]
Parent
Re: (Score:2)
Simple: You use only formats that are openly specified and free software. HTML and everything XML-based actually is text, while format descriptions and decoders for Theora, Vorbis etc. will be around for a long time, probably
Re: (Score:3, Insightful)
While it's not generally too awkward to convert from one characted encoding to another, "just text" is a slight oversimplification.
Try harder (Score:5, Insightful)
Given the media, specifications and some time and money, a trio of engineering, electronics and CS students will make a machine that will read any old tape, punchcard, early HDD, etc. A CD is laughably simple technology, an engineer 100 years from now will build a player (in a way that may not look anything like our current players) in no time at all.
Today's technology is even more well documented and certainly not beyond the capabilities of future generations to make readers for.
If you find an old tape and want to do it in an afternoon, you are out of luck. If you are an historian that really, really wants to get to the data, it is not all that hard.
Parent
Re: (Score:3, Insightful)
If you;re uncomvinced go study the maths on auto focusing an pit tracking lasers, not to mention D/A conversion, reed solomon error corection etc.
Why would you use such arcane methods a 100 years from now? If they looked closely at the disc, they would see the patterns. Knowing (as they will) that we used to use "binary", they'll quickly assume they represent 1 and 0. Take a quick scan of the entire disc and do the rest in memory. Somehow I doubt they'll have much of a problem with D/A conversion either. (which is so simple, they'll figure that one out too. Understanding the data is supposed to be audio, they'll quickly put two and two together. Mos
Re: (Score:3, Insightful)
You have to remember that it is going to be pretty obvious for anyone that the original use was to play back music. Most likely, they will find them in places where the player is still next to it - even if it doesn't work. Even without the red
Goat Skin works fine... (Score:3, Funny)
I am having trouble playing them in my PS3 though.
Re: (Score:3, Insightful)
Re: (Score:3, Funny)
Sometimes old tech is best (Score:5, Insightful)
Stone and chisel. That's the way to store data for 1,000 years. The reason why I say this is simple. The more "religious" the world's populations become, the closer to the dark ages we become. (The reverse is true as well as history illustrates.) I expect there will be a second "dark ages" at which point all other technologies will simply not be available.
Re: (Score:2)
Re:Sometimes old tech is best (Score:5, Interesting)
Parent
Re:Sometimes old tech is best (Score:5, Informative)
Parent
Re: (Score:3, Informative)
I think you could make an argument that Russia and China were theocracies for much of the Stalinist period. For example I read that Mao apparently gave a speech which was interpreted as him saying that quarks were the fundamental constituent of matter. After that Chinese physicists were careful not to publish papers that might contradict the great man. In Russia Lysenkoism was famously the officially supported theory of agriculture.
No.
Government providing support to stupid opinions and doctrines does not make them a religion -- for something to be a religion it has to specifically include belief in a supernatural deity. I remember that in USSR saying that someone believes in god was the ultimate insult to his intelligence.
Re:Uh, what? (Score:4, Interesting)
I mean that Communism and Nazism behaved like religions.
No. I was there, and I can most certainly say that they were ideologies and not religions. Religion always includes or endorses some ideology, but the reverse is not true, ideology does not necessarily have anything to do with religious belief.
A state-supported ideology is common and often nearly invisible for the member of society that practices it -- it is proclaimed (often clumsily) by government officials, is seen kinda working because society can prosper while supposedly implementing it for decades, it is assumed to be right by most and rarely questioned, but people also rarely actually think about it, or any alternatives, it's as if its validity or invalidity is irrelevant to the people's lives as long as society is capable of implementing it without creating discomfort and unrest. After all, it merely claims what is "a better way of running a society" as opposed to making claims about physical world that exists independently outside of human mind and ideas. Since most of people are not politicians, assuming that politicians are following some sort of rules that have little impact on everyday lives is a natural (though often stupid) thing to do, however for, say, a physicist it would be impossible to assume that religion's creation myth is correct -- it contradict with things physicist experiences in his work. In US the ideas of "capitalism" and "democracy" enjoy the same kind of ideological support -- I can make a case of both of them being pretty poorly thought out ideas in the first place, and separately of neither of them actually playing an important role in the way US society operates, however none of it will be a scientific argument because I will have to discuss people's ideas, behavior, motivation and impression about life. At most I can catch government and businesses lying and manipulating people using ideology as the tool to achieve desired behavior of the masses, however for every my claim there would be tens of millions of rednecks claiming that they naturally love doing exactly what I see them manipulated into doing.
Religion, on the other hand, requires actual belief and is treated not only as important part of everyday lives, ethics and history but also makes claims of facts -- something that ideology often approaches but never actually does. Even Nazi had to form their ideas of "superiority" and "rightful claim" of control in subjective terms -- though they used religious imagery and pseudo-scientific language, they neither required belief in any deity or creation myth, nor bothered to find scientific evidence of any kind. Their ideas are only "religious" in a way of "but won't it be nice if YOUR ethnicity was destined to rule the world?" as their first and last greatest proof of their ideas, not unlike "but won't it be nice if the world was ruled by benevolent deity?" is the first and last greatest proof of religion. It's a pretty weak analogy.
In that sense the Communist belief in Lysenkoism is a bit like the Catholic aversion to birth control. Neither were part of the original doctrine, but once you have priests or politicians that believe they have access to the absolute truth a bit sprouting is almost inevitable.
No. It's merely one person who gained favorable treatment by the government and massively abused the power he gained through it. This has nothing to do with religion and everything with government officials' irresponsibility and concentration of power. After the end of Stalinism in mid-50's, Lysenko's theories were thoroughly discredited, and it remains a single such event in the whole USSR history -- it taught post-Stalin governments to never mess with the content of scientific discourse, and limit government's influence to choosing directions to fund and support.
US propaganda loves picking such blunders in USSR history (almost exclusively taking them from Stalin's time) and present them as if they discredit wide aspects of USSR or Russian society, C
Parent
Re: (Score:3, Interesting)
Something I didn't realise about the Old Testament until recently is that when they talk of the the Philistines binding Samson in 'chains of iron' it's because the Philistines had managed to master the technology to use iron but the Israelites hadn't.
http://en.wikipedia.org/wiki/Philistines#History [wikipedia.org]
The Philistines long held a monopoly on iron smithing (a skill they possibly acquired during conquests in Anatolia)
Re:Uh, what? (Score:4, Informative)
It wasn't technology gap, it was arms control enforced during centuries of oppression. They certainly did have the technology, as the technology itself is described in dozens of passages. (Deu 4:20, 1 Sa 12:31)
But don't worry your arrogant little head about it. Other people are stupid and you are smart.
Parent
From TFA, quite sick, really. (Score:2, Informative)
Santa Cruz (CA) - Have you ever thought how vulnerable your data may be through the simple fact that you may be storing your entire digital life on a single hard drive? On single drive can hold tens of thousands of pictures, thousands of music files, videos, letters and countless other documents. One malfunctioning drive can wipe out your virtual life in a blink of an eye. A scary thought. On a greater scale, at least portions of the digital information describing our generation may be put at risk
Re:From TFA, quite sick, really. (Score:4, Funny)
That being said, i'm also not a fan of jacking myself up on drugs so I can "hack" wandering vehicles. I'm thinking any weapon I may wield in such a world would have to be capable of A, using some sort of warp singularity to disrupt all technological defenses of the target, and B, use that same singularity to power down the defender.
Why killem when you can simply turn them off? If that hot animated chick can kill people by fucking with their computerized brains, I can also generate singularity charges with my ham radio set and obliterate enemy cyborgs
Dear God, I really am overdoing the sarcasm lately, aren't I?
Parent
Maybe /. needs something that lasts a bit longer.. (Score:5, Funny)
tm
But what about... (Score:3, Insightful)
Since there will be many holes shot into this theory, let me be one of the first to fire a shot. Electricity (as we know it) may not be around then. I am not predicting the dark ages, but who's to say that far in advance there is still a live socket.
Any storage device that relies on outside power cannot be guaranteed for 100 years, let alone 1400. I would have more faith in a stone tablet.
This is a fine example of "academic" research dollars at work.
Re: (Score:2, Insightful)
Re: (Score:2)
As opposed to the pragmatic issues of industry, this long-term thinking is actually is the sort of problem that academia is supposed to tackle, because it sometimes gives the major breakthroughs which revolutionize life. Like, for example, some sort of giant computer system which would survive a nuclear attack... in case you really need those trajectory tables calculated remotely during nuclear winter.
And it does have pragmatic uses. It is a la
Re: (Score:2, Insightful)
I'm not sure how you expect electricity to 'change' in the future.
If a civilization can't generate electricity, then they wouldn't have the technical knowledge to even know what to do with digital data, so the whole point would be moot.
Wikipedia (Score:2)
Born for this job (Score:5, Funny)
What about filling it up? (Score:2)
How long will this array take to fill up the first time around?
A 10 PB storage system could be built for about $4700 with an annual operational cost (power for running and cooling the system) of about $50.
Unless 10 PB (petabytes) means something other than what I think (10,000 terabytes), where did they get the $4700 number?
I even read their definition of static cost [usenix.org] (You have to go up a few paragraphs) and I still don't know.
Re:What about filling it up? (Score:5, Informative)
Does $4.7 million sound a bit more realistic?
Parent
Steganography and P2P (Score:5, Funny)
Clearly, the answer for long term data storage is to use steganographic techniques to encode your data into various types of creative skinpics. Pick famous folks, pretty folks, strange fetishes... the whole gamut. Pick things that people will keep. A hundred years later, all someone needs is the key phrases to search for.
"We need that Higgs Boson experiment data from 2012, how will we get it? The infocalypse has destroyed all of our cataloged data!"
"No problem, my great grandfather left a note in his journal telling his descendants to search for 'Britney spears enema' and use 'wet riffs' to decode the LHC data in whatever we use for files."
"President Spears? That's crazy!"
Voila!
Sounds like it could be in a movie... (Score:2)
Constant data migration is the key. (Score:2)
Rotate your media (Score:3, Insightful)
In addition to taking advantage of the falling cost of storage for a fixed-size data set -- making future replacement media purchases much cheaper than redundant media purchases today -- you also have the opportunity to re-process the data into new formats, so that you'll still be able to read it when you want it.
Lasers. (Score:3, Interesting)
ah yes, here, [rosettaproject.org] that seeks to preserve all the languages of the world by laser-engraving them onto stainless steel plates. They've changed things up a bit, but the basic idea is the same: put it somewhere it won't get lost or corrupted, and if it's important, people will figure it out later. If it's not important, then it doesn't matter.
Very few things in the world are really worth keeping for even a lifetime. If your grandkids inherit all of your stuff, what will they save and keep, and what will they throw away? If you know what they will throw away, why not save them the trouble and toss it yourself?
We've gotten ourselves into this mindset where making backups of every piece of data you've ever owned ought to be saved, for no other reason than because it's easy and cheap. I think everyone should have a periodic storage meltdown to force them to reconsider what it is they really need to have.
Two methods for long-term reliable storage (Score:3, Interesting)
Electronic storage is by its very nature unreliable -- electromagnetic properties (like charge accumulation, ferromagnetic hysteresis, etc) are inherently volatile.
And even if you manage to solve the problem of transporting your data into the future, you're still faced with the problem of making sense of it. Electronic formats change (just ask the guy out in California who makes a *FORTUNE* charging law people to retrieve files from obsolete formats and/or media). In the physical realm, this is true as well - languages change and become very difficult to read. (If you don't believe me, try reading Beowulf in its original old-English form, circa 700 AD).
Why have physical storage at all? (Score:4, Interesting)
And I mean it literally -- why have any physical storage at all? Why not just bounce chunks of data around forever on the Internet? Presumably the 'net is going to be here for a long, long time. Imagine a mass P2P network where the data being traded is just encrypted chunks of the data of other users. It needn't ever get written to a mass storage device at all -- just received from one peer and immediately sent to others.
A protocol could be developed to allow one peer to request, or steer, the network to locate and deliver requested blocks on demand. This might be a high-cost operation, akin to bringing data in from backup tape. Or, a client could just wait for the right chunk of data to recirculate to its position in the network. But storing data is easy -- just encrypt it, format it a certain way, and inject it into the network.
A natural model for the topology of such a network, and the protocol itself, is the circulatory system. Here, cells move in a fluid, generally in one direction, but through a complex network of vessels, and in a circulatory manner. The immune system might provide inspiration for directed movement of data chunks. (See? The Internet really is just a series of tubes.)
Over time, the infrastructure of the Internet, the P2P clients, and the exchange protocol itself could evolve, as long as enough redundant chunks are allowed to constantly recirculate. Specialized clients could cache data to "long term" storage for periods of a few days or weeks, in case of large, random outages, but permanent data storage would never rely on any specific technology at all -- even TCP/IP itself. It's all just this mass of recirculating encrypted chunks of data, like cells in the blood stream.
Re: (Score:3, Interesting)
Good idea but some one first tried this in the 1950's The idea was to send the data encoded on a microwave beam and aim the beam at the moon. The signal would bounce off the moon and come back to Earth a few seconds later. A receiver would detect the signal and feed it back to the transmitter. Many thousands od bis would be stored in the radio signal.
This was an extention of
Idiotic (Score:5, Insightful)
First, it ignores physics. MTBF can't be used in reverse. Yes, it is possible that the MTBF on a newish disc is 300K hours or more, put differently, if you've got 1000 such discs running, then every 300 hours, about every 2 weeks, one will die.
This does however:
It would offcourse if degradation in idle state was -ZERO-. If aging made -ZERO- difference and if the MTBF-rates quoted are realistic AND constant over centuries (i.e. older discs DONT start to fail more often, not even if they're centuries old)
In short: bullshit. It's overwhelmingly likely that not a single disc out of 1000 will remain functional after a millenium, even if it is powered down 97% of the time. At which point no amount of redundancy, distributed or not, will help.
Also, the exersize is pointless. As long as storage-capacities keep growing exponentially, nearly the entire cost of storing a set of data is in the first few years. If you've paid what it costs to safeguard data for a decade, you've already paid 95% or thereabouts of what it costs to store it forever.
So, storing something safely for a very long time is actually a easy task, all you need to do is:
Yeah, this -does- mean that data that nobody cares about will die. Tough luck.
For example, if you -currently- have a petabyte you want stored, you could buy 3 petabyte enterprise storage-servers, at a cost of perhaps $3million. You host these at three separate companies, say one in europe, one in japan, one in usa. For this you may pay $300.000/year. Total cost for first 5 years: $4.5 million
After 5 years you buy 3 new entry-level storage-servers. Storage/dollar has doubled ever 18 months, or a factor of 12 over 5 years. The servers now cost let's say $300K, and they're 4U-units rather than complete racks now, so hosting-costs is down to $50.000/year.
Total cost for years 5-10: $550.000
After 10 years you buy 3 new 1U "small office" servers. They cost $21K in total. Hosting is $10K/year. Total cost for years 10-15: $71K.
After 15 years you sign up for the needed amount of space on 3 separate servers and pay $3K/year, or $15K for the period.
After 20 years you put the data on 3 thumbdrives and store them however one can cheaply store a thumbdrive, total cost perhaps $1000
Or you sign up with 3 separate el-cheapo hosting-providers and pay $300/year.
After 25, you send the data as an attachment to your choise of 3 free email-providers, they all come with atleast 500PB free storage anyway, it's not as if you'll notice the extra 1PB attachment.
More likely though, you've got much MORE data to take care of in the future, so you're still paying $1million/year. Only now that buys you a storage-solution where the old 1PB-archive is a completely trivial file, taking up a so minute fraction of the array that it's not even noticeable and the incremental cost is essentially zero.
Reinventing Honeycomb (Score:3, Informative)
Compare article with this whitepaper [sun.com], especially Figure 13 on page 28. Networked nodes with 4 disks each, grouped in cells of 16 + 1 management node. Each object is stured redundantly on disks of different storage nodes. Everything self-contained, accessible by nice API. Oh, and the software is Open Source.
missing the point (Score:4, Insightful)
No one is interested... (Score:3, Insightful)
Nobody but historians? (Score:5, Insightful)
I'm sure that the people in the 11th century would have said the same thing about their accounts and letters, and yet historians and archeologists depend on them to tell us what life was like 1000 years ago.
Parent
Major flaw in plan (Score:3, Interesting)
"In theory, practice is perfect; but in practice, it is often only theory".
Adeptus
Re: (Score:3, Funny)
Re: (Score:3, Funny)
Then, if a super-termite or some sort of paper eating worm ravaged the world and ate all the paper in the world, then we'd be in the same situation.
Re: (Score:3, Interesting)
You don't need a supertermite :)
Just an idiot with a political agenda and authority on his hands:
The Nazis used to burn books if I'm not mistaking.
Also, if I remember correctly, there was some pasha or other in the ottoman empire who said that either the kuran is the only truth and then other books have no purpose, or the kuran is not the only truth, and then the fact that there are other truths must be hidden; thus, he burned the library.
It only takes a bunch of idiots.