The Future of the Cloud Depends On Magnetic Tape (arstechnica.com) 164
An anonymous reader quotes a report from Bloomberg: Although the century-old technology has disappeared from most people's daily view, magnetic tape lives on as the preferred medium for safely archiving critical cloud data in case, say, a software bug deletes thousands of Gmail messages, or a natural disaster wipes out some hard drives. The world's electronic financial, health, and scientific records, collected on state-of-the-art cloud servers belonging to Amazon.com, Microsoft, Google, and others, are also typically recorded on tape around the same time they are created. Usually the companies keep one copy of each tape on-site, in a massive vault, and send a second copy to somebody like Iron Mountain. Unfortunately for the big tech companies, the number of tape manufacturers has shrunk over the past three years from six to just two -- Sony and Fujifilm -- and each seems to think that's still one too many.
The Japanese companies have said the tape business is a mere rounding error as far as they're concerned, but each has spent millions of dollars arguing before the U.S. International Trade Commission to try to ban the other from importing tapes to America. [...] The tech industry worries that if Sony or Fujifilm knocks the other out of the U.S., the winner will hike prices, meaning higher costs for the big cloud providers; for old-line storage makers, including IBM, HPE, and Quantum; and, ultimately, for all those companies' customers. [...] Although Sony and Fujifilm have each assured the trade commission that they could fill the gap if their rival's products were shut out of the U.S., the need for storage continues to grow well beyond old conceptions. Construction is slated to begin as soon as next year on the Square Kilometer Array, a radio telescope with thousands of antennas in South Africa and Australia meant to detect signals emitted more than 13 billion years ago. It's been estimated the project could generate an exabyte (1 billion gigabytes) of raw data every day, the equivalent of 300 times the material in the U.S. Library of Congress and a huge storage headache all by itself.
The Japanese companies have said the tape business is a mere rounding error as far as they're concerned, but each has spent millions of dollars arguing before the U.S. International Trade Commission to try to ban the other from importing tapes to America. [...] The tech industry worries that if Sony or Fujifilm knocks the other out of the U.S., the winner will hike prices, meaning higher costs for the big cloud providers; for old-line storage makers, including IBM, HPE, and Quantum; and, ultimately, for all those companies' customers. [...] Although Sony and Fujifilm have each assured the trade commission that they could fill the gap if their rival's products were shut out of the U.S., the need for storage continues to grow well beyond old conceptions. Construction is slated to begin as soon as next year on the Square Kilometer Array, a radio telescope with thousands of antennas in South Africa and Australia meant to detect signals emitted more than 13 billion years ago. It's been estimated the project could generate an exabyte (1 billion gigabytes) of raw data every day, the equivalent of 300 times the material in the U.S. Library of Congress and a huge storage headache all by itself.
So why doesn't somebody (Score:1)
Re: (Score:1, Funny)
You've got to shave a lot of Japanese to get enough material for magnetic tape obviously, it's a scaling issue.
Re:So why doesn't somebody (Score:5, Interesting)
Not as easy as your think. The startup cost would be enormous. Very few engineers know, in detail, about thin film technology, it's kinda a lost art. just ask Kodak . The equipment would have to be custom made, no one has manufactured them in decades and the old one have long since been hauled off to the scrap yard.
Re:So why doesn't somebody (Score:5, Informative)
Not as easy as your think. The startup cost would be enormous. Very few engineers know, in detail, about thin film technology, it's kinda a lost art. just ask Kodak . The equipment would have to be custom made, no one has manufactured them in decades and the old one have long since been hauled off to the scrap yard.
ATR Magnetics actually did this. They had their own coating machinery made. That's studio recording tape, though, so the tolerances will probably be a lot lower than for ultra-high density digital media on extremely thin backing.
Re: (Score:1)
Not as easy as your think. The startup cost would be enormous. Very few engineers know, in detail, about thin film technology, it's kinda a lost art. just ask Kodak . The equipment would have to be custom made, no one has manufactured them in decades and the old one have long since been hauled off to the scrap yard.
ATR Magnetics actually did this. They had their own coating machinery made. That's studio recording tape, though, so the tolerances will probably be a lot lower than for ultra-high density digital media on extremely thin backing.
ATR seems to manufacture audio recording tape, not archival data storage tape. Magnetic storage drives run much faster than audio recording ones and they cannot be spliced if they break. Thus the specs and manufacturing costs are much higher. To be profitable a new company would have to sign up major cloud storage companies. These companies prioritize reliability based on "track record." A catch-22 situation for a startup with no history.
Re:So why doesn't somebody (Score:5, Informative)
Go ahead. Let us know how it goes.
Hint: you have to be able to produce thin plastic ribbons (5.6 micrometres thick for LTO-7 and LTO-8) that are close to a kilometre long. They need to be 12.65mm (plus or minus .006 mm) wide. You then need to bind barium ferrite particles to those ribbons, in a uniform pattern, to be able to hold 6,656 (LTO-8) tracks in that width, with a linear density of 20,668 bits in every mm (per track). And the ribbon needs to be able to stand up to at least 20,000 end-to-end passes.
This is not a trivial problem, and finding people who have a head start on solving it who don't already work for one of those manufacturers will be... difficult.
Re:So why doesn't somebody (Score:5, Funny)
You mean it can't be 3D printed?
Re:So why doesn't somebody (Score:5, Funny)
3D? But you don't need it!
It's film, so it's 2D what we are talking here: a full 1D of net profit!
Re:So why doesn't somebody (Score:5, Funny)
We must apply blockchain to this!
Re: (Score:3)
Go ahead. Let us know how it goes.
Hint: you have to be able to produce thin plastic ribbons (5.6 micrometres thick for LTO-7 and LTO-8) that are close to a kilometre long. They need to be 12.65mm (plus or minus .006 mm) wide. You then need to bind barium ferrite particles to those ribbons, in a uniform pattern, to be able to hold 6,656 (LTO-8) tracks in that width, with a linear density of 20,668 bits in every mm (per track).
True, but you only really need to worry about coating, slitting and polishing. My understanding from audio tape is that you usually buy in the backing from Dupont or someone. It's still not a trivial process, but it's not impossible either.
Re: (Score:1)
Profitable isn't enough, this is probably why so many closed down (without much warning! four in 3 years and I don't remember any single news article)
Naively, something with a permanent 0.1% profit would be excellent, meaning all wages and taxes are paid forever, etc. But well, there's the whole financial economy and all that. So, 3% to 5% for an industry should do? That was the norm before the neoliberals took over everything. Better sell everything, set on fire the now worthless tape fabrication equipment
Re: (Score:2)
0.1% profit sounds terrible.
I'd want to at least beat inflation by a 1%.
a 2% TIPS being available would be the minimum return anyone with money would invest in I'd think.
Sure, if one is at 0.1% including depreciation, it doesn't make sense to close down, but it doesn't really make for a market one wants to invest in either.
Re: (Score:2)
Even grocery stores make more than that. I'd say a 3-10% profit margin would be useful.
Maybe do like gas stations -- have the media and drives be the low profit item, and then make the money on software or options. For example, the tape drives would ship with basic compression, password-based encryption, and crypto signing for WORM media. However, the tape drives could have optional licenses for more toys, such as better compression, deduplication, automatic expiration of media (so after a certain day, t
Re: (Score:2)
The problem is a number of things:
1: VCs want flash and sizzle. Tape is pedestrian, as opposed to some device that does little other than get compromised and send analytics back.
2: VCs want cheap. You cannot go the cheap route with tape.
3: There is a multi-trillion dollar push to get people to "the cloud". Tape goes against this.
4: There are many patents for density items.
5: There isn't a market for tape. Consumers don't care about backups, and businesses consider backups having no ROI for the most
Re: (Score:2)
The real problem with optical is that for the consumer market, there's insufficient demand to keep quality BD-R manufacturers in business, per my research this month, CMC is the least worst manufacturer today (!!!), I'm not sure any BD-R media below CMC's level is going to last even a year.... MAM-A is still making I assume quality CD-R and DVD-R media and today they're the only company I'd trust for those formats. E.g. Taiyo Yuden exited that business and sold their stuff to CMC.
Tape, well, even if Sony
Re: (Score:2)
As a consumer, for archiving, I use M-Disc [mdisc.com] in quad-layer Blu-Ray, which is 100 Gb per disc. Verbatim makes the discs I buy, and the drive was less than $100.
Re: (Score:2)
Re: (Score:2)
They're archives, so speed doesn't really mean much in the equation and the actual cost is around $15 per disc in lots of 5 from Amazon. My main focus is reliability, for this use. I can burn data to the disk, put it in a jewel case, and set it on a closet shelf at my parent's house and forget about it.
Honestly, the vast majority of consumers don't have 100 Gb of data they need to back up anyway. I only use 1 disc for family pictures, tax returns, non-media storage, and that is overkill. The rest is a back
long term solutions (Score:5, Informative)
Re:long term solutions (Score:5, Informative)
$150ish for 30tb of storage using LTO 8. WD Red 10tb drives are ~400ish. So storage cost is more like 8 to 10 times cheaper. And thats enterprise grade vs "prosumer" grade.
On top of that you need 3 drives to equal 1 tape. So storage costs are 3 times higher. Also I sure as hell wouldn't want to rely on a HDD spinning up for the first time after sitting on a shelf for 10 years, let alone 20 or 30 years. Sure it might, but I wouldn't want to rely on it.
As far as I am aware tape is currently the only viable long term archival storage method.
Re: (Score:1)
You forgot to add in ~$4k for a LTO 8 Drive, using that same $4k would get you ~100TB worth of HDDs (10x 10TB @ $400).
Re:long term solutions (Score:5, Informative)
Also, LTO-8 has only 12 TB of native capacity. Ostensibly, you can get up to 30 TB of storage per tape, but that's the best-case scenario. Realistically, you need to assume that you'll get 12 TB per tape, and if you get more, yay.
Re: (Score:3)
More to the point, $150 will buy you a basic 8 TB external hard drive [newegg.com] these days. So in the worst-case compression scenario, tape is only about 2/3rds the price of storing the data on hard drives, assuming you have sufficient physical space to store the hard drives, and ignoring the cost of the tape drive. (More to the point, if compression can let you store more data on tape, that same compression would also let you store more on a hard drive, so for a fair comparison, only the native capacity matters.)
A
Re: (Score:3)
Or just pay someone else to do it. Chances are you can't beat services that do this on a massive scale, with wide geographic distribution and duplication, and 3-9s SLAs.
For example Microsoft charges $720/year for 30TB off archive storage, plus a few hundred for bandwidth. I doubt you could do it cheaper with tape, especially when you factor in periodic upgrades, duplication and operating costs.
Re:long term solutions (Score:4, Insightful)
Re: (Score:2)
Really, dgatwood was comparing the price to Microsoft of a consumer USB 8TB hard drive to tape storage? And Harlequin80's concerns about a HDD spinning up after 10 years sitting on a shelf is something that they have to contend with in Microsoft datacentres?
Re: (Score:2)
No, I was approaching it from the perspective of a small business that didn't want to back up to the cloud. Most businesses don't need data to be available after a decade. The probability of something still having any value after it gets deleted rapidly approaches zero after a couple of months, and if it existed within the last couple of months, it should be in at least a couple of full backups and possibly incremental backups.
Re: (Score:2)
Re: (Score:2)
3-9s? That's worse than using 10-year-old HDDs, tossing them in a box, and then losing the box. I think you're off somewhere, but then is is MS so who knows. They sell their cloud services at a deep loss, so eventually that will change.
The best cloud archiving is S3 Glacier. It's roughly $50 per TB per year, and gives 11-9s SLA. You can avoid bandwidth costs with Snowball (or if you think in EB instead of TB, Snowmobile).
LTO8 is roughly $10 per TB, plus whatever Iron Mountain charges to store a box ful
Re: (Score:2)
3-9s is under 9 hours of downtime a year. It's hardly terrible, especially compared to what many companies use for in-house DIY solutions.
As for S3 Glacier it is cheap, but I think you are misunderstanding the 11-9s number. It's not an SLA for general availability of your data, in fact it's not even an agreement at all. It's their average reliability per year, in other words a 0.000000001% chance (1 in 1 billion) chance of losing your "archive", which is a zip or tar file up to 40TB. It's a marketing claim,
Re: (Score:2)
This claim of a one in one billion chance of losing your data is also patently false.
The annual odds of a large comet hitting the earth and wiping out the human race is higher than that. Without any humans, there's no way to retrieve the data.
Re: (Score:2)
Ahh, I see. But availability isn't very interesting for archives, where you generally have a few days to retrieve data (since traditionally that means having Iron Mountain deliver a box to you).
S3's SLA for availabilty is 3-9s IIRC. I think most AWS services are, though they've been working on doing better.
Really, though, cloud archiving will come down to "do you trust this company for the next 20 years", more than other considerations. MS and AWS at least have a track record for staying around and keepin
Re: (Score:2)
I think that'll entirely depend on the quantity of data you're storing, and how much you need to access it once it's stored. In terms of raw costs, Azure Archive level blob storage gets down to $0.02/GiB/month for one datacenter no geographic redundancy, whereas as a prosumer I can
Re: (Score:1)
Who might need 640 TB or more of storage? Let me see.
Video. 8K UHD: 7680x4320 pixels, or 33,177,600 pixels. HDR gives a bit depth of 10 bpp, for 40,500 kB per frame. 60 frames per second equals 2.3 GB per second. A two hour movie at that resolution, uncompressed, will be about 16 TB in size. Add in all the extra footage that will be shot, plus audio, and so forth, and it wouldn't take long for a movie (or TV!) studio to need multiple petabytes of storage. Yes, they can compress the data to a certain extent
Re: (Score:3)
Hear that whooshing sound?
Re: long term solutions (Score:2)
Ive never had an issue getting the compressed data amounts onto lto 5 tapes. I dont say any reason that lto8 would suddenly be different.
That said im looking at this from a large scale commercial archival perspective. And in those cases the tapes go off site to an environmentally controlled store.
Then you look at the ease of use you get when you add in tape libraries. For example ones that hold 24 tapes you start to see why they beat other storages.
Re: long term solutions (Score:2)
The point of the article is large scale storage for cloud. $4k on a drive is a rounding error in these scales.
When you are talking 1000s of tapes, and the humidity and temperature controlled archival storage costs the price of the drives is tiny.
Re: long term solutions (Score:2)
To date all lto drives have been backwards compatible.
Re: (Score:2)
Yep, normal rule is write one generation back, read two generations back. This only failed during their switch from metal particulate (MP) to barium ferrite (BaFe) as magnetic media, LTO-8 tapes won't read LTO-6, where either MP or BaFe magnetic media was allowed.
Re:long term solutions (Score:4, Interesting)
There's another factor you didn't consider that limits tape usage to very high volume use only. The tape is cheap, but the drives themselves certainly are not - for your LTO8 tape you need a £3000 drive, plus a server with its own RAID storage array to maintain the required transfer rate and an SAS controller. That's why tape completely disappeared from consumer use and almost disappeared from SOHO - you need to be thinking in terms of multiple hundreds of terabytes to justify the initial equipment costs, even if the tapes themselves are affordable.
Re: (Score:2)
For an enterprise the cost of the drives is the smallest part of the total cost.
If you are needing large scale long term archival storage you are using tape libraries anyway and they are far far more than 3000 pounds. Even then tape beats all other options currently.
Re:long term solutions (Score:4, Interesting)
If you're a prosumer like myself, who's been personally using magnetic tape since the late 1970s, you don't buy the very latest generation of LTO, you go back one or more generations. If you're good at scrounging, you should be able to get a tape drive with a lot of life for $1,000 or less, as I did in 2011 for a new HP LTO-4 drive which I'm still using, when LTO-5 was the new hotness. Today, without going to any real effort, I could buy a new LTO-5 drive from Newegg for $1,700.
A SAS controller is pretty cheap, ones based on the LSI200x chip particularly so right now. If you're patient, you only need a buffer device to avoid shoe-shining your tapes, rather than a fast RAID array. That is, you have your backup software write a 10GiB or so file at a time (probably ought to be larger for the newer LTO generations), and then stream it to the tape drive in one go. I use a Cheetah 15K drive right now, a DRAM tmp file would suffice, you can also scrounge higher end used but not used up Intel DC for enterprise datacenter 2.5 inch drives that were presumably taken out of service because their "small" capacity could no longer be justified.
All in all its quite practical, you have to do the math, including safe deposit box rental or whatever you choose for your offsite storage, and see if it makes sense compared to cloud vendors. Or you might not trust them to exclusively do your offsite backups, tape gives you a level of control you don't get from them.
Re: (Score:2)
There's another factor you didn't consider that limits tape usage to very high volume use only.
Tape is rarely cost effective for personal backup (though I'm sure there's a Slashdotter out there with a 1000 TB hentai collection), but for any company that has a meaningful amount of data it makes sense for archiving.
You need to be thinking in terms of multiple hundreds of terabytes to justify the initial equipment costs, even if the tapes themselves are affordable.
Yes, though calling "hundreds of terabytes" a lot of data sounds odd to me.
Re:long term solutions (Score:4, Interesting)
"Also I sure as hell wouldn't want to rely on a HDD spinning up for the first time after sitting on a shelf for 10 years, let alone 20 or 30 years. Sure it might, but I wouldn't want to rely on it."
That's again, a matter of costs. Tapes have a low marginal cost, which is their "natural" advantage. Hard disks are cheap because sheer volume, but their marginal costs must be higher, so they are cheap... as long as you can use off-the-shelve disks for your own purposes.
What I mean is, in this case, that nowhere says a hard disk must come with its own spinning engine. It's not that hard to think about a "hard disk" to be mounted on an spinning machine (that's basically what you do with tapes) so, on one hand, you cut per-unit costs (only one "spinning machine" for thousands of "disks") and increase reliability (having one engine per thousands of disks allows for building it sturdy and you use it daily instead of once in ten years). Problem? the same than tapes: unless you manage to make this "spinless hard disk" the industry standard, it becomes a niche application, which increases costs.
By the way, there isn't already a standard industry for spinless hard disks? solid state, or something like that?
Re: (Score:1)
What I mean is, in this case, that nowhere says a hard disk must come with its own spinning engine.
That's exactly what an Iomega Jaz disk was, with a hard drive platter in a removable cartridge while the motors and heads were in the drive itself.
Re: (Score:2)
And several "SyQuest" drives before that. Those 44MB/88MB cartridges were industry standard back in the day.
I even had a SyQuest EZ135, which was an attempt to compete with Zip. It had better performance than the Zip, but there was no way they could make those platters cheaper than a Zip disk.
One problem was the reliability/durability implications of people treating spinning platters the same way they treat tape. The other was the inability to keep up with the densities possible in fixed-spindle drives w
Re: (Score:3)
The "spinless hard disks" or SSD drives are much, much more expensive per Gigabyte than hard drives or tape.
Re: (Score:2)
"The "spinless hard disks" or SSD drives are much, much more expensive per Gigabyte than hard drives or tape."
Think about why there's such a big difference between SSD's and magnetic-anything and come back with your own answers.
By the way, for long-term/cold storage, won't you think a "drive" the size, say, of a shoe box could be a thing?
Re: (Score:2)
They're already quite common, they're a major part of the market for large, USB connected, spinning drives. They can require a bit of thought and caution to avoid disconnecting them while data is being written to the drive, but they're quite effective backup systems in small environments that cannot afford and do not need tape backup.
Re: (Score:3)
Kinda depends on what your aim is. Always on storage then hard disks. But not for archival purposes.
One example of stuff I have worked on is the storage of seismic data. It is simply too much data to keep hot all the time. Especially since most of it is never used. So it is stored on tape. It goes into an environmentally controlled building and goes into a data migration programme where the tapes are read onto new media every 10 years.
I'm sure there is no technical reason you couldn't drop HDD platter
Re: (Score:2)
Removable disk hard drives have been here since the earliest days. Sealed disk was an invention along the way. It isn't an accident that the latter technology now dominates - you just can't do modern HDD densities without a controlled environment. Heck, all my recent HDDs are helium-filled.
Tape gives you a much larger surface area for a removable cartridge than you're ever going to get with disk, which is why latest-gen tapes generally store more than latest-gen HDDs, despite the limitations of "uncontro
Re: (Score:2)
What I mean is, in this case, that nowhere says a hard disk must come with its own spinning engine.
It's a cost and space issue. Making a good interface between the motor and the spindle which will function at 7200+ RPM is extremely nontrivial. It will take up space and it will add complexity to the system. Currently everything is mounted firmly to the same chassis, it's simple and convenient.
Re: (Score:2)
"It's a cost and space issue."
No, it isn't. Look at the main article, we are talking here about entire buildings for long term storage. It is about, as I said, mainstream vs niche.
"Making a good interface between the motor and the spindle which will function at 7200+ RPM is extremely nontrivial"
Of course it isn't. And you need it that way why...? Maybe because you want mean seek times in the miliseconds league? And why hard disks are about A5 size or less? Maybe because we are talking about all-purpose
Re: (Score:2)
Lubricants aren't necessarily designed to survive that long, especially at room temperature. Glues can eventually fail. Heads parked on disk surfaces might build up too much stiction. The plastic in the flexible ribbon cable that connects the fixed electronics to the disk arm might degrade.
Then there's non-moving stuff, flash memory will lose its charge g
Re: (Score:2)
Sounds like sticky-shed syndrome [wikipedia.org]. Maybe Intel was unlucky in the tape manufacturers they bought from? Or like way too many other companies, were careless about the environmental conditions they were kept?
But you raise a good point, we really don't know if these tapes will still be readable in 30 years. It's just that tape has about the best record in affordable digital longevity. If you want better and also proven, microfilm and fiche might be your best bet, assuming you can still buy it and the equipme
Never underestimate the bandwidth of a.. (Score:2)
..truck loaded full of magnetic tapes.
write bandwidth... (Score:2)
transfer bandwidth is something quite different from job complete time
by the time you write to all those tapes the Square Kilometer Array will have generated more data...
they wont be using tapes for transfers...
Re: (Score:2)
I was going for funny. But, theoretically assuming the antenna array was operating continuously 24/7, then a few thousand tape drives all writing in parallel would significantly reduce the write bandwidth problem.
The write bandwidth of any tape backup array needs to be at least as much as the average capture/save bandwidth of the data, otherwise it would never complete. In reality, that array would either pre-process some amount of data before archiving and/or only capture data in bursts - so total archival
Re: Never underestimate the bandwidth of a.. (Score:1)
The first time.
Twenty years ago.
Re: (Score:2)
Well, it was "a station wagon full of tapes hurtling down the highway" when I first read it Tannenbaum's Computer Systems textbook. And it's still funny twenty years later (mildly or otherwise), because it's still true.
In fact the SETI project still does exactly this to deal with insufficient internet bandwidth by transferring data in the form of a big pile of magnetic tapes from the radio telescope array in Puerto Rico to California for analysis. Which as alluded in the summary is a problem that may exist
AI compression. (Score:2)
Construction is slated to begin as soon as next year on the Square Kilometer Array, a radio telescope with thousands of antennas in South Africa and Australia meant to detect signals emitted more than 13 billion years ago. It's been estimated the project could generate an exabyte (1 billion gigabytes) of raw data every day, the equivalent of 300 times the material in the U.S. Library of Congress and a huge storage headache all by itself
Good thing we just had a Slashdot article about intelligent compression. Even though most poo pooed it as not needed.
Re: (Score:2)
about 10 years ago (Score:2, Interesting)
I was talking with a coworker still at a former employer. He said their tape budget was up to $100k/month, that they were doing nearly a petabyte every night in backups. This company is still around and grown bigger since. They're not as big as Google, but they're up there.
Does not surprise me that this is still big business.
FINALLY. Something I can understand. (Score:2)
the project could generate an exabyte (1 billion gigabytes) of raw data every day, the equivalent of 300 LoCs.
Bytes, meters, inches, gallons, tons, carets, troy ounces, femtoseconds, microwatts -- pshaw, I was WONDERING when we were going to get back to normal units of measurement. Now who wants a pony?
Back on Topic: Never underestimate the bandwidth of a station wagon full of tapes hurtling down the highway. -- A. S. Tanenbaum
Re: FINALLY. Something I can understand. (Score:2)
Unless it's in a convoy, the bandwidth is low. The latency is terrible.
Re: (Score:2)
A unit of measurement that requires calculus to translate. Since the amount of data in an LoC is continuously changing by a variable amount of delta... I mean is there an LoC service I can ping like NTP to get the current value of its scale? Can I get access to historical data? I'm trying to read an article from 1992 and am having trouble understanding the scale it's trying to convey in 1992 LoCs!
I really need to sort out the conversion algorithms to other useful units of measure like:
LHCDO (Large Hadron Co
Does magneto-optical tape exist? (Score:3)
Is there any particular reason why nobody makes a product that's basically like non-LTH (phase-change/magneto-optical) BD-R, but on a flexible film substrate stored on reels instead of bulky discs?
The main problem I see with magnetic tape is that it's inherently susceptible to stray magnetic fields (including the Earth's poles). In contrast, phase-change media can theoretically have a passive lifespan that's measured in decades (centuries, if "being able to read it with normal, consumer-grade hardware as a normal OS filesystem" isn't a hard requirement, and you can deal with forensic data-recovery using exotic purpose-built hardware).
Re: (Score:2)
I'd guess that it's hard to optically read tracks that are spaced at a micrometer apart from each other when all 10000 tracks across the width of the tape need to be read in parallel. If you look at the read/writd head in a dvd player, you see that it's about a centimeter for the lens and the suspension around it, and it can only read one track at a time.
You'd also need a tape substrate that is opticaly clear, thin, and still strong and capable of preventing the data carrying chemicals from degradation.
Re: Does magneto-optical tape exist? (Score:2)
There was research into liquid crystal memory, which could have been used like optical tape, but it proved to be impractical in reality.
Re: (Score:2)
That's not quite how LTO tape drives work, they have tape heads with 8 parallel read/write heads for LTO-1 and -2, 16 for -3 through -6, and 32 for -7 and -8. After writing a "wrap", a single end to end pass, the tape head moves a bit and writes another, partially overlapping the previous set of tracks in the style of SMR hard
Re: (Score:3)
The cost of developing such technology doesn't justify it. Tape is good enough, companies are used to storing it securely for the long term, and they already have tape drives to read/write it.
Re:Does magneto-optical tape exist? (Score:5, Interesting)
These tapes are in massive libraries. Typically you string ~16 rack sized chassis together, which using LTO8 will give you around ~300PB of uncompressed storage. We are talking the likes of the IBM TS3500 or the newer TS4500. The other two players in the market are SpectraLogic and Oracle/StorTek who have similar libraries. With the TS3500 you used to be able at least to get a passover option so you could string 15 rows of libraries together for insane amounts of storage.
The only thing I doubt in the article is the rubbish about Iron Mountain. If you are Google/Facebook/Amazon etc. you just replicate your data to one of your many remote data centers. No point messing about having humans physically handling tapes on a daily basis (well other than feeding Audrey with new tapes). To be honest actually having your tape library onsite is a fairly dumb tactic anyway as there is a good chance the reason you need to use your backup is because the data centre has been transformed into a pile of smoking rubble or a large swimming pool.
Finally when you need to change tape technologies you just have the software copy it from the old tapes to the new tapes, and if they are all in the library while it might take several months it does not involve human interaction. Other than take old tapes out and putting new ones in every few days. You are going to need to do this probably every 6-7 years if you stretch it so the tapes only need to be able to reliably store data for say 10 years. That said provided it is stored in the correct environment LTO is good for 30 years from memory.
Re: (Score:1)
The only thing I doubt in the article is the rubbish about Iron Mountain. If you are Google/Facebook/Amazon etc. you just replicate your data to one of your many remote data centers. No point messing about having humans physically handling tapes on a daily basis (well other than feeding Audrey with new tapes). To be honest actually having your tape library onsite is a fairly dumb tactic anyway as there is a good chance the reason you need to use your backup is because the data centre has been transformed into a pile of smoking rubble or a large swimming pool.
Best practice for a while has been disk-to-disk-tape. Trying to go from the backed-up client directly to tape will cause shoe shining for a while now (even with multiplexing streams).
So back up your clients to a VTL, replicate the first copy of the data to another DC to a second VTL, and then if you need to keep the data around for more than "x" weeks, replicate it a third time to actual-tape.
Generally one would also probably have snapshots on traditional file stores, so one probably doesn't even have to go
Re: Does magneto-optical tape exist? (Score:2)
Oh dear, someone else who's knowledge is well out of date. Since LTO4 the tape speed has been variable to avoid shoe shinning. That is the drive will adjust the tape speed to match the incomming data rate. That said I have only used TSM (all other backup products being rubbish in comparison) and yes best practice is to have a fast disk pool for you daily churn, which is then punched out to a primary and copy pool of tape. You only need a VTL if your backup software is junk (aka not TSM/Spectrum Protect) or
Re: (Score:2)
Which I can most certainly hear as my HP lower end LTO-4 drive reads data off my 15K Cheetah hard drive buffer. But what can the drive do if it doesn't get data for some number of seconds? How low is the lowest rate it will accept data without having to periodically stop the transport?
Re: (Score:2)
IBM TS4500 R3 Tape Library Guide [oreilly.com]
IBM TS1150 tape drives deliver the fastest and largest capacity drive for enterprise archiving and data protection [ibm.com]
Woof! The rest of the text would make paint cry.
That makes 230 PB of uncompressed storage.
But there's a more
Re: (Score:2)
https://reellibrarians.files.wordpress.com/2012/04/brainstorm-closeup.jpg
Re: (Score:2)
As tape storage capacity increases you normally consolidate the older tapes onto the newer tapes to save on space and to eliminate to issue of not being able to read the tapes with onsite tape drives. We use automated tape libraries to handle the mounts/copies/ejects. Software knows whats on every ocr labeled tape and scheduling/tracking/expiring of tapes going to/from offsite facility is automated.
This has been standard procedure for decades. Nobody plans on tapes sitting out there for decades, they're con
Re: (Score:2)
That would be silly... but what if you took the basic idea and applied it to laser-exposed microfilm? Sure, it might be slow to expose & probably require off-site developing... but once you had it done, you'd have a storage medium that could passively survive decades, maybe centuries.
The fundamental problem with any data-storage mechanism that requires active handling every few years to preserve it going forward is the fact that such data is unlikely to survive long enough to BE of interest to future hi
So long as the sync is good (Score:2)
Parallel file store onto striped tape systems provides the best throughput for serial data.
Scientific data can be stored using parallel NetCDF, which is designed for such cases.
Tape is useless for random access, but that's not what you do with backup/restore or simple data logging from scientific instruments.
Durability (Score:3)
Isn't it funny? (Score:2, Interesting)
Re: (Score:3)
How is the government intervening here? The two competitors are lobbying the government to ban the other, and the government is refusing to intervene.
What part of the cost is tape cost? (Score:2)
>meaning higher costs for the big cloud providers
What part of the cost of the cloud-keeping is tape cost?
Cant you just (Score:1)
You know backup your cloud to another cloud? Who needs this old fangled tape tech. LOL!
Tape drives (Score:1)
This just makes me remember at some point in the 90s when I was struggling with my 1GB hard drive and wanted more storage space. I'd heard about tape drives and DESPERATELY wanted one. I knew nothing more than they could hold a lot of stuff. Would be cool to just keep around as a memory these days.
I'm pretty sure I was under the impression that I could install computer games and such to it at the time, but I'm not sure if that's what I actually thought.
Fahrenheit 451 (Score:2)
THESE guys still make magnetic tape (Score:2)
MOAR and MOAR features (Score:1)
Holographic storage? (Score:2)
Tapes not reliable (Score:2)
10 years ago we backed up using tapes. Always always always had issues with reliability of the data on them. Talking to peers, everyone experienced these problems. I don't see anybody talking about it here... am I missing something?
Re: (Score:2)
You're missing something. I've used tape since the summer of 1978, DECtape then, BASF magtape in the 1980s, Sony DDS in the 1990s, Fujifilm and "HP" LTO-4 in this decade, and never had problems. Perhaps you bought tape from one of the companies that just happened to drop out of the market? Sure you stored them properly, and didn't let the drive temp get too high while writing them?
This is the first I've heard of LTO tapes having systemic problems, aside from one machine room incident where the HVAC faile
Re: (Score:2)
Unless it was with audio tapes on a Commodore. Those were pretty flaky.
Re: (Score:2)
Yeah, that's not a use for which the tapes were intended. I still got the impression in the late 1970s from my friends with various audio tape systems attached to their microcomputers that the Commodore PET's was the best of all of them. AlphaMicro also had a VHS videotape based backup system around that time, which my family decided not to mess with. DECtape of that era? Rock solid in my summer's use of one. Magtape in the 1980s, ditto.
Magtape in the 1950s was used as an alternative to cards for prima
Re: (Score:2)
The only advantage magnetic tape has is it can hold more data.
Classic Slashdot
Re:Disks are superior (Score:4, Interesting)
It's completely unclear the BD-R optical discs consumers can get their hands on are superior, let alone more durable. CMC seems to currently be the least worst manufacturer, all the higher quality manufacturers have stopped making them, and they're obviously not highly trusted because of their history with previous generations of optical media.
For DVDs, I'd go with MAM-A, silver or gold, ditto CD-Rs, which I trust a lot more than DVD recordable media, since pressed DVDs pushed red laser CD technology as far as possible. (Taiyo Yuden exited the optical disc market in 2015, selling their stuff to CMC.) Therefore not going to calculate their costs, especially since their small capacity will start to really affect your off-site storage costs, unless you can stash them with friends or family, and trust them to keep the environment in which they're stored within the requirements (both tape and optical discs are picky here, that's the one advantage hard disks have over them.
Now we get to capacities, if you're going for low costs, single layer is where it's at, 25GB for BD-R, 4.7GB for DVD-R. Compare to 800GB native for LTO-4 tape, back when they were not ancient you could get new high quality Fujifilm ones for ~$22 in lots of 20, I now see a price of $14.70. I see today that Newegg is selling LTO-5 1.5TB native quantity 1 at $23, LTO-6 2.5TB native at $32, and LTO-7 6TB native at $82 (that's less than $1/TB more expensive than LTO-6), and a quick check at Amazon shows their LTO-6 and -7 prices are not competitive, even before we get into quantity discounts, which are the standard way to buy tape.
Comparing my first purchase of 25 Verbatim 25GB BD-Rs just this month from Amazon, to a quantity 20 price from a 3rd party I trust, Malelo and Company, for LTO-6 tape, we're talking $0.0352/GB vs. $0.0105/GB. LTO-5 weights in at $0.013/GB and LTO-4 at $0.0184. And I trust tape from Fujifilm infinitely more than I trust BD-Rs from CMC. Ah, Verbatim at quantity 50 BD-Rs only gets you down to $0.0306/GB.
Re: (Score:1)
A few years back, I upgraded my storage server, new CPU, RAM, and a half dozen 4TB drives in a raidz2. Went from a few hundred gigs on failing old drives to 15 TBs. I had more space than I knew what to do with, so I started trying to bring everything I had burned to CD and DVD back online.
My old CDs from the 90s worked ok (yay Verbatim and old school TDK!) and I was able to read almost all of them after some cleanings. The DVD-R's were a different matter entirely. After as little as 5 years, they had degrad
Re: (Score:2)
DVD-R technology is very marginal, the original pressed DVD version pushed red laser technology as far as it could go. But you still have to buy quality media, for CD-Rs I went with Taiyo Yuden (early on branded as Fujifilm in the US) and not a single one has failed me yet.
For DVD-R I got some from Taiyo Yuden as well, but didn't trust them if for no other reason than that they only cost a cent more than their CD-Rs. MAM-A gold DVD+Rs were my target for "archival quality", ought to test the few that I cut
Re: (Score:2)
Tape drive prices are all over the place, there's lots of variables there including of course speed and generation, but you're completely off about media. Amazon prices from a good 3rd party company I've done business with before, Fujifilm tapes, for LTO-6, we're talking $0.0352/GB, LTO-5 weights in at $0.013/GB and LTO-4 at $0.0184.
Newegg prices for 8TB drives, the current sweet spot in capacity, range from $0.0256/GB to $0.0325 for the lower end of the 5 year warranty 550TB bandwidth/year enterprise driv
Re: (Score:2)