Beta
×

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

Thank you!

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

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

How the LHC Is Reviving Magnetic Tape

samzenpus posted about a year ago | from the what's-old-is-new dept.

Data Storage 267

sandbagger writes "The Large Hadron Collider is the world's biggest science experiment. When spinning, it reportedly generates up to six gigs of data per second. Today's six-terabyte tape cartridges fill rapidly when you're creating that amount of material. The Economist reports that despite the advances in SSDs and hard drives, tape still seems to be the way to go when you need to store massive amounts of digital assets."

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

Never underestimate the bandwidth (4, Funny)

Gothmolly (148874) | about a year ago | (#45574963)

Of a station wagon loaded with tapes.

Also, -1, Duh, because this is an obvious, stupid article.

Re:Never underestimate the bandwidth (1)

Danathar (267989) | about a year ago | (#45575023)

Why use a Station Wagon? Why not a 747?

Re:Never underestimate the bandwidth (3, Funny)

NatasRevol (731260) | about a year ago | (#45575307)

Ping times.

Re:Never underestimate the bandwidth (1)

Thanshin (1188877) | about a year ago | (#45575309)

Why use a Station Wagon? Why not a 747?

$/GB

Re:Never underestimate the bandwidth (5, Funny)

Dachannien (617929) | about a year ago | (#45575369)

Why use a Station Wagon? Why not a 747?

When's the last time you saw a 747 with that totally swank wood trim on the outside?

Re:Never underestimate the bandwidth (4, Interesting)

Isca (550291) | about a year ago | (#45575029)

Actually I found the article informative. I knew tapes were the cheapest and most cost effective backup solution but I didn't realize that they were so fast once the tap has been loaded.

It's also interesting to see the advances in tape reading technology that they are striving for - it sounds as if it will keep pace with HD and SSD technology to keep staying relevant.

Re:Never underestimate the bandwidth (5, Interesting)

SuricouRaven (1897204) | about a year ago | (#45575215)

Cheapest, sort of.

The price of storage roughly follows the y=mx+c linear graph: m is the cost of the media, while c is the cost of the equipment needed to access it.

For hard drives, it's easy: c=0. A drive is self-contained.

For tape, c is large (Up to several thousand pounds for one tape drive), but m is smaller (Tape, purchased in bulk, is cheap).

So if you're storing a small amount of data, a rack full of hard drives is cheaper. For larger amounts, tape is cheaper.

This ignores issues of ease of access and management software.

Re:Never underestimate the bandwidth (0)

Anonymous Coward | about a year ago | (#45575331)

c is not 0 for hard drives. It is only zero up until you reach the maximum capacity in drives for your particular computer. For example, if you have a notebook it can usually hold either one or two drives. If you want another, c is not zero. (You could say, ah, but I have USB, but even that has a maximum number of connections and doesn't scale well to large numbers of drives). You end up needing a way to group and access the drives. It can be something as simple and small as a Dobo unit or as large and complex as a Hitachi SAN. But you cannot call c 0 for arrays of hard drives.

Re:Never underestimate the bandwidth (2)

SuricouRaven (1897204) | about a year ago | (#45575505)

Only if you need to access them all at once.

My library for a long time was in the form of a row of drives sitting on the shelf, and a hot-swap bay.

Re:Never underestimate the bandwidth (1)

GTRacer (234395) | about a year ago | (#45575847)

Wouldn't that make your c the cost of the hot-swap bay?

Re:Never underestimate the bandwidth (1)

wed128 (722152) | about a year ago | (#45576015)

Nope, the hot swap bay is a convenience. The drives are accessible without it.

Re:Never underestimate the bandwidth (1)

aaarrrgggh (9205) | about a year ago | (#45575367)

Tape works very well for applications where you have a large number of archival batches; us use the fixed resources (parent's "c") more per TB storage. Once you have a tape silo with 100,000+ slots, your incremental storage costs are very small.

Re:Never underestimate the bandwidth (2)

eek_the_kat (249620) | about a year ago | (#45575495)

interesting graph, but I think your explanation on C is a little muddy. I would just say C is the initial cost before any storage medium is acquired.

Re:Never underestimate the bandwidth (4, Informative)

dshk (838175) | about a year ago | (#45575423)

Yes, they are surprisingly fast. The maximum speed of a current Tandberg LTO-6 drive is 160 megabytes/s if the data is uncompressable. With the usual compressible data it can be about 320 megabytes/s (officially 400).

These drives can even be too fast. The drives do speed matching, but they have a minimum speed, below that they start shoe-shining. One reason I have chosen an older generation, LTO-3 tape drive, instead of the current generation, because I cannot easily feed an LTO-6 with at least 60 MB/s, which is the minimum speed of the drive. Considering compression, that is about 120 MB/s, which saturates a 1Gb network.

Re:Never underestimate the bandwidth (0)

Anonymous Coward | about a year ago | (#45575485)

That's not exactly surprisingly fast.
160MB/s is ~average linear transfer rate of a current 7200RPM 1TB/platter 3.5" consumer HD.

Re:Never underestimate the bandwidth (5, Informative)

dshk (838175) | about a year ago | (#45575951)

Sequential access speed is only relevant if you backup huge non-fragmented files or entire raw partitions, and nothing else.

Re:Never underestimate the bandwidth (4, Interesting)

TooMuchToDo (882796) | about a year ago | (#45575901)

I used to work on data taking for the CMS detector at the LHC. We were using Storagetek tape silos [http://computing.fnal.gov/cdtracks/2009/january/images/robot.jpg [fnal.gov] ] for long-term storage of data at Tier1.

Tape allows for cheaper storage and large capacities, but you're then fighting contention issues (there are only so many robotic arms and tape drives for your tape library) as well as having data on tapes go bad without knowing it. When data is on disk, I can at least verify it immediately. Bit rot is definitely alive and well on tape.

Re:Never underestimate the bandwidth (0)

Anonymous Coward | about a year ago | (#45576031)

the first thing that entered my mind upon seeing the picture in the parent comment was a voice that said: "Stop, Dave. Will you please...?"

Re:Never underestimate the bandwidth (4, Informative)

Doc Hopper (59070) | about a year ago | (#45575911)

The drives do speed matching, but they have a minimum speed, below that they start shoe-shining.

Agreed. At my work we do parallel streams to multiple Sun T10000 T2 tapes (T10K "C" drives) at 250Mbyte/sec uncompressed (500 megabytes per second compressed, more or less, usually quite a bit more). If for some reason we push less than about 120mbytes/sec, the tape rewind times cause all kinds of issues.

We make the same kind of decision when choosing Sun T10000 "B" drives instead of "C" or the new "D" drives if the source cannot push data fast enough.

I've long laughed at articles saying tape is dead. For large-scale* backup, retention, transport, and legal hold problems, there simply is no other solution that scales reasonably well.

*My definition of "large-scale" for this specific context: hundreds of terabytes or more, much of it transported thousands of miles regularly. If you don't work with hundreds of terabytes and at least dozens of petabytes on a daily basis, you may suffer from optimistic delusions regarding disk storage capabilities, one which disk storage vendors are all too glad to reinforce, to the detriment of customers faced with half-baked solutions that cannot hope to meet their throughput requirements. Given "large-scale" data, there's no replacement for tape at present; everything else is a low-throughput also-ran, typically harboring enormous and unplanned complications. We're also heavy users of VTL, replication, cloning, S3-workalikes, and various disk technologies. Tape remains vital to large enterprise operations, and those predicting its imminent death have been the butt of jokes about marketing wonks for a decade and a half.

Re:Never underestimate the bandwidth (0)

Anonymous Coward | about a year ago | (#45575675)

Actually I found the article informative. I knew tapes were the cheapest and most cost effective backup solution but I didn't realize that they were so fast once the tap has been loaded..

Fast, *if* you want all the files, and you want them in order. If you need just 1MB from the middle of that 6TB block though, the effective speed becomes quite low.

Re:Never underestimate the bandwidth (1)

Anonymous Coward | about a year ago | (#45575169)

A station wagon load with microSDXC cards surpasses it by an order of magnitude:
LTO-6 - 2.5TB
200g -> ~80 gram/TB
231142.2mm -> ~92500mm/TB

uSDXC - 64GB
0.5 gram -> ~8 gram/TB
165mm -> ~2580mm/TB

that's cubic mm, slashderp eats ³

Re:Never underestimate the bandwidth (0)

Anonymous Coward | about a year ago | (#45575285)

It's about cost, not total bandwidth. We could also put the miroSDXC cards in a Ferrari.

Re:Never underestimate the bandwidth (0)

Anonymous Coward | about a year ago | (#45575301)

Which is why GP wrote
"Never underestimate the cheapness of a station wagon loaded with tapes"
oh, wait...

Re:Never underestimate the bandwidth (1)

CreatureComfort (741652) | about a year ago | (#45575375)

But both will still be stuck doing 25 mph on the outer loop during rush hour.

Re:Never underestimate the bandwidth (1)

rossdee (243626) | about a year ago | (#45575565)

Ferraris don't have a lot of trunk space.
You could try a stretched Limo.
The British company Daimler (which was owned by Jaguar) used to make a nice limo with a huge boot (that's trunk for people born in the USA)

Re:Never underestimate the bandwidth (1)

jonbryce (703250) | about a year ago | (#45575821)

A Ford Transit would be better for that sort of thing.

Re:Never underestimate the bandwidth (0)

Anonymous Coward | about a year ago | (#45575941)

The Porsche Boxter has front and back trunks which gives it a ton of room.

Re:Never underestimate the bandwidth (1)

cdrudge (68377) | about a year ago | (#45575513)

I've yet to see an automated uSDXC storage silo, a flash drive that's rated for thousands of insertions and removals, and the time to swap cards kills the size advantage because you're swapping out media about 40x more often.

Re:Never underestimate the bandwidth (0)

Anonymous Coward | about a year ago | (#45575857)

1. "I haven't seen one " != "You can't design one".
2. Sockets rated for 10000s of insertion cycles are available off the shelf. Make the socket carrier modules swappable and you get another few orders of magnitude.
3. You'd need some sort of magazine that allows easy handling and automated loading/unloading... engineering challenge, but certainly doable without adding too much extra bulk.
4. A library could easily have dozens to hundreds of readers/writers.

Of course that ignores the major issues of reliability (SD cards seem to like to die for no apparent reason) and $/GB (tape wins by 2 orders of magnitude).
But then we just wanted fucktons of bandwidth.

but what about cheap disk? (1)

alen (225700) | about a year ago | (#45574993)

i remember a few years back backup to "cheap" disk was all the rage. if you were backing up to tape you were seen as some kind of mental patient

tape has its issues, but sucking up money like a trophy wife isn't one of them

Re:but what about cheap disk? (2)

jones_supa (887896) | about a year ago | (#45575073)

I also sometimes get the "mental patient" stamp for saying that I still use optical discs.

I just cringe the idea of storing long term archived data using an electric charge (flash, HDD, tape). Optical disc has also the benefit of being truly read-only so that you or a piece of malware cannot destroy the data afterwards by software.

Re:but what about cheap disk? (3, Interesting)

MightyMartian (840721) | about a year ago | (#45575133)

It depends on the optical disc. If you fork out the money for an archival media like gold CDs or DVDs, then you can probably expect something like 20 to 40 years. All in all, from what I've read, tape still is king in long term storage.

Re:but what about cheap disk? (1)

drinkypoo (153816) | about a year ago | (#45575527)

We've already seen some of the long-life optical discs fail long before their life was supposed to end. Tape in a cool, dark place is the answer.

Re:but what about cheap disk? (3, Informative)

Doc Hopper (59070) | about a year ago | (#45576009)

long-life optical discs fail... [store] tape in a cool, dark place...

This, this, one-thousand times this. I've worked in data centers for a decade and a half, and seen innumerable optical media go bad within just a few years (typically about 3 years) even in DVD jukeboxes in climate-controlled environments. Meanwhile, we restore from fairly ancient tapes on a regular basis.

In reality, most companies don't store tapes longer than 7 years anyway; that's the upper limit of typical audit liability. The data on the tapes may be older than that, kept indefinitely on-disk, but most large companies have a fairly aggressive destruction/over-write schedule for data on tape older than 7 years.

It's very unlikely we'll need data off a tape 20 years from now, but kept in the right conditions -- like the bat-cave of a tape silo room housing tens of thousands of 10TB tapes a few feet away from me right now -- there's a really good chance the data will be readable. While we do have plenty of tape failures (hundreds per year), they are almost always caught at write-time by the verification head.

On a modern tape drive, you usually have several dozen "heads" on any given tape drive, and there will be two sets of them each with its own mechanism to align it with a precision of just a few microns. Pretty amazing, really; if you drop by the Denver, CO area some time, the Oracle/Sun building engineers there can often arrange a tour of our tape testing facilities if you sign a NDA and represent a potential sale. Anyway, the second mechanism will be engaged on the tape in order to read what the first just wrote and verify it before it passes the "successful write" confirmation back up the fibre channel chain. This way you can guarantee you don't get "write once, read never" media.

Re:but what about cheap disk? (1)

sexconker (1179573) | about a year ago | (#45575967)

It depends on the optical disc. If you fork out the money for an archival media like gold CDs or DVDs, then you can probably expect something like 20 to 40 years. All in all, from what I've read, tape still is king in long term storage.

"Archival" optical discs are a scam. They fare no better than Office Depot brand shit.

Re:but what about cheap disk? (1)

SuricouRaven (1897204) | about a year ago | (#45575243)

Writeable optical storage has severe issues with longevity. The medium is chemical in nature, and degrades over time. Optical discs are fine for short term, but don't depend on them still being readable in even a year.

Re:but what about cheap disk? (0)

Anonymous Coward | about a year ago | (#45575591)

http://www.mdisc.com/
This one has an inorganic recording layer that is supposed to last longer.

Re:but what about cheap disk? (4, Informative)

MightyYar (622222) | about a year ago | (#45575253)

Just be careful - optical disks degrade, too. Years ago before hard drives became so incredibly dirt cheap, I would do my little video editing thing and then back up the project files to DVD. And not just any DVD - I did my homework and found the best-rated archival DVDs (sorry, don't remember the brand - only that they came from Japan). Anyway, I just sucked them back onto my NAS, and some of them had developed a teeny bit of unreadable data. Fortunately, I had made PAR2 files for everything. Between par2repair and ddrescue, I was able to recover the data. But the moral of the story is don't rely on optical disks to be magical storage that does not degrade.

Re:but what about cheap disk? (0)

Anonymous Coward | about a year ago | (#45576101)

Taiyo Yuden was the brand I bet.

Re:but what about cheap disk? (0)

Anonymous Coward | about a year ago | (#45575297)

HDD and tape don't use an electric charge, but magnetization. And note that optical discs, especially the writeable ones, also have limited life time (indeed, if you don't buy a good one, your data may vanish much faster than on tape).

Also, if you read the disk from the burner, I'm note entirely sure that a malware could in no case ever convince the drive to switch on the write laser over an already-written disc area. Which certainly would destroy it (it should however be safe from manipulation).

Re:but what about cheap disk? (0)

Anonymous Coward | about a year ago | (#45575363)

I have plenty HDs from the early-mid 90s that can still be read without any issues.
Meanwhile very close to 100% of my "archival grade" CD-Rs have degraded far enough to show 1000s of uncorrectable read errors.

Re:but what about cheap disk? (1)

Joce640k (829181) | about a year ago | (#45575377)

I just cringe the idea of storing long term archived data using an electric charge (flash, HDD, tape).

I think you'll find that two of those use a magnetic charge.

Re:but what about cheap disk? (0)

Anonymous Coward | about a year ago | (#45575489)

You mean magnetic polarization. A magnetic charge would imply the presence of a magnetic monopole, which have not been shown to exist in this universe. /pedantic

Re:but what about cheap disk? (0)

Anonymous Coward | about a year ago | (#45575813)

Great, now I'm hearing Sheldon on helium in my head.

Re:but what about cheap disk? (1)

marcosdumay (620877) | about a year ago | (#45575417)

HDD and tape do not use electric charge. They use spin orientation, what is much more stable, and self sustaining. Flash do use charges, and optical disk, chemical reactions. Theoreticaly, spin orientation is the most stable of those options.

By the way, where is the phase change memory IBM was promissing us 15 years ago? Moving atoms full nanometers from their original position... that would be stable.

Re:but what about cheap disk? (4, Informative)

rickb928 (945187) | about a year ago | (#45575493)

The bottom line in managing long-term archiving (5+ years) is that you need to both refresh and verify you storage, at several different levels.

1. Shoot the initial copy.
2. Copy this asap. "Copy1"
3. Stash both in disparate locations.
4. Go back to the 'original' on a 6-9 month schedule and verify it.
5. Go back to the 'copy1' on a schedule and verify it on a different schedule.
6. Go back to the 'original' on a different 9-12 month schedule and refresh(copy) it, stored to the other site.
7. Go back to the 'copy1' on a different schedule and refresh (copy) it, stored to the other site.
8. Repeat 4&5 on a year schedule. Do you need to re-write the data in 'current' formats and retain both original and new? Are you moving to new media?
9. Repeat 6&7 on a year schedule. Ditto the rest of step 8.
10. We should be at year 2 or 2.5. Repeat steps 1-9 once for a 6+/- year retention, again for 10+ year retention.

Are you changing data formats, and is it possible to ensure integrity by copy8ing and archiving in new formats?
As you change media, do you need to retain old media systems, or will you move to the new media?
At what point is the data no longer valid, determined by the owners?
Are the 'owners' the only stakeholders? If not, expand the set.

In all of this, you have a dedicated media management system including media drives, copy/verify capabilities, and stand-in for restoration.

This is all very interesting to me. Medical records in particular seem to be assumed to have a lifetime retention, but other than the date and nature of the event, how important are the details of your appendectomy performed at age 5 when you are 60? Is that benign tumor removed at age 12 important at age 45? How much LHC data collected in 2013 will be useful in 2023? Different criteria. Different processes.

Re:but what about cheap disk? (2)

MightyMartian (840721) | about a year ago | (#45575083)

I've always insisted on a tape backup system. Hard drive backups certainly have their place, but tape cannot be beat for long-term archival storage. One of our weekly offsight backups goes into a safety deposit box, where sits a duplicate tape drive. I don't want to be searching around for a replacement while my organization is down and out due to some cataclysmic failure.

Re:but what about cheap disk? (1)

bob_super (3391281) | about a year ago | (#45575181)

Per Murphy's law, you do need two tape drives in that deposit box.

Re:but what about cheap disk? (1)

drinkypoo (153816) | about a year ago | (#45575547)

Per Murphy's law, you do need two tape drives in that deposit box.

Only if you can plug the replacement in wrong. Murphy's law is often incorrectly interpreted to refer to failures. It isn't about that. It's about fuckups.

Re:but what about cheap disk? (1)

Minwee (522556) | about a year ago | (#45575695)

And Finagle's Law states that anyone trying to explain the difference between it and Murphy's Law will get it wrong.

Re:but what about cheap disk? (0)

Anonymous Coward | about a year ago | (#45575749)

I've always insisted on a tape backup system. Hard drive backups certainly have their place, but tape cannot be beat for long-term archival storage. One of our weekly offsight backups goes into a safety deposit box, where sits a duplicate tape drive. I don't want to be searching around for a replacement while my organization is down and out due to some cataclysmic failure.

"Boss! boss! I have fetched all our data from the safety deposit box, including the spare tape drive! Just tell me where to plug it in and we are all set!"

          "Somewhere under that pile of rubble is a LVD SCSI port, and it might even have power"

Re:but what about cheap disk? (1)

TooMuchToDo (882796) | about a year ago | (#45575915)

Hard drive storage > tape storage.

How quickly can you verify the integrity of your off-site tape backup? I can verify my hot backups in S3/Glacier in seconds.

Re:but what about cheap disk? (0)

Anonymous Coward | about a year ago | (#45575955)

I would like to know the longevity of upcoming resistance based memory. From what I understood from articles many many years ago, it requires a high voltage to change the resistance, but once changed, should remain. Many things could have changed in this amount of time and it could be a different variation of it, but I can't wait to see it when it comes out next year.

Re:but what about cheap disk? (1)

silas_moeckel (234313) | about a year ago | (#45575319)

Check the undetected and uncorrectable bit error rates for cheap disk. Tape drives even read everything written to insure it got there and is correct allowing it to retry the operation till it works or it fails out the tape. There is no "consumer" grade tape anymore without all those nice enterprise features baked in.

Current pricing is about $60 for 1.5TB ($120 for a 3tb drive) for consumer disk vs LTO5 $30 + 2k for a tape head (LTO6 is more expensive as the takes a 3x the cost).

Re:but what about cheap disk? (1)

Joce640k (829181) | about a year ago | (#45575335)

tape has its issues, but sucking up money like a trophy wife isn't one of them

It's OK for jobs like this where it doesn't really matter if you lose a few bits of data every now and again.

Re:but what about cheap disk? (1)

tlhIngan (30335) | about a year ago | (#45575441)

i remember a few years back backup to "cheap" disk was all the rage. if you were backing up to tape you were seen as some kind of mental patient

tape has its issues, but sucking up money like a trophy wife isn't one of them

Depends how much you want to store.

If it's just a little bit, using a DVD-R is perfectly adequate as a backup solution. Even BD-R for slightly larger amounts.

But if you have to store more, say a few to double digit TB, hard drives might be a reasonable solution - they're quite cheap and of reasonable size - 10 4TB drives can be had for just over $1K giving you 40TB of un-RAIDed storage.

But once you're up there in storage, where you can afford the $5k+ tape drive costs and $100 tapes (though which can store 10/20/30+ TB each), tape is definitely affordable.

And the LHC generates petabytes of data per second during an experiment, so tape drives are definitely economical.

There's a balance between cost per byte and initial acquisition cost. DVDs and BDs have extremely low acquisition costs, but relatively high cost per byte (you can get started with $100). Hard drives have higher costs, but lower cost per byte. Tape has the least cost per byte, but initial costs are quite high, and special requirements may make implementation using hard drives viable for a long time yet.

Re:but what about cheap disk? (1)

compro01 (777531) | about a year ago | (#45575643)

If it's just a little bit, using a DVD-R is perfectly adequate as a backup solution. Even BD-R for slightly larger amounts.

And you're not needing to back it up for very long. Writable optical media doesn't have a very long archival lifespan.

Re:but what about cheap disk? (1)

alen (225700) | about a year ago | (#45575795)

who in their right mind is going to store 4TB of company data on unRAIDed disk?

first you have to buy the enterprise gear with the 4 hour or next day warranty. then RAID-5 at the minimum and probably RAID-6. and if your server runs out of storage its $3000 for a jbod plus $1000 for the RAID controller and then the disks

and then you have to have a second backup server with the same data standing by just in case your primary server crashes. disks have this problem where if the OS crashed or something happens to other hardware in the server your data might be lost forever

"Reviving?" (0)

Anonymous Coward | about a year ago | (#45575013)

Doesn't something need to be dead or dying to be revived?

I work on satellite weather data, and I'd say about 95-99% of it ends up on a tape deck somewhere.

Re:"Reviving?" (1)

jythie (914043) | about a year ago | (#45575427)

People often confuse 'not currently sexy with companies less then 5 years old' with 'dead and or dying'.

maybe (0)

Anonymous Coward | about a year ago | (#45575035)

Maybe there are some cases where tape is cheaper than drives. However, Amazon has stated that they do not use tape for their Glacier service, which probably stores more data than even the mighty LHC. That is strong evidence that hard drives are cheaper for the Glacier use case.

Re:maybe (1)

prefec2 (875483) | about a year ago | (#45575097)

I doubt that Amazon has to handle a similar amount of data than the LHC. However, the rest of your statement is correct.

Re:maybe (2)

MightyMartian (840721) | about a year ago | (#45575107)

I don't think "cheapness" is the problem being solved. More important for an organization like the LHC is archival reliability. Tapes can lost a long time while retaining their data integrity. I honestly doubt even high end hard drives can make that claim.

Re:maybe (1)

alen (225700) | about a year ago | (#45575125)

disk based backup is cheaper for text type data files since it compresses very well. i tested disk backup on SQL Server for a year and while it did compress pretty good, not enough to make the disk cheaper.

its probably cheaper now that you can get a lot more storage per server than a few years ago, but i haven't run the numbers

Re:maybe (1)

Joce640k (829181) | about a year ago | (#45575409)

Tapes use data compression, too.

(In fact most of the "capacity" and "speed" numbers in the sales brochure are for compressed data).

Re:maybe (1)

SJHillman (1966756) | about a year ago | (#45575131)

It depends on what you're doing. Amazon has many thousands of unrelated chunks of data from different users spread all over that are accessed at random times, in random orders and in random chunks. They can also move chunks of data to all different places. The LHC however would probably prefer to keep its data all together, as it is likely to all be accessed in a considerably more sequential order. The lesson I get is that tape is still better *for large chunks of related data* while HDDs may be better for *large amounts of unrelated data*.

Re:maybe (1)

MightyYar (622222) | about a year ago | (#45575345)

Yes. I think Amazon simply needs more automation. If a researcher needs to analyze some LHC data, some poor grad student can go rifling through mountains of tape. If an Amazon customer needs their Glacier data, Amazon would need to construct some sort of massive tape loading and library mechanism. I know these already exist commercially (e.g. StorageTek, etc.), but they are not cheap and they are probably not on the scale that Amazon would need.

Re:maybe (1)

Isca (550291) | about a year ago | (#45576093)

I think Amazon's system is a hybrid. There have been numerous articles about it but Amazon has kept their system tightly locked down with NDA's for all parties involved. However the reason why lots of people have come up with this conclusion is simple -- there are occasional but regular complaints you'll see on the internet where the 3-5 hour window is blown up to 10-24 hours. I suspect that they use commodity hard drives that are powered off once filled. But backing up those hard drives is a tape system that is only kicked in when they find a bad hard drive (and the tape backs up the hard drive). This way they don't use power when the drives are on.

NSA hates them (0)

Anonymous Coward | about a year ago | (#45575077)

It takes too much time to copy or scan one. They don't have any future with the agency.

six gigs (-1)

Anonymous Coward | about a year ago | (#45575085)

What the hell is a gig? Are you referring to gigabytes, gigabits, jiggawatts, or something else?

Data storage is usually (but not always) measured in bytes. Here we have a data rate (six gigasomething per second), and rates can be measured in bits, bytes, or records per second. Please fix the summary.

Re:six gigs (1)

SJHillman (1966756) | about a year ago | (#45575165)

A gig is a performance, usually given by a band. It's a little known fact that the Higgs boson likes to rock out.

It's not storage they're worried about (0)

Anonymous Coward | about a year ago | (#45575099)

You can generate all the data in the world but it's useless if you can't actually move it anywhere to do work on it. Tapes are lighter than drives, ergo less shipping costs. It doesn't hurt that you can get vastly higher TB/$ ratios as well with tape.

No shit Sherlock (3, Informative)

morcego (260031) | about a year ago | (#45575235)

No one in the data retention business ever stopped using tapes. See the numbers on LTO units being sold, if you need proof.

This is a shitty article.

Re:No shit Sherlock (1)

Anonymous Coward | about a year ago | (#45575269)

Exactly, I don't get why people think tape is dead.

Just because commercial audio/video tape storage stopped doesn't mean it's a dead format.

Re:No shit Sherlock (0)

Anonymous Coward | about a year ago | (#45575517)

I don't get why people think tape is dead

Same reason they think every other technology is "dead": because they're too young to know better.

Re:No shit Sherlock (0)

Anonymous Coward | about a year ago | (#45575667)

To their detriment. LHC has a legitimate use for tape. But doing backups of company data on tape is a bad idea. A bad reader can ruin tape. Its also susceptible to strong EM events. Optical is the way to go.

Re:No shit Sherlock (1)

stox (131684) | about a year ago | (#45575837)

Show me optical media that is good for 10+ years. How big a stack of Blu-Rays am I going to need to match one 6TB LTO?

The death of tape (2)

cyberchondriac (456626) | about a year ago | (#45575259)

..has been greatly exaggerated lately by trade journals. There are some backup scenarios for which hard disc backup just isn't viable.
Viva la tape.

Re:The death of tape (0)

Anonymous Coward | about a year ago | (#45575391)

There are some backup scenarios for which hard disc backup just isn't viable.

So you're saying I need a backup plan for my backup plan?! Good God man, where does it end?

Re:The death of tape (1)

bobbied (2522392) | about a year ago | (#45575433)

How much risk do you need to avoid?

Gmail is backed up to tape (3, Interesting)

Albanach (527650) | about a year ago | (#45575265)

A couple of years ago, Google restored lost gmail from tape [blogspot.com] . I'd expect that even with deduplication they must use a phenomonal amount of tape.

A bit out of date... (1)

Robear (68955) | about a year ago | (#45575295)

There are 8.5TB uncompressed capacity tapes in enterprise use right now. The 6TB compressed sounds like, oh, two generations back or so.

magnetic tape? (0)

Anonymous Coward | about a year ago | (#45575315)

never heard of it. I grew up with Solid disk drives, 7200 RPM SATA 3 drives and Blu-Ray discs. Ok, I'm showing my age. :p

thanks for the post about old technology though.

Makes Sense (0)

Anonymous Coward | about a year ago | (#45575341)

Where something like SSD will out perform tape when it comes to random accessed data, when linear storage will do, I don't think anything can beat the durability & cost/performance of tape.

Although, when working one of the worlds strongest electromagnets, I would have expected non-magnetic based media.

Too much data...NOT (0)

unixcorn (120825) | about a year ago | (#45575355)

I think Netflix puts their data on tape too. Oh wait, no they don't because they have to use it. If the LHC folks are putting the data directly on tape, I am guessing the data isn't really worth much. If it was valuable and needed to be analyzed, it would go directly to a hard disk.

Re:Too much data...NOT (1)

amalcolm (1838434) | about a year ago | (#45575459)

I would guess data generated in each run is stored to disk, then copied to tape for analysis elsewhere, freeing up disk space for the next experiment.

Re:Too much data...NOT (0)

Anonymous Coward | about a year ago | (#45575581)

I think Netflix puts their data on tape too. Oh wait, no they don't because they have to use it. If the LHC folks are putting the data directly on tape, I am guessing the data isn't really worth much. If it was valuable and needed to be analyzed, it would go directly to a hard disk.

*sigh*... you could try, you know reading the first few sentences of the article? Or, you know, you could skip that and try elementary logic? 'hey, thousands of the smartest people in the world are working on this huge machine, and they think tape is the best solution... either I am smarter than them, or they might know something I dont'. Which optionally might lead you to reading the article in an attempt to find out what that might be.

Speed, reliability, ease of long term preservation of the data and security... all advantages over harddisks. Speed? Yes speed... You can get data from tape much faster than from hds. In highly specialized cases where you don't care about random access.

Why don't they backup to teh Cloud? (0)

Anonymous Coward | about a year ago | (#45575387)

The Cloud is so amazing surely LHC data is no problem for the Cloud.

Reviving? (1)

Lumpy (12016) | about a year ago | (#45575429)

Magnetic tape has been alive and well. Most big companies and research labs use it daily.

Sounds like the article writer knows nothing at all about corporate or industrial IT.

my senses collect 6GiB/s (0)

Anonymous Coward | about a year ago | (#45575463)

But they're much better at knowing what to discard.

Tape is bullshit. (-1)

Anonymous Coward | about a year ago | (#45575475)

Tape is slow, expensive, proprietary and unreliable.

The only people who still use it are those who have to, or idiots with money to burn.

All Wrong (1)

burni2 (1643061) | about a year ago | (#45575815)

1.) Tape is fast - your sata2 hdd will hardly be able to support a steady flow of data to an LTO5 drive (SAS 3/6gbs)
Disadvantage - no random access but that's not what tape is usefull

2.) proprietary - partly wrong if you want to use those vendor lock in products (cheaper drive - expensive cartridges)
LTO5 (and next LTO6) is downward compatible at least one version you can read data from your LTO5 tape with a LTO6 drive

3.) unreliable
in which way ? due to it's crc and sophisticated(develloped over decades) error correction tech

4.) idiots with money to burn buy one disk drive after another if they don't chose to invest more into the drive an be cheaper on the long run as the media price for (Example LTO5) is extremly low, especially if you find good unopened goods on ebay

Perhaps you got it, I'm a happy LTO5 (private, HD movie filmer) user and I occasionally look at ebay for cheap "10x Sony/Fujutsu/HP" disk packs, unopened, then I pay as low as 5€ per 1TByte, I don't need to buy new 4TB drives for backup, where the price per 1TB equals 40-45€

Re:All Wrong (0)

Anonymous Coward | about a year ago | (#45575841)

" due to it's crc and sophisticated(develloped over decades) error correction tech"

Obviously, extra apostrophe detection and spell-checking is optional...

Re:All Wrong (0)

Anonymous Coward | about a year ago | (#45575991)

The "sophisticated" ECC for LTO is plain old RS coding. Which is also used by pretty much every other modern data storage medium.
Other than that, agreed.
Happily using LTO4 for archival here.

I wish that they looked like the old ones (1)

ModernGeek (601932) | about a year ago | (#45575531)

I'd love to see a Petabyte-Scale Tape Storage System that looked something like this, only modernized: http://youtu.be/Nq3mNYKR7FM [youtu.be]

Will SyQuest come back? (1)

50000BTU_barbecue (588132) | about a year ago | (#45575555)

Or can I sell my cartridges on Craigslist now?

Spinning? (2)

rossdee (243626) | about a year ago | (#45575625)

" When spinning it reportedly generates up to six gigs of data per second."

The LHC itself doesn't spin, rvrn though there are protons moving around the circular track at very near lightspeed. /pedant

Reviving Magnetic Tape? (2)

bravecanadian (638315) | about a year ago | (#45575639)

For *reliable* backup and archive purposes tape never went out of style.

Consumer vs enterprise tape technology (3, Interesting)

BenJeremy (181303) | about a year ago | (#45575797)

I've worked as a tape monkey in a large facility (Camp Foster RASC, Okinawa, circa 1989-90), so I know tapes do work well in the enterprise, but my experience with tapes in the consumer space in the 90s was anything but good. 90% of the tape backups made (using several different formats) using consumer-grade systems were corrupt and worthless.

We took great care with the tapes, but when we checked them (thankfully never needed them, except one occasion), they were mostly all bad.

Optical isn't much more reassuring as a backup media, given that optical discs tend to degrade over time.

If somebody has a tape system that can store terabytes on a cartridge, reliably, for say... $10/TB or less, and the system costs less than $200, I'd look at it, though. Otherwise, it is still more worthwhile just to use hard drives to back up data (even at their inflated prices)

WRONG (-1, Troll)

Anonymous Coward | about a year ago | (#45575917)

The cost of magnetic tape, if the data EVER needs to be accessed and processed in any regular way, is VASTLY higher than the cost of using HDDs. The only reason tape gets used today is because DEADHEADS whose IT knowledge is decades out of date have positions of power over some IT project. Big government projects like Obamacare, or LHC are the absolute worst for this.

The point about data is that if you neither know about it, or can easily get at it, it might as well not exist. Everyone who placed masses of files on CD and then DVD discovered this phenomenon. Data at hand is data used. Data deep archived is data forgotten. When tape had a significant capacity and price advantage over magnetic platters and optical, it made SOME sense, but was always a horrid solution. The ability to move entirely away from tape, and the growth of that concept we know as the Internet, are hardly unrelated.

However, never forget, it is the most braindead decision any IT manager can make to say "slap it on tape", and the kick-backs from the remaining tape archive storage companies are unthinkably massive. ONLY kick-backs (large, 'untraceable' cheques) keep the large scale tape archival systems going.

Hear about a little thing called "the cloud"? You think every cloud company did not seek to gain this contract? Sadly, in this case, graft and corruption won out. It usually does where government meets IT. Do not forget, the NSA's R+D arm, Google, was created entirely as an answer to solving the eternal problem of Government IT projects ruined by corruption. Google 'appears' to be in the private sector, but provides the hardware designs, and software solutions to every major intelligence agency in the West (the NSA uses 'shadow' Google facilities to store, process, index and search its FULL SURVEILLANCE data).

In IT, your system (software and hardware) is either good, or it is not. When a government determines to have a good IT system for a given enterprise, it actually cares about results. Clearly, no-one really cares about the work at the LHC. You'll find far better, state-of-the-art, IT solutions at those facilities where Team Obama and others work to develop the next generation of the West's nuclear based holocaust weapons.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?