The largest issue with tape is that the drives themselves cost absurd amounts, and you better not cheap out because failure is both time consuming and scary.
Swapping tapes continues to be human intensive and restore times long. But the tapes themselves are so cheap that at this scale it becomes worthwhile again.
I'd be surprised if you could even get tapes for it that aren't sketch grey market stuff that you wouldn't want to use for backups anyway.
The tapes are pretty cheap at $8 on Amazon if you buy 20.
Those tapes only hold 200 GB, and you can get a 10 TB hard drive today for less than $300:
https://www.newegg.com/red-wd101efax-10tb/p/N82E16822234407
While tapes are theoretically cool, the the drives are just too rare for them to be of any practical value to a home user. Even if the media has a better archival life than a hard disk (say 50 years), it won't do you a damn bit of good if there are no drives available in 50 years to read it.
IMHO, hard drives are better for backup (even offline backup, just get a hot-swap bay and imagine the drive is tape [1]). Archival is a harder problem, but I've settled on using high-grade optical media, burned slow for fewer errors, making a bunch of redundant copies. Even though the media might not last as long, I'm pretty much guaranteed to be able to find a drive for the next several decades [2].
[1] "pretend this hard drive is a tape" is even an enterprise product: https://en.wikipedia.org/wiki/RDX_Technology
[2] For instance, you can still attach a 5.25 floppy drive to a modern computer: https://www.ebay.com/sch/i.html?_nkw=5.25+floppy+drive + http://www.deviceside.com/fc5025.html
That was a link to an obsolete LTO-2 drive. If you’re using LTO-8, which is the current generation, you’d get a 10-pack of 12TB tapes for around $500. Noticeably cheaper per byte than hard drives.
I don’t recommend LTO-2 just because I don’t think that the drives are well-supported.
> While tapes are theoretically cool, the the drives are just too rare for them to be of any practical value to a home user. Even if the media has a better archival life than a hard disk (say 50 years), it won't do you a damn bit of good if there are no drives available in 50 years to read it.
If you’re evaluating just on the basis of the price of drives / media, then there’s a cutoff where tape becomes cheaper than hard drives. The easy way to calculate this cutoff is to divide the overhead cost (tape drive price) by the difference in the cost per TB of tapes and hard drives, which in the example here, is around $3k divided by $25/TB, or 120 TB.
In other words, if you have more than about 120 TB of data, then it is cheaper to buy a tape drive. I think any comments about whether tape drives are suitable for home use are really comments about whether you are interested in the use case of people who need to store >120 TB at home.
If you are running a YouTube channel as a hobby, or you run a side business doing videography for weddings, the tape drive starts to sound a lot better. The 120 TB cutoff might be around 300 hours of video, which might be only 50 events.
There are a lot of other reasons why you might NOT want to use tape, but it’s easy to have enough data that tape is the cheapest storage option. At “enterprise” scale the cost calculus is completely different and involves things like support contracts with Oracle (not necessary for hard drives), power/cooling in your DC (tape is very low-power), etc.
And let’s not forget that if you have 120TB of hard drives, you’re in the regime where you start having to buy multiple machines.
As for longetivity—I don’t have the data handy. If you are storing data on tape, you need to migrate to newer generations of tape, as old generations become obsolete and unavailable. If you are storing on hard disks, you also need to migrate because hard disks eventually fail (even if they are not powered on).
But on tape, the controller mechanism is separated from the storage medium. The controller mechanism is inside the drive readers itself, which will eventually fail.
So for both, it’s a trade off. They’re both going to eventually fail.
But it looks like the cheapest drive on Newegg for that is $3,299.00: https://www.newegg.com/p/2BM-0046-00001
> In other words, if you have more than about 120 TB of data, then it is cheaper to buy a tape drive. I think any comments about whether tape drives are suitable for home use are really comments about whether you are interested in the use case of people who need to store >120 TB at home.
> If you are running a YouTube channel as a hobby, or you run a side business doing videography for weddings, the tape drive starts to sound a lot better. The 120 TB cutoff might be around 300 hours of video, which might be only 50 events.
No dispute there, but I think most >120 TB home use cases run into the question of if it's even worth it to keep the data (raw/uncompressed). For most people, the answer is probably no, and curation/compression makes far more sense. For instance, I don't think it's even typical for wedding photographers/videographers to store their final product indefinitely, let alone the raw footage for a re-edit. You can keep a lot more events in a lot less space if you're only keep the raw footage for a few recent events and the 15-30 minute final edit for a year after it's finalized.
> And let’s not forget that if you have 120TB of hard drives, you’re in the regime where you start having to buy multiple machines.
Not if you swap disks as offline storage.
> As for longetivity—I don’t have the data handy. If you are storing data on tape, you need to migrate to newer generations of tape, as old generations become obsolete and unavailable. If you are storing on hard disks, you also need to migrate because hard disks eventually fail (even if they are not powered on).
Honestly, the theoretical longevity is the only aspect of tape that appeals to me, but like you said enterprise tapes will end up being like these enterprise optical disks in a fairly short period of time, so you're regularly going to have migration legwork to do or your data's effectively toast.
The nice thing about LTO as a format is its relative predictability and ease of acquiring the parts, even the very obsolete ones. It's all SCSI or SAS, most of the interesting stuff happens at the hardware level, with a bog-standard API. Your average backup app, whether it be Backup Exec or mtx/tar/etc. on Linux doesn't need to care about the media format. Unlike actual "enterprise" shops with datacenters and support contracts and such cruft, where the primary concern is "does it work", it is fine to buy older units second-hand. They are plentiful and cheap.
That's still... pretty terrible. If we compare you costs for a tape drive against a 14TB easystore @ $190[1], the break-even point is around 72TB. I don't know about you, but that's of data you have to store for it to be worth it. Even at 150TB you're only looking at around ~25% (~$500) in savings compared to hard drive, which I don't think is much when you factor in how much of a hassle tape drives are to work with.
[1] https://slickdeals.net/f/14587381-14tb-wd-easystore-external...
[2] https://www.wolframalpha.com/input/?i=solve+y+%3D+500+%2B+%2...
LTO5 onward supports LTFS, which exposes the tape to the OS as if it were any other removable storage, with the one proviso that deleting files doesn't reclaim space unless the entire tape is wiped.
It has been 8+ years since I played with LTFS, so maybe it has improved.
I was attempting only to answer the question and explain the source of confusion.
In native English speech, it would usually be expected that a business-case purchasor would speak of a more general case, perhaps by using "we".
“we” is even frequently employed by auctors writing papers to depersonalize.
Anyway, I guess this is the pedantry we (!) should expect from HN
Restore times are definitely long, but you can mostly avoid human labor by putting the tapes in a tape library, which will load tapes in the drives using robots. You still need technicians around because tapes / drives / robots will break, but individual restore operations can be completely automated.
The parent is clearly seeking to confirm serious long-term use, as you say, in considering the costs of failure cases.
Is this a question? I can't tell you if that's how you find my comment or not, sorry.
They wants a cheap tape device because they just want to use it in the home. Tape devices aren't cheap... because they aren't aimed at use just in the home.
They aren't aiming at home users - I think that's a simple fact not presuming anything.
Even if you believed they were a home user, they clearly demonstrated in their original comment that they did know that it was for long-term, high volume storage, and they did know the cost, and you appeared still to belittle them for not knowing.
It's a question in the sense of - why did you choose to say it in this way, which seemed impolite? What did you intend your comment to add?