Up to 2 minutes seek time for cold data. Very niche.
Obviously that cache can massively accelerate repeated access to the same data, and reduce tape wear and mechanical wear and energy usage.
But I think the critical issue is where you want the cache to be. Because end point devices already have local cache.
So this product only seems to have a big advantage on applications where you expect many unique users to access the same archive data for the first time, and within a short period of time before it expires from the tape drive’s SSD cache.
This is why I think it’s a small niche. Maybe too small to be worthwhile.
Edit: it also has the disadvantage that the first few devices to try to access the data would have a huge delay for a minute or more while the data is located on the tape. It’s also vulnerable to DDOS by attackers requesting random cold data, to fill the SSD.
If the alternative is slow storage, getting it from a different client on the LAN might be win.
- Archive for the film industry. 2 minutes to retrieve an archived take is a good compromise of cost and time.
- Archive for the recording industry. 2 minutes to recover the "master tapes" when you remaster for the umpteenth time is a good compromise of cost and time.
- The product I work on has requirements to archive data for a year / 10 years / 20 years and then generate a report. A 2 minute delay is perfectly acceptable.
But whether it's the best option is a big maybe.
Glacier is great at smaller scales, or to make things simple. (Well, great excluding the egress prices.)
But by the time your data won't fit on a large NAS (>200TB), a $5000 tape drive and a bunch of $5/TB tapes are cheaper than glacier.
You could also predict What is the next video the user will want.
Also, the 2 minute seek time is from one end of the tape to the other. But you could also move accross tracks, vertically so that gives another route for short seek times for some of your data.
So it might be possible to build something with a reasonable performance.
The intriguing use case (thinking as a consumer) is ~2tb "hot", and effectively treating the remainder tape as kindof "append-only/WAL" (and: e.g. incremental backups).
I have been randomly ripping my DVDs, mostly keeping the transcoded MP4s, but hesitant to delete the ISO's because they require physical handling and _time_ to re-rip.
If it's ~2min to seek to an 8gb ISO, that's potentially faster than re-downloading it from somewhere offsite, and would match my hypothetical use cases really well.
Keeping a local ~2tb drive backed up to a ~4tb+40tb "ssd-tape-hard-drive" is probably cheaper than most long-term cloud stuff (backblaze ~$6/tb/mo!!, glacier ~$4/tb/mo, but with lots of asterisks on retrieval time), and simpler than messing around with a NAS.
Glad I don't truly have these problems!
Similar could be some new media production company. Archive B-roll or parts of older videos and then have the stuff you use very common available much faster.
Zing!