[EricBurnett]

Hyperscalars use a blend of storage flavours covering the whole spectrum, and for most data-heavy purposes can mix hot and cold bytes on the same device to get the right IO/byte mix. At which point you can simplify down to _"are they currently buying disks to get more bytes or more IO"_ - if the HDD mix skews far enough that they're overall byte constrained, yeah they'll be looking to add byte-heavy disks to the pool. If they've got surplus bytes already, they'll keep introducing colder storage products and mix those bytes onto disks bought for IO instead.

[throw0101a]

> Hyperscalars use a blend of storage flavours covering the whole spectrum

Probably including taping, which most non-enterprise folks are often surprised still exists.

There's an upfront cost for the infrastructure (drives, usually robotic libraries), but once you get to certain volumes they're quite handy because of the automation that can occur.

[EricBurnett]

Tapes are awkward though, since they can't directly satisfy the same random-access use-cases. E.g. even GCS's 'Archive' storage class, for the coldest of the cold, offers sub-second retrieval, so there's at least one copy on HDD or similar at any time.

Tapes are suitable for tape-oriented async-retrieval products (not sure if any Clouds have one?), or for putting _some_ replicas of data on as an implementation detail if the TCO is lower than achieving replication/durability guaranteed from HDD alone. But that still puts a floor on the non-tape cold bytes, where this sort of drive might help.