Fujifilm Created a Magnetic Tape That Can Store 580 Terabytes

Remember when we could do 64Kb/s reliably over the web? Then you could do 'voice'. And after that threshold was crossed, you could basically do unlimited voice very quickly.

So Wikipedia - text only - is ballpark 50G - which is to say it would fit on a single mobile phone.

That is bigger than the first Google index!

I don't know how old you are, but the notion that you could walk around with this massive database, literally the size of all of Google right in their pockets in 1999 - would have blown people's minds. It was basically unthinkable.

The rate of growth of storage has slowed down a little in the last decade but there are still jumps to be had, and it's not inconceivable that we get 100-500TB storage in the nex1 10-15 years in regular devices, meaning 10-100x that in a slightly large storage device.

While video data is expanding (4K is much bigger than original HD) it can't go on forever, meaning, just like voice and text, once we cross a certain threshold, then it becomes irrelevantly small relative to storage as well.

So I think there's some value in my point:

In 10-20 years from now, as video storage becomes 'trivial' just as text is today (aka all of wiki text on your phone) - then huge amounts of data become available, instantly.

Though some data sources change a lot - others do not.

It's not inconceivable that we put the 'entire western canon' in everyone's homes.

The other thing no so evident in my comment is that there's only so much use for all of this data.

We are getting massively smaller marginal returns for all this 'big data' we store, frankly, I question in many cases if it's worth it at all. I think a lot of companies have been duped into saving every mouse click or whatever concerning every customer. The world is just not that complicated.

What this means - is as computers miniturize - and storage as well - we may see regular data centers shift away from the cloud back to 'on premise'.

If you can fit 'infinite computing power' in a little closet, and the parts are easily replaced ... then I can see companies doing that.

The promise of cloud computing today largely rests on the economies of scale of physicality: parts take up space, cables, power, heating/cooling, you want a lot of flex/headspace, configurations.

I don't see why in 20 years from no, you can buy 'off the shelf' a 'box' that has the equivalent of 100Ec2s, 500TB of storage and multiple G/s networking cards.

You could run an entire corporate office of 1000 people from just a single box.

The 'physicality' of it all would be mundane and irrelevant. Obviously, it would be 'super complex' and still need 200 IT people to admin all of the software, but physically it could be small and cheap.

'Big maybe' of course, but there are some possibilities in there I think.

Yawn on the raw density figure, though.

The chip inside a 128 gigabyte micro SD card is a small fraction of a square inch and is cunning enough to provide random access.

You just can't easily and cheaply have a long tape of them.

It used to be the case once upon a time that mass storage media like magnetic tapes and discs based on writing on surfaces with a head had better density than memory chips.

The hardware is not going to read 300 Gb/in density at bicycle speeds. :)

>Checksums will identify something went wrong, and then you need to redownload the file to a quarantine network and scan it. Takes time.

Surely a sensible file transfer algorithm would compute checksums on small and easy-to-retransmit chunks? Does rsync not do this? Isn't it already happening in TCP?

>Not to mention most major studios will contractually prevent you from exposing anything to the web.

I understand that workstations with media on them are not going to have internet access, but do they really prohibit site to site VPNs?

>Amazon just released a device (forget the name) for exactly the same use case. We developed it in house.

Snowball and Snowmobile? IIRC these are primarily meant for one-time migration from on-prem storage to S3. Do people really use them on an ongoing basis?