Hacker News new | ask | show | jobs
by iamleppert 3551 days ago
I've always wondered this, but why don't we just scale up some data storage device? Like create a massive hard drive, 10 feet across? It has to be more efficient than tons of tiny little drives.
4 comments

From what I understand, there are a few issues, including:

1) The head has to move further to read the next sector of interest, which is particularly problematic for fragmented data.

2) It is more difficult to manufacture high data density (AKA high-precision) disks in large formats, as some surface defects are cumulative, and get worse as the disk gets larger.

3) Manufacturing defects which occur pseudo-randomly increase proportionally to the surface area of the disk, so the reject rate increases as a square of the radius.

4) Smaller drives can be spun much faster, allowing for higher data rates, as the centripetal accelerations in the disk are proportional to the square of the radius (and I believe the stresses are proportional to the cube of radius).

For these reasons and many others, HDDs have been moving to smaller and smaller form factors.

You know how hard it was to make the lens for the Hubble Space Telescope? Now imagine that you need to make it even more fine-grained in precision and accuracy as well as being electromagnetically within tolerance across that whole surface.
The cost of making high-precision surfaces goes up exponentially with the surface area of each unit. It's much cheaper to make lots of smaller ones than one large one.

The same probably applies for things like the actuator for the heads, etc.

The I/O bandwidth would have to be tremendous. I'm not sure the technology even exists.

Or else split the I/O into a zillion little independent ports.