• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

Just a thought

D

Druneau

[H]ard|Gawd
Joined
Jan 3, 2006
Messages
1,745
Why aren't there any hard drives with two platters and somekind of built-in raid0. What i mean is that the hard drive itself would split the data onto the two platters. Now i don't know how to engineer hard drives at all, but theoretically could it be done? Assuming it could be done, then would this increase performance and not change the mean time to failure?
 
Well think about it, the only thing they would commonly share would be the spindle holding the platters. You'll need separate heads, actuator arms, buffers, etc. to each do their half of the work, which will decrease the MTBF. Then if the drive dies, you've basically lost two drives.........
 
Yep. You'd have to duplicate most of the circuitry, and not enough enthusiasts exist to get a large shipment of them going. Therefore, it's not economically feasible to make these, especially when you could just buy two drives and get the same thing.

 
Oh,

I was thinking that only 1 actuator could work. I agree with the two buffers those would be needed. But why couldn't 1 actuator with the two head work? When the drive writes to one platter it would have to write to the second one at the same time... (splitting the data evenly)
 
The actuators aren't completely stiff; they flex a little under the amount of force exerted on them (try calculating the minimum acceleration needed to get 13ms average seek times on a 7200 rpm drives!) so they don't all end up in precisely the same place. Imagine you've got a bunch of foam noodles (the kind you'd find at a pool) attached to a stick, so that they're like the letter E. Then imagine a series of holes in a straight line. Your job is to get all the noodles into all the holes, as fast as possible. See how that would be hard? With bits the size that they are now, hard drives are about analogous to this scenario.

So, in other words, it's not as easy as it sounds :p

 
You must log in or register to reply here.
Back
Top