1 |
On Thursday 30 September 2010 17:50:41 Florian Philipp wrote: |
2 |
> Am 30.09.2010 18:00, schrieb Peter Humphrey: |
3 |
> > On Thursday 30 September 2010 14:10:42 Florian Philipp wrote: |
4 |
> >> An HDD gets slower when you read the inner tracks. The angular |
5 |
> >> velocity is constant (5400 RPM) while the tangential velocity gets |
6 |
> >> lower with the radius. |
7 |
> > |
8 |
> > Are you telling us that the length of a stored bit is constant? I'd |
9 |
> > have thought it was the time needed to read or write a bit that |
10 |
> > was constant; otherwise the electronics would get extremely |
11 |
> > complex. In that case it's the angular velocity that counts, not |
12 |
> > the linear velocity, and it matters not which track your data are |
13 |
> > on. (If a block goes past the head twice as fast, it also occupies |
14 |
> > twice the space, so you're back where you were.) |
15 |
> |
16 |
> Yes, the length of a block is constant. If the innermost "ring" |
17 |
> (track) contains 4 blocks, the next ring contains maybe 5 blocks.[1] |
18 |
> |
19 |
> Put another way: If you could pack your bits more densely on |
20 |
> innermost tracks, why wouldn't you pack them that densely on the |
21 |
> whole disk and thereby increase the overall capacity? |
22 |
> |
23 |
> > That's the way it was with our imposing new 2MB disks in 1974, |
24 |
> > anyway. They occupied boxes four feet tall and six feet long, and |
25 |
> > had external air systems; I was one of those responsible for the |
26 |
> > maintenance; we were sent on a training course specifically for |
27 |
> > the disks. I can't remember who made them, but they were part of a |
28 |
> > Ferranti Argus 500 system at the then national grid control |
29 |
> > centre. |
30 |
> > |
31 |
> > Maybe technology has changed since then. |
32 |
> |
33 |
> Well, we are talking about devices employing the GMR effect while |
34 |
> also doing error correction and remapping of defect sectors |
35 |
> on-the-fly. I guess a little lookup table from track number to |
36 |
> time-per-block doesn't add too much complexity. |
37 |
> |
38 |
> You can easily test this if you have various partitions on your HDD. |
39 |
> Just compare dd throughput for your first partition versus your last |
40 |
> one. |
41 |
|
42 |
Seems like technology has moved on. Well, it has had 35 years or more. |
43 |
|
44 |
-- |
45 |
Rgds |
46 |
Peter. Linux Counter 5290, 1994-04-23. |