1 |
On Sat, Jul 31, 2021 at 12:58 AM William Kenworthy <billk@×××××××××.au> wrote: |
2 |
> |
3 |
> I am amused in a cynical way at disk manufacturers using decimal values ... |
4 |
> |
5 |
|
6 |
So, the disk manufacturers obviously have marketing motivations. |
7 |
However, IMO the programming community would be well-served to just |
8 |
join basically every other profession/industry on the planet and use |
9 |
the SI units. If you want to use GiB to measure things by all means |
10 |
do so, but at least stick the "i" in your output. |
11 |
|
12 |
You're not going to change ANYTHING by using SI decimal prefixes to |
13 |
refer to base-2 units. Everybody on the planet who isn't a programmer |
14 |
is already using SI prefixes, recognizes SI as the authoritative |
15 |
standards body, and most of the governments on the planet probably |
16 |
have the SI prefixes enacted as a matter of law. No court on the |
17 |
planet is going to recognize even the most accomplished computer |
18 |
scientists on the planet as speaking with authority on this matter. |
19 |
|
20 |
All sticking to the old prefix meanings does is confuse people, |
21 |
because when you say "GB" nobody knows what you mean. |
22 |
|
23 |
Plus it creates other kinds of confusion. Suppose you're measuring |
24 |
recording densities in KB/mm^2. Under SI prefixes 1KB/mm^2 equals |
25 |
1MB/m^2, and that is why basically every engineer/scientist/etc on the |
26 |
planet loves the metric system. If you're going to use base-2 units |
27 |
for bytes and base-10 for meters, now you have all sorts of conversion |
28 |
headaches. The base-2 system only makes sense if you never combine |
29 |
bytes with any other unit. I get that programming tends to be a bit |
30 |
isolated from engineering and so we like to pretend that never |
31 |
happens, but in EVERY other discipline units of measure tend to be |
32 |
combined all the time, and it certainly happens in engineering real |
33 |
computers that don't use infinitely long tapes and only exist in CS |
34 |
textbooks. :) |
35 |
|
36 |
Just to combine replies: by "read-only" scrubbing I wasn't referring |
37 |
to using "-r" but rather just that the scrub wasn't repairing |
38 |
anything. A scrub operation will repair problems it finds |
39 |
automatically, and that would of course take a huge hit on SMR. I'd |
40 |
expect a scrub that doesn't encounter problems to perform similarly on |
41 |
CMR/SMR, and something that does a ton of repair to perform terribly |
42 |
on SMR. |
43 |
|
44 |
Your numbers suggest that the SMR drive is fine for scrubbing without |
45 |
errors (and if you have no mirroring/parity of data then you can't do |
46 |
repairs anyway). I'm guessing the drive was just busy while |
47 |
scrubbing, and obviously a busy spinning disk isn't going to scrub |
48 |
very quickly (that might be tunable, but if you prioritize scrubbing |
49 |
then regular IO will tank - typically you want scrubbing at idle |
50 |
priority). |
51 |
|
52 |
-- |
53 |
Rich |