1 |
On 27 October 2011 20:35, Mark Knecht <markknecht@×××××.com> wrote: |
2 |
> On Thu, Oct 27, 2011 at 11:41 AM, Jarry <mr.jarry@×××××.com> wrote: |
3 |
>> Hi, perhaps someone could explain this to me: |
4 |
>> |
5 |
>> I have bouth two the same hard-drives. The same model |
6 |
>> (Hitachi HUA722050CLA330), the same firmware (JP20A3EA), |
7 |
>> the same size (500GB). Well, not exactly. Both hdparm |
8 |
>> and fdisk report different number of sectors (976771055 |
9 |
>> versus 976773168). Although not a big difference, yet |
10 |
>> I expected them to be exactly the same (want to use |
11 |
>> them for raid1). |
12 |
>> |
13 |
>> So how is it possible they do not have the same number |
14 |
>> of sectors? I have bought them from one supplier, even |
15 |
>> their serial numbers are very close (only the last 2 |
16 |
>> characters out of 24 are different)... |
17 |
>> |
18 |
>> Jarry |
19 |
> |
20 |
> Maybe one has some stuff mapped out due to bad blocks found during |
21 |
> manufacturing or something like that? Not sure what it will tell you |
22 |
> but have you run smartctl on the drives and looked around at what they |
23 |
> tell you to find any differences? |
24 |
> |
25 |
> - Mark |
26 |
|
27 |
During normal operation, if a bad block is detected, that sector is |
28 |
marked as 'bad', and a one of the free sectors (which are additional |
29 |
to your totals) is allocated to replace it. This is called |
30 |
Re-Allocating Sectors, and according to the Google paper[1], which |
31 |
seems to be the only authoritative (non-marketing, non |
32 |
industry-funded) source on hard-drive failure, re-allocated sectors |
33 |
are indicative of impending drive failure. You can check your |
34 |
Re-Allocated sector count using smartmontools (but I recommend that |
35 |
you try gsmartcontrol in sunrise, which makes life easier). |
36 |
|
37 |
This is made more complicated by the fact that if bad sectors (below a |
38 |
manufacturing threshold) are detected in factory testing, they will |
39 |
re-allocate them, and reset the SMART counter to Zero (the drive _is_ |
40 |
brand new after all!). Thus, you can buy two of the exact same model |
41 |
of drive, and yet have different numbers of available sectors. |
42 |
|
43 |
It is also possible that something entirely different is at play. |
44 |
|
45 |
[1] labs.google.com/papers/disk_failures.pdf |