| 1 |
On Sun, May 3, 2020 at 2:29 PM Mark Knecht <markknecht@×××××.com> wrote: |
| 2 |
> |
| 3 |
> I've used the WD Reds and WD Golds (no not sold) and never had any problem. |
| 4 |
> |
| 5 |
|
| 6 |
Up until a few weeks ago I would have advised the same, but WD was |
| 7 |
just caught shipping unadvertised SMR in WD Red disks. This is going |
| 8 |
to at the very least impact your performance if you do a lot of |
| 9 |
writes, and it can be incompatible with rebuilds in particular with |
| 10 |
some RAID implementations. Seagate and Toshiba have also been quietly |
| 11 |
using it but not in their NAS-labeled drives and not as extensively in |
| 12 |
general. |
| 13 |
|
| 14 |
At the very least you should check the model number lists that have |
| 15 |
been recently released to check if the drive you want to get uses SMR. |
| 16 |
I'd also get it from someplace with a generous return policy and do |
| 17 |
some benchmarking to confirm that the drive isn't SMR (you're probably |
| 18 |
going to have to do continuous random writes exceeding the total |
| 19 |
capacity of the drive before you see problems - or at least quite a |
| 20 |
bit of random writing - the amount of writing needed will be less once |
| 21 |
the drive has been in use for a while but a fresh drive basically acts |
| 22 |
like close to a full-disk-sized write cache as far as SMR goes). |
| 23 |
|
| 24 |
> Build a RAID with a WD Green and you're in for trouble. ;-))) |
| 25 |
|
| 26 |
It really depends on your RAID implementation. Certainly I agree that |
| 27 |
it is better to have TLER, but for some RAID implementations not |
| 28 |
having it just causes performance drops when you actually have errors |
| 29 |
(which should be very rare). For others it can cause drives to be |
| 30 |
dropped. I wouldn't hesitate to use greens in an mdadm or zfs array |
| 31 |
with default options, but with something like hardware RAID I'd be |
| 32 |
more careful. If you use aggressive timeouts on your RAID then the |
| 33 |
Green is more likely to get kicked out. |
| 34 |
|
| 35 |
I agree with the general sentiment to have a spare if it will take you |
| 36 |
a long time to replace failed drives. Alternatively you can have |
| 37 |
additional redundancy, or use a RAID alternative that basically treats |
| 38 |
all free space as an effective spare (like many distributed |
| 39 |
filesystems). |
| 40 |
|
| 41 |
-- |
| 42 |
Rich |
Archives