| 1 |
On Saturday, 23 May 2020 00:31:48 BST Rich Freeman wrote: |
| 2 |
> On Fri, May 22, 2020 at 5:40 PM antlists <antlists@××××××××××××.uk> wrote: |
| 3 |
> > On 22/05/2020 19:23, Rich Freeman wrote: |
| 4 |
> > > A big problem with drive-managed SMR is that it basically has to |
| 5 |
> > > assume the OS is dumb, which means most writes are in-place with no |
| 6 |
> > > trims, assuming the drive even supports trim. |
| 7 |
> > |
| 8 |
> > I think the problem with the current WD Reds is, in part, that the ATA-4 |
| 9 |
> > spec is required to support trim, but the ATA-3 spec is the current |
| 10 |
> > version. Whoops ... |
| 11 |
> |
| 12 |
> Probably was thought up by the same genius who added the 3.3V reset |
| 13 |
> pin to the SATA standard. |
| 14 |
|
| 15 |
Is there a way to determine if a drive on sale is SMR *before* purchase? I |
| 16 |
assume after purchase it is a matter of filling up the drive with zeros and |
| 17 |
keeping an eye on it stalling for minutes at a time; or is there some hdparm/ |
| 18 |
smartctl output to inform accordingly? |
Archives