TRIM support for UFS?

[Julian Elischer]

On 12/9/10 10:13 AM, Kirk McKusick wrote:
> Other than the nit pointed out by Pawel, the diffs look good to me.
> You should consider adding the -t option to newfs so that the TRIM
> option can be specified at the time the filesystem is created (as
> a general rule, anything you can do with tunefs should also be
> possible with newfs).
>
> I agree with your decision to let administrators opt-out of doing
> TRIM. If experience shows it to be generally useful to have it on,
> we can change the default to enabled later. If we do change the
> default to enabled, then we will want to delete the warning about TRIM
> not being supported by the underlying disk that you added at mount
> time as we would start getting a lot of them for all the non-SSD disks.
>
> 	Kirk McKusick
>
I echo the above.
I am very happy to see this happen, and if it goes into 8.x I'll try see
that we (fusion-io) support it in our FreeBSD driver as soon as we can.

Several people have asked why trim is important for flash based devices..

The answer is that 'trimmed' packets get added back to the 'free pool
of pages available for a flash device to use and that helps in two ways.
firstly the average free space recoverable when you wring out a used
block of sectors increases, meaning that you have to garbage collect
fewer of them, which means that you have less overhead eating into
your performance, and secondly, when you start off after a period of
low utilisation, you have more headroom to write into before you need
to start garbage collection.  it's a win-win..