FreeBSD and SSD drives

[Adam Vande More]

On Sat, Feb 12, 2011 at 6:14 AM, Dave <dave at g8kbv.demon.co.uk> wrote:

> Define "a *lot*".   If you look up the spec's on the common (currently)
> available SSD systems, it's only in the 10's of 1000's writes.  Pittiful
> compared to magnetic media.
>

Chances are on many setups, by the time you've written enough data to
significantly wear out the drive your magnetic media would died of
mechanical failure long before.  Purchase what you need MLC/SLC.


> The way they work too, if you write one "sector" you actualy re-write a
> much larger block of memory.


Depends on full setup, the write amplification effect on the X-25's is about
1.1x.  Recent SSD's all are much more efficient compared to when these were
large, legitimate concerns.


> Wear leveling, not that common with SSD
> Hard Drives, but very common with USB (Flash) memory sticks,
>

Completely wrong even the first gen modern SSD's had wear leveling built in.


> SSD's have a place, but not for things like swapfiles or working data
> that changes a lot..
>

I guess ZIL's wouldn't be a good use for such devices either.  Perhaps you
can inform FS designers that they are doing it wrong.

-- 
Adam Vande More