[Discuss] SSD drives vs. Mechanical drives

[bogstad at pobox.com (Bill Bogstad)]

On Tue, May 6, 2014 at 11:29 AM, Mike Small <smallm at panix.com> wrote:
> Kent Borg <kentborg at borg.org> writes:
>> Go ahead and trust SSDs on par with HDDs. I am going to hold off until
>> I see it, let the young industry grow up a lot more.
>
> Is the failure mode for SSDs different? It happened that a newish
> Windows 7 machine I use at work ran out of memory and crashed without
> syncing to disk one day last year. I was surprised to find that the SSD
> on the machine had huge numbers of corrupt blocks across many source
> files and system dlls (but somehow it limped along to boot and be
> somewhat useable). The D: drive was a HDD and had no corruption at
> all.
>
> Perhaps this is off topic since it was a software/OS (and not one most
> here care about I assume, I know I don't)/file system "failure" not a
> hardware failure. But it was very surprising to me. From experience at
> home my expectation from unexpected shutdowns is just a long fsck at
> next start up, at worst some file and directory structure that was
> recently written being lost or corrupted. This was all over the place,
> stuff that would have been opened for read and not written to
> recently. I don't get it.

Guessing here....

1.  SSDs are constantly moving data around in order to do wear leveling.
2. Not all SSDs have batteries/super capacitors to finish those activities if
power is lost.

If the windows system was power cycled in such a way that the SSD wasn't warned,
it might lose things.   Disk drives can have similar issues if they
are caching writes,
but typically there is less data and I think that some of them pull
energy from the rotation of
the platters to finish up.  Or at least I seem to recall hearing about
that once.

Bill Bogstad