PATCH: Forcible delaying of UFS (soft)updates

[Oliver Fromme]

Chris Dillon <cdillon at wolves.k12.mo.us> wrote:
 > On Wed, 16 Apr 2003, Terry Lambert wrote:
 > > [Flash memory]
 > > The life expectancy of these devices is really, really
 > > underestimated.  In practice, I've seen two million write cycles
 > > from some of these in lab machines which get rewritten pretty often.
 > 
 > I realize they have what looks like a really big number of writes on a
 > human scale, but to a computer which does things methodically day in
 > and day out without stopping, those writes can add up relatively
 > quickly.  Even with a life of two million write cycles, the
 > "occasional" 30-second round of updates that happen to write the same
 > bits over and over

The controller in things such as CompactFlash cards will
_not_ write the same physical bits over and over.
Those beasts are clever enough to remap logical blocks
to different physical blocks upon each write access, so
that the written-to flash cells are evenly distributed
over the whole physical range.

You can probably update the atime of files 100 million
times and more without any problems, because all of those
100 million writes will end up on all different flash
blocks.  Of course, that's provided that there are also
areas in your filesystem which are less frequently written
to, but that's usually the case (how often do you rewrite
binaries and libs?).

So I agree with Terry that the life expectancy of flash
devices really underestimated.

Regards
   Oliver

-- 
Oliver Fromme, secnetix GmbH & Co KG, Oettingenstr. 2, 80538 München
Any opinions expressed in this message may be personal to the author
and may not necessarily reflect the opinions of secnetix in any way.

"If you do things right, people won't be sure you've done
anything at all." -- God in Futurama season 4 episode 8