vdev/pool math with combined raidzX vdevs...

[Bob Friesenhahn]

On Wed, 11 Jul 2012, Jason Usher wrote:
>
> Thanks for responding.  So I must be mistaken, and the failure 
> probability of each vdev is not additive ?  As I mentioned earlier 
> in the thread, I am not a probability person, nor would I trust my 
> own calculations if I tried.

The probabilty is indeed additive just as you say.  My point is that 
the fundamental integrity is offered at the vdev level.  If a vdev 
fails, then the whole pool is gone.  The MTTDL calculations for 
various vdev topologies vary by orders of magnitude, which tends to 
make the additive nature of more vdevs insignificant.

Here are some useful blog articles about MTTDL:

https://blogs.oracle.com/relling/entry/raid_recommendations_space_vs_mttdl

http://blog.richardelling.com/2010/02/zfs-data-protection-comparison.html

http://www.servethehome.com/raid-reliability-failure-anthology-part-1-primer/

Bob
-- 
Bob Friesenhahn
bfriesen at simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/
GraphicsMagick Maintainer,    http://www.GraphicsMagick.org/