ZFS, OpenSolaris, Nexenta -- eating my words

Carl Youngblood carl at youngbloods.org
Sat Nov 19 12:54:30 MST 2005


I think you are being a little overly pedantic with your analysis. 
Moore's "law" is frequently applied to fields that are related, and
one could say that cost per megabyte has roughly followed the same
curve as Moore's "law" (which is far from a law anyway and is more of
just a general description of a trend).  I don't think having 128-bit
addresses is a big deal because each increase in address size gives an
exponential increase in address space, so the cost is probably not
huge, and we can definitely say that they won't be needed larger
addresses any time soon.  So I wouldn't call this a stupid decision
but rather a very smart one.  The performance characteristics they
describe also seem to support their decision.

Your accusation of technobabble is somewhat exaggerated.  I think I
understood what they meant, which was basically that the amount of
storage that could be contained on planet earth would not exhaust the
address space.  Granted this seems like a fairly dubious and highly
theoretical claim, but I'm not sure it was complete crap.

Overall I think you are quibbling about minor technicalities and
failing to acknowledge what most would call a great achievement.

Carl

On 11/19/05, Michael Halcrow <mike at halcrow.us> wrote:
> Slide 19 is just ridiculous. They totally misapplied Moore's Law to
> justify their 128-bit address space design decision; those who
> actually read Moore's paper would know that Moore's Law actually
> refers to the density of functional components on silicon devices, not
> the density of magnetic domains on hard disk platters. They are
> entirely different technologies with entirely different trends.
>
> Incurring the overhead of a 128-bit address space and justifying it by
> saying that it will be needed a couple of decades from now is the same
> class of fallacy as incurring the cost of a 512-bit symmetric key
> while making wild conjectures about computational power a couple of
> decades from now. That ``exceeds quantum limit of earth-based
> storage'' claim is pure marketing babblespeak that has no bearing on
> real-life problems in the marketplace, like those caused by eating up
> a whole 128 bits for every address you need to pass around in ZFS.



More information about the PLUG mailing list