Woodhouse on flash storage

Martin Langhoff martin.langhoff at gmail.com
Tue Oct 6 07:19:07 EDT 2009


On Tue, Oct 6, 2009 at 12:43 PM, Mitch Bradley <wmb at laptop.org> wrote:
> The raw-access device will not be cheaper, because any possible (small)
> savings in silicon area will be overwhelmed by the lower-volume factor.  The
> managed-NAND  solution will "lock in".

Yes, that's what usually happens, and the most likely scenario.

Given that there are 2 components at play, if the controller that
achieves lock-in can't be matched (either via unmatched cleverness or
- more likely - patents) and is expensive there may be a reason for
vendors of good quality NAND to try a different tack. The "commoditize
your complements" tack.

As for the validity of this scenario, it's just me lighting a candle
to a hope. Chances are that there will be a couple of winning
controllers, they will be acceptably priced, and whatever possible
advantage of raw access will be marginal as to be drowned by the cost
and risk.

As Scott hints, it may well be a missed opportunity. We are pros at
collecting those in the attic.


m
-- 
 martin.langhoff at gmail.com
 martin at laptop.org -- School Server Architect
 - ask interesting questions
 - don't get distracted with shiny stuff  - working code first
 - http://wiki.laptop.org/go/User:Martinlanghoff



More information about the Devel mailing list