Eraseblocks torture: OneNAND results
dedekind at infradead.org
Fri Dec 8 08:52:30 EST 2006
On Fri, 2006-12-08 at 14:43 +0100, Ricard Wanderlof wrote:
> Isn't 100000 a figure quoted by the flash manufacturer to be the _minimum_
> number of erase cycles, a specification which all devices must meet, even
> at extreme operating conditions (e.g. high temperature and extreme supply
> voltages)? That would imply that during more ordinary conditions, a random
> sample of flash chip would very likely be erasable many more times.
Probably. Not sure. Need to carefully look to the manual. Do not have it
now handy. But probably you are right. Also HW guys say that such a very
frequent erase may matter.
> Another thing: Why implement it as a kernel module? Speed I would assume?
Yeah, wanted to make it quicker.
Artem Bityutskiy (Битюцкий Артём)
More information about the linux-mtd