[OLPC-devel] Re: NAND flash controller speed.

[Thomas Gleixner]

On Mon, 2006-06-05 at 15:47 -0600, Ronald G Minnich wrote:
> ow. ow. ow. I don't think it is possible for price and debug reasons to 
> think about an asic from now to this fall.
> 
> I lost track of this a bit -- why the heck is this so slow? Is this a 
> chipset issue, or what? Are there any usb options we could use, since we 
> have usb on there anyway?

The USB solutions are similar to the CF-Card style IDE NAND controller
solutions. They emulate a block device and have their own internal magic
of handling the FLASH vs. wear levelling etc. You don't have access to
the raw FLASH chip. It's a know issue that those solutions are prone to
power fail problems. You have to make sure, that power is kept up for at
least 250, better 500ms after the last write access to the device. Also
there are issues with wear out depending on the filesystem you use on
top of the device.

	tglx