mount time (was Re: Fwd: Hello -- NAND/NOR Flash design for GTA02)
andy at openmoko.com
Thu Jan 17 12:46:33 CET 2008
-----BEGIN PGP SIGNED MESSAGE-----
Somebody in the thread at some point said:
> Andy Green wrote:
>> This is going to be a win all over Werner, since no doubt the usermode
>> init is held back by raw NAND throughput, great work!
> Thanks :) Read performance drops noticeably if we don't have hardware
> ECC. With it, I get about 6.7 MB/s, without it 5.2 MB/s. (nanddump
> from a "raw" MTD partition.)
So just to recap -- by not shooting ourselves in the foot with the
broken image generation, we end up with the performance anyone else
would have started with... and HW ECC started working because we moved
to 2.6.24, again anyone else would just tick that box now.
Still, from where we were yesterday, it is a big leap.
I'm looking forward to see if having normal relations with the NAND now
has any other positive effects on the userspace experience.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.7 (GNU/Linux)
Comment: Using GnuPG with Fedora - http://enigmail.mozdev.org
-----END PGP SIGNATURE-----
More information about the openmoko-kernel