[PATCH 0/2] Improve GTA02 NAND read performance by 41%

[Andy Green]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Somebody in the thread at some point said:

| I'm really lost here, don't know what else to do.  I'll get some
profiles on a
| soft-ECC and on a non-irq-based-NAND kernel to compare the results and
see if
| they also show this 'artefact'.  Maybe 'top' is actually wrong?  Any
ideas?

What you could do is control one or more GPIO (eg, LED) based on what
the code is doing, and measure that with a 'scope.  Because the platform
GPIO code is slow it can be worth doing it direct to the CPU GPIO
register.  You'll need interrupts locked out for the duration to remove
jitter unless it's the time-to-interrupt you are measuring.  That way
can learn the absolute duration of these things, the time between them
and the rough "density" of the actions.

- -Andy
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.9 (GNU/Linux)
Comment: Using GnuPG with Fedora - http://enigmail.mozdev.org

iEYEARECAAYFAkj9o9UACgkQOjLpvpq7dMonFACdH31vpM/h/WHtfHoVLjA19aMH
qGUAoINUR8V8On4Ts1BmpCc8QW9adakP
=ywjT
-----END PGP SIGNATURE-----