[PATCHv3 4/5] mtd: mxc_nand fixups

Ivo Clarysse ivo.clarysse at gmail.com
Fri Jun 25 10:46:44 EDT 2010


On Thu, Jun 24, 2010 at 9:27 AM, Sascha Hauer <s.hauer at pengutronix.de> wrote:
[...]
>
> BTW I observed that at least on i.MX27 the latencies introduced by
> waiting for an interrupt cause a significant performance drop. The
> driver gets much faster when we just poll all the time. I don't know how
> this affects system performance otherwise, but it may be a possibility
> to drop interrupt support at least for i.MX21. I have no idea how long
> the longest possible time we'd have to poll is though.

I'm noticing the same thing on i.MX21: when using interrupts,
"Scanning device for bad blocks" takes 982 (!) seconds.  When always
using polling, the same scan takes 'only' 500 seconds.


Ivo.



More information about the linux-arm-kernel mailing list