Philip Blundell (pb@nexus.co.uk)
Mon, 19 Oct 1998 11:33:25 +0200
>"port cache" algo. Currently I cache the parallel port base address and
>perform direct IO based on this. If I had to resolve the port base address
>each time I wanted to access an IO port the look-up cripples the driver.
Is it really that bad? I guess two pointer chases is a bit much but I'd
expect the time to do that to be dwarfed by the time for the ISA cycle.
I'd be interested in measurements of performance for your direct I/O method
against going through parport. If there really is a problem then I'll
certainly have a think about ways to get the overhead down.
>The question I have, does anyone use parport with a parallel port driver other
>than parport_pc AND have a ZIP drive?
Not that I'm aware of but this may change. Some of the m68k people might well
be keen on being able to use Zip drives.
p.
-- To unsubscribe, send mail to: linux-parport-request@torque.net --
-- with the single word "unsubscribe" in the body of the message. --
This archive was generated by hypermail 2.0b3 on Wed 30 Dec 1998 - 10:18:37 EST