> I spent yesterday testing out my sg device driver with
> Jaroslav's DMA page allocation patch. A discussion of
> the tests and the results (with a section on memory
> issues) can be found at:
> http://www.torque.net/sg/s_index.html
>
> Basically it all went very well. However for my test
> configuration the 2 MB chosen for the DMA page pool
> size wasn't quite enough. So I think we need the kernel
> parameters as suggested by Dan Hollis.
>
> Also the implementation seems to give up when the
> 2 MB is exhausted without checking the main pool.
> [Hopefully I'm wrong here].
>
> This patch is obviously not architecturely independent
> so we need to think how to handle this. For example,
> the second page pool (for DMA) is only generated on
> architectures that need it.
I made this WWW page about this problem:
http://www.alsa-project.org/~perex/page_alloc.html.
Jaroslav
-----
Jaroslav Kysela <perex@suse.cz>
SuSE Linux http://www.suse.com
ALSA project http://www.alsa-project.org
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/