[ardour-dev] Latency: AGP vs PCI video card and XFS journalling vs not

[Eric]

I know I can do hardware monitoring and therefore set the sample size
high, but I would like to be able to monitor with some effects.  Has
anyone ever been able to do this at reasonable latency?

eric.

On Mon, Feb 23, 2004 at 07:30:22AM -0600, Jan Depner wrote:
> On Mon, 2004-02-23 at 03:10, Tommi Sakari Uimonen wrote:
> > 
> > For recording purposes, "write as much as possible, as fast as possible",
> > (so no reading other tracks at the same time, just writing) I found ext2
> > to be fastest (ext3,reiserfs were included in the test), since it doesn't
> > spend time journaling.
> > 
> 
> With a Delta 66 you don't need a small sample size which helps with the
> first part.  I have to disagree with the ext2 part.  Check out Mark
> Knecht's filesystem tests on my page
> (http://myweb.cableone.net/eviltwin69/Arcana.html).  He used Benno's
> latency test for his comparison.  I use Reiser and I get fewer xruns
> than I did with ext2 or ext3.
> 
> Jan
> 
> 

-- 
http://ir.iit.edu/~ej