1 Mar
2013
1 Mar
'13
12:55 p.m.
On Fri, 01 Mar 2013 12:41:29 +0100, Harry van Haaren
<harryhaaren(a)gmail.com> wrote:
Hey all,
I'm currently attempting to stress test my setup of -rt kernel, rtirq
scripts, and a Jack client program I've been working on.
So my idea is to create a script that runs the programs, and also a
cpu-load generating program (cpuburn or alternative).
Then collecting stats based on Xruns, % DSP load, etc.
I intend to show (trough brute force) that an application is RT capable
on
machine X with a latency of Y ms.
Of course this won't be 100% representative, but the stats will show some
RT-safe-ness.
Has anybody done this kind of profiling / stress testing with JACK
before?
Hints / tips / advice / etc welcomed! -Harry
As far as just putting stress on the CPU, that is perhaps a good way to
determine just the fact that the RT process is not affected by full CPU
load. One that I see a lot is people compiling a kernel while they do
audio testing.
If you involve specific parts of your hardware and related drivers, you
may see new results. Some have extremely poor performance with nvidia and
nouveau drivers for instance. But, that I suppose is beyond the scope of
what you want to test.
I don't know what a good neutral setup would be. Seems like there's a
great many things that could affect the results.