Re: [LAU] Kxstudio RT kernel vs low latency

>> On Jul 28, 2014, at 3:22 PM, James Stone <jamesmstone@email-addr-hidden> wrote:

>> Thanks for this hint!
>>
>> I played around with adding
>>
>> processor.max_cstate=0 idle=halt to the boot parameters, which had
>> the same effect as running cyclictest with /dev/cpu_dma_latency = 0..
>>
>> I then removed this and had a poke around in the bios, and found that
>> the main culprits for the xruns were C6 mode, and "AMD Power Now".
>> Disabling these, and I now have an xrun-free experience with
>> frames/period = 32/2 with pulseaudio/jack on my Scarlett 2i4, which is
>> pretty amazing for a USB device IMO!
>>
>> There was also CPD mode and CState Pmin, which I disabled initially,
>> but these don't seem to have any impact on xruns on my system. Cstate
>> pmin seems to affect the reported DSP load - but otherwise doesn't
>> affect xruns - so I think it's safe to keep on (and maybe is saving
>> some power??). CPD mode doesn't seem to have any impact at all.
>>

Hi Russell!

>
> Great follow on discussion from you guys!
>
> I have many hiding spots to probe as it were. I do want to ask about older bios laptops tho. Running intel dual core 1.6ghz... So the application of these (ACPI? APM?) are handed off to OS software layer? Kernel module or whatever? If so (pls correct where I'm off) how to use equivalent control of settings from CL or tools? Given the sig change of stable state that Jame's refers to, it would be helpful to document this stuff somewhere under the "realtime Linux audio tweaks". The 32/2 with stability over USB2 would be a big deal in my case. I've not been able to come within screaming distance of that result.
>

OK.. There are a few things that spring to mind. I am not sure that
the CPU mode switching thing is likely to be an issue on an older
board, and even if it is, if you deactivate it, it is going to
seriously impact on power efficiency and heat buildup on a laptop..
Anyway, easiest way to test if it is that to run cyclictest with:
"sudo cyclictest -m -n -Sp99 -i100 -d0" at the same time as running
jackd and see if it makes any of the xruns go away. if it doesn't it
is something else!

The second thing I wanted to point out, is my "xrun free" experience
at 32/2 is very delicate.. Too much CPU strain makes the xruns pop up
again.. so something like Mixbus (which is a massive resource hog) is
definitely not runnable at this latency. Anyway, for recording there
is not much need to run at such low latencies. 1024/2 is absolutely
fine unless you need realtime software monitoring. I would usually use
256/2 at which latency, software monitoring is still fine, but
hardware (dry mix) monitoring also possible on my system. Probably
lower is possible with PCI etc. but not on my USB soundcard on my rig.

If you need to record at such low latencies try using something like
qtractor, or maybe Ardour?

> To elaborate on the end game (I hope) for this laptop... I have many occasions where a flexible, compact, simple, yet functionally powerful recording rig is useful. {I'm talking only for small stuff... < 12 live channels.}
>

This sounds like a fair load to me - not super-light.. but should be
doable with some flexibility on the need for ultra low latency.

James
_______________________________________________
Linux-audio-user mailing list
Linux-audio-user@email-addr-hidden
http://lists.linuxaudio.org/listinfo/linux-audio-user
Received on Tue Jul 29 12:15:02 2014