Re: [LAT] [Fwd: [pure:dyne] a working rt-kernel -- please test]

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: krgn <k.gebbert@...>
Cc: <linux-audio-tuning@...>
Date: Friday, August 8, 2008 - 1:39 pm

Hash: SHA1

krgn wrote:

I should have said: without rtirq the setup is not really usable for
professional sound-production or live-performance, but handy nonetheless.

> really? how so?
because you can not guarantee that soundcard I/O is handled in time.
you might just as well run a lowlatency kernel without RT.

> I mean I can understand what it doesn, but I personally

The general I/O performance may even go down; since fi. the sound-card
would be allowed to /interrupt/ network-i/o. - In >99% of cases the
system will run without RTirq as it will with RTirq.

If we reach a more stable 2.6.26-rt - we should ask the PPL on
ardour-users ; some of them do 64 or 128 audio-channels and you will
definitely experience a difference there.

> that said, I

heh, hints are hard to come by.

most of the time I run at 64 * 3 (for recording) and 1024 or 2048 (for
mastering); mobile via USB, if I need more channels via 1394. The
build-in HDA on this TP-X60s does only "work" at 128, 1024 and up, but
that's OT; i mostly use it only as "phone". - I use max. 10
hardware-channels, but occasionally go above 256 jack ports.

I never succeeded to get a Xrun free setup without rtIRQ - but the hdsp
multiface PCI/PCMCIA interface may be more /forgiving/ that the USB or
firewire stack.

Version: GnuPG v1.4.9 (GNU/Linux)

Linux-audio-tuning mailing list

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
Re: [LAT] build ALSA debian way, Jaromír Mikeš, (Tue Oct 7, 11:03 am)
Re: [LAT] [Fwd: [pure:dyne] a working rt-kernel -- please te..., Robin Gareus, (Fri Aug 8, 1:39 pm)