5 Mar
2006
5 Mar
'06
1:36 p.m.
Eric Dantan Rzewnicki wrote:
On Sun, Mar 05, 2006 at 02:02:18AM -0800, Florin
Andrei wrote:
No problems with dual 3.0GHz Xeons running either 2.6.13-1.1532_FC4smp
or 2.6.13-0.3.rdt.rhfc4.ccrmasmp
On Sun, 2006-03-05 at 03:35 -0500, Eric Dantan
Rzewnicki wrote:
Does anyone know if dual HyperThreaded Xeon's might impact this at all?
I've got a user reporting jackd dieing on such hardware with an rme
digi96/8 pad. It happens to be sharing and IRQ between these things:
10: 38948682 0 0 0 XT-PIC
libata, RME96, uhci_hcd:usb1, eth0
Haven't had a chance to get physical access to the box, yet, to do some
thorough sorting of the issue. But, just wondered if this might in
anyway be a possible source of problems.
Old school Linux Audio lore held that it was bad
to let your audio card
share an IRQ with anything else. Is this a myth, or still good solid
practical advice?
It might still have some influence, but nowadays the typical hardware is
so fast, it doesn't matter like it used to.
I'm getting pretty good latency with no xruns when running jackd with
real-time priority, despite INT 5 being crowded like hell: