23 Jun
2006
23 Jun
'06
8:12 a.m.
Lee Revell wrote:
On Fri, 2006-06-23 at 09:44 +0930, Jonathan Woithe
wrote:
Why not?
If the 1394 test user thread has a lower priority, and the ohci1394 irq
priority is also lower, there is no reason for the latency tester to be
preempted by them.
Despite what the log says, this was running a 2.0
GHz "Dothan"
Centrino CPU. Kernel was 2.6.16-rt25, distro was Slackware 10.2. Both
the stress tester and the monitor were run with RT privilege access.
The firewire interface used has a TI OHCI chipset.
I apologise that the run was particularly short and that therefore the
statistics aren't particularly good, but it does seem to confirm the
observations you made on your machine. The large latencies only occur
when the stress tester is running.
What if you run the latency tester at RT priority 99? Testing at 80 is
not particularly useful.
If anything else is running at 99, what happens if you
lower those other
processes to 98?
I'll have to recheck, but if I remember correcly I have done this
experiment. The only thing at 99 is the system timer. I tried giving it
a lower priority than the latency test thread, which didn't change anything.
Pieter