Re: 2.6.11, IDE: Strange scheduling behaviour: high-pri RT process not scheduled?
From: Ingo Molnar <hidden>
Date: 2005-03-31 11:35:47
Also in:
lkml
From: Ingo Molnar <hidden>
Date: 2005-03-31 11:35:47
Also in:
lkml
* kus Kusche Klaus [off-list ref] wrote:
I've written a small test program which enables periodic RTC interrupts at 8192 Hz and then goes into a loop reading /dev/rtc and collecting timing statistics (using the rdtscl macro).
getting /dev/rtc handling right for latency measurement is ... tricky. The method i'm using under PREEMPT_RT is: chrt -f 84 -p `pidof 'IRQ 0'` chrt -f 95 -p `pidof 'IRQ 8'` ./rtc_wakeup -f 1024 -t 100000 you can get rtc_wakeup from: http://www.affenbande.org/~tapas/wiki/index.php?rtc_wakeup written by Florian Schmidt. do you see high latencies even with rtc_wakeup? Ingo