On Wed, Mar 22, 2000 at 12:03:41PM +0000, Paolo Mantegazza wrote:
> [EMAIL PROTECTED] wrote:
>
> > I'd love to see a solid timing study showing that. Can you do
> > ping -f someone &
> > while true; do tar cf /dev/null /dev/hda_x ; done; &
> > while true; do make -j 4 bzImage ; done; &
> > and still get sub ms latencies?
> > That would be cool.
>
> Nice challange. I took it, in a slightly different way, as follows:
>
> ping - f server
> do make -j 4 bzImage
> while "true"; do ls -aR /; done
> while "true"; do cat /proc/interrupts; done
>
> while running 3 hard real time tasks at 10 Khz in oneshot mode, amid 12
> Linux SCHED_FIFO, in USER SPACE as a nonroot user .
>
> The highest priority hard real time task measures its scheduling
> latency. After testing for 1 hour I got the following results:
> MAX JITTER 30 us,
> AVERAGE JITTER 10 us.
I know that hard RT gets as good or better measurements.
The question is whether the Linux "low latency patch" by Ingo can assure
sub millisecond bounds for Linux processes and it seems that this is not
what you are measuring -- or did I misunderstand?
(BTW: from the Linux man page:
As SCHED_FIFO and SCHED_RR processes can preempt
other processes forever, only root processes are allowed to activate these
policies under Linux.
)
--
---------------------------------------------------------
Victor Yodaiken
FSMLabs: www.fsmlabs.com www.rtlinux.com
FSMLabs is a servicemark and a service of
VJY Associates L.L.C, New Mexico.
-- [rtl] ---
To unsubscribe:
echo "unsubscribe rtl" | mail [EMAIL PROTECTED] OR
echo "unsubscribe rtl <Your_email>" | mail [EMAIL PROTECTED]
---
For more information on Real-Time Linux see:
http://www.rtlinux.org/rtlinux/