> > I have read a fair amount of the literature on RTLinux available on the
> > web site and it seems to me that the major problem with using RTLinux
> > would be its interrupt latency. From the literature it seems that the
> > worst case interrupt latency can be as high as 15 to 20 us - this is a
> > large amount of the available 100 us and would be a major problem.
> >
> carfull with these numbers , these are worst case , on a C40 you can get
> simmilar numbers if the context switch does a full STI/STF on all 12 40bit
> regs and STI on the other 20 ,especially if you have to do this to a
> off-chip DRAM, or need to take sychronisation of COMPORTS/DMA into account
> (infact it can get quite a lot worse than 15us)....
Point taken.
> > I would imagine that this interrupt latency is solely caused by the amount
> > of time required to switch contexts - i.e. push all the registers etc.
> >
> > So the question is - Is this large latency due to the structure of context
> > switching programmed into the interrupt executive within RTLinux, or is it
> > due to the structure of the hardware - i.e. the amount of x86 instructions
> > required.
>
> it is largely hardware related, you are seeing the limitations of the x86
> not of RTLinux here.
At this point in time is RTLinux ported to any other (better) hardware -
something with good interrupt handling etc? Or is the porting a trivial
matter?
To continue the thread, what would be some good hardware to use for a system
such as I have described? Something with fast interrupt response.
--
Andrew Tuckey
Postdoctoral Research Scientist
Eindhoven University of Technology
EE Dept., Group EMV, Room EL 1.13
PO Box 513 Phone: +31 - 40 2 47 3895
5600 MB EINDHOVEN Fax: +31 - 40 2 43 4364
The Netherlands Email: [EMAIL PROTECTED]
-- [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/
