On Monday 03 December 2001 17:31, Stefan Doehla wrote:
[...]
> Too much work meant:
> Are you a realtime programmer or a XFree programmer? (Personally: I
> wouldn't like to read some 1000 lines of code I don't understand ...)
> If you can fix the problem - do it ...
Well, for anyone with the time and motivation to hack XFree86;
1. Some drivers don't bother to check the hardware
command FIFO status before writing, which occasionally
results in the CPU blocking on the PCI bus - which
really means *blocking* - even busmaster DMA is
delayed! In some cases, this can be fixed with a
configuration option, but I don't know if it fixes
the problem with all drivers, or all cases.
2. Some drivers/servers disable IRQs directly using CPU
instructions (to implement fast sync constructs
without kernel calls?) - which means that no kernel
patch can prevent this from affecting RT IRQ latency!
Don't know if this is still the case with 4.1.x - and
no one knows for sure what's in those nVidia
drivers... ;-)
//David Olofson --- Programmer, Reologica Instruments AB
.- M A I A -------------------------------------------------.
| Multimedia Application Integration Architecture |
| A Free/Open Source Plugin API for Professional Multimedia |
`----------------------------> http://www.linuxdj.com/maia -'
.- David Olofson -------------------------------------------.
| Audio Hacker - Open Source Advocate - Singer - Songwriter |
`-------------------------------------> http://olofson.net -'
-- [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/
