> > My suggestion is that you recompile X with this macro set to false - so that X
>doesn't
> > try to disable irqs and see if that fixes your problem. I suspect that this is not
> > your problem.
>
> You are correct that it is probably not the dissabling of interruprts
> that is the problem, bacuse that is only used in a few places (the ATI
> driver and in SupperProbe) and only to do the clockprobing.
Video drivers can hose RTLinux/RTAI by writing to a command FIFO on the
video board without first checking if it's full. In the past some
Windows drivers have done this as an "optimization" (it speeds up the
common case by eliminating a PCI read). A write to a full FIFO will
stall the PCI bus (and the rest of the machine) - this condition can
last for many milliseconds.
I don't know if this is what you're seeing, but it is consistent with
low RTL latency on a quiet box and high RTL latency when you drag a
window around. The stream of blits generated by dragging a window can
easily fill up a command FIFO.
If this is the case, the solution is to either convince the driver
writers that they are doing something wrong, or if that doesn't work
then distribute patches and warn the RTL community about which drivers
misbehave.
John Regehr
On Mon, 20 Nov 2000, Erwin Rol wrote:
>
>
> [EMAIL PROTECTED] wrote:
> >
> > On Mon, Nov 20, 2000 at 10:20:16AM +0100, Erwin Rol wrote:
> > > hard way. But basicly what you are saying is ,
> > > "sory you just can't use X with realtime linux" ? If thats true realtime
> > > linux
> >
> > That's not at all the case. X has, for a long time, used the intel specific
> > ioperm calls to use cli/sti in user mode.
> > The RTLinux patch, at one time, caught ioperm calls and complained. But we found
> > that the number of X-servers that used this feature was small and dwindling, and
> > the problem became not significant. I don't know if the new X makes the mistake
> > of going back to this design - I suspect not because ioperm is totally non-portable
> > out of x86.
> Well they are using ioperm on about all the iX386 OS's, so i gues they
> still like to use it.
>
> I am aware that X has been used for a long time with RT linux , but has
> anybody ever tried XFree 4.0.x ? Because there are big changes to the
> internal structure for things like DRI and so on.
>
> I will hack some more on it tonight when i get home, expect some more
> detailed info on what worked and what did not work :-)
>
> I am very interested to hear if someone is running RT-Linux/RTAI on
> linux 2.2.16 with XFree 4.0.1 and how good it works !
>
> - Erwin
> -- [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/
>
-- [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/
