Mr. Culianu,
Did you see my post earlier on this subject? It covered these
issues nicely.
> Wait.. so in the kernel the rtf_put() call can fail if the fifo is too
> full?
No, Mr. Kavaler is wrong.
> I thought it clobbered the existing data, but, not actually
> failed.. hmm.
Despite what I wrote earlier, Mr. Kavaler is correct on this issue.
The call will fail with -ENOSPC if insufficient space exists in the FIFO.
This is consistent with the man page for rtf_put.
> And you are also telling me that a read()
> system call in
> userland will NOT be interrupted for the duration of the system call?
> That is good news on one hand, but on the other I suspect such things
> affect real-time scheduler jitter :)
It is not obvious to me from the source that this is guaranteed.
Only a small portion of the read is protected with spinlocks and they do
just a small fraction of the total work. I would not count on this behavior
unless you test it thoroughly yourself.
Regards,
Steve Cohen
--------------------------
Stephen D. Cohen
Xybion Sensor Positioning Systems
11528 53rd Street North
Clearwater, FL 33760
Voice: (727) 299-0150
Fax: (727) 299-0804
[EMAIL PROTECTED]
www.xybion.com
-- [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/
