I ran a simple test to measure the time required to perform 120,000 task
switches:
// Both tasks A and B were initialised for FPU, B's priority < A's
TaskA()
{
for(i=0;i<60000;i++) rt_task_resume(B);// do nothing else
}
TaskB()
{
for(;;) rt_task_suspend(B);// do nothing else
}
Using a 233 MHz MMX processor I get the following elapsed times:
RTLinux V1 .753 second
RTAI .303 second
Can someone explain why RTAI is so much faster despite the SMP overhead?
--
-------------------------
- POSEIDON CONTROLS INC -
- Phone: (450)-659-9186 -
- Fax: (450)-659-0014 -
--- [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/
