With a little example, perhaps it could be easier to understand what I want to know...
First I'm interested with the RT tasks side. Imagine, I've 2 tasks : - first cyclic task at 10 ms (priority +) - second cyclic task at 100 ms (priority -) If my first task take 8 ms to execute at each period (10 ms), then my second task will have only 20 ms maximum free time to execute during the free time (when task 1 waiting). What I would know is : 80% for task 1. And 10% for task 2, if task 2 take 10 ms at each execution... For the first task (priority +), I could use 2 getthrtime() at the start and the end to have an idea, but for the second task which use free time when the first task is not running, how to do ? Another question: When we see the idle time for the linux side, does it take into account the fact that some RT tasks are running ? Thanks. >> Hello everybody, >> >> How can we know the CPU load taken with the tasks running under RTLinux, and if possible, task per task ? >> >You need to explain your concept of CPU-load - do you mean the Linux non-RT load ? or the RT-side. On the RT-side the issue is simply, ither there is a RT-task running or the idle task there is no load indication for the number of runable tasks What do you mean by CPU-load "task by task" ? hofrat --- Marc Le Douarain "[EMAIL PROTECTED]" http://www.multimania.com/mavati -- [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/
