I'm looking at the scheduling routines in sched.c in the kernel 2.2.1,
and I have some questions regarding the timer. My understanding is that
every 10 ms a timer interrupt comes and the kernel checks if it needs
to do a context switch or not.
So, assuming an SMP machine and an x86 architecture, my two questions
are
- which CPU is interrupted by the timer ? Is it always the same ? If
not, where should I look to the mechanism of CPU selection ?
- if we wish the interrupted CPU to preempt some of the other CPUs, is
this possible ? I understand there are some kind of interrupt mechanism
between CPUs.
Thanks in advance
Hugo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/