On Wed, 8 Mar 2000, Boris Okun wrote:
>Andrea Arcangeli wrote:
>
>> The timer irq could keep running on the same CPU with irq disabled for
>> more than the rtdsc lower 32bits wrap around. Thus the per-cpu rdtsc info
>
>Why? Could you explain the difference (or point me to the refs)?
>Who decides where timer irq happens?
>If this is the case, I certainly agree with the statement below.
>I don't see it here.
I understand it's not easy to reproduce (mainly with two cpus) but the
IO-APIC chooses the CPU where to deliver irq in hardware and you can't
know which CPU will run the irq handler. So you shouldn't rely on the
timer irq to run on all CPUs in the system in a certain amount time.
Andrea
-
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/
This archive was generated by hypermail 2b29 : Wed Mar 15 2000 - 21:00:15 EST