Messages in this thread | | | Subject | RE: Latency traces I cannot interpret (sa1100, 2.6.15-rc7-rt1) | Date | Fri, 30 Dec 2005 11:35:22 +0100 | From | "kus Kusche Klaus" <> |
| |
> From: Ingo Molnar > there seem to be leaked preempt counts: > > <idle>-0 0.n.1 8974us : touch_critical_timing (cpu_idle) > > we should never have preemption disabled in cpu_idle(). To > debug leaked > preemption counts, enable CONFIG_DEBUG_PREEMPT.
I enabled CONFIG_DEBUG_PREEMPT.
I still have that latency trace in <idle>-0 with that line at the end. In fact, it is the most common trace on this system: I always get that trace immediately after resetting the latency tracer, always close to 9 ms (until an even longer latency happens).
Moreover, I looked up the address shown in asm_do_IRQ in the second line of all those traces. <idle>-0 0D..1 1us!: touch_critical_timing (default_idle) <idle>-0 0D..2 8841us+: asm_do_IRQ (c021da44 1a 0) It is always the same address, and it is in "cpu_idle".
However, CONFIG_DEBUG_PREEMPT remains silent: No bugs, no warns, just plain nothing in the syslog.
-- Klaus Kusche (Software Development - Control Systems) KEBA AG Gewerbepark Urfahr, A-4041 Linz, Austria (Europe) Tel: +43 / 732 / 7090-3120 Fax: +43 / 732 / 7090-6301 E-Mail: kus@keba.com WWW: www.keba.com - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |