Re: [BUG] local_softirq_pending storm

[Thomas Gleixner <tglx@linutronix.de>]

On Sun, 2007-05-20 at 02:53 +0530, Anant Nitya wrote:
> > 1 == TASK_INTERRUPTIBLE, so we know that ksoftirqd was not woken up. At
> > least it is not a scheduler problem.
> >
> > I work out a more complex debug patch and pester you to test once I'm
> > done.
> No problem :)

You asked for it :)

Please patch 2.6.22-rc2 with

http://tglx.de/projects/hrtimers/2.6.22-rc2/patch-2.6.22-rc2-hrt2.patch
and
http://www.tglx.de/private/tglx/ht-debug/tracer.diff

Compile it with the config

http://www.tglx.de/private/tglx/ht-debug/config.debug

You should find something like:

(         swapper-0    |#0): new 67173 us user-latency.

along with the familiar "NOHZ ......" message in your log file.

Once that happened please do:

$ cat /proc/latency_trace >trace.txt

compress it and send it to me along with the full dmesg output or put
both up to some place, where I can download it.

Michal,

IIRC you encountered the same P4/HT related wreckage. Can you do the
same ?

Thanks,

	tglx


-
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/