diagnosing interrupt storms?

[Scott Long]

On Tue, 9 Mar 2004, Alfred Perlstein wrote:
> * Scott Long <scottl at freebsd.org> [040309 00:08] wrote:
> > On Mon, 8 Mar 2004, Alfred Perlstein wrote:
> > > At a certain point after booting my SMP 5-current box gets all
> > > weird, typically I see 50%+ time spent in interrupt.  If I run "top
> > > -S" I typically see one of the ithreads using 50% cpu.
> > >
> > > I'm trying to figure out what it's doing, what has gone wrong etc.
> > >
> > > Are there any sysctls to look at or things I can do to diagnose
> > > this?
> > >
> > > (also I my laptop still can't boot with top-of-the-tree current) :(
> > >
> >
> > A dmesg here would help, of course.  You might have a similar problem as
> > me, where the SMI interrupt is misconfigured as active-low instead of
> > active-high, so it storms the system.  Does disabling ACPI make a
> > difference?  Since it's SMP, does disabling APIC (and thus turning it into
> > UP) make a difference?
>
> dmesg doesn't report anything out of the ordinary.
>
> I will try your suggestions the next time I get wedged.
>
> thank you,

dmesg would show how the interrupts are assigned and routed.

Scott