[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <83d29a0c-dab2-4570-8be0-539b43237724@paulmck-laptop>
Date: Thu, 3 Oct 2024 05:45:47 -0700
From: "Paul E. McKenney" <paulmck@...nel.org>
To: Peter Zijlstra <peterz@...radead.org>
Cc: vschneid@...hat.com, linux-kernel@...r.kernel.org, sfr@...b.auug.org.au,
linux-next@...r.kernel.org, kernel-team@...a.com
Subject: Re: [BUG almost bisected] Splat in dequeue_rt_stack() and build error
On Thu, Oct 03, 2024 at 02:28:24PM +0200, Peter Zijlstra wrote:
> On Thu, Oct 03, 2024 at 11:27:07AM +0200, Peter Zijlstra wrote:
> > On Thu, Oct 03, 2024 at 10:47:43AM +0200, Peter Zijlstra wrote:
> > > On Thu, Oct 03, 2024 at 10:40:39AM +0200, Peter Zijlstra wrote:
> > > > On Wed, Aug 21, 2024 at 02:57:16PM -0700, Paul E. McKenney wrote:
> > > >
> > > > > My reproducer on the two-socket 40-core 80-HW-thread systems is:
> > > > >
> > > > > tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 1m --configs "50*TREE03" --trust-make
> > > > >
> > > >
> > > > This gets me a very long stream of:
> > > >
> > > > Results directory: /usr/src/linux-rcu/tools/testing/selftests/rcutorture/res/2024.10.03-09.30.33
> > > > tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 1m --configs 50*TREE03 --trust-make
> > > > TREE03 -------
> > > > QEMU error, output:
> > > > cat: /usr/src/linux-rcu/tools/testing/selftests/rcutorture/res/2024.10.03-09.30.33/TREE03/qemu-output: No such file or directory
> > > > TREE03.10 -------
> > > > QEMU error, output:
> > > > cat: /usr/src/linux-rcu/tools/testing/selftests/rcutorture/res/2024.10.03-09.30.33/TREE03.10/qemu-output: No such file or directory
> > > > ...
> > > >
> > > >
> > > > Did I not do it right?
> > >
> > > Urgh, for some reason my machine doesn't auto load kvm_intel.ko and then
> > > proceeds to not do anything useful.. Let me try again.
> >
> > Works a ton better now, obviously no splat yet :/
>
> I have by now ran many hundreds of 1m TREE03 instances, and not yet seen
> anything. Surely I'm doing it wrong?
I ran 100*TREE03 for 18 hours each, and got 23 instances of *something*
happening (and I need to suppress stalls on the repeat). One of the
earlier bugs happened early, but sadly not this one.
Thanx, Paul
Powered by blists - more mailing lists