Re: 4.2-rc5 rcu stalls.

[Dave Jones <davej@codemonkey.org.uk>]

On Wed, Aug 05, 2015 at 02:37:59PM +0200, Frederic Weisbecker wrote:
 > On Tue, Aug 04, 2015 at 08:12:50PM -0400, Dave Jones wrote:
 > > On Tue, Aug 04, 2015 at 12:54:35AM -0400, Sasha Levin wrote:
 > >  > On 08/03/2015 06:03 PM, Paul E. McKenney wrote:
 > >  > >> > Ugh, that doesn't revert cleanly.  Got something handy ?
 > >  > > I do not, but perhaps either Sasha or Frederic do.
 > >  > 
 > >  > I've attached a revert courtesy of Peter.
 > > 
 > > Thanks.  At first I thought this was doing the trick, but then I hit this again.
 > > 
 > > 
 > > [23643.545873] INFO: rcu_preempt detected stalls on CPUs/tasks:
 > 
 > If it still happens after Sasha's revert, which basically revert all the offending
 > patches related to preempt lately, then the reason might be elsewhere.
 > 
 > How hard was it to reproduce? I see 23000 secs in your dmesg logs which is around 6 hours.

yeah. That's why I thought it had fixed it up until that point.
My subsequent overnight run hit a different bug (that unpinning an unpinned lock bug in the scheduler)
so I haven't had it happen since.

 > Also did you just launch trinity? no specific options?
 
basically

while [ 1 ];
do
  trinity -N 1000000 -q -l off -C256 -a64 -x fsync -x fdatasync -x syncfs -x sync -P INET --enable-fds=sockets
  sudo ipcrm -a
done

(The ipcrm thing is needed for long runs or eventually you oom, because trinity lacks the cleanup smarts)

	Dave