[PATCHSET] block: per-queue policy activation, take#2

Tejun Heo tj at kernel.org
Wed Apr 25 18:19:05 UTC 2012


On Fri, Apr 20, 2012 at 09:08:35PM +0200, Jens Axboe wrote:
> On 2012-04-20 19:17, Tejun Heo wrote:
> > Hello, Jens.
> > 
> > On Fri, Apr 20, 2012 at 02:02:05PM +0200, Jens Axboe wrote:
> >> Tejun, everything merged in cleanly. A boot test didn't not go so well,
> >> I'm afraid. It complains about stuck RCU. Even with extra RCU
> >> debugging/info turned on, it doesn't give my any extra info.
> >>
> >> Config is attached. I can try and debug this on Monday, for now I've
> >> pulled it out of for-next again.
> > 
> > Hmmm... it works fine with the same config here (qemu w/ 4 cpus
> > configured).  Doesn't stuck RCU usually come from unbalanced RCU
> > lock/unlocking?  That should trigger context or RCU warnings before
> > anything else, weird.  Anyways, it would be great if you can provide
> > more info on how to reproduce the problem.
> 
> The machine just sat there. I'll get some more info out of it and run a
> bisect too.

Any progress on this?

Thanks.

-- 
tejun


More information about the Containers mailing list