Messages in this thread | | | Date | Wed, 1 Oct 2014 18:10:58 +0200 | From | Peter Zijlstra <> | Subject | Re: [PATCH 10/11] sched: Debug nested sleeps |
| |
On Tue, Sep 30, 2014 at 11:47:32PM +0200, Oleg Nesterov wrote:
> > > This is minor, but this way CONFIG_DEBUG_ATOMIC_SLEEP will not imply > > > a subtle behavioural change. > > > > You mean the __set_current_state() that's extra? > > Yes, and note that it only does __set_current_state(RUNNING) if > CONFIG_DEBUG_ATOMIC_SLEEP. This means that disabling/enabling this > option can, silently hide/uncover a bug. > > > I would actually argue > > to keep that since it makes the 'problem' much worse. > > OK, I won't insist, but could you explain why the suggested change can > make the problem (and which problem ;) worse?
Sure, so the trivial problem is not actually going to sleep in the outer wait primitive because the inner wait primitive reset ->state to TASK_RUNNING.
So by always setting the ->state to TASK_RUNNING it never goes to sleep and it'll revert to spinning, causing spikes in CPU usage that should hopefully be far easier to notice than the occasional funny.
| |