Re: [GIT PULL] adaptive spinning mutexes

[Andrew Morton]

On Wed, 14 Jan 2009 20:50:50 +0100
Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> wrote:

> On Wed, 2009-01-14 at 11:36 -0800, Andrew Morton wrote:
> 
> > Do people enable CONFIG_SCHED_DEBUG?
> 
> Well, I have it always enabled, but I've honestly no idea if that makes
> me weird.

It'd be weird if you're not weird.

> > CONFIG_DEBUG_MUTEXES=n, CONFIG_SCHED_DEBUG=y is getting to be a pretty
> > small subset?
> 
> Could be, do you fancy me doing a sysctl? shouldn't be hard.

The /sys/debug knob depends upon CONFIG_SCHED_DEBUG, I assume?

umm, yes, I do think that it would be prudent to make this control
unconditionally available.  Experience tells us that any regressions
which this change causes could take a long time to turn up - sometimes
years.  By which time the people who are reporting the regressions are
running packaged kernels, and if that packaged kernel didn't enable
CONFIG_SCHED_DEBUG, we're a bit screwed.

Did we end up deciding to remove the CONFIG_DEBUG_MUTEXES=n dependency?
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/