Re: [PATCH] Do not force shutdown/reboot to boot cpu.

[Ingo Molnar <mingo@kernel.org>]

* Robin Holt <holt@sgi.com> wrote:

> On Wed, Apr 10, 2013 at 06:59:34PM +0200, Ingo Molnar wrote:
> > 
> > * Russ Anderson <rja@sgi.com> wrote:
> > 
> > > Yes, I have a test patch that replaces for_each_online_cpu(cpu) with a cpu 
> > > bitmask in disable_nonboot_cpus().  The lower level routines already take a 
> > > bitmask.  It allows __stop_machine() to be called just once.  That change 
> > > reduces shutdown time on a 1024 cpu machine from 16 minutes 4 minutes.  
> > > Significant improvement, but not good enough.
> > > 
> > > The next significant bottleneck is __cpu_notify().  Tried creating worker 
> > > threads to parallelize the shutdown, but the problem is __cpu_notify() is not 
> > > thread safe.  Putting a lock around it caused all the worker threads to fight 
> > > over the lock.
> > 
> > 4 minutes bootup is 240 seconds, with 1024 CPUs that's about 240 msecs per CPU.
> > 
> > That sounds a lot, given that unlike bootup there's not much real work to be done 
> > during shutdown - we don't initialize anything, etc.
> > 
> > Maybe much of those 240 msecs are spent in some stupid udelay loop or so, which 
> > could be made parallel?
> > 
> > Would it be possible to create a 'reboot but stop at the end and reactivate all 
> > CPUs again' reboot flag, so that it can all be NMI-profiled, to see where the true 
> > bottleneck is? A naked disable_nonboot_cpus() call in essence.
> 
> What, exactly, are you proposing with the NMI profiling? [...]

I'm proposing to make 'reboot' overhead profilable, via a debug hack:

        echo 1 > /proc/sys/kernel/magic_dont_fully_reboot_flag

	perf record reboot

perf is using NMIs to profile - and since much of cpu_down() is with irqs 
disabled, NMI profiling would be needed to see inside the overhead.

(Assuming the 240 msecs is CPU overhead, not waiting for some IRQ/IPI event.)

Thanks,

	Ingo