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

[Robin Holt <holt@sgi.com>]

On Wed, Apr 10, 2013 at 07:22:36PM +0200, Ingo Molnar wrote:
> 
> * 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.)

Let me give it a try.

Robin