Re: [PATCH] hrtimer: increase clock min delta threshold while interrupt hanging

[Frederic Weisbecker <fweisbec@gmail.com>]

On Sat, Dec 27, 2008 at 11:53:34AM +0100, Ingo Molnar wrote:
> 
> * Frederic Weisbecker <fweisbec@gmail.com> wrote:
> 
> > Impact: avoid hanging on slow systems
> > 
> > While using the function graph tracer on a virtualized system, the 
> > hrtimer_interrupt can hang the system on an infinite loop. This can be 
> > caused on several situation where something intrusive is slowing the 
> > system (ie: tracing) and the next clock events to program are always 
> > before the current time. This patch implements a reasonable compromise. 
> > If such a situation is detected, we share the CPUs time in 1/4 to 
> > process the hrtimer interrupts. This is enough to let the system running 
> > without serious starvation.
> > 
> > It has been successfully tested under VirtualBox with 1000 HZ and 100 HZ 
> > with function graph tracer launched. On both cases, the clock events 
> > were increased until about 25 ms periodic ticks, which means 40 HZ.
> > 
> > Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
> > Cc: Thomas Gleixner <tglx@linutronix.de>
> > ---
> >  kernel/hrtimer.c |   30 +++++++++++++++++++++++++++++-
> >  1 files changed, 29 insertions(+), 1 deletions(-)
> 
> applied to tip/timers/hrtimers, thanks Frederic!


I will apply the comments that came along these reviews in a delta patch.
Note that I still wonder about false positive with a 5 loop check. I think
I will increase it to 10. This a more reasonable.

(I remember I had false positive but I'm not sure if that was because of early_printk
used for debugging. I didn't worry about it first, because I hadn't these false positive
on my last tests, just before I send this patch.)

> 
> Thomas, any objections/observations?
> 
> 	Ingo