Re: [PATCH 2/2] CFS CGroup: Report usage

[Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>]

On Mon, Oct 22, 2007 at 11:06:54PM -0700, Paul Menage wrote:
> > > +     for_each_possible_cpu(i) {
> > > +             unsigned long flags;
> > > +             spin_lock_irqsave(&tg->cfs_rq[i]->rq->lock, flags);
> >
> > Is the lock absolutely required here?
> 
> I'm not sure, I was hoping you or Ingo could comment on this. But some
> kind of locking seems to required at least on 32-bit platforms, since
> sum_exec_runtime is a 64-bit number.

I tend to agree abt 32-bit platforms requiring a lock to read the 64-bit
sum_exec_runtime field.

Ingo/Dmitry, what do you think? fs/proc/array.c:task_utime() is also
buggy in that case.

-- 
Regards,
vatsa