Re: [PATCH v2] sched, timer: Use atomics for thread_group_cputimer to improve scalability

[Jason Low <jason.low2@hp.com>]

On Thu, 2015-03-19 at 10:59 -0700, Linus Torvalds wrote:
> On Thu, Mar 19, 2015 at 10:21 AM, Jason Low <jason.low2@hp.com> wrote:
> >
> > I tested this patch on a 32 bit ARM system with 4 cores. Using the
> > generic 64 bit atomics, I did not see any performance change with this
> > patch, and the relevant functions (account_group_*_time(), ect...) don't
> > show up in perf reports.
> 
> Ok.
> 
> > One factor might be because locking/cacheline contention isn't as
> > apparent on smaller systems to begin with, and lib/atomic64.c also
> > mentions that "this is expected to used on systems with small numbers of
> > CPUs (<= 4 or so)".
> 
> Yeah, that's probably a valid argument anyway - 32-bit systems aren't
> really going to be multi-node big systems any more.
> 
> So I'm ok with the patch,

Okay, I will be sending out a v3 patch which will also mention a bit
about its effect on 32 bit systems in the changelog, in addition to the
changes that were discussed about in this thread (using WRITE_ONCE(),
ect...).

Thanks,
Jason