On Thu, Oct 14, 2010 at 11:39:34AM +0900, KOSAKI Motohiro wrote:
> > > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > > index 53627fa..194bdaa 100644
> > > --- a/mm/page_alloc.c
> > > +++ b/mm/page_alloc.c
> > > @@ -4897,6 +4897,15 @@ static void setup_per_zone_wmarks(void)
> > > for_each_zone(zone) {
> > > u64 tmp;
> > >
> > > + /*
> > > + * If max drift are less than 1%, reserve max drift pages
> > > + * instead costly runtime calculation.
> > > + */
> > > + if (zone->percpu_drift_mark < (zone->present_pages/100)) {
> > > + pages_min += zone->percpu_drift_mark;
> > > + zone->percpu_drift_mark = 0;
> > > + }
> > > +
> >
> > I don't see how this solves Shaohua's problem as such. Large systems will
> > still suffer a bug performance penalty from zone_page_state_snapshot(). I
> > do see the logic of adjusting min for larger systems to limit the amount of
> > time per-cpu thresholds are lowered but that would be as a follow-on to my
> > patch rather than a replacement.
>
> My patch rescue 256cpus or more smaller systems.
True, and it would be nice to limit how many machines any of this logic
applies to.
> and I assumed 4096cpus system don't
> run IO intensive workload such as Shaohua's case.
Also true, but they still suffer the drift problem. The reproduction
case would change but otherwise the drift must still be handled.
> they always use cpusets and run hpc
> workload.
>
> If you know another >1024cpus system, please let me know.
> And again, my patch works on 4096cpus sysmtem although slow, but your don't.
>
> Am I missing something?
>
I think both are ultimately needed. For my patch, I need to make sure that
wakeup_kswapd() actually wakes up kswapd by using
zone_page_state_snapshot() when necessary. Your patch avoids the problem
differently but in a way that is nice for "smaller" machines.
--
Mel Gorman
Part-time Phd Student Linux Technology Center
University of Limerick IBM Dublin Software Lab
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>