Re: [PATCH 2/2] mlock use lru_add_drain_all_async()

[KOSAKI Motohiro]

> On Tue, 2009-10-06 at 11:41 +0900, KOSAKI Motohiro wrote:
> > Recently, Peter Zijlstra reported RT-task can lead to prevent mlock
> > very long time.
> > 
> >   Suppose you have 2 cpus, cpu1 is busy doing a SCHED_FIFO-99 while(1),
> >   cpu0 does mlock()->lru_add_drain_all(), which does
> >   schedule_on_each_cpu(), which then waits for all cpus to complete the
> >   work. Except that cpu1, which is busy with the RT task, will never run
> >   keventd until the RT load goes away.
> > 
> >   This is not so much an actual deadlock as a serious starvation case.
> > 
> > Actually, mlock() doesn't need to wait to finish lru_add_drain_all().
> > Thus, this patch replace it with lru_add_drain_all_async().
> > 
> > Cc: Oleg Nesterov <onestero@xxxxxxxxxx>
> > Reported-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> 
> > Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
> 
> It was actually Mike Galbraith who brought it to my attention.
> 
> Patch looks sane enough, altough I'm not sure I'd have split it in two
> like you did (leaves the first without a real changelog too).

Ah, yes. they shold be folded. thanks.
In my local patch queue, this patch series have another two caller.

  - lumpy reclaim: currently, PCP often cause failure large order allocation.
  - page migration: in almost case, PCP doesn't hold the migration target page.

but they are still testing.





--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/