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

[KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>]

> 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@redhat.com>
> > Reported-by: Peter Zijlstra <a.p.zijlstra@chello.nl> 
> > Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
> 
> 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, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>