Re: kswapd0: excessive CPU usage

[Thorsten Leemhuis]

Hi!

On 15.10.2012 13:09, Mel Gorman wrote:
> On Mon, Oct 15, 2012 at 11:54:13AM +0200, Jiri Slaby wrote:
> > On 10/12/2012 03:57 PM, Mel Gorman wrote:
> > > mm: vmscan: scale number of pages reclaimed by reclaim/compaction only in direct reclaim
> > > Jiri Slaby reported the following:
> [...]
> > > diff --git a/mm/vmscan.c b/mm/vmscan.c
> > > index 2624edc..2b7edfa 100644
> > > --- a/mm/vmscan.c
> > > +++ b/mm/vmscan.c
> > > @@ -1763,14 +1763,20 @@ static bool in_reclaim_compaction(struct scan_control *sc)
> > >   #ifdef CONFIG_COMPACTION
> > >   /*
> > >    * If compaction is deferred for sc->order then scale the number of pages
> > > - * reclaimed based on the number of consecutive allocation failures
> > > + * reclaimed based on the number of consecutive allocation failures. This
> > > + * scaling only happens for direct reclaim as it is about to attempt
> > > + * compaction. If compaction fails, future allocations will be deferred
> > > + * and reclaim avoided. On the other hand, kswapd does not take compaction
> > > + * deferral into account so if it scaled, it could scan excessively even
> > > + * though allocations are temporarily not being attempted.
> > >    */
> > >   static unsigned long scale_for_compaction(unsigned long pages_for_compaction,
> > >   			struct lruvec *lruvec, struct scan_control *sc)
> > >   {
> > >   	struct zone *zone = lruvec_zone(lruvec);
> > >
> > > -	if (zone->compact_order_failed <= sc->order)
> > > +	if (zone->compact_order_failed <= sc->order &&
> > > +	    !current_is_kswapd())
> > >   		pages_for_compaction <<= zone->compact_defer_shift;
> > >   	return pages_for_compaction;
> > >   }
> > Yes, applying this instead of the revert fixes the issue as well.

Just wondering, is there a reason why this patch wasn't applied to 
mainline? Did it simply fall through the cracks? Or am I missing something?

I'm asking because I think I stil see the issue on 
3.7-rc2-git-checkout-from-friday. Seems Fedora rawhide users are hitting 
it, too:
https://bugzilla.redhat.com/show_bug.cgi?id=866988

Or are we seeing something different which just looks similar? I can 
test the patch if it needs further testing, but from the discussion I 
got the impression that everything is clear and the patch ready for merging.

CU
 knurd
--
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/