Re: [PATCH 1/9] mm: fix 100% CPU kswapd busyloop on unreclaimable nodes

[Johannes Weiner]

On Mon, Mar 06, 2017 at 10:37:40AM +0900, Minchan Kim wrote:
> On Fri, Mar 03, 2017 at 08:59:54AM +0100, Michal Hocko wrote:
> > On Fri 03-03-17 10:26:09, Minchan Kim wrote:
> > > On Tue, Feb 28, 2017 at 04:39:59PM -0500, Johannes Weiner wrote:
> > > > @@ -3316,6 +3325,9 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
> > > >  			sc.priority--;
> > > >  	} while (sc.priority >= 1);
> > > >  
> > > > +	if (!sc.nr_reclaimed)
> > > > +		pgdat->kswapd_failures++;
> > > 
> > > sc.nr_reclaimed is reset to zero in above big loop's beginning so most of time,
> > > it pgdat->kswapd_failures is increased.

That wasn't intentional; I didn't see the sc.nr_reclaimed reset.

---