On (06/29/15 15:45), Minchan Kim wrote:
[..]
> > +/*
> > + * Make sure that we actually can compact this class,
> > + * IOW if migration will release at least one szpage.
>
> zspage,
ok.
> > + *
> > + * Should be called under class->lock
>
> Please comment about return.
ok.
> > + */
> > +static unsigned long zs_can_compact(struct size_class *class)
> > +{
> > + /*
> > + * Calculate how many unused allocated objects we
> > + * have and see if we can free any zspages. Otherwise,
> > + * compaction can just move objects back and forth w/o
> > + * any memory gain.
> > + */
> > + unsigned long obj_wasted = zs_stat_get(class, OBJ_ALLOCATED) -
> > + zs_stat_get(class, OBJ_USED);
> > +
>
> I want to check one more thing.
>
> We could have lots of ZS_ALMOST_FULL but no ZS_ALMOST_EMPTY.
> In this implementation, compaction cannot have a source so
> it would better to bail out.
> IOW,
>
> if (!zs_stat_get(class, CLASS_ALMOST_EMPTY))
> return 0;
ok.
-ss
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>