[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20150616144106.GD20596@swordfish>
Date: Tue, 16 Jun 2015 23:41:06 +0900
From: Sergey Senozhatsky <sergey.senozhatsky@...il.com>
To: Minchan Kim <minchan@...nel.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky@...il.com>,
Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org,
Sergey Senozhatsky <sergey.senozhatsky.work@...il.com>
Subject: Re: [RFC][PATCHv2 5/8] zsmalloc: introduce zs_can_compact() function
On (06/16/15 23:19), Minchan Kim wrote:
> On Fri, Jun 05, 2015 at 09:03:55PM +0900, Sergey Senozhatsky wrote:
> > This function checks if class compaction will free any pages.
> > Rephrasing -- do we have enough unused objects to form at least
> > one ZS_EMPTY page and free it. It aborts compaction if class
> > compaction will not result in any (further) savings.
> >
> > EXAMPLE (this debug output is not part of this patch set):
> >
> > -- class size
> > -- number of allocated objects
> > -- number of used objects,
> > -- estimated number of pages that will be freed
> >
> > [..]
> > class-3072 objs:24652 inuse:24628 maxobjs-per-page:4 pages-tofree:6
>
> Please use clear term. We have been used zspage as cluster of pages.
>
> maxobjs-per-zspage:4
>
OK, will correct.
class size
sats[OBJ_ALLOCATED]
stats[OBJ_USED]
get_maxobj_per_zspage()
+pages-per-zspage
zspages-to-free
> And say what is pages-per-zspage for each class.
> then, write how you calculate it for easy reviewing.
>
> * class-3072
> * pages-per-zspage: 3
> * maxobjs-per-zspage = 4
>
> In your example, allocated obj = 24652 and inuse obj = 24628
> so 24652 - 24628 = 24 = 4(ie, maxobjs-per-zspage) * 6
> so we can save 6 zspage. A zspage includes 3 pages so we can
> save 3 * 6 = 18 pages via compaction.
>
>
[..]
> > + * Make sure that we actually can compact this class,
> > + * IOW if migration will empty at least one page.
>
> free at least one zspage
OK.
> > + *
> > + * Should be called under class->lock
> > + */
> > +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);
> > +
> > + obj_wasted /= get_maxobj_per_zspage(class->size,
> > + class->pages_per_zspage);
>
> I don't think we need division and make it simple.
>
> return obj_wasted >= get_maxobj_per_zspage
I use this number later for the shrinker, as a shrinker.count_objects()
return value (total number of zsages that can be freed).
-ss
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists