From: Minchan Kim <minchan@kernel.org> To: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Subject: Re: [RFC][PATCHv2 5/8] zsmalloc: introduce zs_can_compact() function Date: Tue, 16 Jun 2015 23:19:14 +0900 [thread overview] Message-ID: <20150616141914.GC31387@blaptop> (raw) In-Reply-To: <1433505838-23058-6-git-send-email-sergey.senozhatsky@gmail.com> 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 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. > class-3072 objs:24648 inuse:24628 maxobjs-per-page:4 pages-tofree:5 > class-3072 objs:24644 inuse:24628 maxobjs-per-page:4 pages-tofree:4 > class-3072 objs:24640 inuse:24628 maxobjs-per-page:4 pages-tofree:3 > class-3072 objs:24636 inuse:24628 maxobjs-per-page:4 pages-tofree:2 > class-3072 objs:24632 inuse:24628 maxobjs-per-page:4 pages-tofree:1 > class-2720 objs:17970 inuse:17966 maxobjs-per-page:3 pages-tofree:1 > class-2720 objs:17967 inuse:17966 maxobjs-per-page:3 pages-tofree:0 > class-2720: Compaction is useless > class-2448 objs:7680 inuse:7674 maxobjs-per-page:5 pages-tofree:1 > class-2336 objs:13510 inuse:13500 maxobjs-per-page:7 pages-tofree:1 > class-2336 objs:13503 inuse:13500 maxobjs-per-page:7 pages-tofree:0 > class-2336: Compaction is useless > class-1808 objs:1161 inuse:1154 maxobjs-per-page:9 pages-tofree:0 > class-1808: Compaction is useless > class-1744 objs:2135 inuse:2131 maxobjs-per-page:7 pages-tofree:0 > class-1744: Compaction is useless > class-1536 objs:1328 inuse:1323 maxobjs-per-page:8 pages-tofree:0 > class-1536: Compaction is useless > class-1488 objs:8855 inuse:8847 maxobjs-per-page:11 pages-tofree:0 > class-1488: Compaction is useless > class-1360 objs:14880 inuse:14878 maxobjs-per-page:3 pages-tofree:0 > class-1360: Compaction is useless > class-1248 objs:3588 inuse:3577 maxobjs-per-page:13 pages-tofree:0 > class-1248: Compaction is useless > class-1216 objs:3380 inuse:3372 maxobjs-per-page:10 pages-tofree:0 > class-1216: Compaction is useless > class-1168 objs:3416 inuse:3401 maxobjs-per-page:7 pages-tofree:2 > class-1168 objs:3409 inuse:3401 maxobjs-per-page:7 pages-tofree:1 > class-1104 objs:605 inuse:599 maxobjs-per-page:11 pages-tofree:0 > class-1104: Compaction is useless > [..] > > Every "Compaction is useless" indicates that we saved some CPU cycles. > > class-1104 has > 605 object allocated > 599 objects used > 11 objects per-page > > Even if we have a ALMOST_EMPTY zspage, we still don't have enough room to > migrate all of its objects and free this zspage; so compaction will not > make a lot of sense here, it's better to just leave it as is. > > Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> > --- > mm/zsmalloc.c | 25 +++++++++++++++++++++++++ > 1 file changed, 25 insertions(+) > > diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c > index 0453347..5d8f1d4 100644 > --- a/mm/zsmalloc.c > +++ b/mm/zsmalloc.c > @@ -1682,6 +1682,28 @@ static struct page *isolate_source_page(struct size_class *class) > return page; > } > > +/* > + * Make sure that we actually can compact this class, > + * IOW if migration will empty at least one page. free at least one zspage > + * > + * 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 > + return obj_wasted; > +} > + > static unsigned long __zs_compact(struct zs_pool *pool, > struct size_class *class) > { > @@ -1695,6 +1717,9 @@ static unsigned long __zs_compact(struct zs_pool *pool, > > BUG_ON(!is_first_page(src_page)); > > + if (!zs_can_compact(class)) > + break; > + > cc.index = 0; > cc.s_page = src_page; > > -- > 2.4.2.387.gf86f31a > -- Kind regards, Minchan Kim
WARNING: multiple messages have this Message-ID (diff)
From: Minchan Kim <minchan@kernel.org> To: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Subject: Re: [RFC][PATCHv2 5/8] zsmalloc: introduce zs_can_compact() function Date: Tue, 16 Jun 2015 23:19:14 +0900 [thread overview] Message-ID: <20150616141914.GC31387@blaptop> (raw) In-Reply-To: <1433505838-23058-6-git-send-email-sergey.senozhatsky@gmail.com> 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 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. > class-3072 objs:24648 inuse:24628 maxobjs-per-page:4 pages-tofree:5 > class-3072 objs:24644 inuse:24628 maxobjs-per-page:4 pages-tofree:4 > class-3072 objs:24640 inuse:24628 maxobjs-per-page:4 pages-tofree:3 > class-3072 objs:24636 inuse:24628 maxobjs-per-page:4 pages-tofree:2 > class-3072 objs:24632 inuse:24628 maxobjs-per-page:4 pages-tofree:1 > class-2720 objs:17970 inuse:17966 maxobjs-per-page:3 pages-tofree:1 > class-2720 objs:17967 inuse:17966 maxobjs-per-page:3 pages-tofree:0 > class-2720: Compaction is useless > class-2448 objs:7680 inuse:7674 maxobjs-per-page:5 pages-tofree:1 > class-2336 objs:13510 inuse:13500 maxobjs-per-page:7 pages-tofree:1 > class-2336 objs:13503 inuse:13500 maxobjs-per-page:7 pages-tofree:0 > class-2336: Compaction is useless > class-1808 objs:1161 inuse:1154 maxobjs-per-page:9 pages-tofree:0 > class-1808: Compaction is useless > class-1744 objs:2135 inuse:2131 maxobjs-per-page:7 pages-tofree:0 > class-1744: Compaction is useless > class-1536 objs:1328 inuse:1323 maxobjs-per-page:8 pages-tofree:0 > class-1536: Compaction is useless > class-1488 objs:8855 inuse:8847 maxobjs-per-page:11 pages-tofree:0 > class-1488: Compaction is useless > class-1360 objs:14880 inuse:14878 maxobjs-per-page:3 pages-tofree:0 > class-1360: Compaction is useless > class-1248 objs:3588 inuse:3577 maxobjs-per-page:13 pages-tofree:0 > class-1248: Compaction is useless > class-1216 objs:3380 inuse:3372 maxobjs-per-page:10 pages-tofree:0 > class-1216: Compaction is useless > class-1168 objs:3416 inuse:3401 maxobjs-per-page:7 pages-tofree:2 > class-1168 objs:3409 inuse:3401 maxobjs-per-page:7 pages-tofree:1 > class-1104 objs:605 inuse:599 maxobjs-per-page:11 pages-tofree:0 > class-1104: Compaction is useless > [..] > > Every "Compaction is useless" indicates that we saved some CPU cycles. > > class-1104 has > 605 object allocated > 599 objects used > 11 objects per-page > > Even if we have a ALMOST_EMPTY zspage, we still don't have enough room to > migrate all of its objects and free this zspage; so compaction will not > make a lot of sense here, it's better to just leave it as is. > > Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> > --- > mm/zsmalloc.c | 25 +++++++++++++++++++++++++ > 1 file changed, 25 insertions(+) > > diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c > index 0453347..5d8f1d4 100644 > --- a/mm/zsmalloc.c > +++ b/mm/zsmalloc.c > @@ -1682,6 +1682,28 @@ static struct page *isolate_source_page(struct size_class *class) > return page; > } > > +/* > + * Make sure that we actually can compact this class, > + * IOW if migration will empty at least one page. free at least one zspage > + * > + * 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 > + return obj_wasted; > +} > + > static unsigned long __zs_compact(struct zs_pool *pool, > struct size_class *class) > { > @@ -1695,6 +1717,9 @@ static unsigned long __zs_compact(struct zs_pool *pool, > > BUG_ON(!is_first_page(src_page)); > > + if (!zs_can_compact(class)) > + break; > + > cc.index = 0; > cc.s_page = src_page; > > -- > 2.4.2.387.gf86f31a > -- Kind regards, Minchan Kim -- 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>
next prev parent reply other threads:[~2015-06-16 14:19 UTC|newest] Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top 2015-06-05 12:03 [RFC][PATCHv2 0/8] introduce automatic pool compaction Sergey Senozhatsky 2015-06-05 12:03 ` Sergey Senozhatsky 2015-06-05 12:03 ` [RFC][PATCHv2 1/8] zsmalloc: drop unused variable `nr_to_migrate' Sergey Senozhatsky 2015-06-05 12:03 ` Sergey Senozhatsky 2015-06-05 12:03 ` [RFC][PATCHv2 2/8] zsmalloc: partial page ordering within a fullness_list Sergey Senozhatsky 2015-06-05 12:03 ` Sergey Senozhatsky 2015-06-16 13:19 ` Minchan Kim 2015-06-16 13:19 ` Minchan Kim 2015-06-16 14:30 ` Sergey Senozhatsky 2015-06-16 14:30 ` Sergey Senozhatsky 2015-06-05 12:03 ` [RFC][PATCHv2 3/8] zsmalloc: lower ZS_ALMOST_FULL waterline Sergey Senozhatsky 2015-06-05 12:03 ` Sergey Senozhatsky 2015-06-16 13:37 ` Minchan Kim 2015-06-16 13:37 ` Minchan Kim 2015-06-16 14:35 ` Sergey Senozhatsky 2015-06-16 14:35 ` Sergey Senozhatsky 2015-06-05 12:03 ` [RFC][PATCHv2 4/8] zsmalloc: always keep per-class stats Sergey Senozhatsky 2015-06-05 12:03 ` Sergey Senozhatsky 2015-06-05 12:03 ` [RFC][PATCHv2 5/8] zsmalloc: introduce zs_can_compact() function Sergey Senozhatsky 2015-06-05 12:03 ` Sergey Senozhatsky 2015-06-16 14:19 ` Minchan Kim [this message] 2015-06-16 14:19 ` Minchan Kim 2015-06-16 14:41 ` Sergey Senozhatsky 2015-06-16 14:41 ` Sergey Senozhatsky 2015-06-05 12:03 ` [RFC][PATCHv2 6/8] zsmalloc: cosmetic compaction code adjustments Sergey Senozhatsky 2015-06-05 12:03 ` Sergey Senozhatsky 2015-06-05 12:03 ` [RFC][PATCHv2 7/8] zsmalloc/zram: move `num_migrated' to zs_pool Sergey Senozhatsky 2015-06-05 12:03 ` Sergey Senozhatsky 2015-06-05 12:03 ` [RFC][PATCHv2 8/8] zsmalloc: register a shrinker to trigger auto-compaction Sergey Senozhatsky 2015-06-05 12:03 ` Sergey Senozhatsky 2015-06-16 14:47 ` Minchan Kim 2015-06-16 14:47 ` Minchan Kim 2015-06-16 15:45 ` Sergey Senozhatsky 2015-06-16 15:45 ` Sergey Senozhatsky 2015-06-18 1:50 ` Minchan Kim 2015-06-18 1:50 ` Minchan Kim 2015-06-18 2:41 ` Sergey Senozhatsky 2015-06-18 2:41 ` Sergey Senozhatsky 2015-06-18 3:01 ` Sergey Senozhatsky 2015-06-18 3:01 ` Sergey Senozhatsky 2015-06-18 3:46 ` Minchan Kim 2015-06-18 3:46 ` Minchan Kim 2015-06-18 3:39 ` Minchan Kim 2015-06-18 3:39 ` Minchan Kim 2015-06-18 3:58 ` Sergey Senozhatsky 2015-06-18 3:58 ` Sergey Senozhatsky 2015-06-17 7:11 ` Sergey Senozhatsky 2015-06-17 7:11 ` Sergey Senozhatsky 2015-06-10 0:04 ` [RFC][PATCHv2 0/8] introduce automatic pool compaction Minchan Kim 2015-06-10 0:04 ` Minchan Kim 2015-06-10 0:07 ` Sergey Senozhatsky 2015-06-10 0:07 ` Sergey Senozhatsky
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20150616141914.GC31387@blaptop \ --to=minchan@kernel.org \ --cc=akpm@linux-foundation.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=sergey.senozhatsky.work@gmail.com \ --cc=sergey.senozhatsky@gmail.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.