linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Vlastimil Babka <vbabka@suse.cz>
To: Harry Yoo <harry.yoo@oracle.com>, akpm@linux-foundation.org
Cc: andreyknvl@gmail.com, cl@gentwo.org, dvyukov@google.com,
	glider@google.com, hannes@cmpxchg.org, linux-mm@kvack.org,
	mhocko@kernel.org, muchun.song@linux.dev, rientjes@google.com,
	roman.gushchin@linux.dev, ryabinin.a.a@gmail.com,
	shakeel.butt@linux.dev, surenb@google.com,
	vincenzo.frascino@arm.com, yeoreum.yun@arm.com, tytso@mit.edu,
	adilger.kernel@dilger.ca, linux-ext4@vger.kernel.org,
	linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
	hao.li@linux.dev
Subject: Re: [PATCH V6 9/9] mm/slab: place slabobj_ext metadata in unused space within s->size
Date: Tue, 13 Jan 2026 13:50:31 +0100	[thread overview]
Message-ID: <fecd4166-618d-4d69-be02-d9b3e8f0f271@suse.cz> (raw)
In-Reply-To: <20260113061845.159790-10-harry.yoo@oracle.com>

On 1/13/26 7:18 AM, Harry Yoo wrote:
> When a cache has high s->align value and s->object_size is not aligned
> to it, each object ends up with some unused space because of alignment.
> If this wasted space is big enough, we can use it to store the
> slabobj_ext metadata instead of wasting it.
> 
> On my system, this happens with caches like kmem_cache, mm_struct, pid,
> task_struct, sighand_cache, xfs_inode, and others.
> 
> To place the slabobj_ext metadata within each object, the existing
> slab_obj_ext() logic can still be used by setting:
> 
>   - slab->obj_exts = slab_address(slab) + (slabobj_ext offset)
>   - stride = s->size
> 
> slab_obj_ext() doesn't need know where the metadata is stored,
> so this method works without adding extra overhead to slab_obj_ext().
> 
> A good example benefiting from this optimization is xfs_inode
> (object_size: 992, align: 64). To measure memory savings, 2 millions of
> files were created on XFS.
> 
> [ MEMCG=y, MEM_ALLOC_PROFILING=n ]
> 
> Before patch (creating ~2.64M directories on xfs):
>   Slab:            5175976 kB
>   SReclaimable:    3837524 kB
>   SUnreclaim:      1338452 kB
> 
> After patch (creating ~2.64M directories on xfs):
>   Slab:            5152912 kB
>   SReclaimable:    3838568 kB
>   SUnreclaim:      1314344 kB (-23.54 MiB)
> 
> Enjoy the memory savings!
> 
> Suggested-by: Vlastimil Babka <vbabka@suse.cz>
> Signed-off-by: Harry Yoo <harry.yoo@oracle.com>

Does this look OK to you or was there a reason you didn't do it? :)

diff --git a/mm/slub.c b/mm/slub.c
index ba15df4ca417..deb69bd9646a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -981,8 +981,7 @@ static inline bool obj_exts_in_slab(struct kmem_cache *s, struct slab *slab)
 #if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT)
 static bool obj_exts_in_object(struct kmem_cache *s, struct slab *slab)
 {
-       return obj_exts_in_slab(s, slab) &&
-              (slab_get_stride(slab) == s->size);
+       return obj_exts_in_slab(s, slab) && (s->flags & SLAB_OBJ_EXT_IN_OBJ);
 }
 
 static unsigned int obj_exts_offset_in_object(struct kmem_cache *s)



  reply	other threads:[~2026-01-13 12:50 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-13  6:18 [PATCH V6 0/9] mm/slab: reduce slab accounting memory overhead by allocating slabobj_ext metadata within unsed slab space Harry Yoo
2026-01-13  6:18 ` [PATCH V6 1/9] mm/slab: use unsigned long for orig_size to ensure proper metadata align Harry Yoo
2026-01-13  6:18 ` [PATCH V6 2/9] mm/slab: allow specifying free pointer offset when using constructor Harry Yoo
2026-01-13  6:18 ` [PATCH V6 3/9] ext4: specify the free pointer offset for ext4_inode_cache Harry Yoo
2026-01-13  6:18 ` [PATCH V6 4/9] mm/slab: abstract slabobj_ext access via new slab_obj_ext() helper Harry Yoo
2026-01-13  6:18 ` [PATCH V6 5/9] mm/slab: use stride to access slabobj_ext Harry Yoo
2026-01-13  6:18 ` [PATCH V6 6/9] mm/memcontrol,alloc_tag: handle slabobj_ext access under KASAN poison Harry Yoo
2026-01-13  6:18 ` [PATCH V6 7/9] mm/slab: save memory by allocating slabobj_ext array from leftover Harry Yoo
2026-01-13  6:18 ` [PATCH V6 8/9] mm/slab: move [__]ksize and slab_ksize() to mm/slub.c Harry Yoo
2026-01-13 12:44   ` Vlastimil Babka
2026-01-13 13:05     ` Harry Yoo
2026-01-13 13:45       ` Vlastimil Babka
2026-01-13  6:18 ` [PATCH V6 9/9] mm/slab: place slabobj_ext metadata in unused space within s->size Harry Yoo
2026-01-13 12:50   ` Vlastimil Babka [this message]
2026-01-13 13:01     ` Harry Yoo
2026-01-13 13:32       ` Harry Yoo
2026-01-13 13:42         ` Vlastimil Babka
2026-01-13 14:13 ` [PATCH V6 0/9] mm/slab: reduce slab accounting memory overhead by allocating slabobj_ext metadata within unsed slab space Vlastimil Babka

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=fecd4166-618d-4d69-be02-d9b3e8f0f271@suse.cz \
    --to=vbabka@suse.cz \
    --cc=adilger.kernel@dilger.ca \
    --cc=akpm@linux-foundation.org \
    --cc=andreyknvl@gmail.com \
    --cc=cgroups@vger.kernel.org \
    --cc=cl@gentwo.org \
    --cc=dvyukov@google.com \
    --cc=glider@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=hao.li@linux.dev \
    --cc=harry.yoo@oracle.com \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=muchun.song@linux.dev \
    --cc=rientjes@google.com \
    --cc=roman.gushchin@linux.dev \
    --cc=ryabinin.a.a@gmail.com \
    --cc=shakeel.butt@linux.dev \
    --cc=surenb@google.com \
    --cc=tytso@mit.edu \
    --cc=vincenzo.frascino@arm.com \
    --cc=yeoreum.yun@arm.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: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox