From: Jesper Dangaard Brouer <brouer@redhat.com>
To: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: linux-mm@kvack.org, Christoph Lameter <cl@linux.com>,
Vladimir Davydov <vdavydov@virtuozzo.com>,
Andrew Morton <akpm@linux-foundation.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
brouer@redhat.com
Subject: Re: [PATCH 10/10] mm: new API kfree_bulk() for SLAB+SLUB allocators
Date: Fri, 8 Jan 2016 12:20:25 +0100 [thread overview]
Message-ID: <20160108122025.4605528c@redhat.com> (raw)
In-Reply-To: <20160108030348.GC14457@js1304-P5Q-DELUXE>
On Fri, 8 Jan 2016 12:03:48 +0900
Joonsoo Kim <iamjoonsoo.kim@lge.com> wrote:
> On Thu, Jan 07, 2016 at 03:04:23PM +0100, Jesper Dangaard Brouer wrote:
> > This patch introduce a new API call kfree_bulk() for bulk freeing
> > memory objects not bound to a single kmem_cache.
> >
> > Christoph pointed out that it is possible to implement freeing of
> > objects, without knowing the kmem_cache pointer as that information is
> > available from the object's page->slab_cache. Proposing to remove the
> > kmem_cache argument from the bulk free API.
> >
> > Jesper demonstrated that these extra steps per object comes at a
> > performance cost. It is only in the case CONFIG_MEMCG_KMEM is
> > compiled in and activated runtime that these steps are done anyhow.
> > The extra cost is most visible for SLAB allocator, because the SLUB
> > allocator does the page lookup (virt_to_head_page()) anyhow.
> >
> > Thus, the conclusion was to keep the kmem_cache free bulk API with a
> > kmem_cache pointer, but we can still implement a kfree_bulk() API
> > fairly easily. Simply by handling if kmem_cache_free_bulk() gets
> > called with a kmem_cache NULL pointer.
> >
> > This does increase the code size a bit, but implementing a separate
> > kfree_bulk() call would likely increase code size even more.
> >
> > Below benchmarks cost of alloc+free (obj size 256 bytes) on
> > CPU i7-4790K @ 4.00GHz, no PREEMPT and CONFIG_MEMCG_KMEM=y.
> >
> > Code size increase for SLAB:
> >
> > add/remove: 0/0 grow/shrink: 1/0 up/down: 74/0 (74)
> > function old new delta
> > kmem_cache_free_bulk 660 734 +74
> >
> > SLAB fastpath: 85 cycles(tsc) 21.468 ns (step:0)
> > sz - fallback - kmem_cache_free_bulk - kfree_bulk
> > 1 - 101 cycles 25.291 ns - 41 cycles 10.499 ns - 130 cycles 32.522 ns
>
> This looks experimental error. Why does kfree_bulk() takes more time
> than fallback?
This does look like an experimental error. Sometimes instabilities
occurs, when slab_caches gets merged, but I tried to counter that by
using boot param slab_nomerge.
In the case for SLAB kfree_bulk() single object, then it can be slower
than the fallback, because it will likely always hit a branch
mispredict for the kfree case (which is okay, as that is not the case
we optimize for, single obj free).
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
Author of http://www.iptv-analyzer.org
LinkedIn: http://www.linkedin.com/in/brouer
--
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:[~2016-01-08 11:20 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-01-07 14:03 [PATCH 00/10] MM: More bulk API work Jesper Dangaard Brouer
2016-01-07 14:03 ` [PATCH 01/10] slub: cleanup code for kmem cgroup support to kmem_cache_free_bulk Jesper Dangaard Brouer
2016-01-07 15:54 ` Christoph Lameter
2016-01-07 17:41 ` Jesper Dangaard Brouer
2016-01-08 2:58 ` Joonsoo Kim
2016-01-08 11:05 ` Jesper Dangaard Brouer
2016-01-07 14:03 ` [PATCH 02/10] mm/slab: move SLUB alloc hooks to common mm/slab.h Jesper Dangaard Brouer
2016-01-07 14:03 ` [PATCH 03/10] mm: fault-inject take over bootstrap kmem_cache check Jesper Dangaard Brouer
2016-01-07 14:03 ` [PATCH 04/10] slab: use slab_pre_alloc_hook in SLAB allocator shared with SLUB Jesper Dangaard Brouer
2016-01-08 3:05 ` Joonsoo Kim
2016-01-07 14:03 ` [PATCH 05/10] mm: kmemcheck skip object if slab allocation failed Jesper Dangaard Brouer
2016-01-07 14:04 ` [PATCH 06/10] slab: use slab_post_alloc_hook in SLAB allocator shared with SLUB Jesper Dangaard Brouer
2016-01-07 14:04 ` [PATCH 07/10] slab: implement bulk alloc in SLAB allocator Jesper Dangaard Brouer
2016-01-07 14:04 ` [PATCH 08/10] slab: avoid running debug SLAB code with IRQs disabled for alloc_bulk Jesper Dangaard Brouer
2016-01-07 14:04 ` [PATCH 09/10] slab: implement bulk free in SLAB allocator Jesper Dangaard Brouer
2016-01-07 14:04 ` [PATCH 10/10] mm: new API kfree_bulk() for SLAB+SLUB allocators Jesper Dangaard Brouer
2016-01-08 3:03 ` Joonsoo Kim
2016-01-08 11:20 ` Jesper Dangaard Brouer [this message]
2016-01-07 18:54 ` [PATCH 00/10] MM: More bulk API work Linus Torvalds
2016-01-12 15:13 ` [PATCH V2 00/11] " Jesper Dangaard Brouer
2016-01-12 15:13 ` [PATCH V2 01/11] slub: cleanup code for kmem cgroup support to kmem_cache_free_bulk Jesper Dangaard Brouer
2016-01-12 15:13 ` [PATCH V2 02/11] mm/slab: move SLUB alloc hooks to common mm/slab.h Jesper Dangaard Brouer
2016-01-12 15:14 ` [PATCH V2 03/11] mm: fault-inject take over bootstrap kmem_cache check Jesper Dangaard Brouer
2016-01-12 15:14 ` [PATCH V2 04/11] slab: use slab_pre_alloc_hook in SLAB allocator shared with SLUB Jesper Dangaard Brouer
2016-01-12 15:14 ` [PATCH V2 05/11] mm: kmemcheck skip object if slab allocation failed Jesper Dangaard Brouer
2016-01-12 15:14 ` [PATCH V2 06/11] slab: use slab_post_alloc_hook in SLAB allocator shared with SLUB Jesper Dangaard Brouer
2016-01-12 15:15 ` [PATCH V2 07/11] slab: implement bulk alloc in SLAB allocator Jesper Dangaard Brouer
2016-01-12 15:15 ` [PATCH V2 08/11] slab: avoid running debug SLAB code with IRQs disabled for alloc_bulk Jesper Dangaard Brouer
2016-01-12 15:15 ` [PATCH V2 09/11] slab: implement bulk free in SLAB allocator Jesper Dangaard Brouer
2016-01-12 15:16 ` [PATCH V2 10/11] mm: new API kfree_bulk() for SLAB+SLUB allocators Jesper Dangaard Brouer
2016-01-12 15:16 ` [PATCH V2 11/11] mm: fix some spelling Jesper Dangaard Brouer
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=20160108122025.4605528c@redhat.com \
--to=brouer@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=linux-mm@kvack.org \
--cc=torvalds@linux-foundation.org \
--cc=vdavydov@virtuozzo.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;
as well as URLs for NNTP newsgroup(s).